diff --git a/downsample_wb.py b/downsample_wb.py
new file mode 100644
index 0000000000000000000000000000000000000000..9347f650f36bb061dd3997409bf8e9b69615cdd0
--- /dev/null
+++ b/downsample_wb.py
@@ -0,0 +1,49 @@
+import os
+import cv2
+import glob
+
+def downsample_image(image_path):
+    # 读取图像
+    img = cv2.imread(image_path)
+    if img is None:
+        print(f"Error reading image: {image_path}")
+        return None
+    
+    # 获取原始尺寸
+    h, w = img.shape[:2]
+    
+    # 下采样到一半大小
+    resized = cv2.resize(img, (w//2, h//2), interpolation=cv2.INTER_CUBIC)
+    
+    return resized
+
+def process_folders():
+    # 定义需要处理的文件夹
+    folders = [
+        'DIV2K_train_EDGE_disturbed',
+        'DIV2K_train_HR',
+        'DIV2K_train_LR_bicubic/X1'  # LR_bicubic中的图像在X1子文件夹中
+    ]
+    
+    # 需要处理的图片名称
+    target_images = ['wb1.jpg', 'wb2.jpg', 'wb3.jpg']
+    
+    for folder in folders:
+        print(f"\n处理文件夹: {folder}")
+        
+        # 处理每个目标图片
+        for img_name in target_images:
+            img_path = os.path.join(folder, img_name)
+            if os.path.exists(img_path):
+                print(f"处理图片: {img_path}")
+                # 下采样图片
+                resized = downsample_image(img_path)
+                if resized is not None:
+                    # 直接覆盖原图片
+                    cv2.imwrite(img_path, resized)
+                    print(f"已完成下采样: {img_path}")
+            else:
+                print(f"找不到图片: {img_path}")
+
+if __name__ == '__main__':
+    process_folders() 
\ No newline at end of file
diff --git a/experiment/.DS_Store b/experiment/.DS_Store
new file mode 100644
index 0000000000000000000000000000000000000000..9d6655e83f63a38999004a4a0866285da01479fd
Binary files /dev/null and b/experiment/.DS_Store differ
diff --git a/experiment/log.txt b/experiment/log.txt
new file mode 100644
index 0000000000000000000000000000000000000000..6459a0bccf619117878bd5e80f7f65ea83abccc1
--- /dev/null
+++ b/experiment/log.txt
@@ -0,0 +1,7 @@
+smgarn_1：
+使用4个视频，正常图像，EWT模型，训练集520，测试集50
+python main.py --scale 1 --patch_size 64 --save smgarn --ext sep_reset --save_results
+
+smagrn_2:
+对参考图像增加高斯噪声和高斯模糊，其余不变。在div2k.py中31行，hardcode了噪声图像文件夹信息
+python main.py --scale 1 --patch_size 64 --save smgarn --ext sep_reset --save_results
\ No newline at end of file
diff --git a/experiment/smgarn/config.txt b/experiment/smgarn/config.txt
new file mode 100644
index 0000000000000000000000000000000000000000..fa45e72508e642477fe5e996bc3b48f51be8a82a
--- /dev/null
+++ b/experiment/smgarn/config.txt
@@ -0,0 +1,124 @@
+2025-01-06-05:02:54
+
+debug: False
+template: .
+n_threads: 6
+cpu: False
+n_GPUs: 2
+seed: 1
+dir_data: ../dataset
+dir_demo: ../test
+data_train: ['DIV2K']
+data_test: ['DIV2K']
+data_range: 1-520/521-570
+ext: sep_reset
+scale: [1]
+patch_size: 64
+rgb_range: 255
+n_colors: 3
+chop: False
+no_augment: False
+model: EWT
+act: relu
+pre_train: 
+extend: .
+n_resblocks: 16
+n_feats: 64
+res_scale: 1
+shift_mean: True
+dilation: False
+precision: single
+G0: 64
+RDNkSize: 3
+RDNconfig: B
+n_resgroups: 10
+reduction: 16
+reset: False
+test_every: 1000
+epochs: 300
+batch_size: 16
+split_batch: 1
+self_ensemble: False
+test_only: False
+gan_k: 1
+lr: 0.0001
+decay: 100
+gamma: 0.5
+optimizer: ADAM
+momentum: 0.9
+betas: (0.9, 0.999)
+epsilon: 1e-08
+weight_decay: 0
+gclip: 0
+loss: 1*L1
+skip_threshold: 100000000.0
+save: smgarn
+load: 
+resume: 0
+save_models: False
+print_every: 100
+save_results: True
+save_gt: False
+
+2025-01-06-05:03:11
+
+debug: False
+template: .
+n_threads: 6
+cpu: False
+n_GPUs: 2
+seed: 1
+dir_data: ../dataset
+dir_demo: ../test
+data_train: ['DIV2K']
+data_test: ['DIV2K']
+data_range: 1-520/521-570
+ext: sep_reset
+scale: [1]
+patch_size: 64
+rgb_range: 255
+n_colors: 3
+chop: False
+no_augment: False
+model: EWT
+act: relu
+pre_train: 
+extend: .
+n_resblocks: 16
+n_feats: 64
+res_scale: 1
+shift_mean: True
+dilation: False
+precision: single
+G0: 64
+RDNkSize: 3
+RDNconfig: B
+n_resgroups: 10
+reduction: 16
+reset: False
+test_every: 1000
+epochs: 300
+batch_size: 16
+split_batch: 1
+self_ensemble: False
+test_only: False
+gan_k: 1
+lr: 0.0001
+decay: 100
+gamma: 0.5
+optimizer: ADAM
+momentum: 0.9
+betas: (0.9, 0.999)
+epsilon: 1e-08
+weight_decay: 0
+gclip: 0
+loss: 1*L1
+skip_threshold: 100000000.0
+save: smgarn
+load: 
+resume: 0
+save_models: False
+print_every: 100
+save_results: True
+save_gt: False
+
diff --git a/experiment/smgarn/log.txt b/experiment/smgarn/log.txt
new file mode 100644
index 0000000000000000000000000000000000000000..4722b341393df6cbdc2a76d9187de73fd1084a41
--- /dev/null
+++ b/experiment/smgarn/log.txt
@@ -0,0 +1,5611 @@
+EWT(
+  (DWT): DWT()
+  (IWT): IWT()
+  (trans): MFAM(
+    (conv_first): Conv2d(24, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (patch_embed): PatchEmbed(
+      (norm): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+    )
+    (patch_unembed): PatchUnEmbed()
+    (pos_drop): Dropout(p=0.0, inplace=False)
+    (layers): ModuleList(
+      (0): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): Identity()
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.014)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+      (1): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.029)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.043)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+      (2): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.057)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.071)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (2): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.086)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (3): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.100)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+    )
+    (norm): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+    (conv_after_body): ResBlock(
+      (body): Sequential(
+        (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (1): ReLU(inplace=True)
+        (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      )
+    )
+    (conv_last): Conv2d(96, 12, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+  )
+)
+[Epoch 1]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 39.1730]	12.9+0.9s
+[3200/15600]	[L1: 28.6782]	11.3+0.1s
+[4800/15600]	[L1: 23.6468]	10.8+0.1s
+[6400/15600]	[L1: 20.6448]	11.0+0.1s
+[8000/15600]	[L1: 18.5010]	11.1+0.1s
+[9600/15600]	[L1: 16.7156]	10.0+0.1s
+[11200/15600]	[L1: 15.1871]	9.8+0.1s
+[12800/15600]	[L1: 13.8983]	10.9+0.1s
+[14400/15600]	[L1: 12.8568]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 38.435 (Best: 38.435 @epoch 1)
+Forward: 65.66s
+
+Saving...
+Total: 66.24s
+
+[Epoch 2]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 4.1257]	13.4+12.5s
+[3200/15600]	[L1: 4.0572]	11.0+0.1s
+[4800/15600]	[L1: 3.9493]	11.0+0.1s
+[6400/15600]	[L1: 3.8716]	13.4+0.1s
+[8000/15600]	[L1: 3.7974]	11.0+0.1s
+[9600/15600]	[L1: 3.7445]	10.9+0.1s
+[11200/15600]	[L1: 3.6817]	11.6+0.1s
+[12800/15600]	[L1: 3.6325]	13.0+0.1s
+[14400/15600]	[L1: 3.5798]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 41.828 (Best: 41.828 @epoch 2)
+Forward: 92.41s
+
+Saving...
+Total: 92.95s
+
+[Epoch 3]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 2.9799]	12.7+0.6s
+[3200/15600]	[L1: 2.9687]	10.9+0.1s
+[4800/15600]	[L1: 2.9725]	10.9+0.1s
+[6400/15600]	[L1: 2.9419]	12.2+0.1s
+[8000/15600]	[L1: 2.8952]	10.7+0.1s
+[9600/15600]	[L1: 2.8775]	10.9+0.1s
+[11200/15600]	[L1: 2.8594]	12.4+0.1s
+[12800/15600]	[L1: 2.8384]	10.7+0.1s
+[14400/15600]	[L1: 2.8041]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 43.388 (Best: 43.388 @epoch 3)
+Forward: 63.83s
+
+Saving...
+Total: 64.41s
+
+[Epoch 4]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 2.5549]	11.1+1.1s
+[3200/15600]	[L1: 2.5515]	12.6+0.1s
+[4800/15600]	[L1: 2.5167]	10.5+0.1s
+[6400/15600]	[L1: 2.4931]	10.2+0.1s
+[8000/15600]	[L1: 2.4859]	10.3+0.1s
+[9600/15600]	[L1: 2.4706]	12.7+0.1s
+[11200/15600]	[L1: 2.4463]	10.1+0.1s
+[12800/15600]	[L1: 2.4369]	10.3+0.1s
+[14400/15600]	[L1: 2.4144]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 43.420 (Best: 43.420 @epoch 4)
+Forward: 60.80s
+
+Saving...
+Total: 61.31s
+
+[Epoch 5]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 2.1779]	12.4+2.4s
+[3200/15600]	[L1: 2.1827]	10.4+0.1s
+[4800/15600]	[L1: 2.1870]	10.0+0.1s
+[6400/15600]	[L1: 2.1864]	11.7+0.1s
+[8000/15600]	[L1: 2.1557]	10.6+0.1s
+[9600/15600]	[L1: 2.1547]	10.7+0.1s
+[11200/15600]	[L1: 2.1449]	11.4+0.1s
+[12800/15600]	[L1: 2.1319]	11.8+0.1s
+[14400/15600]	[L1: 2.1201]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 44.083 (Best: 44.083 @epoch 5)
+Forward: 62.35s
+
+Saving...
+Total: 62.91s
+
+[Epoch 6]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.9331]	10.7+0.7s
+[3200/15600]	[L1: 1.9542]	10.6+0.1s
+[4800/15600]	[L1: 1.9679]	12.4+0.1s
+[6400/15600]	[L1: 1.9502]	10.8+0.1s
+[8000/15600]	[L1: 1.9480]	10.8+0.1s
+[9600/15600]	[L1: 1.9338]	12.4+0.1s
+[11200/15600]	[L1: 1.9238]	10.4+0.1s
+[12800/15600]	[L1: 1.9201]	10.3+0.1s
+[14400/15600]	[L1: 1.9098]	12.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 43.909 (Best: 44.083 @epoch 5)
+Forward: 58.44s
+
+Saving...
+Total: 59.02s
+
+[Epoch 7]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.8531]	12.6+0.6s
+[3200/15600]	[L1: 1.8407]	10.7+0.1s
+[4800/15600]	[L1: 1.8078]	10.9+0.1s
+[6400/15600]	[L1: 1.7936]	12.2+0.1s
+[8000/15600]	[L1: 1.7862]	11.0+0.1s
+[9600/15600]	[L1: 1.7796]	10.7+0.1s
+[11200/15600]	[L1: 1.7733]	10.7+0.1s
+[12800/15600]	[L1: 1.7603]	12.4+0.1s
+[14400/15600]	[L1: 1.7609]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 45.592 (Best: 45.592 @epoch 7)
+Forward: 65.05s
+
+Saving...
+Total: 65.57s
+
+[Epoch 8]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.7315]	10.8+0.5s
+[3200/15600]	[L1: 1.6909]	10.9+0.1s
+[4800/15600]	[L1: 1.6911]	12.5+0.1s
+[6400/15600]	[L1: 1.6867]	10.7+0.1s
+[8000/15600]	[L1: 1.6898]	10.8+0.1s
+[9600/15600]	[L1: 1.6735]	12.4+0.1s
+[11200/15600]	[L1: 1.6691]	10.9+0.1s
+[12800/15600]	[L1: 1.6564]	10.1+0.1s
+[14400/15600]	[L1: 1.6555]	11.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 43.193 (Best: 45.592 @epoch 7)
+Forward: 60.13s
+
+Saving...
+Total: 60.67s
+
+[Epoch 9]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.5863]	12.4+0.6s
+[3200/15600]	[L1: 1.5806]	10.7+0.1s
+[4800/15600]	[L1: 1.5915]	10.4+0.1s
+[6400/15600]	[L1: 1.5883]	12.1+0.1s
+[8000/15600]	[L1: 1.5768]	10.6+0.1s
+[9600/15600]	[L1: 1.5768]	10.5+0.1s
+[11200/15600]	[L1: 1.5748]	10.6+0.1s
+[12800/15600]	[L1: 1.5635]	12.1+0.1s
+[14400/15600]	[L1: 1.5584]	10.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 45.707 (Best: 45.707 @epoch 9)
+Forward: 62.60s
+
+Saving...
+Total: 63.16s
+
+[Epoch 10]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.5751]	10.8+0.6s
+[3200/15600]	[L1: 1.5093]	10.8+0.1s
+[4800/15600]	[L1: 1.5104]	12.3+0.1s
+[6400/15600]	[L1: 1.5133]	10.7+0.1s
+[8000/15600]	[L1: 1.4968]	10.7+0.1s
+[9600/15600]	[L1: 1.4879]	12.4+0.1s
+[11200/15600]	[L1: 1.4820]	10.8+0.1s
+[12800/15600]	[L1: 1.4667]	10.7+0.1s
+[14400/15600]	[L1: 1.4679]	11.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 44.957 (Best: 45.707 @epoch 9)
+Forward: 62.24s
+
+Saving...
+Total: 62.86s
+
+[Epoch 11]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.4042]	13.5+0.8s
+[3200/15600]	[L1: 1.4037]	11.1+0.1s
+[4800/15600]	[L1: 1.4000]	9.4+0.1s
+[6400/15600]	[L1: 1.3987]	10.2+0.1s
+[8000/15600]	[L1: 1.4009]	11.5+0.1s
+[9600/15600]	[L1: 1.3980]	9.5+0.1s
+[11200/15600]	[L1: 1.4010]	9.4+0.1s
+[12800/15600]	[L1: 1.4000]	11.3+0.1s
+[14400/15600]	[L1: 1.3954]	9.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 46.103 (Best: 46.103 @epoch 11)
+Forward: 63.88s
+
+Saving...
+Total: 64.42s
+
+[Epoch 12]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.3946]	10.7+0.6s
+[3200/15600]	[L1: 1.3561]	10.2+0.1s
+[4800/15600]	[L1: 1.3481]	10.0+0.1s
+[6400/15600]	[L1: 1.3462]	11.5+0.1s
+[8000/15600]	[L1: 1.3456]	10.4+0.1s
+[9600/15600]	[L1: 1.3473]	10.1+0.1s
+[11200/15600]	[L1: 1.3459]	11.6+0.1s
+[12800/15600]	[L1: 1.3479]	9.7+0.1s
+[14400/15600]	[L1: 1.3471]	9.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 45.266 (Best: 46.103 @epoch 11)
+Forward: 60.45s
+
+Saving...
+Total: 60.93s
+
+[Epoch 13]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.2866]	10.8+0.6s
+[3200/15600]	[L1: 1.2905]	11.4+0.1s
+[4800/15600]	[L1: 1.2951]	12.0+0.1s
+[6400/15600]	[L1: 1.2884]	10.9+0.1s
+[8000/15600]	[L1: 1.2847]	10.7+0.1s
+[9600/15600]	[L1: 1.2953]	12.2+0.1s
+[11200/15600]	[L1: 1.2861]	10.0+0.1s
+[12800/15600]	[L1: 1.2777]	9.7+0.1s
+[14400/15600]	[L1: 1.2819]	11.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 46.744 (Best: 46.744 @epoch 13)
+Forward: 61.59s
+
+Saving...
+Total: 62.14s
+
+[Epoch 14]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.2418]	12.2+1.2s
+[3200/15600]	[L1: 1.2167]	10.8+0.1s
+[4800/15600]	[L1: 1.2374]	10.1+0.1s
+[6400/15600]	[L1: 1.2439]	12.0+0.1s
+[8000/15600]	[L1: 1.2394]	9.7+0.1s
+[9600/15600]	[L1: 1.2423]	9.8+0.1s
+[11200/15600]	[L1: 1.2405]	9.9+0.1s
+[12800/15600]	[L1: 1.2384]	11.7+0.1s
+[14400/15600]	[L1: 1.2356]	10.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 42.621 (Best: 46.744 @epoch 13)
+Forward: 60.37s
+
+Saving...
+Total: 60.89s
+
+[Epoch 15]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.2098]	11.4+0.8s
+[3200/15600]	[L1: 1.2211]	9.9+0.1s
+[4800/15600]	[L1: 1.2056]	10.8+0.1s
+[6400/15600]	[L1: 1.2073]	9.6+0.1s
+[8000/15600]	[L1: 1.2231]	9.7+0.1s
+[9600/15600]	[L1: 1.2166]	10.2+0.1s
+[11200/15600]	[L1: 1.2143]	11.2+0.1s
+[12800/15600]	[L1: 1.2129]	10.0+0.1s
+[14400/15600]	[L1: 1.2095]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 47.196 (Best: 47.196 @epoch 15)
+Forward: 61.83s
+
+Saving...
+Total: 62.33s
+
+[Epoch 16]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.1675]	11.0+0.6s
+[3200/15600]	[L1: 1.1596]	12.5+0.1s
+[4800/15600]	[L1: 1.1465]	10.8+0.1s
+[6400/15600]	[L1: 1.1556]	10.9+0.1s
+[8000/15600]	[L1: 1.1483]	12.5+0.1s
+[9600/15600]	[L1: 1.1475]	10.7+0.1s
+[11200/15600]	[L1: 1.1442]	10.6+0.1s
+[12800/15600]	[L1: 1.1380]	11.5+0.1s
+[14400/15600]	[L1: 1.1430]	11.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 47.648 (Best: 47.648 @epoch 16)
+Forward: 57.64s
+
+Saving...
+Total: 58.49s
+
+[Epoch 17]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.1698]	10.7+0.8s
+[3200/15600]	[L1: 1.1542]	10.9+0.1s
+[4800/15600]	[L1: 1.1438]	10.9+0.1s
+[6400/15600]	[L1: 1.1274]	11.8+0.1s
+[8000/15600]	[L1: 1.1269]	10.9+0.1s
+[9600/15600]	[L1: 1.1248]	10.7+0.1s
+[11200/15600]	[L1: 1.1278]	12.3+0.1s
+[12800/15600]	[L1: 1.1411]	10.3+0.1s
+[14400/15600]	[L1: 1.1429]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 48.015 (Best: 48.015 @epoch 17)
+Forward: 56.23s
+
+Saving...
+Total: 56.81s
+
+[Epoch 18]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.1169]	9.7+0.5s
+[3200/15600]	[L1: 1.1066]	10.7+0.1s
+[4800/15600]	[L1: 1.1072]	12.2+0.1s
+[6400/15600]	[L1: 1.1036]	10.1+0.1s
+[8000/15600]	[L1: 1.1064]	10.1+0.1s
+[9600/15600]	[L1: 1.1056]	11.6+0.1s
+[11200/15600]	[L1: 1.1006]	9.6+0.1s
+[12800/15600]	[L1: 1.0979]	10.0+0.1s
+[14400/15600]	[L1: 1.1042]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 47.752 (Best: 48.015 @epoch 17)
+Forward: 59.91s
+
+Saving...
+Total: 60.41s
+
+[Epoch 19]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.0423]	11.0+0.5s
+[3200/15600]	[L1: 1.0899]	12.0+0.1s
+[4800/15600]	[L1: 1.0786]	11.0+0.1s
+[6400/15600]	[L1: 1.0769]	11.1+0.1s
+[8000/15600]	[L1: 1.0747]	12.8+0.1s
+[9600/15600]	[L1: 1.0796]	11.0+0.1s
+[11200/15600]	[L1: 1.0751]	10.9+0.1s
+[12800/15600]	[L1: 1.0700]	12.9+0.1s
+[14400/15600]	[L1: 1.0711]	10.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 47.736 (Best: 48.015 @epoch 17)
+Forward: 58.42s
+
+Saving...
+Total: 58.95s
+
+[Epoch 20]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.1533]	11.1+0.5s
+[3200/15600]	[L1: 1.0761]	10.9+0.1s
+[4800/15600]	[L1: 1.0656]	12.9+0.1s
+[6400/15600]	[L1: 1.0618]	11.1+0.1s
+[8000/15600]	[L1: 1.0553]	11.0+0.1s
+[9600/15600]	[L1: 1.0499]	12.8+0.1s
+[11200/15600]	[L1: 1.0494]	11.3+0.1s
+[12800/15600]	[L1: 1.0494]	11.4+0.1s
+[14400/15600]	[L1: 1.0573]	13.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 48.740 (Best: 48.740 @epoch 20)
+Forward: 60.49s
+
+Saving...
+Total: 61.01s
+
+[Epoch 21]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.0583]	13.0+0.5s
+[3200/15600]	[L1: 1.0627]	11.3+0.1s
+[4800/15600]	[L1: 1.0465]	11.0+0.1s
+[6400/15600]	[L1: 1.0517]	12.8+0.1s
+[8000/15600]	[L1: 1.0482]	11.1+0.1s
+[9600/15600]	[L1: 1.0474]	11.1+0.1s
+[11200/15600]	[L1: 1.0567]	12.6+0.1s
+[12800/15600]	[L1: 1.0575]	11.4+0.1s
+[14400/15600]	[L1: 1.0531]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 47.528 (Best: 48.740 @epoch 20)
+Forward: 62.65s
+
+Saving...
+Total: 63.15s
+
+[Epoch 22]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.0821]	10.9+0.6s
+[3200/15600]	[L1: 1.0742]	11.0+0.1s
+[4800/15600]	[L1: 1.0564]	13.1+0.1s
+[6400/15600]	[L1: 1.0408]	11.0+0.1s
+[8000/15600]	[L1: 1.0317]	11.3+0.1s
+[9600/15600]	[L1: 1.0305]	13.4+0.1s
+[11200/15600]	[L1: 1.0333]	11.1+0.1s
+[12800/15600]	[L1: 1.0297]	11.2+0.1s
+[14400/15600]	[L1: 1.0305]	12.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 48.820 (Best: 48.820 @epoch 22)
+Forward: 57.41s
+
+Saving...
+Total: 57.89s
+
+[Epoch 23]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.9399]	13.0+0.8s
+[3200/15600]	[L1: 0.9895]	10.1+0.1s
+[4800/15600]	[L1: 1.0118]	10.3+0.1s
+[6400/15600]	[L1: 1.0189]	11.1+0.1s
+[8000/15600]	[L1: 1.0191]	11.1+0.1s
+[9600/15600]	[L1: 1.0087]	9.7+0.1s
+[11200/15600]	[L1: 1.0099]	9.0+0.1s
+[12800/15600]	[L1: 1.0050]	10.8+0.1s
+[14400/15600]	[L1: 1.0050]	9.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 47.620 (Best: 48.820 @epoch 22)
+Forward: 59.02s
+
+Saving...
+Total: 59.78s
+
+[Epoch 24]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.9658]	11.4+0.8s
+[3200/15600]	[L1: 1.0171]	11.0+0.1s
+[4800/15600]	[L1: 1.0206]	10.9+0.1s
+[6400/15600]	[L1: 1.0031]	12.8+0.1s
+[8000/15600]	[L1: 0.9984]	11.0+0.1s
+[9600/15600]	[L1: 1.0005]	11.1+0.1s
+[11200/15600]	[L1: 0.9959]	12.7+0.1s
+[12800/15600]	[L1: 0.9971]	10.3+0.1s
+[14400/15600]	[L1: 0.9994]	10.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.307 (Best: 49.307 @epoch 24)
+Forward: 54.25s
+
+Saving...
+Total: 54.78s
+
+[Epoch 25]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.9650]	10.9+0.6s
+[3200/15600]	[L1: 0.9577]	12.5+0.1s
+[4800/15600]	[L1: 0.9678]	11.0+0.1s
+[6400/15600]	[L1: 0.9815]	11.0+0.1s
+[8000/15600]	[L1: 0.9856]	11.2+0.1s
+[9600/15600]	[L1: 0.9850]	12.2+0.1s
+[11200/15600]	[L1: 0.9801]	11.0+0.1s
+[12800/15600]	[L1: 0.9781]	10.9+0.1s
+[14400/15600]	[L1: 0.9723]	12.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 48.160 (Best: 49.307 @epoch 24)
+Forward: 55.01s
+
+Saving...
+Total: 55.53s
+
+[Epoch 26]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.9579]	13.2+0.6s
+[3200/15600]	[L1: 0.9601]	11.0+0.1s
+[4800/15600]	[L1: 0.9529]	11.1+0.1s
+[6400/15600]	[L1: 0.9517]	12.9+0.1s
+[8000/15600]	[L1: 0.9500]	11.0+0.1s
+[9600/15600]	[L1: 0.9609]	11.1+0.1s
+[11200/15600]	[L1: 0.9624]	12.8+0.1s
+[12800/15600]	[L1: 0.9636]	11.0+0.1s
+[14400/15600]	[L1: 0.9640]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.306 (Best: 49.307 @epoch 24)
+Forward: 55.27s
+
+Saving...
+Total: 55.77s
+
+[Epoch 27]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.9769]	10.0+0.5s
+[3200/15600]	[L1: 0.9806]	11.3+0.1s
+[4800/15600]	[L1: 0.9688]	12.8+0.1s
+[6400/15600]	[L1: 0.9635]	11.0+0.1s
+[8000/15600]	[L1: 0.9664]	10.9+0.1s
+[9600/15600]	[L1: 0.9612]	12.6+0.1s
+[11200/15600]	[L1: 0.9630]	11.1+0.1s
+[12800/15600]	[L1: 0.9679]	10.9+0.1s
+[14400/15600]	[L1: 0.9627]	12.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 48.323 (Best: 49.307 @epoch 24)
+Forward: 57.80s
+
+Saving...
+Total: 58.30s
+
+[Epoch 28]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.9503]	13.1+0.6s
+[3200/15600]	[L1: 0.9444]	11.0+0.1s
+[4800/15600]	[L1: 0.9426]	11.1+0.1s
+[6400/15600]	[L1: 0.9426]	12.9+0.1s
+[8000/15600]	[L1: 0.9368]	11.0+0.1s
+[9600/15600]	[L1: 0.9289]	11.1+0.1s
+[11200/15600]	[L1: 0.9290]	12.9+0.1s
+[12800/15600]	[L1: 0.9268]	11.0+0.1s
+[14400/15600]	[L1: 0.9257]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 48.192 (Best: 49.307 @epoch 24)
+Forward: 59.08s
+
+Saving...
+Total: 59.61s
+
+[Epoch 29]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.9728]	11.0+0.8s
+[3200/15600]	[L1: 0.9486]	11.0+0.1s
+[4800/15600]	[L1: 0.9321]	13.4+0.1s
+[6400/15600]	[L1: 0.9418]	10.5+0.1s
+[8000/15600]	[L1: 0.9430]	10.6+0.1s
+[9600/15600]	[L1: 0.9372]	12.7+0.1s
+[11200/15600]	[L1: 0.9319]	11.1+0.1s
+[12800/15600]	[L1: 0.9293]	10.7+0.1s
+[14400/15600]	[L1: 0.9269]	9.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.390 (Best: 49.390 @epoch 29)
+Forward: 82.52s
+
+Saving...
+Total: 83.30s
+
+[Epoch 30]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8398]	13.2+0.8s
+[3200/15600]	[L1: 0.8924]	11.0+0.1s
+[4800/15600]	[L1: 0.8967]	10.4+0.1s
+[6400/15600]	[L1: 0.8984]	11.6+0.1s
+[8000/15600]	[L1: 0.8942]	9.2+0.1s
+[9600/15600]	[L1: 0.9093]	10.5+0.1s
+[11200/15600]	[L1: 0.9111]	12.0+0.1s
+[12800/15600]	[L1: 0.9054]	9.5+0.1s
+[14400/15600]	[L1: 0.9122]	9.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.301 (Best: 49.390 @epoch 29)
+Forward: 62.99s
+
+Saving...
+Total: 63.66s
+
+[Epoch 31]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.9141]	10.9+0.7s
+[3200/15600]	[L1: 0.9216]	10.3+0.1s
+[4800/15600]	[L1: 0.9281]	12.2+0.1s
+[6400/15600]	[L1: 0.9166]	10.9+0.1s
+[8000/15600]	[L1: 0.9112]	10.2+0.1s
+[9600/15600]	[L1: 0.9165]	10.2+0.1s
+[11200/15600]	[L1: 0.9161]	12.1+0.1s
+[12800/15600]	[L1: 0.9107]	9.3+0.1s
+[14400/15600]	[L1: 0.9145]	9.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 48.071 (Best: 49.390 @epoch 29)
+Forward: 60.63s
+
+Saving...
+Total: 61.13s
+
+[Epoch 32]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8751]	11.3+0.8s
+[3200/15600]	[L1: 0.8796]	10.6+0.1s
+[4800/15600]	[L1: 0.8929]	13.5+0.1s
+[6400/15600]	[L1: 0.9085]	9.6+0.1s
+[8000/15600]	[L1: 0.9091]	10.2+0.1s
+[9600/15600]	[L1: 0.9148]	11.7+0.1s
+[11200/15600]	[L1: 0.9120]	12.0+0.1s
+[12800/15600]	[L1: 0.9064]	10.2+0.1s
+[14400/15600]	[L1: 0.8989]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.719 (Best: 49.719 @epoch 32)
+Forward: 69.16s
+
+Saving...
+Total: 69.68s
+
+[Epoch 33]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8430]	13.1+0.5s
+[3200/15600]	[L1: 0.8541]	11.0+0.1s
+[4800/15600]	[L1: 0.8670]	11.1+0.1s
+[6400/15600]	[L1: 0.8731]	12.8+0.1s
+[8000/15600]	[L1: 0.8856]	10.7+0.1s
+[9600/15600]	[L1: 0.8901]	10.2+0.1s
+[11200/15600]	[L1: 0.8903]	12.1+0.1s
+[12800/15600]	[L1: 0.8915]	9.6+0.1s
+[14400/15600]	[L1: 0.8858]	10.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.735 (Best: 49.735 @epoch 33)
+Forward: 62.52s
+
+Saving...
+Total: 63.05s
+
+[Epoch 34]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.9540]	10.7+0.5s
+[3200/15600]	[L1: 0.9154]	11.9+0.1s
+[4800/15600]	[L1: 0.9078]	11.4+0.1s
+[6400/15600]	[L1: 0.8899]	11.0+0.1s
+[8000/15600]	[L1: 0.8868]	10.8+0.1s
+[9600/15600]	[L1: 0.8824]	12.5+0.1s
+[11200/15600]	[L1: 0.8771]	10.8+0.1s
+[12800/15600]	[L1: 0.8801]	10.7+0.1s
+[14400/15600]	[L1: 0.8801]	12.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.155 (Best: 50.155 @epoch 34)
+Forward: 55.69s
+
+Saving...
+Total: 56.25s
+
+[Epoch 35]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8431]	11.9+0.5s
+[3200/15600]	[L1: 0.8889]	10.9+0.1s
+[4800/15600]	[L1: 0.8984]	9.8+0.1s
+[6400/15600]	[L1: 0.8879]	11.9+0.1s
+[8000/15600]	[L1: 0.8749]	10.5+0.1s
+[9600/15600]	[L1: 0.8734]	9.8+0.1s
+[11200/15600]	[L1: 0.8676]	9.7+0.1s
+[12800/15600]	[L1: 0.8711]	11.8+0.1s
+[14400/15600]	[L1: 0.8688]	9.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.663 (Best: 50.155 @epoch 34)
+Forward: 59.67s
+
+Saving...
+Total: 60.15s
+
+[Epoch 36]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8364]	11.0+0.6s
+[3200/15600]	[L1: 0.8828]	10.9+0.1s
+[4800/15600]	[L1: 0.8775]	12.3+0.1s
+[6400/15600]	[L1: 0.8783]	11.5+0.1s
+[8000/15600]	[L1: 0.8821]	11.0+0.1s
+[9600/15600]	[L1: 0.8805]	11.0+0.1s
+[11200/15600]	[L1: 0.8825]	12.8+0.1s
+[12800/15600]	[L1: 0.8780]	11.1+0.1s
+[14400/15600]	[L1: 0.8786]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.367 (Best: 50.155 @epoch 34)
+Forward: 57.65s
+
+Saving...
+Total: 58.17s
+
+[Epoch 37]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8539]	10.7+0.5s
+[3200/15600]	[L1: 0.8421]	12.6+0.1s
+[4800/15600]	[L1: 0.8374]	10.8+0.1s
+[6400/15600]	[L1: 0.8369]	11.0+0.1s
+[8000/15600]	[L1: 0.8371]	12.5+0.1s
+[9600/15600]	[L1: 0.8358]	10.8+0.1s
+[11200/15600]	[L1: 0.8425]	11.0+0.1s
+[12800/15600]	[L1: 0.8511]	12.8+0.1s
+[14400/15600]	[L1: 0.8477]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.726 (Best: 50.726 @epoch 37)
+Forward: 63.23s
+
+Saving...
+Total: 64.11s
+
+[Epoch 38]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8613]	11.2+1.0s
+[3200/15600]	[L1: 0.8404]	10.3+0.1s
+[4800/15600]	[L1: 0.8301]	9.3+0.1s
+[6400/15600]	[L1: 0.8406]	11.3+0.1s
+[8000/15600]	[L1: 0.8466]	9.1+0.1s
+[9600/15600]	[L1: 0.8404]	9.9+0.1s
+[11200/15600]	[L1: 0.8468]	10.6+0.1s
+[12800/15600]	[L1: 0.8548]	11.4+0.1s
+[14400/15600]	[L1: 0.8563]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.142 (Best: 50.726 @epoch 37)
+Forward: 63.98s
+
+Saving...
+Total: 64.47s
+
+[Epoch 39]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7950]	11.0+0.7s
+[3200/15600]	[L1: 0.8008]	9.8+0.1s
+[4800/15600]	[L1: 0.8155]	12.0+0.1s
+[6400/15600]	[L1: 0.8280]	10.6+0.1s
+[8000/15600]	[L1: 0.8236]	10.2+0.1s
+[9600/15600]	[L1: 0.8258]	10.0+0.1s
+[11200/15600]	[L1: 0.8263]	12.0+0.1s
+[12800/15600]	[L1: 0.8311]	10.2+0.1s
+[14400/15600]	[L1: 0.8372]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 48.403 (Best: 50.726 @epoch 37)
+Forward: 60.22s
+
+Saving...
+Total: 60.77s
+
+[Epoch 40]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8767]	10.8+0.6s
+[3200/15600]	[L1: 0.8857]	12.6+0.1s
+[4800/15600]	[L1: 0.8684]	11.0+0.1s
+[6400/15600]	[L1: 0.8570]	10.7+0.1s
+[8000/15600]	[L1: 0.8386]	12.5+0.1s
+[9600/15600]	[L1: 0.8401]	10.8+0.1s
+[11200/15600]	[L1: 0.8448]	10.0+0.1s
+[12800/15600]	[L1: 0.8407]	11.5+0.1s
+[14400/15600]	[L1: 0.8434]	11.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.576 (Best: 50.726 @epoch 37)
+Forward: 62.07s
+
+Saving...
+Total: 62.90s
+
+[Epoch 41]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8384]	11.1+0.5s
+[3200/15600]	[L1: 0.8319]	10.8+0.1s
+[4800/15600]	[L1: 0.8315]	10.9+0.1s
+[6400/15600]	[L1: 0.8378]	12.2+0.1s
+[8000/15600]	[L1: 0.8352]	10.8+0.1s
+[9600/15600]	[L1: 0.8377]	11.0+0.1s
+[11200/15600]	[L1: 0.8345]	12.4+0.1s
+[12800/15600]	[L1: 0.8384]	11.0+0.1s
+[14400/15600]	[L1: 0.8362]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.994 (Best: 50.726 @epoch 37)
+Forward: 59.87s
+
+Saving...
+Total: 60.52s
+
+[Epoch 42]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8061]	10.9+0.6s
+[3200/15600]	[L1: 0.8193]	12.4+0.1s
+[4800/15600]	[L1: 0.8080]	11.0+0.1s
+[6400/15600]	[L1: 0.8111]	11.0+0.1s
+[8000/15600]	[L1: 0.8061]	12.9+0.1s
+[9600/15600]	[L1: 0.8115]	11.3+0.1s
+[11200/15600]	[L1: 0.8138]	11.0+0.1s
+[12800/15600]	[L1: 0.8119]	12.6+0.1s
+[14400/15600]	[L1: 0.8132]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.246 (Best: 50.726 @epoch 37)
+Forward: 56.85s
+
+Saving...
+Total: 57.54s
+
+[Epoch 43]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8355]	11.1+0.5s
+[3200/15600]	[L1: 0.8301]	10.5+0.1s
+[4800/15600]	[L1: 0.8119]	10.7+0.1s
+[6400/15600]	[L1: 0.8028]	12.1+0.1s
+[8000/15600]	[L1: 0.8090]	10.9+0.1s
+[9600/15600]	[L1: 0.8136]	11.0+0.1s
+[11200/15600]	[L1: 0.8220]	12.5+0.1s
+[12800/15600]	[L1: 0.8203]	10.8+0.1s
+[14400/15600]	[L1: 0.8188]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.194 (Best: 50.726 @epoch 37)
+Forward: 57.38s
+
+Saving...
+Total: 57.89s
+
+[Epoch 44]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8092]	11.2+0.8s
+[3200/15600]	[L1: 0.8151]	12.1+0.1s
+[4800/15600]	[L1: 0.8113]	10.3+0.1s
+[6400/15600]	[L1: 0.8163]	10.2+0.1s
+[8000/15600]	[L1: 0.8086]	11.0+0.1s
+[9600/15600]	[L1: 0.8068]	11.8+0.1s
+[11200/15600]	[L1: 0.8091]	10.9+0.1s
+[12800/15600]	[L1: 0.8096]	10.3+0.1s
+[14400/15600]	[L1: 0.8108]	12.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.384 (Best: 50.726 @epoch 37)
+Forward: 57.47s
+
+Saving...
+Total: 57.95s
+
+[Epoch 45]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8279]	11.7+0.7s
+[3200/15600]	[L1: 0.8172]	9.7+0.1s
+[4800/15600]	[L1: 0.8185]	9.2+0.1s
+[6400/15600]	[L1: 0.8134]	11.3+0.1s
+[8000/15600]	[L1: 0.8083]	10.2+0.1s
+[9600/15600]	[L1: 0.7957]	10.3+0.1s
+[11200/15600]	[L1: 0.7962]	10.2+0.1s
+[12800/15600]	[L1: 0.7990]	11.9+0.1s
+[14400/15600]	[L1: 0.7965]	10.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.169 (Best: 50.726 @epoch 37)
+Forward: 56.28s
+
+Saving...
+Total: 56.75s
+
+[Epoch 46]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7932]	11.1+0.6s
+[3200/15600]	[L1: 0.7865]	11.0+0.1s
+[4800/15600]	[L1: 0.7872]	13.4+0.1s
+[6400/15600]	[L1: 0.7894]	11.4+0.1s
+[8000/15600]	[L1: 0.7956]	11.1+0.1s
+[9600/15600]	[L1: 0.7965]	12.7+0.1s
+[11200/15600]	[L1: 0.7949]	11.4+0.1s
+[12800/15600]	[L1: 0.7986]	11.1+0.1s
+[14400/15600]	[L1: 0.7985]	12.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.228 (Best: 50.726 @epoch 37)
+Forward: 59.97s
+
+Saving...
+Total: 60.42s
+
+[Epoch 47]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8037]	13.3+0.7s
+[3200/15600]	[L1: 0.8080]	10.7+0.1s
+[4800/15600]	[L1: 0.7961]	10.3+0.1s
+[6400/15600]	[L1: 0.7992]	10.3+0.1s
+[8000/15600]	[L1: 0.8012]	12.2+0.1s
+[9600/15600]	[L1: 0.7973]	10.2+0.1s
+[11200/15600]	[L1: 0.7973]	10.1+0.1s
+[12800/15600]	[L1: 0.7962]	11.8+0.1s
+[14400/15600]	[L1: 0.7942]	9.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.224 (Best: 50.726 @epoch 37)
+Forward: 58.46s
+
+Saving...
+Total: 59.30s
+
+[Epoch 48]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7851]	10.3+0.7s
+[3200/15600]	[L1: 0.7823]	9.6+0.1s
+[4800/15600]	[L1: 0.7844]	9.7+0.1s
+[6400/15600]	[L1: 0.7823]	11.6+0.1s
+[8000/15600]	[L1: 0.7791]	10.6+0.1s
+[9600/15600]	[L1: 0.7837]	10.6+0.1s
+[11200/15600]	[L1: 0.7892]	11.5+0.1s
+[12800/15600]	[L1: 0.7885]	11.1+0.1s
+[14400/15600]	[L1: 0.7890]	10.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.365 (Best: 50.726 @epoch 37)
+Forward: 58.89s
+
+Saving...
+Total: 59.37s
+
+[Epoch 49]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7928]	10.5+0.8s
+[3200/15600]	[L1: 0.7879]	10.4+0.1s
+[4800/15600]	[L1: 0.7801]	12.1+0.1s
+[6400/15600]	[L1: 0.7853]	10.2+0.1s
+[8000/15600]	[L1: 0.7876]	10.3+0.1s
+[9600/15600]	[L1: 0.7861]	10.8+0.1s
+[11200/15600]	[L1: 0.7798]	11.4+0.1s
+[12800/15600]	[L1: 0.7799]	10.2+0.1s
+[14400/15600]	[L1: 0.7772]	10.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.035 (Best: 51.035 @epoch 49)
+Forward: 54.97s
+
+Saving...
+Total: 55.47s
+
+[Epoch 50]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7727]	11.2+0.7s
+[3200/15600]	[L1: 0.7849]	12.1+0.1s
+[4800/15600]	[L1: 0.7826]	10.5+0.1s
+[6400/15600]	[L1: 0.7734]	11.1+0.1s
+[8000/15600]	[L1: 0.7746]	12.9+0.1s
+[9600/15600]	[L1: 0.7683]	11.2+0.1s
+[11200/15600]	[L1: 0.7660]	10.8+0.1s
+[12800/15600]	[L1: 0.7743]	11.3+0.1s
+[14400/15600]	[L1: 0.7700]	12.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.778 (Best: 51.035 @epoch 49)
+Forward: 57.28s
+
+Saving...
+Total: 57.75s
+
+[Epoch 51]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8169]	12.9+0.6s
+[3200/15600]	[L1: 0.7885]	10.9+0.1s
+[4800/15600]	[L1: 0.8053]	10.4+0.1s
+[6400/15600]	[L1: 0.7939]	13.3+0.1s
+[8000/15600]	[L1: 0.7894]	10.3+0.1s
+[9600/15600]	[L1: 0.8028]	9.8+0.1s
+[11200/15600]	[L1: 0.8033]	10.3+0.1s
+[12800/15600]	[L1: 0.7989]	13.2+0.1s
+[14400/15600]	[L1: 0.7941]	10.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.976 (Best: 51.035 @epoch 49)
+Forward: 61.24s
+
+Saving...
+Total: 61.90s
+
+[Epoch 52]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7714]	11.2+0.6s
+[3200/15600]	[L1: 0.7598]	11.1+0.1s
+[4800/15600]	[L1: 0.7856]	12.0+0.1s
+[6400/15600]	[L1: 0.7705]	11.9+0.1s
+[8000/15600]	[L1: 0.7672]	10.5+0.1s
+[9600/15600]	[L1: 0.7743]	10.8+0.1s
+[11200/15600]	[L1: 0.7764]	11.9+0.1s
+[12800/15600]	[L1: 0.7699]	10.8+0.1s
+[14400/15600]	[L1: 0.7631]	10.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.303 (Best: 51.303 @epoch 52)
+Forward: 59.03s
+
+Saving...
+Total: 59.53s
+
+[Epoch 53]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7652]	11.2+0.5s
+[3200/15600]	[L1: 0.7525]	12.6+0.1s
+[4800/15600]	[L1: 0.7442]	10.9+0.1s
+[6400/15600]	[L1: 0.7597]	10.9+0.1s
+[8000/15600]	[L1: 0.7575]	12.9+0.1s
+[9600/15600]	[L1: 0.7584]	10.8+0.1s
+[11200/15600]	[L1: 0.7590]	10.9+0.1s
+[12800/15600]	[L1: 0.7593]	12.1+0.1s
+[14400/15600]	[L1: 0.7626]	11.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.935 (Best: 51.303 @epoch 52)
+Forward: 59.11s
+
+Saving...
+Total: 60.05s
+
+[Epoch 54]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7697]	11.3+1.1s
+[3200/15600]	[L1: 0.7650]	11.2+0.1s
+[4800/15600]	[L1: 0.7684]	11.7+0.1s
+[6400/15600]	[L1: 0.7579]	13.0+0.1s
+[8000/15600]	[L1: 0.7577]	10.8+0.1s
+[9600/15600]	[L1: 0.7575]	10.6+0.1s
+[11200/15600]	[L1: 0.7613]	13.8+0.1s
+[12800/15600]	[L1: 0.7549]	11.0+0.1s
+[14400/15600]	[L1: 0.7587]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.018 (Best: 51.303 @epoch 52)
+Forward: 60.94s
+
+Saving...
+Total: 61.45s
+
+[Epoch 55]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7943]	11.3+0.7s
+[3200/15600]	[L1: 0.7847]	13.8+0.1s
+[4800/15600]	[L1: 0.7781]	11.0+0.1s
+[6400/15600]	[L1: 0.7618]	11.1+0.1s
+[8000/15600]	[L1: 0.7555]	13.5+0.1s
+[9600/15600]	[L1: 0.7578]	11.2+0.1s
+[11200/15600]	[L1: 0.7585]	11.1+0.1s
+[12800/15600]	[L1: 0.7560]	11.4+0.1s
+[14400/15600]	[L1: 0.7535]	13.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.098 (Best: 51.303 @epoch 52)
+Forward: 61.77s
+
+Saving...
+Total: 62.98s
+
+[Epoch 56]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7330]	11.9+1.0s
+[3200/15600]	[L1: 0.7212]	10.7+0.1s
+[4800/15600]	[L1: 0.7442]	11.0+0.1s
+[6400/15600]	[L1: 0.7466]	13.7+0.1s
+[8000/15600]	[L1: 0.7539]	11.1+0.1s
+[9600/15600]	[L1: 0.7510]	10.9+0.1s
+[11200/15600]	[L1: 0.7548]	13.7+0.1s
+[12800/15600]	[L1: 0.7536]	11.0+0.1s
+[14400/15600]	[L1: 0.7500]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.265 (Best: 51.303 @epoch 52)
+Forward: 59.01s
+
+Saving...
+Total: 59.47s
+
+[Epoch 57]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7613]	10.8+0.6s
+[3200/15600]	[L1: 0.7529]	13.0+0.1s
+[4800/15600]	[L1: 0.7465]	11.6+0.1s
+[6400/15600]	[L1: 0.7502]	11.1+0.1s
+[8000/15600]	[L1: 0.7513]	10.7+0.1s
+[9600/15600]	[L1: 0.7499]	13.5+0.1s
+[11200/15600]	[L1: 0.7474]	10.8+0.1s
+[12800/15600]	[L1: 0.7493]	11.1+0.1s
+[14400/15600]	[L1: 0.7476]	13.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.782 (Best: 51.303 @epoch 52)
+Forward: 59.94s
+
+Saving...
+Total: 60.44s
+
+[Epoch 58]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7690]	14.4+0.7s
+[3200/15600]	[L1: 0.7446]	11.2+0.1s
+[4800/15600]	[L1: 0.7456]	11.2+0.1s
+[6400/15600]	[L1: 0.7318]	13.7+0.1s
+[8000/15600]	[L1: 0.7394]	11.1+0.1s
+[9600/15600]	[L1: 0.7330]	11.0+0.1s
+[11200/15600]	[L1: 0.7287]	11.4+0.1s
+[12800/15600]	[L1: 0.7292]	11.6+0.1s
+[14400/15600]	[L1: 0.7314]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.788 (Best: 51.303 @epoch 52)
+Forward: 60.82s
+
+Saving...
+Total: 61.32s
+
+[Epoch 59]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7528]	11.0+0.7s
+[3200/15600]	[L1: 0.7472]	10.8+0.1s
+[4800/15600]	[L1: 0.7533]	13.4+0.1s
+[6400/15600]	[L1: 0.7462]	10.9+0.1s
+[8000/15600]	[L1: 0.7520]	10.7+0.1s
+[9600/15600]	[L1: 0.7614]	10.7+0.1s
+[11200/15600]	[L1: 0.7561]	13.4+0.1s
+[12800/15600]	[L1: 0.7556]	10.8+0.1s
+[14400/15600]	[L1: 0.7527]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.852 (Best: 51.852 @epoch 59)
+Forward: 59.97s
+
+Saving...
+Total: 60.48s
+
+[Epoch 60]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7803]	11.3+0.7s
+[3200/15600]	[L1: 0.7413]	13.7+0.1s
+[4800/15600]	[L1: 0.7284]	11.0+0.1s
+[6400/15600]	[L1: 0.7373]	10.9+0.1s
+[8000/15600]	[L1: 0.7318]	13.4+0.1s
+[9600/15600]	[L1: 0.7368]	11.1+0.1s
+[11200/15600]	[L1: 0.7357]	10.8+0.1s
+[12800/15600]	[L1: 0.7330]	13.1+0.1s
+[14400/15600]	[L1: 0.7291]	11.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.058 (Best: 51.852 @epoch 59)
+Forward: 63.30s
+
+Saving...
+Total: 64.19s
+
+[Epoch 61]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7313]	11.4+1.0s
+[3200/15600]	[L1: 0.7313]	10.9+0.1s
+[4800/15600]	[L1: 0.7212]	10.8+0.1s
+[6400/15600]	[L1: 0.7296]	13.6+0.1s
+[8000/15600]	[L1: 0.7280]	11.2+0.1s
+[9600/15600]	[L1: 0.7315]	11.3+0.1s
+[11200/15600]	[L1: 0.7308]	13.6+0.1s
+[12800/15600]	[L1: 0.7320]	11.0+0.1s
+[14400/15600]	[L1: 0.7308]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.112 (Best: 51.852 @epoch 59)
+Forward: 60.88s
+
+Saving...
+Total: 61.50s
+
+[Epoch 62]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7350]	10.4+0.6s
+[3200/15600]	[L1: 0.7526]	12.9+0.1s
+[4800/15600]	[L1: 0.7513]	10.2+0.1s
+[6400/15600]	[L1: 0.7435]	9.8+0.1s
+[8000/15600]	[L1: 0.7407]	9.2+0.1s
+[9600/15600]	[L1: 0.7394]	11.5+0.1s
+[11200/15600]	[L1: 0.7365]	9.3+0.1s
+[12800/15600]	[L1: 0.7382]	9.1+0.1s
+[14400/15600]	[L1: 0.7380]	9.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.912 (Best: 51.852 @epoch 59)
+Forward: 60.62s
+
+Saving...
+Total: 61.09s
+
+[Epoch 63]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7713]	11.3+0.8s
+[3200/15600]	[L1: 0.7785]	13.3+0.1s
+[4800/15600]	[L1: 0.7764]	10.8+0.1s
+[6400/15600]	[L1: 0.7615]	10.9+0.1s
+[8000/15600]	[L1: 0.7576]	13.8+0.1s
+[9600/15600]	[L1: 0.7482]	10.9+0.1s
+[11200/15600]	[L1: 0.7470]	10.8+0.1s
+[12800/15600]	[L1: 0.7469]	12.7+0.1s
+[14400/15600]	[L1: 0.7412]	11.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.395 (Best: 51.852 @epoch 59)
+Forward: 62.92s
+
+Saving...
+Total: 63.89s
+
+[Epoch 64]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7449]	11.3+1.0s
+[3200/15600]	[L1: 0.7312]	11.0+0.1s
+[4800/15600]	[L1: 0.7472]	10.5+0.1s
+[6400/15600]	[L1: 0.7434]	13.2+0.1s
+[8000/15600]	[L1: 0.7317]	10.0+0.1s
+[9600/15600]	[L1: 0.7328]	10.3+0.1s
+[11200/15600]	[L1: 0.7348]	12.8+0.1s
+[12800/15600]	[L1: 0.7320]	11.2+0.1s
+[14400/15600]	[L1: 0.7272]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.445 (Best: 51.852 @epoch 59)
+Forward: 61.00s
+
+Saving...
+Total: 61.48s
+
+[Epoch 65]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7003]	11.3+0.7s
+[3200/15600]	[L1: 0.7255]	11.0+0.1s
+[4800/15600]	[L1: 0.7251]	14.0+0.1s
+[6400/15600]	[L1: 0.7290]	11.1+0.1s
+[8000/15600]	[L1: 0.7267]	11.0+0.1s
+[9600/15600]	[L1: 0.7255]	13.8+0.1s
+[11200/15600]	[L1: 0.7263]	11.1+0.1s
+[12800/15600]	[L1: 0.7286]	11.0+0.1s
+[14400/15600]	[L1: 0.7271]	14.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.201 (Best: 51.852 @epoch 59)
+Forward: 59.56s
+
+Saving...
+Total: 60.08s
+
+[Epoch 66]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6811]	14.0+0.7s
+[3200/15600]	[L1: 0.6940]	11.1+0.1s
+[4800/15600]	[L1: 0.7025]	10.9+0.1s
+[6400/15600]	[L1: 0.7034]	13.0+0.1s
+[8000/15600]	[L1: 0.7121]	11.9+0.1s
+[9600/15600]	[L1: 0.7140]	11.0+0.1s
+[11200/15600]	[L1: 0.7142]	11.2+0.1s
+[12800/15600]	[L1: 0.7159]	14.0+0.1s
+[14400/15600]	[L1: 0.7155]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.105 (Best: 51.852 @epoch 59)
+Forward: 61.45s
+
+Saving...
+Total: 61.95s
+
+[Epoch 67]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7363]	11.0+0.7s
+[3200/15600]	[L1: 0.7295]	10.5+0.1s
+[4800/15600]	[L1: 0.7202]	11.2+0.1s
+[6400/15600]	[L1: 0.7268]	13.0+0.1s
+[8000/15600]	[L1: 0.7256]	11.0+0.1s
+[9600/15600]	[L1: 0.7184]	11.0+0.1s
+[11200/15600]	[L1: 0.7179]	12.6+0.1s
+[12800/15600]	[L1: 0.7175]	9.8+0.1s
+[14400/15600]	[L1: 0.7164]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.688 (Best: 51.852 @epoch 59)
+Forward: 61.70s
+
+Saving...
+Total: 62.23s
+
+[Epoch 68]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7464]	11.0+0.7s
+[3200/15600]	[L1: 0.7163]	11.2+0.1s
+[4800/15600]	[L1: 0.7089]	13.8+0.1s
+[6400/15600]	[L1: 0.7118]	11.1+0.1s
+[8000/15600]	[L1: 0.7165]	11.0+0.1s
+[9600/15600]	[L1: 0.7141]	14.3+0.1s
+[11200/15600]	[L1: 0.7130]	11.0+0.1s
+[12800/15600]	[L1: 0.7117]	11.0+0.1s
+[14400/15600]	[L1: 0.7099]	13.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.247 (Best: 51.852 @epoch 59)
+Forward: 62.52s
+
+Saving...
+Total: 63.19s
+
+[Epoch 69]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7220]	13.3+0.7s
+[3200/15600]	[L1: 0.7217]	10.2+0.1s
+[4800/15600]	[L1: 0.7247]	9.7+0.1s
+[6400/15600]	[L1: 0.7226]	12.1+0.1s
+[8000/15600]	[L1: 0.7199]	11.8+0.1s
+[9600/15600]	[L1: 0.7228]	10.9+0.1s
+[11200/15600]	[L1: 0.7198]	11.1+0.1s
+[12800/15600]	[L1: 0.7191]	12.7+0.1s
+[14400/15600]	[L1: 0.7161]	9.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.537 (Best: 51.852 @epoch 59)
+Forward: 62.19s
+
+Saving...
+Total: 62.86s
+
+[Epoch 70]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6984]	11.0+0.7s
+[3200/15600]	[L1: 0.6983]	10.0+0.1s
+[4800/15600]	[L1: 0.7178]	9.8+0.1s
+[6400/15600]	[L1: 0.7144]	12.4+0.1s
+[8000/15600]	[L1: 0.7234]	9.5+0.1s
+[9600/15600]	[L1: 0.7297]	10.4+0.1s
+[11200/15600]	[L1: 0.7230]	13.7+0.1s
+[12800/15600]	[L1: 0.7220]	10.2+0.1s
+[14400/15600]	[L1: 0.7210]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.790 (Best: 51.852 @epoch 59)
+Forward: 64.52s
+
+Saving...
+Total: 65.01s
+
+[Epoch 71]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6871]	10.2+0.7s
+[3200/15600]	[L1: 0.7015]	10.3+0.1s
+[4800/15600]	[L1: 0.7072]	13.5+0.1s
+[6400/15600]	[L1: 0.7148]	10.5+0.1s
+[8000/15600]	[L1: 0.7082]	10.4+0.1s
+[9600/15600]	[L1: 0.7024]	13.3+0.1s
+[11200/15600]	[L1: 0.7014]	11.5+0.1s
+[12800/15600]	[L1: 0.7018]	10.8+0.1s
+[14400/15600]	[L1: 0.7079]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.192 (Best: 51.852 @epoch 59)
+Forward: 61.72s
+
+Saving...
+Total: 62.22s
+
+[Epoch 72]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7312]	11.6+0.7s
+[3200/15600]	[L1: 0.7336]	13.1+0.1s
+[4800/15600]	[L1: 0.7174]	11.0+0.1s
+[6400/15600]	[L1: 0.7116]	11.1+0.1s
+[8000/15600]	[L1: 0.7139]	13.7+0.1s
+[9600/15600]	[L1: 0.7167]	10.7+0.1s
+[11200/15600]	[L1: 0.7115]	10.6+0.1s
+[12800/15600]	[L1: 0.7114]	13.8+0.1s
+[14400/15600]	[L1: 0.7098]	10.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.988 (Best: 51.852 @epoch 59)
+Forward: 61.34s
+
+Saving...
+Total: 62.35s
+
+[Epoch 73]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6458]	11.1+1.0s
+[3200/15600]	[L1: 0.6697]	10.8+0.1s
+[4800/15600]	[L1: 0.6803]	11.5+0.1s
+[6400/15600]	[L1: 0.6991]	13.0+0.1s
+[8000/15600]	[L1: 0.7063]	10.4+0.1s
+[9600/15600]	[L1: 0.7027]	10.7+0.1s
+[11200/15600]	[L1: 0.7005]	13.8+0.1s
+[12800/15600]	[L1: 0.7016]	11.5+0.1s
+[14400/15600]	[L1: 0.6989]	11.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.154 (Best: 51.852 @epoch 59)
+Forward: 65.05s
+
+Saving...
+Total: 65.57s
+
+[Epoch 74]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6861]	12.0+0.7s
+[3200/15600]	[L1: 0.6880]	12.7+0.1s
+[4800/15600]	[L1: 0.7039]	10.7+0.1s
+[6400/15600]	[L1: 0.7027]	10.8+0.1s
+[8000/15600]	[L1: 0.6988]	13.4+0.1s
+[9600/15600]	[L1: 0.7039]	10.5+0.1s
+[11200/15600]	[L1: 0.7005]	10.9+0.1s
+[12800/15600]	[L1: 0.7041]	13.4+0.1s
+[14400/15600]	[L1: 0.7004]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.523 (Best: 51.852 @epoch 59)
+Forward: 62.63s
+
+Saving...
+Total: 63.49s
+
+[Epoch 75]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6961]	11.2+1.0s
+[3200/15600]	[L1: 0.6967]	10.0+0.1s
+[4800/15600]	[L1: 0.7011]	10.3+0.1s
+[6400/15600]	[L1: 0.6930]	13.3+0.1s
+[8000/15600]	[L1: 0.6998]	10.2+0.1s
+[9600/15600]	[L1: 0.6992]	11.0+0.1s
+[11200/15600]	[L1: 0.6966]	13.3+0.1s
+[12800/15600]	[L1: 0.6977]	9.7+0.1s
+[14400/15600]	[L1: 0.6965]	9.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.161 (Best: 51.852 @epoch 59)
+Forward: 63.77s
+
+Saving...
+Total: 64.27s
+
+[Epoch 76]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7057]	11.2+0.7s
+[3200/15600]	[L1: 0.7092]	11.2+0.1s
+[4800/15600]	[L1: 0.7105]	12.3+0.1s
+[6400/15600]	[L1: 0.7083]	10.6+0.1s
+[8000/15600]	[L1: 0.7055]	9.9+0.1s
+[9600/15600]	[L1: 0.7018]	11.8+0.1s
+[11200/15600]	[L1: 0.6990]	11.3+0.1s
+[12800/15600]	[L1: 0.6911]	10.2+0.1s
+[14400/15600]	[L1: 0.6914]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.616 (Best: 51.852 @epoch 59)
+Forward: 60.76s
+
+Saving...
+Total: 61.31s
+
+[Epoch 77]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6625]	10.8+0.7s
+[3200/15600]	[L1: 0.6662]	13.1+0.1s
+[4800/15600]	[L1: 0.6745]	10.8+0.1s
+[6400/15600]	[L1: 0.6898]	10.6+0.1s
+[8000/15600]	[L1: 0.6949]	13.6+0.1s
+[9600/15600]	[L1: 0.6952]	11.2+0.1s
+[11200/15600]	[L1: 0.6950]	10.9+0.1s
+[12800/15600]	[L1: 0.6912]	11.4+0.1s
+[14400/15600]	[L1: 0.6882]	12.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.295 (Best: 52.295 @epoch 77)
+Forward: 61.79s
+
+Saving...
+Total: 62.79s
+
+[Epoch 78]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6601]	12.4+1.1s
+[3200/15600]	[L1: 0.6691]	11.0+0.1s
+[4800/15600]	[L1: 0.6800]	11.2+0.1s
+[6400/15600]	[L1: 0.6777]	13.6+0.1s
+[8000/15600]	[L1: 0.6941]	11.1+0.1s
+[9600/15600]	[L1: 0.7024]	10.9+0.1s
+[11200/15600]	[L1: 0.7009]	13.6+0.1s
+[12800/15600]	[L1: 0.7009]	10.3+0.1s
+[14400/15600]	[L1: 0.6950]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.726 (Best: 52.295 @epoch 77)
+Forward: 60.46s
+
+Saving...
+Total: 60.99s
+
+[Epoch 79]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7070]	10.7+0.7s
+[3200/15600]	[L1: 0.6900]	10.5+0.1s
+[4800/15600]	[L1: 0.6941]	13.1+0.1s
+[6400/15600]	[L1: 0.6863]	10.7+0.1s
+[8000/15600]	[L1: 0.6868]	10.6+0.1s
+[9600/15600]	[L1: 0.6822]	11.8+0.1s
+[11200/15600]	[L1: 0.6824]	13.1+0.1s
+[12800/15600]	[L1: 0.6829]	11.1+0.1s
+[14400/15600]	[L1: 0.6789]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.368 (Best: 52.368 @epoch 79)
+Forward: 58.34s
+
+Saving...
+Total: 58.91s
+
+[Epoch 80]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6554]	11.3+0.7s
+[3200/15600]	[L1: 0.6698]	13.5+0.1s
+[4800/15600]	[L1: 0.6870]	11.0+0.1s
+[6400/15600]	[L1: 0.6886]	11.0+0.1s
+[8000/15600]	[L1: 0.6865]	13.8+0.1s
+[9600/15600]	[L1: 0.6866]	10.9+0.1s
+[11200/15600]	[L1: 0.6861]	10.5+0.1s
+[12800/15600]	[L1: 0.6832]	13.0+0.1s
+[14400/15600]	[L1: 0.6862]	11.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.091 (Best: 52.368 @epoch 79)
+Forward: 58.44s
+
+Saving...
+Total: 59.29s
+
+[Epoch 81]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6817]	10.1+0.8s
+[3200/15600]	[L1: 0.6692]	10.2+0.1s
+[4800/15600]	[L1: 0.6671]	10.1+0.1s
+[6400/15600]	[L1: 0.6632]	11.6+0.1s
+[8000/15600]	[L1: 0.6720]	10.0+0.1s
+[9600/15600]	[L1: 0.6710]	10.3+0.1s
+[11200/15600]	[L1: 0.6747]	11.0+0.1s
+[12800/15600]	[L1: 0.6732]	12.6+0.1s
+[14400/15600]	[L1: 0.6717]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.782 (Best: 52.368 @epoch 79)
+Forward: 63.78s
+
+Saving...
+Total: 64.28s
+
+[Epoch 82]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7049]	11.6+0.8s
+[3200/15600]	[L1: 0.6873]	10.1+0.1s
+[4800/15600]	[L1: 0.6790]	13.0+0.1s
+[6400/15600]	[L1: 0.6819]	11.3+0.1s
+[8000/15600]	[L1: 0.6782]	11.1+0.1s
+[9600/15600]	[L1: 0.6864]	11.3+0.1s
+[11200/15600]	[L1: 0.6872]	12.1+0.1s
+[12800/15600]	[L1: 0.6875]	9.7+0.1s
+[14400/15600]	[L1: 0.6867]	10.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.149 (Best: 52.368 @epoch 79)
+Forward: 61.39s
+
+Saving...
+Total: 61.91s
+
+[Epoch 83]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6753]	11.0+0.7s
+[3200/15600]	[L1: 0.6772]	13.6+0.1s
+[4800/15600]	[L1: 0.6701]	10.9+0.1s
+[6400/15600]	[L1: 0.6772]	10.8+0.1s
+[8000/15600]	[L1: 0.6830]	12.4+0.1s
+[9600/15600]	[L1: 0.6782]	11.9+0.1s
+[11200/15600]	[L1: 0.6837]	10.8+0.1s
+[12800/15600]	[L1: 0.6792]	11.0+0.1s
+[14400/15600]	[L1: 0.6802]	13.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.321 (Best: 52.368 @epoch 79)
+Forward: 65.14s
+
+Saving...
+Total: 66.01s
+
+[Epoch 84]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6435]	12.0+0.9s
+[3200/15600]	[L1: 0.6757]	10.9+0.1s
+[4800/15600]	[L1: 0.6802]	11.1+0.1s
+[6400/15600]	[L1: 0.6760]	13.6+0.1s
+[8000/15600]	[L1: 0.6750]	11.0+0.1s
+[9600/15600]	[L1: 0.6709]	11.1+0.1s
+[11200/15600]	[L1: 0.6742]	13.8+0.1s
+[12800/15600]	[L1: 0.6714]	11.1+0.1s
+[14400/15600]	[L1: 0.6691]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.827 (Best: 52.368 @epoch 79)
+Forward: 61.30s
+
+Saving...
+Total: 61.93s
+
+[Epoch 85]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6873]	11.0+0.7s
+[3200/15600]	[L1: 0.6874]	13.8+0.1s
+[4800/15600]	[L1: 0.6905]	10.7+0.1s
+[6400/15600]	[L1: 0.6882]	10.9+0.1s
+[8000/15600]	[L1: 0.6789]	13.9+0.1s
+[9600/15600]	[L1: 0.6824]	10.9+0.1s
+[11200/15600]	[L1: 0.6813]	11.1+0.1s
+[12800/15600]	[L1: 0.6831]	12.1+0.1s
+[14400/15600]	[L1: 0.6804]	12.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.242 (Best: 52.368 @epoch 79)
+Forward: 64.75s
+
+Saving...
+Total: 65.61s
+
+[Epoch 86]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6673]	11.1+1.0s
+[3200/15600]	[L1: 0.6653]	10.9+0.1s
+[4800/15600]	[L1: 0.6679]	11.4+0.1s
+[6400/15600]	[L1: 0.6683]	13.4+0.1s
+[8000/15600]	[L1: 0.6690]	10.9+0.1s
+[9600/15600]	[L1: 0.6712]	10.9+0.1s
+[11200/15600]	[L1: 0.6728]	13.7+0.1s
+[12800/15600]	[L1: 0.6736]	11.0+0.1s
+[14400/15600]	[L1: 0.6735]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.656 (Best: 52.368 @epoch 79)
+Forward: 59.05s
+
+Saving...
+Total: 59.51s
+
+[Epoch 87]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6598]	10.7+0.7s
+[3200/15600]	[L1: 0.6636]	13.1+0.1s
+[4800/15600]	[L1: 0.6662]	9.6+0.1s
+[6400/15600]	[L1: 0.6672]	10.4+0.1s
+[8000/15600]	[L1: 0.6641]	10.4+0.1s
+[9600/15600]	[L1: 0.6621]	13.0+0.1s
+[11200/15600]	[L1: 0.6604]	10.5+0.1s
+[12800/15600]	[L1: 0.6571]	10.4+0.1s
+[14400/15600]	[L1: 0.6605]	12.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.838 (Best: 52.368 @epoch 79)
+Forward: 59.26s
+
+Saving...
+Total: 59.77s
+
+[Epoch 88]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6667]	12.7+0.8s
+[3200/15600]	[L1: 0.6939]	11.0+0.1s
+[4800/15600]	[L1: 0.6903]	11.1+0.1s
+[6400/15600]	[L1: 0.6815]	13.8+0.1s
+[8000/15600]	[L1: 0.6778]	11.1+0.1s
+[9600/15600]	[L1: 0.6698]	11.0+0.1s
+[11200/15600]	[L1: 0.6650]	11.5+0.1s
+[12800/15600]	[L1: 0.6672]	13.3+0.1s
+[14400/15600]	[L1: 0.6661]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.046 (Best: 52.368 @epoch 79)
+Forward: 65.06s
+
+Saving...
+Total: 65.70s
+
+[Epoch 89]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6670]	11.1+0.7s
+[3200/15600]	[L1: 0.6835]	10.7+0.1s
+[4800/15600]	[L1: 0.6695]	14.0+0.1s
+[6400/15600]	[L1: 0.6664]	11.0+0.1s
+[8000/15600]	[L1: 0.6635]	11.0+0.1s
+[9600/15600]	[L1: 0.6642]	13.8+0.1s
+[11200/15600]	[L1: 0.6632]	10.8+0.1s
+[12800/15600]	[L1: 0.6642]	11.2+0.1s
+[14400/15600]	[L1: 0.6646]	12.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.230 (Best: 52.368 @epoch 79)
+Forward: 63.71s
+
+Saving...
+Total: 64.35s
+
+[Epoch 90]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6874]	13.6+0.7s
+[3200/15600]	[L1: 0.6721]	10.8+0.1s
+[4800/15600]	[L1: 0.6673]	10.4+0.1s
+[6400/15600]	[L1: 0.6662]	10.2+0.1s
+[8000/15600]	[L1: 0.6689]	13.3+0.1s
+[9600/15600]	[L1: 0.6671]	10.1+0.1s
+[11200/15600]	[L1: 0.6666]	10.1+0.1s
+[12800/15600]	[L1: 0.6732]	12.9+0.1s
+[14400/15600]	[L1: 0.6696]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.295 (Best: 52.368 @epoch 79)
+Forward: 64.12s
+
+Saving...
+Total: 64.91s
+
+[Epoch 91]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6484]	11.2+0.9s
+[3200/15600]	[L1: 0.6352]	11.2+0.1s
+[4800/15600]	[L1: 0.6447]	12.2+0.1s
+[6400/15600]	[L1: 0.6427]	12.7+0.1s
+[8000/15600]	[L1: 0.6483]	11.1+0.1s
+[9600/15600]	[L1: 0.6504]	11.1+0.1s
+[11200/15600]	[L1: 0.6538]	13.9+0.1s
+[12800/15600]	[L1: 0.6490]	11.6+0.1s
+[14400/15600]	[L1: 0.6497]	11.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.526 (Best: 52.526 @epoch 91)
+Forward: 63.18s
+
+Saving...
+Total: 63.71s
+
+[Epoch 92]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6084]	12.2+0.7s
+[3200/15600]	[L1: 0.6249]	12.6+0.1s
+[4800/15600]	[L1: 0.6411]	11.0+0.1s
+[6400/15600]	[L1: 0.6571]	11.3+0.1s
+[8000/15600]	[L1: 0.6629]	14.2+0.1s
+[9600/15600]	[L1: 0.6624]	11.0+0.1s
+[11200/15600]	[L1: 0.6581]	10.4+0.1s
+[12800/15600]	[L1: 0.6546]	13.5+0.1s
+[14400/15600]	[L1: 0.6570]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.954 (Best: 52.526 @epoch 91)
+Forward: 61.65s
+
+Saving...
+Total: 62.16s
+
+[Epoch 93]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7218]	10.1+0.6s
+[3200/15600]	[L1: 0.6851]	10.5+0.1s
+[4800/15600]	[L1: 0.6797]	11.0+0.1s
+[6400/15600]	[L1: 0.6730]	13.6+0.1s
+[8000/15600]	[L1: 0.6693]	10.9+0.1s
+[9600/15600]	[L1: 0.6666]	9.7+0.1s
+[11200/15600]	[L1: 0.6653]	12.4+0.1s
+[12800/15600]	[L1: 0.6601]	10.4+0.1s
+[14400/15600]	[L1: 0.6553]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.338 (Best: 52.526 @epoch 91)
+Forward: 65.30s
+
+Saving...
+Total: 65.80s
+
+[Epoch 94]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6624]	11.1+0.8s
+[3200/15600]	[L1: 0.6567]	11.2+0.1s
+[4800/15600]	[L1: 0.6609]	13.3+0.1s
+[6400/15600]	[L1: 0.6558]	9.8+0.1s
+[8000/15600]	[L1: 0.6571]	9.7+0.1s
+[9600/15600]	[L1: 0.6547]	11.7+0.1s
+[11200/15600]	[L1: 0.6587]	11.1+0.1s
+[12800/15600]	[L1: 0.6550]	9.7+0.1s
+[14400/15600]	[L1: 0.6534]	9.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.451 (Best: 52.526 @epoch 91)
+Forward: 63.90s
+
+Saving...
+Total: 64.40s
+
+[Epoch 95]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6858]	10.9+0.7s
+[3200/15600]	[L1: 0.6526]	13.6+0.1s
+[4800/15600]	[L1: 0.6607]	10.8+0.1s
+[6400/15600]	[L1: 0.6695]	10.9+0.1s
+[8000/15600]	[L1: 0.6706]	13.7+0.1s
+[9600/15600]	[L1: 0.6665]	11.0+0.1s
+[11200/15600]	[L1: 0.6669]	11.1+0.1s
+[12800/15600]	[L1: 0.6666]	13.6+0.1s
+[14400/15600]	[L1: 0.6664]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.368 (Best: 52.526 @epoch 91)
+Forward: 66.01s
+
+Saving...
+Total: 66.50s
+
+[Epoch 96]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6637]	11.1+0.7s
+[3200/15600]	[L1: 0.6656]	10.7+0.1s
+[4800/15600]	[L1: 0.6784]	12.0+0.1s
+[6400/15600]	[L1: 0.6700]	11.9+0.1s
+[8000/15600]	[L1: 0.6665]	10.9+0.1s
+[9600/15600]	[L1: 0.6634]	10.8+0.1s
+[11200/15600]	[L1: 0.6622]	13.4+0.1s
+[12800/15600]	[L1: 0.6630]	10.9+0.1s
+[14400/15600]	[L1: 0.6585]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.519 (Best: 52.526 @epoch 91)
+Forward: 62.73s
+
+Saving...
+Total: 63.23s
+
+[Epoch 97]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6181]	10.5+0.6s
+[3200/15600]	[L1: 0.6324]	12.7+0.1s
+[4800/15600]	[L1: 0.6494]	11.0+0.1s
+[6400/15600]	[L1: 0.6461]	11.2+0.1s
+[8000/15600]	[L1: 0.6418]	13.1+0.1s
+[9600/15600]	[L1: 0.6415]	11.3+0.1s
+[11200/15600]	[L1: 0.6397]	10.7+0.1s
+[12800/15600]	[L1: 0.6430]	12.9+0.1s
+[14400/15600]	[L1: 0.6418]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.754 (Best: 52.526 @epoch 91)
+Forward: 64.67s
+
+Saving...
+Total: 65.20s
+
+[Epoch 98]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6929]	11.3+0.5s
+[3200/15600]	[L1: 0.6965]	11.4+0.1s
+[4800/15600]	[L1: 0.6732]	13.2+0.1s
+[6400/15600]	[L1: 0.6658]	11.0+0.1s
+[8000/15600]	[L1: 0.6626]	11.0+0.1s
+[9600/15600]	[L1: 0.6530]	12.7+0.1s
+[11200/15600]	[L1: 0.6545]	11.0+0.1s
+[12800/15600]	[L1: 0.6525]	10.9+0.1s
+[14400/15600]	[L1: 0.6525]	12.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.856 (Best: 52.526 @epoch 91)
+Forward: 62.33s
+
+Saving...
+Total: 63.03s
+
+[Epoch 99]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6762]	13.7+0.8s
+[3200/15600]	[L1: 0.6528]	11.0+0.1s
+[4800/15600]	[L1: 0.6519]	11.1+0.1s
+[6400/15600]	[L1: 0.6544]	13.7+0.1s
+[8000/15600]	[L1: 0.6542]	11.3+0.1s
+[9600/15600]	[L1: 0.6581]	11.2+0.1s
+[11200/15600]	[L1: 0.6625]	11.5+0.1s
+[12800/15600]	[L1: 0.6592]	13.5+0.1s
+[14400/15600]	[L1: 0.6630]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.408 (Best: 52.526 @epoch 91)
+Forward: 65.88s
+
+Saving...
+Total: 66.40s
+
+[Epoch 100]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.6006]	11.3+0.7s
+[3200/15600]	[L1: 0.5932]	11.4+0.1s
+[4800/15600]	[L1: 0.5796]	13.7+0.1s
+[6400/15600]	[L1: 0.5798]	11.1+0.1s
+[8000/15600]	[L1: 0.5773]	11.0+0.1s
+[9600/15600]	[L1: 0.5751]	13.9+0.1s
+[11200/15600]	[L1: 0.5766]	11.0+0.1s
+[12800/15600]	[L1: 0.5741]	11.1+0.1s
+[14400/15600]	[L1: 0.5725]	13.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.329 (Best: 53.329 @epoch 100)
+Forward: 65.31s
+
+Saving...
+Total: 65.82s
+
+[Epoch 101]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5781]	14.1+0.7s
+[3200/15600]	[L1: 0.5738]	11.1+0.1s
+[4800/15600]	[L1: 0.5727]	11.3+0.1s
+[6400/15600]	[L1: 0.5760]	14.1+0.1s
+[8000/15600]	[L1: 0.5783]	11.4+0.1s
+[9600/15600]	[L1: 0.5747]	11.4+0.1s
+[11200/15600]	[L1: 0.5747]	14.1+0.1s
+[12800/15600]	[L1: 0.5751]	10.9+0.1s
+[14400/15600]	[L1: 0.5736]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.083 (Best: 53.329 @epoch 100)
+Forward: 65.46s
+
+Saving...
+Total: 65.96s
+
+[Epoch 102]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5913]	11.1+0.7s
+[3200/15600]	[L1: 0.5799]	10.4+0.1s
+[4800/15600]	[L1: 0.5818]	13.6+0.1s
+[6400/15600]	[L1: 0.5795]	10.7+0.1s
+[8000/15600]	[L1: 0.5768]	10.6+0.1s
+[9600/15600]	[L1: 0.5735]	13.6+0.1s
+[11200/15600]	[L1: 0.5723]	11.1+0.1s
+[12800/15600]	[L1: 0.5747]	10.1+0.1s
+[14400/15600]	[L1: 0.5751]	12.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.665 (Best: 53.329 @epoch 100)
+Forward: 61.28s
+
+Saving...
+Total: 61.85s
+
+[Epoch 103]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5481]	13.8+0.7s
+[3200/15600]	[L1: 0.5626]	10.9+0.1s
+[4800/15600]	[L1: 0.5630]	10.9+0.1s
+[6400/15600]	[L1: 0.5643]	13.5+0.1s
+[8000/15600]	[L1: 0.5633]	11.0+0.1s
+[9600/15600]	[L1: 0.5637]	11.2+0.1s
+[11200/15600]	[L1: 0.5647]	11.9+0.1s
+[12800/15600]	[L1: 0.5654]	12.9+0.1s
+[14400/15600]	[L1: 0.5655]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.761 (Best: 53.329 @epoch 100)
+Forward: 66.65s
+
+Saving...
+Total: 67.16s
+
+[Epoch 104]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5897]	11.2+0.7s
+[3200/15600]	[L1: 0.5803]	10.8+0.1s
+[4800/15600]	[L1: 0.5786]	13.6+0.1s
+[6400/15600]	[L1: 0.5713]	10.9+0.1s
+[8000/15600]	[L1: 0.5731]	11.0+0.1s
+[9600/15600]	[L1: 0.5802]	13.5+0.1s
+[11200/15600]	[L1: 0.5788]	10.8+0.1s
+[12800/15600]	[L1: 0.5762]	10.0+0.1s
+[14400/15600]	[L1: 0.5776]	11.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.286 (Best: 53.329 @epoch 100)
+Forward: 64.59s
+
+Saving...
+Total: 65.09s
+
+[Epoch 105]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5924]	13.7+0.7s
+[3200/15600]	[L1: 0.5865]	10.8+0.1s
+[4800/15600]	[L1: 0.5852]	10.6+0.1s
+[6400/15600]	[L1: 0.5821]	12.2+0.1s
+[8000/15600]	[L1: 0.5770]	10.7+0.1s
+[9600/15600]	[L1: 0.5749]	10.1+0.1s
+[11200/15600]	[L1: 0.5742]	10.9+0.1s
+[12800/15600]	[L1: 0.5740]	13.0+0.1s
+[14400/15600]	[L1: 0.5764]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.315 (Best: 53.329 @epoch 100)
+Forward: 66.17s
+
+Saving...
+Total: 66.73s
+
+[Epoch 106]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5545]	11.3+0.7s
+[3200/15600]	[L1: 0.5618]	11.0+0.1s
+[4800/15600]	[L1: 0.5630]	13.2+0.1s
+[6400/15600]	[L1: 0.5642]	11.5+0.1s
+[8000/15600]	[L1: 0.5686]	11.0+0.1s
+[9600/15600]	[L1: 0.5694]	11.7+0.1s
+[11200/15600]	[L1: 0.5685]	13.5+0.1s
+[12800/15600]	[L1: 0.5684]	10.5+0.1s
+[14400/15600]	[L1: 0.5683]	11.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.305 (Best: 53.329 @epoch 100)
+Forward: 64.90s
+
+Saving...
+Total: 65.43s
+
+[Epoch 107]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5686]	12.4+0.7s
+[3200/15600]	[L1: 0.5812]	10.8+0.1s
+[4800/15600]	[L1: 0.5773]	11.0+0.1s
+[6400/15600]	[L1: 0.5830]	11.1+0.1s
+[8000/15600]	[L1: 0.5770]	13.6+0.1s
+[9600/15600]	[L1: 0.5734]	10.9+0.1s
+[11200/15600]	[L1: 0.5724]	11.2+0.1s
+[12800/15600]	[L1: 0.5695]	13.9+0.1s
+[14400/15600]	[L1: 0.5686]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.117 (Best: 53.329 @epoch 100)
+Forward: 65.80s
+
+Saving...
+Total: 66.30s
+
+[Epoch 108]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5632]	9.9+0.7s
+[3200/15600]	[L1: 0.5637]	11.1+0.1s
+[4800/15600]	[L1: 0.5667]	11.5+0.1s
+[6400/15600]	[L1: 0.5714]	11.4+0.1s
+[8000/15600]	[L1: 0.5711]	9.5+0.1s
+[9600/15600]	[L1: 0.5725]	10.0+0.1s
+[11200/15600]	[L1: 0.5737]	13.2+0.1s
+[12800/15600]	[L1: 0.5721]	10.2+0.1s
+[14400/15600]	[L1: 0.5717]	9.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.715 (Best: 53.329 @epoch 100)
+Forward: 65.08s
+
+Saving...
+Total: 65.62s
+
+[Epoch 109]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.6021]	10.5+0.7s
+[3200/15600]	[L1: 0.5888]	10.8+0.1s
+[4800/15600]	[L1: 0.5834]	13.5+0.1s
+[6400/15600]	[L1: 0.5766]	10.8+0.1s
+[8000/15600]	[L1: 0.5786]	10.8+0.1s
+[9600/15600]	[L1: 0.5768]	13.6+0.1s
+[11200/15600]	[L1: 0.5775]	10.6+0.1s
+[12800/15600]	[L1: 0.5742]	10.8+0.1s
+[14400/15600]	[L1: 0.5713]	13.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.270 (Best: 53.329 @epoch 100)
+Forward: 64.32s
+
+Saving...
+Total: 64.98s
+
+[Epoch 110]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5744]	13.7+0.7s
+[3200/15600]	[L1: 0.5735]	11.0+0.1s
+[4800/15600]	[L1: 0.5702]	11.0+0.1s
+[6400/15600]	[L1: 0.5675]	13.6+0.1s
+[8000/15600]	[L1: 0.5658]	11.1+0.1s
+[9600/15600]	[L1: 0.5678]	11.0+0.1s
+[11200/15600]	[L1: 0.5652]	13.0+0.1s
+[12800/15600]	[L1: 0.5641]	10.7+0.1s
+[14400/15600]	[L1: 0.5634]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.968 (Best: 53.329 @epoch 100)
+Forward: 62.26s
+
+Saving...
+Total: 62.76s
+
+[Epoch 111]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5527]	10.8+0.6s
+[3200/15600]	[L1: 0.5539]	11.0+0.1s
+[4800/15600]	[L1: 0.5572]	13.2+0.1s
+[6400/15600]	[L1: 0.5691]	10.3+0.1s
+[8000/15600]	[L1: 0.5658]	11.3+0.1s
+[9600/15600]	[L1: 0.5659]	13.0+0.1s
+[11200/15600]	[L1: 0.5664]	10.1+0.1s
+[12800/15600]	[L1: 0.5673]	10.7+0.1s
+[14400/15600]	[L1: 0.5653]	11.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.992 (Best: 53.329 @epoch 100)
+Forward: 63.31s
+
+Saving...
+Total: 63.83s
+
+[Epoch 112]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5710]	14.0+0.7s
+[3200/15600]	[L1: 0.5689]	10.9+0.1s
+[4800/15600]	[L1: 0.5713]	11.0+0.1s
+[6400/15600]	[L1: 0.5661]	12.3+0.1s
+[8000/15600]	[L1: 0.5637]	12.4+0.1s
+[9600/15600]	[L1: 0.5613]	10.9+0.1s
+[11200/15600]	[L1: 0.5604]	11.0+0.1s
+[12800/15600]	[L1: 0.5610]	13.6+0.1s
+[14400/15600]	[L1: 0.5635]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.299 (Best: 53.329 @epoch 100)
+Forward: 64.19s
+
+Saving...
+Total: 64.71s
+
+[Epoch 113]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5635]	11.1+0.8s
+[3200/15600]	[L1: 0.5650]	11.0+0.1s
+[4800/15600]	[L1: 0.5658]	13.4+0.1s
+[6400/15600]	[L1: 0.5628]	11.0+0.1s
+[8000/15600]	[L1: 0.5615]	11.0+0.1s
+[9600/15600]	[L1: 0.5566]	13.5+0.1s
+[11200/15600]	[L1: 0.5561]	10.8+0.1s
+[12800/15600]	[L1: 0.5590]	10.9+0.1s
+[14400/15600]	[L1: 0.5607]	12.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.447 (Best: 53.447 @epoch 113)
+Forward: 61.75s
+
+Saving...
+Total: 62.28s
+
+[Epoch 114]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5570]	12.7+0.7s
+[3200/15600]	[L1: 0.5702]	10.8+0.1s
+[4800/15600]	[L1: 0.5727]	11.3+0.1s
+[6400/15600]	[L1: 0.5721]	13.8+0.1s
+[8000/15600]	[L1: 0.5687]	11.0+0.1s
+[9600/15600]	[L1: 0.5680]	11.2+0.1s
+[11200/15600]	[L1: 0.5673]	11.0+0.1s
+[12800/15600]	[L1: 0.5658]	13.8+0.1s
+[14400/15600]	[L1: 0.5642]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.063 (Best: 53.447 @epoch 113)
+Forward: 64.98s
+
+Saving...
+Total: 65.71s
+
+[Epoch 115]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5522]	11.3+0.7s
+[3200/15600]	[L1: 0.5624]	10.8+0.1s
+[4800/15600]	[L1: 0.5693]	13.1+0.1s
+[6400/15600]	[L1: 0.5657]	10.8+0.1s
+[8000/15600]	[L1: 0.5665]	11.1+0.1s
+[9600/15600]	[L1: 0.5642]	13.3+0.1s
+[11200/15600]	[L1: 0.5640]	10.0+0.1s
+[12800/15600]	[L1: 0.5664]	10.8+0.1s
+[14400/15600]	[L1: 0.5651]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.048 (Best: 53.447 @epoch 113)
+Forward: 61.96s
+
+Saving...
+Total: 62.53s
+
+[Epoch 116]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5716]	13.7+0.7s
+[3200/15600]	[L1: 0.5755]	11.1+0.1s
+[4800/15600]	[L1: 0.5802]	11.1+0.1s
+[6400/15600]	[L1: 0.5710]	11.8+0.1s
+[8000/15600]	[L1: 0.5651]	12.9+0.1s
+[9600/15600]	[L1: 0.5662]	11.0+0.1s
+[11200/15600]	[L1: 0.5656]	11.1+0.1s
+[12800/15600]	[L1: 0.5645]	13.8+0.1s
+[14400/15600]	[L1: 0.5619]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.103 (Best: 53.447 @epoch 113)
+Forward: 64.07s
+
+Saving...
+Total: 64.57s
+
+[Epoch 117]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5436]	10.6+0.6s
+[3200/15600]	[L1: 0.5601]	9.6+0.1s
+[4800/15600]	[L1: 0.5626]	10.7+0.1s
+[6400/15600]	[L1: 0.5612]	11.2+0.1s
+[8000/15600]	[L1: 0.5625]	9.7+0.1s
+[9600/15600]	[L1: 0.5608]	9.3+0.1s
+[11200/15600]	[L1: 0.5607]	11.5+0.1s
+[12800/15600]	[L1: 0.5605]	9.3+0.1s
+[14400/15600]	[L1: 0.5615]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.794 (Best: 53.447 @epoch 113)
+Forward: 65.32s
+
+Saving...
+Total: 65.85s
+
+[Epoch 118]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5413]	11.0+0.7s
+[3200/15600]	[L1: 0.5526]	11.6+0.1s
+[4800/15600]	[L1: 0.5506]	13.9+0.1s
+[6400/15600]	[L1: 0.5595]	10.9+0.1s
+[8000/15600]	[L1: 0.5577]	11.0+0.1s
+[9600/15600]	[L1: 0.5587]	13.6+0.1s
+[11200/15600]	[L1: 0.5602]	10.9+0.1s
+[12800/15600]	[L1: 0.5599]	11.0+0.1s
+[14400/15600]	[L1: 0.5595]	13.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.000 (Best: 53.447 @epoch 113)
+Forward: 62.88s
+
+Saving...
+Total: 63.44s
+
+[Epoch 119]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5491]	13.6+0.7s
+[3200/15600]	[L1: 0.5641]	10.9+0.1s
+[4800/15600]	[L1: 0.5628]	10.8+0.1s
+[6400/15600]	[L1: 0.5686]	13.4+0.1s
+[8000/15600]	[L1: 0.5646]	10.8+0.1s
+[9600/15600]	[L1: 0.5648]	11.0+0.1s
+[11200/15600]	[L1: 0.5640]	10.8+0.1s
+[12800/15600]	[L1: 0.5630]	13.4+0.1s
+[14400/15600]	[L1: 0.5617]	10.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.955 (Best: 53.447 @epoch 113)
+Forward: 66.76s
+
+Saving...
+Total: 67.26s
+
+[Epoch 120]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5696]	11.5+0.7s
+[3200/15600]	[L1: 0.5703]	11.0+0.1s
+[4800/15600]	[L1: 0.5728]	13.6+0.1s
+[6400/15600]	[L1: 0.5666]	11.0+0.1s
+[8000/15600]	[L1: 0.5637]	11.1+0.1s
+[9600/15600]	[L1: 0.5635]	13.8+0.1s
+[11200/15600]	[L1: 0.5639]	11.0+0.1s
+[12800/15600]	[L1: 0.5633]	10.6+0.1s
+[14400/15600]	[L1: 0.5638]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.577 (Best: 53.577 @epoch 120)
+Forward: 63.21s
+
+Saving...
+Total: 63.86s
+
+[Epoch 121]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5428]	13.8+0.7s
+[3200/15600]	[L1: 0.5427]	11.2+0.1s
+[4800/15600]	[L1: 0.5443]	11.0+0.1s
+[6400/15600]	[L1: 0.5479]	11.8+0.1s
+[8000/15600]	[L1: 0.5471]	13.1+0.1s
+[9600/15600]	[L1: 0.5456]	11.1+0.1s
+[11200/15600]	[L1: 0.5468]	11.0+0.1s
+[12800/15600]	[L1: 0.5471]	13.8+0.1s
+[14400/15600]	[L1: 0.5487]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.086 (Best: 53.577 @epoch 120)
+Forward: 64.86s
+
+Saving...
+Total: 65.39s
+
+[Epoch 122]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5783]	11.3+0.7s
+[3200/15600]	[L1: 0.5648]	11.1+0.1s
+[4800/15600]	[L1: 0.5631]	13.8+0.1s
+[6400/15600]	[L1: 0.5604]	11.0+0.1s
+[8000/15600]	[L1: 0.5612]	11.0+0.1s
+[9600/15600]	[L1: 0.5596]	13.8+0.1s
+[11200/15600]	[L1: 0.5585]	11.0+0.1s
+[12800/15600]	[L1: 0.5568]	11.0+0.1s
+[14400/15600]	[L1: 0.5565]	11.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.456 (Best: 53.577 @epoch 120)
+Forward: 64.21s
+
+Saving...
+Total: 64.76s
+
+[Epoch 123]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5575]	13.6+0.7s
+[3200/15600]	[L1: 0.5500]	10.4+0.1s
+[4800/15600]	[L1: 0.5507]	9.7+0.1s
+[6400/15600]	[L1: 0.5524]	10.9+0.1s
+[8000/15600]	[L1: 0.5490]	12.9+0.1s
+[9600/15600]	[L1: 0.5495]	10.0+0.1s
+[11200/15600]	[L1: 0.5515]	9.7+0.1s
+[12800/15600]	[L1: 0.5517]	12.4+0.1s
+[14400/15600]	[L1: 0.5528]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.506 (Best: 53.577 @epoch 120)
+Forward: 65.96s
+
+Saving...
+Total: 66.46s
+
+[Epoch 124]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5456]	10.0+0.7s
+[3200/15600]	[L1: 0.5567]	9.8+0.1s
+[4800/15600]	[L1: 0.5593]	10.0+0.1s
+[6400/15600]	[L1: 0.5587]	12.8+0.1s
+[8000/15600]	[L1: 0.5569]	10.9+0.1s
+[9600/15600]	[L1: 0.5546]	10.0+0.1s
+[11200/15600]	[L1: 0.5556]	13.0+0.1s
+[12800/15600]	[L1: 0.5552]	9.9+0.1s
+[14400/15600]	[L1: 0.5547]	10.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.710 (Best: 53.577 @epoch 120)
+Forward: 62.33s
+
+Saving...
+Total: 62.83s
+
+[Epoch 125]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5458]	11.3+0.7s
+[3200/15600]	[L1: 0.5424]	11.0+0.1s
+[4800/15600]	[L1: 0.5472]	13.3+0.1s
+[6400/15600]	[L1: 0.5454]	10.9+0.1s
+[8000/15600]	[L1: 0.5468]	11.0+0.1s
+[9600/15600]	[L1: 0.5476]	13.4+0.1s
+[11200/15600]	[L1: 0.5461]	10.9+0.1s
+[12800/15600]	[L1: 0.5461]	11.0+0.1s
+[14400/15600]	[L1: 0.5474]	11.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.302 (Best: 53.577 @epoch 120)
+Forward: 63.19s
+
+Saving...
+Total: 63.70s
+
+[Epoch 126]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5490]	13.6+0.7s
+[3200/15600]	[L1: 0.5456]	10.8+0.1s
+[4800/15600]	[L1: 0.5441]	10.8+0.1s
+[6400/15600]	[L1: 0.5466]	12.3+0.1s
+[8000/15600]	[L1: 0.5475]	12.1+0.1s
+[9600/15600]	[L1: 0.5487]	10.8+0.1s
+[11200/15600]	[L1: 0.5479]	10.8+0.1s
+[12800/15600]	[L1: 0.5482]	13.5+0.1s
+[14400/15600]	[L1: 0.5480]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.282 (Best: 53.577 @epoch 120)
+Forward: 66.74s
+
+Saving...
+Total: 67.25s
+
+[Epoch 127]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5549]	11.0+0.6s
+[3200/15600]	[L1: 0.5556]	10.5+0.1s
+[4800/15600]	[L1: 0.5522]	12.7+0.1s
+[6400/15600]	[L1: 0.5499]	10.0+0.1s
+[8000/15600]	[L1: 0.5517]	10.1+0.1s
+[9600/15600]	[L1: 0.5517]	10.2+0.1s
+[11200/15600]	[L1: 0.5534]	12.5+0.1s
+[12800/15600]	[L1: 0.5534]	10.1+0.1s
+[14400/15600]	[L1: 0.5543]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.075 (Best: 53.577 @epoch 120)
+Forward: 65.07s
+
+Saving...
+Total: 65.76s
+
+[Epoch 128]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5626]	11.1+0.6s
+[3200/15600]	[L1: 0.5600]	13.1+0.1s
+[4800/15600]	[L1: 0.5615]	10.7+0.1s
+[6400/15600]	[L1: 0.5565]	10.5+0.1s
+[8000/15600]	[L1: 0.5527]	10.5+0.1s
+[9600/15600]	[L1: 0.5514]	12.9+0.1s
+[11200/15600]	[L1: 0.5515]	10.6+0.1s
+[12800/15600]	[L1: 0.5530]	10.5+0.1s
+[14400/15600]	[L1: 0.5509]	12.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.540 (Best: 53.577 @epoch 120)
+Forward: 63.64s
+
+Saving...
+Total: 64.15s
+
+[Epoch 129]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5624]	13.6+0.8s
+[3200/15600]	[L1: 0.5599]	10.8+0.1s
+[4800/15600]	[L1: 0.5564]	11.0+0.1s
+[6400/15600]	[L1: 0.5520]	13.4+0.1s
+[8000/15600]	[L1: 0.5532]	10.8+0.1s
+[9600/15600]	[L1: 0.5560]	11.0+0.1s
+[11200/15600]	[L1: 0.5560]	13.7+0.1s
+[12800/15600]	[L1: 0.5549]	11.0+0.1s
+[14400/15600]	[L1: 0.5560]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.535 (Best: 53.577 @epoch 120)
+Forward: 62.29s
+
+Saving...
+Total: 62.80s
+
+[Epoch 130]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5377]	11.1+0.6s
+[3200/15600]	[L1: 0.5423]	9.9+0.1s
+[4800/15600]	[L1: 0.5435]	12.8+0.1s
+[6400/15600]	[L1: 0.5396]	10.0+0.1s
+[8000/15600]	[L1: 0.5424]	10.5+0.1s
+[9600/15600]	[L1: 0.5469]	10.3+0.1s
+[11200/15600]	[L1: 0.5503]	12.5+0.1s
+[12800/15600]	[L1: 0.5494]	9.8+0.1s
+[14400/15600]	[L1: 0.5491]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.556 (Best: 53.577 @epoch 120)
+Forward: 63.47s
+
+Saving...
+Total: 63.99s
+
+[Epoch 131]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5505]	11.3+0.8s
+[3200/15600]	[L1: 0.5483]	13.8+0.1s
+[4800/15600]	[L1: 0.5475]	11.1+0.1s
+[6400/15600]	[L1: 0.5461]	11.0+0.1s
+[8000/15600]	[L1: 0.5480]	13.9+0.1s
+[9600/15600]	[L1: 0.5453]	11.1+0.1s
+[11200/15600]	[L1: 0.5472]	11.0+0.1s
+[12800/15600]	[L1: 0.5499]	13.9+0.1s
+[14400/15600]	[L1: 0.5514]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.404 (Best: 53.577 @epoch 120)
+Forward: 63.74s
+
+Saving...
+Total: 64.52s
+
+[Epoch 132]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5472]	10.3+0.7s
+[3200/15600]	[L1: 0.5442]	11.0+0.1s
+[4800/15600]	[L1: 0.5426]	10.3+0.1s
+[6400/15600]	[L1: 0.5488]	12.6+0.1s
+[8000/15600]	[L1: 0.5489]	10.8+0.1s
+[9600/15600]	[L1: 0.5442]	10.8+0.1s
+[11200/15600]	[L1: 0.5431]	13.0+0.1s
+[12800/15600]	[L1: 0.5431]	9.5+0.1s
+[14400/15600]	[L1: 0.5443]	9.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.446 (Best: 53.577 @epoch 120)
+Forward: 64.59s
+
+Saving...
+Total: 65.11s
+
+[Epoch 133]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5241]	11.4+0.7s
+[3200/15600]	[L1: 0.5200]	11.0+0.1s
+[4800/15600]	[L1: 0.5299]	13.9+0.1s
+[6400/15600]	[L1: 0.5294]	11.0+0.1s
+[8000/15600]	[L1: 0.5327]	11.1+0.1s
+[9600/15600]	[L1: 0.5329]	13.8+0.1s
+[11200/15600]	[L1: 0.5371]	11.1+0.1s
+[12800/15600]	[L1: 0.5405]	11.0+0.1s
+[14400/15600]	[L1: 0.5424]	13.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.535 (Best: 53.577 @epoch 120)
+Forward: 63.33s
+
+Saving...
+Total: 63.82s
+
+[Epoch 134]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5456]	13.9+0.7s
+[3200/15600]	[L1: 0.5395]	11.0+0.1s
+[4800/15600]	[L1: 0.5382]	11.2+0.1s
+[6400/15600]	[L1: 0.5424]	13.8+0.1s
+[8000/15600]	[L1: 0.5401]	11.0+0.1s
+[9600/15600]	[L1: 0.5409]	11.0+0.1s
+[11200/15600]	[L1: 0.5414]	13.1+0.1s
+[12800/15600]	[L1: 0.5423]	11.3+0.1s
+[14400/15600]	[L1: 0.5460]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.563 (Best: 53.577 @epoch 120)
+Forward: 65.69s
+
+Saving...
+Total: 66.25s
+
+[Epoch 135]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5418]	11.3+0.7s
+[3200/15600]	[L1: 0.5409]	9.8+0.1s
+[4800/15600]	[L1: 0.5434]	13.1+0.1s
+[6400/15600]	[L1: 0.5424]	10.4+0.1s
+[8000/15600]	[L1: 0.5425]	11.0+0.1s
+[9600/15600]	[L1: 0.5445]	13.8+0.1s
+[11200/15600]	[L1: 0.5444]	11.0+0.1s
+[12800/15600]	[L1: 0.5464]	10.9+0.1s
+[14400/15600]	[L1: 0.5469]	12.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.916 (Best: 53.577 @epoch 120)
+Forward: 63.16s
+
+Saving...
+Total: 63.82s
+
+[Epoch 136]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5265]	13.5+0.7s
+[3200/15600]	[L1: 0.5271]	10.7+0.1s
+[4800/15600]	[L1: 0.5313]	11.1+0.1s
+[6400/15600]	[L1: 0.5296]	13.7+0.1s
+[8000/15600]	[L1: 0.5376]	11.1+0.1s
+[9600/15600]	[L1: 0.5403]	11.0+0.1s
+[11200/15600]	[L1: 0.5436]	12.0+0.1s
+[12800/15600]	[L1: 0.5427]	12.9+0.1s
+[14400/15600]	[L1: 0.5431]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.473 (Best: 53.577 @epoch 120)
+Forward: 64.99s
+
+Saving...
+Total: 65.53s
+
+[Epoch 137]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5337]	11.3+0.7s
+[3200/15600]	[L1: 0.5291]	11.1+0.1s
+[4800/15600]	[L1: 0.5417]	13.8+0.1s
+[6400/15600]	[L1: 0.5482]	11.3+0.1s
+[8000/15600]	[L1: 0.5464]	11.1+0.1s
+[9600/15600]	[L1: 0.5486]	13.6+0.1s
+[11200/15600]	[L1: 0.5496]	10.9+0.1s
+[12800/15600]	[L1: 0.5492]	11.2+0.1s
+[14400/15600]	[L1: 0.5484]	13.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.566 (Best: 53.577 @epoch 120)
+Forward: 63.10s
+
+Saving...
+Total: 63.61s
+
+[Epoch 138]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5471]	13.8+0.7s
+[3200/15600]	[L1: 0.5346]	10.8+0.1s
+[4800/15600]	[L1: 0.5340]	11.0+0.1s
+[6400/15600]	[L1: 0.5367]	13.6+0.1s
+[8000/15600]	[L1: 0.5386]	11.1+0.1s
+[9600/15600]	[L1: 0.5384]	11.0+0.1s
+[11200/15600]	[L1: 0.5413]	13.5+0.1s
+[12800/15600]	[L1: 0.5421]	11.4+0.1s
+[14400/15600]	[L1: 0.5429]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.649 (Best: 53.649 @epoch 138)
+Forward: 65.31s
+
+Saving...
+Total: 65.85s
+
+[Epoch 139]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5412]	11.1+0.7s
+[3200/15600]	[L1: 0.5386]	11.2+0.1s
+[4800/15600]	[L1: 0.5374]	13.2+0.1s
+[6400/15600]	[L1: 0.5396]	11.0+0.1s
+[8000/15600]	[L1: 0.5407]	11.2+0.1s
+[9600/15600]	[L1: 0.5402]	13.6+0.1s
+[11200/15600]	[L1: 0.5403]	11.1+0.1s
+[12800/15600]	[L1: 0.5420]	11.0+0.1s
+[14400/15600]	[L1: 0.5410]	13.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.618 (Best: 53.649 @epoch 138)
+Forward: 63.24s
+
+Saving...
+Total: 63.74s
+
+[Epoch 140]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5346]	13.2+0.7s
+[3200/15600]	[L1: 0.5349]	11.0+0.1s
+[4800/15600]	[L1: 0.5410]	11.2+0.1s
+[6400/15600]	[L1: 0.5424]	13.6+0.1s
+[8000/15600]	[L1: 0.5413]	10.0+0.1s
+[9600/15600]	[L1: 0.5428]	10.9+0.1s
+[11200/15600]	[L1: 0.5423]	14.0+0.1s
+[12800/15600]	[L1: 0.5406]	10.9+0.1s
+[14400/15600]	[L1: 0.5416]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.608 (Best: 53.649 @epoch 138)
+Forward: 64.94s
+
+Saving...
+Total: 65.46s
+
+[Epoch 141]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5412]	11.4+0.7s
+[3200/15600]	[L1: 0.5390]	10.9+0.1s
+[4800/15600]	[L1: 0.5410]	13.5+0.1s
+[6400/15600]	[L1: 0.5381]	10.8+0.1s
+[8000/15600]	[L1: 0.5415]	11.0+0.1s
+[9600/15600]	[L1: 0.5412]	13.4+0.1s
+[11200/15600]	[L1: 0.5420]	11.0+0.1s
+[12800/15600]	[L1: 0.5473]	10.9+0.1s
+[14400/15600]	[L1: 0.5456]	13.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.988 (Best: 53.649 @epoch 138)
+Forward: 63.25s
+
+Saving...
+Total: 63.76s
+
+[Epoch 142]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5475]	13.6+0.7s
+[3200/15600]	[L1: 0.5571]	11.1+0.1s
+[4800/15600]	[L1: 0.5540]	10.1+0.1s
+[6400/15600]	[L1: 0.5510]	12.6+0.1s
+[8000/15600]	[L1: 0.5485]	10.7+0.1s
+[9600/15600]	[L1: 0.5445]	11.2+0.1s
+[11200/15600]	[L1: 0.5437]	11.8+0.1s
+[12800/15600]	[L1: 0.5433]	13.0+0.1s
+[14400/15600]	[L1: 0.5436]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.367 (Best: 53.649 @epoch 138)
+Forward: 64.31s
+
+Saving...
+Total: 64.88s
+
+[Epoch 143]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5272]	10.5+0.6s
+[3200/15600]	[L1: 0.5351]	10.4+0.1s
+[4800/15600]	[L1: 0.5316]	12.8+0.1s
+[6400/15600]	[L1: 0.5323]	10.5+0.1s
+[8000/15600]	[L1: 0.5394]	10.3+0.1s
+[9600/15600]	[L1: 0.5410]	10.5+0.1s
+[11200/15600]	[L1: 0.5395]	12.7+0.1s
+[12800/15600]	[L1: 0.5401]	10.4+0.1s
+[14400/15600]	[L1: 0.5411]	10.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.070 (Best: 53.649 @epoch 138)
+Forward: 64.49s
+
+Saving...
+Total: 65.13s
+
+[Epoch 144]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5289]	11.0+0.8s
+[3200/15600]	[L1: 0.5252]	13.4+0.1s
+[4800/15600]	[L1: 0.5325]	11.0+0.1s
+[6400/15600]	[L1: 0.5387]	10.8+0.1s
+[8000/15600]	[L1: 0.5382]	13.6+0.1s
+[9600/15600]	[L1: 0.5426]	10.9+0.1s
+[11200/15600]	[L1: 0.5422]	10.9+0.1s
+[12800/15600]	[L1: 0.5420]	13.2+0.1s
+[14400/15600]	[L1: 0.5404]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.460 (Best: 53.649 @epoch 138)
+Forward: 64.57s
+
+Saving...
+Total: 65.58s
+
+[Epoch 145]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5354]	9.9+0.8s
+[3200/15600]	[L1: 0.5313]	9.5+0.1s
+[4800/15600]	[L1: 0.5289]	9.8+0.1s
+[6400/15600]	[L1: 0.5309]	13.6+0.1s
+[8000/15600]	[L1: 0.5301]	11.1+0.1s
+[9600/15600]	[L1: 0.5326]	11.1+0.1s
+[11200/15600]	[L1: 0.5335]	13.5+0.1s
+[12800/15600]	[L1: 0.5341]	11.1+0.1s
+[14400/15600]	[L1: 0.5353]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.991 (Best: 53.649 @epoch 138)
+Forward: 66.63s
+
+Saving...
+Total: 67.17s
+
+[Epoch 146]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5549]	11.0+0.7s
+[3200/15600]	[L1: 0.5411]	12.1+0.1s
+[4800/15600]	[L1: 0.5405]	12.5+0.1s
+[6400/15600]	[L1: 0.5409]	10.8+0.1s
+[8000/15600]	[L1: 0.5408]	10.9+0.1s
+[9600/15600]	[L1: 0.5402]	13.8+0.1s
+[11200/15600]	[L1: 0.5410]	10.7+0.1s
+[12800/15600]	[L1: 0.5424]	11.0+0.1s
+[14400/15600]	[L1: 0.5438]	13.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.171 (Best: 53.649 @epoch 138)
+Forward: 61.38s
+
+Saving...
+Total: 61.96s
+
+[Epoch 147]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5212]	12.9+0.6s
+[3200/15600]	[L1: 0.5291]	10.1+0.1s
+[4800/15600]	[L1: 0.5247]	10.3+0.1s
+[6400/15600]	[L1: 0.5272]	12.7+0.1s
+[8000/15600]	[L1: 0.5294]	10.4+0.1s
+[9600/15600]	[L1: 0.5307]	10.8+0.1s
+[11200/15600]	[L1: 0.5313]	11.8+0.1s
+[12800/15600]	[L1: 0.5324]	11.9+0.1s
+[14400/15600]	[L1: 0.5340]	10.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.672 (Best: 53.672 @epoch 147)
+Forward: 67.08s
+
+Saving...
+Total: 67.61s
+
+[Epoch 148]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5451]	11.2+0.8s
+[3200/15600]	[L1: 0.5470]	10.9+0.1s
+[4800/15600]	[L1: 0.5434]	13.6+0.1s
+[6400/15600]	[L1: 0.5450]	11.4+0.1s
+[8000/15600]	[L1: 0.5430]	11.1+0.1s
+[9600/15600]	[L1: 0.5407]	13.8+0.1s
+[11200/15600]	[L1: 0.5400]	11.2+0.1s
+[12800/15600]	[L1: 0.5410]	11.0+0.1s
+[14400/15600]	[L1: 0.5411]	13.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.620 (Best: 53.672 @epoch 147)
+Forward: 63.83s
+
+Saving...
+Total: 64.36s
+
+[Epoch 149]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5367]	14.1+0.7s
+[3200/15600]	[L1: 0.5336]	10.9+0.1s
+[4800/15600]	[L1: 0.5288]	11.0+0.1s
+[6400/15600]	[L1: 0.5305]	13.4+0.1s
+[8000/15600]	[L1: 0.5349]	10.9+0.1s
+[9600/15600]	[L1: 0.5342]	10.8+0.1s
+[11200/15600]	[L1: 0.5331]	11.7+0.1s
+[12800/15600]	[L1: 0.5360]	12.7+0.1s
+[14400/15600]	[L1: 0.5374]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.859 (Best: 53.672 @epoch 147)
+Forward: 63.30s
+
+Saving...
+Total: 63.92s
+
+[Epoch 150]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5433]	11.1+0.7s
+[3200/15600]	[L1: 0.5389]	11.1+0.1s
+[4800/15600]	[L1: 0.5363]	13.7+0.1s
+[6400/15600]	[L1: 0.5393]	10.4+0.1s
+[8000/15600]	[L1: 0.5400]	10.4+0.1s
+[9600/15600]	[L1: 0.5438]	12.9+0.1s
+[11200/15600]	[L1: 0.5423]	10.6+0.1s
+[12800/15600]	[L1: 0.5423]	10.3+0.1s
+[14400/15600]	[L1: 0.5421]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.117 (Best: 53.672 @epoch 147)
+Forward: 61.64s
+
+Saving...
+Total: 62.15s
+
+[Epoch 151]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5297]	12.6+0.6s
+[3200/15600]	[L1: 0.5378]	10.8+0.1s
+[4800/15600]	[L1: 0.5284]	10.0+0.1s
+[6400/15600]	[L1: 0.5296]	9.9+0.1s
+[8000/15600]	[L1: 0.5313]	12.7+0.1s
+[9600/15600]	[L1: 0.5349]	10.4+0.1s
+[11200/15600]	[L1: 0.5337]	10.3+0.1s
+[12800/15600]	[L1: 0.5357]	11.1+0.1s
+[14400/15600]	[L1: 0.5339]	11.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.709 (Best: 53.709 @epoch 151)
+Forward: 65.72s
+
+Saving...
+Total: 66.69s
+
+[Epoch 152]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5335]	11.4+0.8s
+[3200/15600]	[L1: 0.5310]	10.8+0.1s
+[4800/15600]	[L1: 0.5343]	12.4+0.1s
+[6400/15600]	[L1: 0.5405]	11.2+0.1s
+[8000/15600]	[L1: 0.5345]	10.1+0.1s
+[9600/15600]	[L1: 0.5344]	10.0+0.1s
+[11200/15600]	[L1: 0.5332]	12.8+0.1s
+[12800/15600]	[L1: 0.5343]	10.0+0.1s
+[14400/15600]	[L1: 0.5344]	10.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.827 (Best: 53.827 @epoch 152)
+Forward: 65.20s
+
+Saving...
+Total: 65.75s
+
+[Epoch 153]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5412]	9.7+0.7s
+[3200/15600]	[L1: 0.5399]	9.7+0.1s
+[4800/15600]	[L1: 0.5342]	12.6+0.1s
+[6400/15600]	[L1: 0.5347]	10.6+0.1s
+[8000/15600]	[L1: 0.5359]	11.1+0.1s
+[9600/15600]	[L1: 0.5347]	13.8+0.1s
+[11200/15600]	[L1: 0.5370]	10.9+0.1s
+[12800/15600]	[L1: 0.5349]	11.1+0.1s
+[14400/15600]	[L1: 0.5349]	11.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.668 (Best: 53.827 @epoch 152)
+Forward: 62.22s
+
+Saving...
+Total: 62.76s
+
+[Epoch 154]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5420]	13.7+0.7s
+[3200/15600]	[L1: 0.5320]	11.0+0.1s
+[4800/15600]	[L1: 0.5364]	11.1+0.1s
+[6400/15600]	[L1: 0.5338]	12.0+0.1s
+[8000/15600]	[L1: 0.5358]	12.5+0.1s
+[9600/15600]	[L1: 0.5341]	11.1+0.1s
+[11200/15600]	[L1: 0.5365]	11.0+0.1s
+[12800/15600]	[L1: 0.5363]	13.6+0.1s
+[14400/15600]	[L1: 0.5391]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.643 (Best: 53.827 @epoch 152)
+Forward: 64.51s
+
+Saving...
+Total: 65.20s
+
+[Epoch 155]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5452]	11.1+0.7s
+[3200/15600]	[L1: 0.5359]	11.1+0.1s
+[4800/15600]	[L1: 0.5369]	13.5+0.1s
+[6400/15600]	[L1: 0.5344]	11.0+0.1s
+[8000/15600]	[L1: 0.5375]	11.0+0.1s
+[9600/15600]	[L1: 0.5391]	13.1+0.1s
+[11200/15600]	[L1: 0.5387]	11.4+0.1s
+[12800/15600]	[L1: 0.5393]	11.0+0.1s
+[14400/15600]	[L1: 0.5399]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.364 (Best: 53.827 @epoch 152)
+Forward: 62.82s
+
+Saving...
+Total: 63.33s
+
+[Epoch 156]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5431]	13.9+0.7s
+[3200/15600]	[L1: 0.5359]	10.9+0.1s
+[4800/15600]	[L1: 0.5383]	11.1+0.1s
+[6400/15600]	[L1: 0.5444]	11.4+0.1s
+[8000/15600]	[L1: 0.5435]	12.1+0.1s
+[9600/15600]	[L1: 0.5417]	10.6+0.1s
+[11200/15600]	[L1: 0.5405]	10.9+0.1s
+[12800/15600]	[L1: 0.5407]	12.8+0.1s
+[14400/15600]	[L1: 0.5398]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.774 (Best: 53.827 @epoch 152)
+Forward: 63.08s
+
+Saving...
+Total: 63.63s
+
+[Epoch 157]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5260]	11.3+0.7s
+[3200/15600]	[L1: 0.5414]	10.9+0.1s
+[4800/15600]	[L1: 0.5401]	12.5+0.1s
+[6400/15600]	[L1: 0.5451]	11.5+0.1s
+[8000/15600]	[L1: 0.5453]	10.0+0.1s
+[9600/15600]	[L1: 0.5438]	10.2+0.1s
+[11200/15600]	[L1: 0.5428]	12.8+0.1s
+[12800/15600]	[L1: 0.5413]	11.0+0.1s
+[14400/15600]	[L1: 0.5396]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.733 (Best: 53.827 @epoch 152)
+Forward: 64.25s
+
+Saving...
+Total: 64.78s
+
+[Epoch 158]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5140]	11.1+0.7s
+[3200/15600]	[L1: 0.5225]	13.5+0.1s
+[4800/15600]	[L1: 0.5280]	10.8+0.1s
+[6400/15600]	[L1: 0.5257]	11.1+0.1s
+[8000/15600]	[L1: 0.5296]	13.5+0.1s
+[9600/15600]	[L1: 0.5301]	10.9+0.1s
+[11200/15600]	[L1: 0.5305]	10.3+0.1s
+[12800/15600]	[L1: 0.5315]	11.8+0.1s
+[14400/15600]	[L1: 0.5294]	12.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.565 (Best: 53.827 @epoch 152)
+Forward: 63.92s
+
+Saving...
+Total: 64.94s
+
+[Epoch 159]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5374]	11.1+1.0s
+[3200/15600]	[L1: 0.5308]	11.0+0.1s
+[4800/15600]	[L1: 0.5333]	11.9+0.1s
+[6400/15600]	[L1: 0.5339]	12.1+0.1s
+[8000/15600]	[L1: 0.5339]	9.4+0.1s
+[9600/15600]	[L1: 0.5324]	10.5+0.1s
+[11200/15600]	[L1: 0.5313]	13.3+0.1s
+[12800/15600]	[L1: 0.5344]	10.7+0.1s
+[14400/15600]	[L1: 0.5339]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.529 (Best: 53.827 @epoch 152)
+Forward: 64.65s
+
+Saving...
+Total: 65.19s
+
+[Epoch 160]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5276]	11.4+0.7s
+[3200/15600]	[L1: 0.5358]	13.7+0.1s
+[4800/15600]	[L1: 0.5347]	11.0+0.1s
+[6400/15600]	[L1: 0.5353]	11.1+0.1s
+[8000/15600]	[L1: 0.5337]	13.0+0.1s
+[9600/15600]	[L1: 0.5318]	11.9+0.1s
+[11200/15600]	[L1: 0.5349]	11.1+0.1s
+[12800/15600]	[L1: 0.5330]	11.0+0.1s
+[14400/15600]	[L1: 0.5320]	13.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.167 (Best: 53.827 @epoch 152)
+Forward: 63.56s
+
+Saving...
+Total: 64.68s
+
+[Epoch 161]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5409]	11.6+0.9s
+[3200/15600]	[L1: 0.5338]	11.0+0.1s
+[4800/15600]	[L1: 0.5371]	11.2+0.1s
+[6400/15600]	[L1: 0.5353]	13.4+0.1s
+[8000/15600]	[L1: 0.5380]	11.1+0.1s
+[9600/15600]	[L1: 0.5359]	10.9+0.1s
+[11200/15600]	[L1: 0.5346]	13.5+0.1s
+[12800/15600]	[L1: 0.5327]	10.7+0.1s
+[14400/15600]	[L1: 0.5338]	9.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.833 (Best: 53.833 @epoch 161)
+Forward: 65.26s
+
+Saving...
+Total: 65.89s
+
+[Epoch 162]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5349]	9.9+0.7s
+[3200/15600]	[L1: 0.5338]	13.4+0.1s
+[4800/15600]	[L1: 0.5424]	10.6+0.1s
+[6400/15600]	[L1: 0.5387]	10.3+0.1s
+[8000/15600]	[L1: 0.5379]	12.5+0.1s
+[9600/15600]	[L1: 0.5357]	11.5+0.1s
+[11200/15600]	[L1: 0.5331]	11.1+0.1s
+[12800/15600]	[L1: 0.5324]	11.0+0.1s
+[14400/15600]	[L1: 0.5319]	13.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.675 (Best: 53.833 @epoch 161)
+Forward: 65.19s
+
+Saving...
+Total: 66.09s
+
+[Epoch 163]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5284]	11.2+0.9s
+[3200/15600]	[L1: 0.5222]	10.9+0.1s
+[4800/15600]	[L1: 0.5270]	12.2+0.1s
+[6400/15600]	[L1: 0.5289]	12.2+0.1s
+[8000/15600]	[L1: 0.5314]	11.1+0.1s
+[9600/15600]	[L1: 0.5343]	11.0+0.1s
+[11200/15600]	[L1: 0.5371]	13.0+0.1s
+[12800/15600]	[L1: 0.5344]	10.4+0.1s
+[14400/15600]	[L1: 0.5336]	9.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.211 (Best: 53.833 @epoch 161)
+Forward: 63.83s
+
+Saving...
+Total: 64.38s
+
+[Epoch 164]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5429]	11.2+0.7s
+[3200/15600]	[L1: 0.5351]	13.7+0.1s
+[4800/15600]	[L1: 0.5325]	11.1+0.1s
+[6400/15600]	[L1: 0.5338]	10.9+0.1s
+[8000/15600]	[L1: 0.5337]	13.6+0.1s
+[9600/15600]	[L1: 0.5343]	11.1+0.1s
+[11200/15600]	[L1: 0.5329]	11.0+0.1s
+[12800/15600]	[L1: 0.5316]	12.4+0.1s
+[14400/15600]	[L1: 0.5336]	12.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.893 (Best: 53.893 @epoch 164)
+Forward: 62.11s
+
+Saving...
+Total: 63.18s
+
+[Epoch 165]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5224]	11.3+1.0s
+[3200/15600]	[L1: 0.5316]	11.1+0.1s
+[4800/15600]	[L1: 0.5282]	11.7+0.1s
+[6400/15600]	[L1: 0.5290]	12.9+0.1s
+[8000/15600]	[L1: 0.5289]	10.8+0.1s
+[9600/15600]	[L1: 0.5272]	11.0+0.1s
+[11200/15600]	[L1: 0.5293]	13.4+0.1s
+[12800/15600]	[L1: 0.5315]	10.8+0.1s
+[14400/15600]	[L1: 0.5302]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.466 (Best: 53.893 @epoch 164)
+Forward: 62.15s
+
+Saving...
+Total: 62.66s
+
+[Epoch 166]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5171]	11.3+0.7s
+[3200/15600]	[L1: 0.5221]	13.3+0.1s
+[4800/15600]	[L1: 0.5235]	10.8+0.1s
+[6400/15600]	[L1: 0.5240]	11.0+0.1s
+[8000/15600]	[L1: 0.5220]	13.7+0.1s
+[9600/15600]	[L1: 0.5249]	10.9+0.1s
+[11200/15600]	[L1: 0.5280]	11.1+0.1s
+[12800/15600]	[L1: 0.5295]	13.7+0.1s
+[14400/15600]	[L1: 0.5290]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.915 (Best: 53.915 @epoch 166)
+Forward: 63.23s
+
+Saving...
+Total: 63.97s
+
+[Epoch 167]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5286]	9.9+0.7s
+[3200/15600]	[L1: 0.5352]	9.8+0.1s
+[4800/15600]	[L1: 0.5295]	9.7+0.1s
+[6400/15600]	[L1: 0.5328]	13.4+0.1s
+[8000/15600]	[L1: 0.5316]	10.6+0.1s
+[9600/15600]	[L1: 0.5303]	10.2+0.1s
+[11200/15600]	[L1: 0.5329]	13.2+0.1s
+[12800/15600]	[L1: 0.5323]	10.9+0.1s
+[14400/15600]	[L1: 0.5336]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.796 (Best: 53.915 @epoch 166)
+Forward: 64.32s
+
+Saving...
+Total: 64.85s
+
+[Epoch 168]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5229]	11.1+0.7s
+[3200/15600]	[L1: 0.5277]	10.4+0.1s
+[4800/15600]	[L1: 0.5352]	12.9+0.1s
+[6400/15600]	[L1: 0.5366]	11.0+0.1s
+[8000/15600]	[L1: 0.5320]	10.9+0.1s
+[9600/15600]	[L1: 0.5335]	13.5+0.1s
+[11200/15600]	[L1: 0.5328]	11.0+0.1s
+[12800/15600]	[L1: 0.5321]	10.9+0.1s
+[14400/15600]	[L1: 0.5326]	13.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.879 (Best: 53.915 @epoch 166)
+Forward: 62.98s
+
+Saving...
+Total: 63.51s
+
+[Epoch 169]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5299]	13.3+0.7s
+[3200/15600]	[L1: 0.5282]	11.0+0.1s
+[4800/15600]	[L1: 0.5333]	9.8+0.1s
+[6400/15600]	[L1: 0.5332]	11.7+0.1s
+[8000/15600]	[L1: 0.5355]	11.2+0.1s
+[9600/15600]	[L1: 0.5334]	10.3+0.1s
+[11200/15600]	[L1: 0.5328]	10.4+0.1s
+[12800/15600]	[L1: 0.5303]	12.0+0.1s
+[14400/15600]	[L1: 0.5302]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.170 (Best: 53.915 @epoch 166)
+Forward: 62.59s
+
+Saving...
+Total: 63.12s
+
+[Epoch 170]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5286]	11.2+0.7s
+[3200/15600]	[L1: 0.5286]	10.9+0.1s
+[4800/15600]	[L1: 0.5254]	12.9+0.1s
+[6400/15600]	[L1: 0.5236]	10.8+0.1s
+[8000/15600]	[L1: 0.5240]	10.8+0.1s
+[9600/15600]	[L1: 0.5207]	11.6+0.1s
+[11200/15600]	[L1: 0.5215]	11.0+0.1s
+[12800/15600]	[L1: 0.5224]	10.5+0.1s
+[14400/15600]	[L1: 0.5258]	9.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.604 (Best: 53.915 @epoch 166)
+Forward: 63.28s
+
+Saving...
+Total: 63.79s
+
+[Epoch 171]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5260]	11.0+0.6s
+[3200/15600]	[L1: 0.5284]	11.0+0.1s
+[4800/15600]	[L1: 0.5312]	10.8+0.1s
+[6400/15600]	[L1: 0.5240]	10.8+0.1s
+[8000/15600]	[L1: 0.5261]	12.5+0.1s
+[9600/15600]	[L1: 0.5282]	10.8+0.1s
+[11200/15600]	[L1: 0.5275]	10.7+0.1s
+[12800/15600]	[L1: 0.5271]	12.2+0.1s
+[14400/15600]	[L1: 0.5266]	10.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.672 (Best: 53.915 @epoch 166)
+Forward: 64.15s
+
+Saving...
+Total: 64.67s
+
+[Epoch 172]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5075]	11.1+0.8s
+[3200/15600]	[L1: 0.5140]	10.4+0.1s
+[4800/15600]	[L1: 0.5160]	12.5+0.1s
+[6400/15600]	[L1: 0.5193]	11.3+0.1s
+[8000/15600]	[L1: 0.5225]	11.4+0.1s
+[9600/15600]	[L1: 0.5257]	10.6+0.1s
+[11200/15600]	[L1: 0.5257]	13.0+0.1s
+[12800/15600]	[L1: 0.5254]	11.1+0.1s
+[14400/15600]	[L1: 0.5246]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.572 (Best: 53.915 @epoch 166)
+Forward: 62.16s
+
+Saving...
+Total: 62.66s
+
+[Epoch 173]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5548]	10.8+0.8s
+[3200/15600]	[L1: 0.5497]	13.0+0.1s
+[4800/15600]	[L1: 0.5407]	10.8+0.1s
+[6400/15600]	[L1: 0.5398]	11.0+0.1s
+[8000/15600]	[L1: 0.5355]	13.3+0.1s
+[9600/15600]	[L1: 0.5334]	9.5+0.1s
+[11200/15600]	[L1: 0.5318]	9.6+0.1s
+[12800/15600]	[L1: 0.5299]	10.4+0.1s
+[14400/15600]	[L1: 0.5288]	13.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.693 (Best: 53.915 @epoch 166)
+Forward: 64.80s
+
+Saving...
+Total: 65.79s
+
+[Epoch 174]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5273]	11.7+1.0s
+[3200/15600]	[L1: 0.5266]	11.5+0.1s
+[4800/15600]	[L1: 0.5233]	13.4+0.1s
+[6400/15600]	[L1: 0.5228]	12.1+0.1s
+[8000/15600]	[L1: 0.5269]	11.4+0.1s
+[9600/15600]	[L1: 0.5267]	12.1+0.1s
+[11200/15600]	[L1: 0.5266]	13.5+0.1s
+[12800/15600]	[L1: 0.5259]	11.3+0.1s
+[14400/15600]	[L1: 0.5255]	11.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.424 (Best: 53.915 @epoch 166)
+Forward: 63.61s
+
+Saving...
+Total: 64.29s
+
+[Epoch 175]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5342]	13.5+0.7s
+[3200/15600]	[L1: 0.5319]	11.0+0.1s
+[4800/15600]	[L1: 0.5304]	11.1+0.1s
+[6400/15600]	[L1: 0.5285]	12.0+0.1s
+[8000/15600]	[L1: 0.5265]	12.6+0.1s
+[9600/15600]	[L1: 0.5253]	11.0+0.1s
+[11200/15600]	[L1: 0.5228]	11.1+0.1s
+[12800/15600]	[L1: 0.5249]	13.2+0.1s
+[14400/15600]	[L1: 0.5248]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.948 (Best: 53.948 @epoch 175)
+Forward: 67.09s
+
+Saving...
+Total: 67.68s
+
+[Epoch 176]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5300]	11.2+0.7s
+[3200/15600]	[L1: 0.5195]	10.8+0.1s
+[4800/15600]	[L1: 0.5231]	13.5+0.1s
+[6400/15600]	[L1: 0.5292]	11.0+0.1s
+[8000/15600]	[L1: 0.5252]	10.8+0.1s
+[9600/15600]	[L1: 0.5221]	13.1+0.1s
+[11200/15600]	[L1: 0.5247]	11.3+0.1s
+[12800/15600]	[L1: 0.5260]	11.0+0.1s
+[14400/15600]	[L1: 0.5238]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.973 (Best: 53.973 @epoch 176)
+Forward: 62.93s
+
+Saving...
+Total: 63.46s
+
+[Epoch 177]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5130]	13.1+0.7s
+[3200/15600]	[L1: 0.5259]	10.0+0.1s
+[4800/15600]	[L1: 0.5265]	10.6+0.1s
+[6400/15600]	[L1: 0.5308]	11.0+0.1s
+[8000/15600]	[L1: 0.5301]	13.7+0.1s
+[9600/15600]	[L1: 0.5293]	11.4+0.1s
+[11200/15600]	[L1: 0.5276]	9.9+0.1s
+[12800/15600]	[L1: 0.5263]	13.0+0.1s
+[14400/15600]	[L1: 0.5280]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.040 (Best: 54.040 @epoch 177)
+Forward: 66.11s
+
+Saving...
+Total: 66.66s
+
+[Epoch 178]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5114]	11.1+0.7s
+[3200/15600]	[L1: 0.5158]	10.4+0.1s
+[4800/15600]	[L1: 0.5182]	12.5+0.1s
+[6400/15600]	[L1: 0.5156]	10.9+0.1s
+[8000/15600]	[L1: 0.5153]	9.7+0.1s
+[9600/15600]	[L1: 0.5170]	9.7+0.1s
+[11200/15600]	[L1: 0.5176]	12.1+0.1s
+[12800/15600]	[L1: 0.5185]	10.8+0.1s
+[14400/15600]	[L1: 0.5178]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.713 (Best: 54.040 @epoch 177)
+Forward: 64.43s
+
+Saving...
+Total: 64.97s
+
+[Epoch 179]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5255]	11.0+0.7s
+[3200/15600]	[L1: 0.5359]	13.6+0.1s
+[4800/15600]	[L1: 0.5340]	11.0+0.1s
+[6400/15600]	[L1: 0.5388]	11.1+0.1s
+[8000/15600]	[L1: 0.5345]	11.1+0.1s
+[9600/15600]	[L1: 0.5332]	13.4+0.1s
+[11200/15600]	[L1: 0.5329]	10.9+0.1s
+[12800/15600]	[L1: 0.5318]	11.0+0.1s
+[14400/15600]	[L1: 0.5312]	13.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.989 (Best: 54.040 @epoch 177)
+Forward: 62.81s
+
+Saving...
+Total: 63.78s
+
+[Epoch 180]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5168]	11.5+1.0s
+[3200/15600]	[L1: 0.5227]	10.8+0.1s
+[4800/15600]	[L1: 0.5203]	11.2+0.1s
+[6400/15600]	[L1: 0.5194]	14.0+0.1s
+[8000/15600]	[L1: 0.5221]	11.3+0.1s
+[9600/15600]	[L1: 0.5185]	11.1+0.1s
+[11200/15600]	[L1: 0.5196]	13.7+0.1s
+[12800/15600]	[L1: 0.5218]	11.0+0.1s
+[14400/15600]	[L1: 0.5209]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.609 (Best: 54.040 @epoch 177)
+Forward: 63.08s
+
+Saving...
+Total: 63.64s
+
+[Epoch 181]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5312]	11.3+0.7s
+[3200/15600]	[L1: 0.5330]	14.0+0.1s
+[4800/15600]	[L1: 0.5317]	11.3+0.1s
+[6400/15600]	[L1: 0.5321]	11.1+0.1s
+[8000/15600]	[L1: 0.5300]	13.9+0.1s
+[9600/15600]	[L1: 0.5302]	11.1+0.1s
+[11200/15600]	[L1: 0.5260]	10.9+0.1s
+[12800/15600]	[L1: 0.5268]	13.6+0.1s
+[14400/15600]	[L1: 0.5245]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.894 (Best: 54.040 @epoch 177)
+Forward: 66.61s
+
+Saving...
+Total: 67.10s
+
+[Epoch 182]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5053]	11.1+0.7s
+[3200/15600]	[L1: 0.5212]	11.0+0.1s
+[4800/15600]	[L1: 0.5209]	12.6+0.1s
+[6400/15600]	[L1: 0.5204]	11.4+0.1s
+[8000/15600]	[L1: 0.5198]	10.9+0.1s
+[9600/15600]	[L1: 0.5189]	10.3+0.1s
+[11200/15600]	[L1: 0.5190]	13.4+0.1s
+[12800/15600]	[L1: 0.5184]	10.8+0.1s
+[14400/15600]	[L1: 0.5198]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.515 (Best: 54.040 @epoch 177)
+Forward: 61.94s
+
+Saving...
+Total: 62.49s
+
+[Epoch 183]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5339]	10.7+0.7s
+[3200/15600]	[L1: 0.5282]	13.3+0.1s
+[4800/15600]	[L1: 0.5244]	10.8+0.1s
+[6400/15600]	[L1: 0.5233]	11.0+0.1s
+[8000/15600]	[L1: 0.5242]	13.4+0.1s
+[9600/15600]	[L1: 0.5239]	10.9+0.1s
+[11200/15600]	[L1: 0.5272]	10.8+0.1s
+[12800/15600]	[L1: 0.5263]	11.2+0.1s
+[14400/15600]	[L1: 0.5270]	12.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.706 (Best: 54.040 @epoch 177)
+Forward: 64.22s
+
+Saving...
+Total: 65.22s
+
+[Epoch 184]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5250]	9.9+1.0s
+[3200/15600]	[L1: 0.5250]	9.5+0.1s
+[4800/15600]	[L1: 0.5272]	10.8+0.1s
+[6400/15600]	[L1: 0.5270]	13.5+0.1s
+[8000/15600]	[L1: 0.5281]	10.9+0.1s
+[9600/15600]	[L1: 0.5268]	11.1+0.1s
+[11200/15600]	[L1: 0.5259]	13.3+0.1s
+[12800/15600]	[L1: 0.5262]	11.1+0.1s
+[14400/15600]	[L1: 0.5277]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.863 (Best: 54.040 @epoch 177)
+Forward: 64.06s
+
+Saving...
+Total: 64.57s
+
+[Epoch 185]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5187]	10.5+0.7s
+[3200/15600]	[L1: 0.5129]	11.7+0.1s
+[4800/15600]	[L1: 0.5208]	12.0+0.1s
+[6400/15600]	[L1: 0.5270]	11.1+0.1s
+[8000/15600]	[L1: 0.5232]	11.2+0.1s
+[9600/15600]	[L1: 0.5237]	13.7+0.1s
+[11200/15600]	[L1: 0.5240]	11.3+0.1s
+[12800/15600]	[L1: 0.5232]	11.2+0.1s
+[14400/15600]	[L1: 0.5228]	13.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.676 (Best: 54.040 @epoch 177)
+Forward: 62.66s
+
+Saving...
+Total: 63.20s
+
+[Epoch 186]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5174]	12.5+0.7s
+[3200/15600]	[L1: 0.5168]	10.8+0.1s
+[4800/15600]	[L1: 0.5172]	10.8+0.1s
+[6400/15600]	[L1: 0.5172]	12.5+0.1s
+[8000/15600]	[L1: 0.5175]	9.2+0.1s
+[9600/15600]	[L1: 0.5168]	10.3+0.1s
+[11200/15600]	[L1: 0.5189]	10.1+0.1s
+[12800/15600]	[L1: 0.5223]	11.6+0.1s
+[14400/15600]	[L1: 0.5216]	9.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.574 (Best: 54.040 @epoch 177)
+Forward: 64.77s
+
+Saving...
+Total: 65.30s
+
+[Epoch 187]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5072]	11.3+0.8s
+[3200/15600]	[L1: 0.5057]	11.0+0.1s
+[4800/15600]	[L1: 0.5121]	13.8+0.1s
+[6400/15600]	[L1: 0.5142]	10.5+0.1s
+[8000/15600]	[L1: 0.5170]	10.4+0.1s
+[9600/15600]	[L1: 0.5162]	12.2+0.1s
+[11200/15600]	[L1: 0.5154]	11.3+0.1s
+[12800/15600]	[L1: 0.5147]	9.9+0.1s
+[14400/15600]	[L1: 0.5183]	9.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.946 (Best: 54.040 @epoch 177)
+Forward: 62.58s
+
+Saving...
+Total: 63.11s
+
+[Epoch 188]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5311]	9.9+0.7s
+[3200/15600]	[L1: 0.5205]	13.1+0.1s
+[4800/15600]	[L1: 0.5205]	11.1+0.1s
+[6400/15600]	[L1: 0.5182]	10.1+0.1s
+[8000/15600]	[L1: 0.5225]	12.8+0.1s
+[9600/15600]	[L1: 0.5220]	10.8+0.1s
+[11200/15600]	[L1: 0.5216]	9.8+0.1s
+[12800/15600]	[L1: 0.5216]	10.9+0.1s
+[14400/15600]	[L1: 0.5201]	13.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.039 (Best: 54.040 @epoch 177)
+Forward: 62.90s
+
+Saving...
+Total: 63.80s
+
+[Epoch 189]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5172]	11.2+0.9s
+[3200/15600]	[L1: 0.5150]	10.2+0.1s
+[4800/15600]	[L1: 0.5108]	11.2+0.1s
+[6400/15600]	[L1: 0.5122]	13.7+0.1s
+[8000/15600]	[L1: 0.5143]	11.1+0.1s
+[9600/15600]	[L1: 0.5143]	10.7+0.1s
+[11200/15600]	[L1: 0.5145]	13.1+0.1s
+[12800/15600]	[L1: 0.5142]	11.1+0.1s
+[14400/15600]	[L1: 0.5156]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.541 (Best: 54.040 @epoch 177)
+Forward: 64.62s
+
+Saving...
+Total: 65.16s
+
+[Epoch 190]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5286]	11.4+0.7s
+[3200/15600]	[L1: 0.5254]	11.3+0.1s
+[4800/15600]	[L1: 0.5222]	12.9+0.1s
+[6400/15600]	[L1: 0.5197]	11.0+0.1s
+[8000/15600]	[L1: 0.5186]	10.9+0.1s
+[9600/15600]	[L1: 0.5208]	13.5+0.1s
+[11200/15600]	[L1: 0.5203]	10.8+0.1s
+[12800/15600]	[L1: 0.5202]	10.9+0.1s
+[14400/15600]	[L1: 0.5206]	13.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.132 (Best: 54.132 @epoch 190)
+Forward: 63.00s
+
+Saving...
+Total: 63.57s
+
+[Epoch 191]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.4932]	13.9+0.7s
+[3200/15600]	[L1: 0.5015]	10.8+0.1s
+[4800/15600]	[L1: 0.5107]	11.0+0.1s
+[6400/15600]	[L1: 0.5198]	13.4+0.1s
+[8000/15600]	[L1: 0.5197]	10.9+0.1s
+[9600/15600]	[L1: 0.5177]	10.8+0.1s
+[11200/15600]	[L1: 0.5178]	13.8+0.1s
+[12800/15600]	[L1: 0.5166]	11.1+0.1s
+[14400/15600]	[L1: 0.5193]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.459 (Best: 54.132 @epoch 190)
+Forward: 64.44s
+
+Saving...
+Total: 64.96s
+
+[Epoch 192]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5137]	10.7+0.6s
+[3200/15600]	[L1: 0.5111]	10.4+0.1s
+[4800/15600]	[L1: 0.5181]	12.8+0.1s
+[6400/15600]	[L1: 0.5161]	10.2+0.1s
+[8000/15600]	[L1: 0.5174]	10.2+0.1s
+[9600/15600]	[L1: 0.5147]	12.6+0.1s
+[11200/15600]	[L1: 0.5153]	10.3+0.1s
+[12800/15600]	[L1: 0.5175]	10.3+0.1s
+[14400/15600]	[L1: 0.5178]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.931 (Best: 54.132 @epoch 190)
+Forward: 64.10s
+
+Saving...
+Total: 64.66s
+
+[Epoch 193]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5338]	13.0+0.8s
+[3200/15600]	[L1: 0.5243]	11.3+0.1s
+[4800/15600]	[L1: 0.5280]	10.6+0.1s
+[6400/15600]	[L1: 0.5304]	10.7+0.1s
+[8000/15600]	[L1: 0.5271]	13.2+0.1s
+[9600/15600]	[L1: 0.5254]	10.9+0.1s
+[11200/15600]	[L1: 0.5233]	10.9+0.1s
+[12800/15600]	[L1: 0.5226]	13.2+0.1s
+[14400/15600]	[L1: 0.5213]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.998 (Best: 54.132 @epoch 190)
+Forward: 65.96s
+
+Saving...
+Total: 66.65s
+
+[Epoch 194]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5077]	11.0+0.7s
+[3200/15600]	[L1: 0.5120]	10.8+0.1s
+[4800/15600]	[L1: 0.5151]	11.5+0.1s
+[6400/15600]	[L1: 0.5164]	12.7+0.1s
+[8000/15600]	[L1: 0.5142]	11.1+0.1s
+[9600/15600]	[L1: 0.5176]	11.1+0.1s
+[11200/15600]	[L1: 0.5171]	13.6+0.1s
+[12800/15600]	[L1: 0.5176]	11.1+0.1s
+[14400/15600]	[L1: 0.5179]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.540 (Best: 54.132 @epoch 190)
+Forward: 64.95s
+
+Saving...
+Total: 65.49s
+
+[Epoch 195]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5026]	11.3+0.7s
+[3200/15600]	[L1: 0.5205]	13.7+0.1s
+[4800/15600]	[L1: 0.5157]	11.0+0.1s
+[6400/15600]	[L1: 0.5157]	11.2+0.1s
+[8000/15600]	[L1: 0.5172]	13.7+0.1s
+[9600/15600]	[L1: 0.5182]	11.1+0.1s
+[11200/15600]	[L1: 0.5182]	11.0+0.1s
+[12800/15600]	[L1: 0.5212]	13.5+0.1s
+[14400/15600]	[L1: 0.5224]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.072 (Best: 54.132 @epoch 190)
+Forward: 65.05s
+
+Saving...
+Total: 65.58s
+
+[Epoch 196]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5216]	11.3+0.7s
+[3200/15600]	[L1: 0.5278]	11.4+0.1s
+[4800/15600]	[L1: 0.5242]	13.4+0.1s
+[6400/15600]	[L1: 0.5218]	11.2+0.1s
+[8000/15600]	[L1: 0.5232]	11.1+0.1s
+[9600/15600]	[L1: 0.5223]	11.3+0.1s
+[11200/15600]	[L1: 0.5197]	13.1+0.1s
+[12800/15600]	[L1: 0.5176]	10.0+0.1s
+[14400/15600]	[L1: 0.5181]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.891 (Best: 54.132 @epoch 190)
+Forward: 61.57s
+
+Saving...
+Total: 62.09s
+
+[Epoch 197]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5069]	10.1+0.7s
+[3200/15600]	[L1: 0.5120]	12.5+0.1s
+[4800/15600]	[L1: 0.5148]	11.0+0.1s
+[6400/15600]	[L1: 0.5171]	11.5+0.1s
+[8000/15600]	[L1: 0.5206]	13.7+0.1s
+[9600/15600]	[L1: 0.5229]	10.2+0.1s
+[11200/15600]	[L1: 0.5218]	10.3+0.1s
+[12800/15600]	[L1: 0.5190]	11.0+0.1s
+[14400/15600]	[L1: 0.5187]	12.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.193 (Best: 54.193 @epoch 197)
+Forward: 65.00s
+
+Saving...
+Total: 65.92s
+
+[Epoch 198]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5223]	11.4+0.9s
+[3200/15600]	[L1: 0.5215]	11.0+0.1s
+[4800/15600]	[L1: 0.5184]	12.2+0.1s
+[6400/15600]	[L1: 0.5195]	12.0+0.1s
+[8000/15600]	[L1: 0.5185]	10.1+0.1s
+[9600/15600]	[L1: 0.5213]	10.0+0.1s
+[11200/15600]	[L1: 0.5210]	13.3+0.1s
+[12800/15600]	[L1: 0.5191]	9.7+0.1s
+[14400/15600]	[L1: 0.5201]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.182 (Best: 54.193 @epoch 197)
+Forward: 64.39s
+
+Saving...
+Total: 64.94s
+
+[Epoch 199]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5130]	11.3+0.7s
+[3200/15600]	[L1: 0.5180]	11.7+0.1s
+[4800/15600]	[L1: 0.5185]	12.4+0.1s
+[6400/15600]	[L1: 0.5169]	11.0+0.1s
+[8000/15600]	[L1: 0.5156]	10.1+0.1s
+[9600/15600]	[L1: 0.5147]	13.3+0.1s
+[11200/15600]	[L1: 0.5163]	10.2+0.1s
+[12800/15600]	[L1: 0.5147]	9.7+0.1s
+[14400/15600]	[L1: 0.5153]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.847 (Best: 54.193 @epoch 197)
+Forward: 61.09s
+
+Saving...
+Total: 61.66s
+
+[Epoch 200]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4927]	12.5+0.6s
+[3200/15600]	[L1: 0.4895]	10.7+0.1s
+[4800/15600]	[L1: 0.4921]	11.0+0.1s
+[6400/15600]	[L1: 0.4878]	12.0+0.1s
+[8000/15600]	[L1: 0.4881]	12.1+0.1s
+[9600/15600]	[L1: 0.4877]	11.1+0.1s
+[11200/15600]	[L1: 0.4862]	10.9+0.1s
+[12800/15600]	[L1: 0.4856]	12.8+0.1s
+[14400/15600]	[L1: 0.4838]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.290 (Best: 54.290 @epoch 200)
+Forward: 62.72s
+
+Saving...
+Total: 63.30s
+
+[Epoch 201]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4701]	11.2+0.6s
+[3200/15600]	[L1: 0.4844]	11.9+0.1s
+[4800/15600]	[L1: 0.4872]	11.8+0.1s
+[6400/15600]	[L1: 0.4898]	11.1+0.1s
+[8000/15600]	[L1: 0.4886]	11.1+0.1s
+[9600/15600]	[L1: 0.4881]	12.8+0.1s
+[11200/15600]	[L1: 0.4868]	10.9+0.1s
+[12800/15600]	[L1: 0.4858]	10.4+0.1s
+[14400/15600]	[L1: 0.4866]	12.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.318 (Best: 54.318 @epoch 201)
+Forward: 62.89s
+
+Saving...
+Total: 63.80s
+
+[Epoch 202]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.5007]	11.3+1.1s
+[3200/15600]	[L1: 0.4943]	11.2+0.1s
+[4800/15600]	[L1: 0.4895]	11.3+0.1s
+[6400/15600]	[L1: 0.4881]	13.6+0.1s
+[8000/15600]	[L1: 0.4910]	11.0+0.1s
+[9600/15600]	[L1: 0.4909]	10.8+0.1s
+[11200/15600]	[L1: 0.4879]	13.4+0.1s
+[12800/15600]	[L1: 0.4870]	11.0+0.1s
+[14400/15600]	[L1: 0.4879]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.340 (Best: 54.340 @epoch 202)
+Forward: 62.99s
+
+Saving...
+Total: 63.57s
+
+[Epoch 203]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4839]	10.8+0.7s
+[3200/15600]	[L1: 0.4823]	13.4+0.1s
+[4800/15600]	[L1: 0.4808]	11.5+0.1s
+[6400/15600]	[L1: 0.4842]	11.2+0.1s
+[8000/15600]	[L1: 0.4831]	13.5+0.1s
+[9600/15600]	[L1: 0.4852]	11.0+0.1s
+[11200/15600]	[L1: 0.4873]	11.2+0.1s
+[12800/15600]	[L1: 0.4864]	13.6+0.1s
+[14400/15600]	[L1: 0.4860]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.094 (Best: 54.340 @epoch 202)
+Forward: 63.98s
+
+Saving...
+Total: 64.68s
+
+[Epoch 204]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4962]	11.1+0.7s
+[3200/15600]	[L1: 0.4792]	10.9+0.1s
+[4800/15600]	[L1: 0.4847]	11.7+0.1s
+[6400/15600]	[L1: 0.4838]	12.5+0.1s
+[8000/15600]	[L1: 0.4816]	11.0+0.1s
+[9600/15600]	[L1: 0.4826]	11.0+0.1s
+[11200/15600]	[L1: 0.4833]	13.6+0.1s
+[12800/15600]	[L1: 0.4830]	11.1+0.1s
+[14400/15600]	[L1: 0.4842]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.255 (Best: 54.340 @epoch 202)
+Forward: 60.86s
+
+Saving...
+Total: 61.41s
+
+[Epoch 205]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4907]	10.8+0.6s
+[3200/15600]	[L1: 0.4877]	13.1+0.1s
+[4800/15600]	[L1: 0.4887]	11.0+0.1s
+[6400/15600]	[L1: 0.4862]	10.3+0.1s
+[8000/15600]	[L1: 0.4831]	12.9+0.1s
+[9600/15600]	[L1: 0.4822]	10.3+0.1s
+[11200/15600]	[L1: 0.4837]	10.0+0.1s
+[12800/15600]	[L1: 0.4840]	11.1+0.1s
+[14400/15600]	[L1: 0.4853]	11.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.335 (Best: 54.340 @epoch 202)
+Forward: 63.19s
+
+Saving...
+Total: 64.10s
+
+[Epoch 206]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4819]	11.4+1.1s
+[3200/15600]	[L1: 0.4838]	11.0+0.1s
+[4800/15600]	[L1: 0.4895]	12.6+0.1s
+[6400/15600]	[L1: 0.4886]	12.2+0.1s
+[8000/15600]	[L1: 0.4876]	11.0+0.1s
+[9600/15600]	[L1: 0.4877]	11.1+0.1s
+[11200/15600]	[L1: 0.4878]	13.8+0.1s
+[12800/15600]	[L1: 0.4854]	11.0+0.1s
+[14400/15600]	[L1: 0.4847]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.252 (Best: 54.340 @epoch 202)
+Forward: 61.40s
+
+Saving...
+Total: 61.89s
+
+[Epoch 207]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4785]	11.2+0.6s
+[3200/15600]	[L1: 0.4789]	12.9+0.1s
+[4800/15600]	[L1: 0.4811]	10.4+0.1s
+[6400/15600]	[L1: 0.4837]	10.2+0.1s
+[8000/15600]	[L1: 0.4845]	12.8+0.1s
+[9600/15600]	[L1: 0.4855]	10.1+0.1s
+[11200/15600]	[L1: 0.4846]	10.3+0.1s
+[12800/15600]	[L1: 0.4832]	10.3+0.1s
+[14400/15600]	[L1: 0.4823]	12.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.399 (Best: 54.399 @epoch 207)
+Forward: 64.74s
+
+Saving...
+Total: 65.57s
+
+[Epoch 208]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4749]	11.1+1.1s
+[3200/15600]	[L1: 0.4813]	10.9+0.1s
+[4800/15600]	[L1: 0.4773]	12.0+0.1s
+[6400/15600]	[L1: 0.4780]	12.4+0.1s
+[8000/15600]	[L1: 0.4792]	10.9+0.1s
+[9600/15600]	[L1: 0.4798]	10.9+0.1s
+[11200/15600]	[L1: 0.4798]	13.6+0.1s
+[12800/15600]	[L1: 0.4794]	11.0+0.1s
+[14400/15600]	[L1: 0.4799]	11.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.404 (Best: 54.404 @epoch 208)
+Forward: 61.07s
+
+Saving...
+Total: 61.61s
+
+[Epoch 209]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4729]	11.3+0.6s
+[3200/15600]	[L1: 0.4784]	12.4+0.1s
+[4800/15600]	[L1: 0.4798]	9.6+0.1s
+[6400/15600]	[L1: 0.4793]	10.5+0.1s
+[8000/15600]	[L1: 0.4793]	12.7+0.1s
+[9600/15600]	[L1: 0.4828]	10.4+0.1s
+[11200/15600]	[L1: 0.4832]	10.1+0.1s
+[12800/15600]	[L1: 0.4820]	10.3+0.1s
+[14400/15600]	[L1: 0.4811]	12.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.048 (Best: 54.404 @epoch 208)
+Forward: 62.16s
+
+Saving...
+Total: 62.69s
+
+[Epoch 210]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4892]	12.7+0.6s
+[3200/15600]	[L1: 0.4847]	10.0+0.1s
+[4800/15600]	[L1: 0.4831]	9.5+0.1s
+[6400/15600]	[L1: 0.4810]	11.5+0.1s
+[8000/15600]	[L1: 0.4785]	10.8+0.1s
+[9600/15600]	[L1: 0.4800]	11.0+0.1s
+[11200/15600]	[L1: 0.4782]	11.1+0.1s
+[12800/15600]	[L1: 0.4779]	11.5+0.1s
+[14400/15600]	[L1: 0.4792]	9.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.302 (Best: 54.404 @epoch 208)
+Forward: 64.36s
+
+Saving...
+Total: 64.86s
+
+[Epoch 211]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4780]	11.2+0.8s
+[3200/15600]	[L1: 0.4896]	10.8+0.1s
+[4800/15600]	[L1: 0.4790]	13.8+0.1s
+[6400/15600]	[L1: 0.4792]	10.9+0.1s
+[8000/15600]	[L1: 0.4785]	11.0+0.1s
+[9600/15600]	[L1: 0.4791]	13.1+0.1s
+[11200/15600]	[L1: 0.4802]	11.6+0.1s
+[12800/15600]	[L1: 0.4822]	11.2+0.1s
+[14400/15600]	[L1: 0.4827]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.214 (Best: 54.404 @epoch 208)
+Forward: 64.35s
+
+Saving...
+Total: 64.83s
+
+[Epoch 212]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4859]	13.6+0.7s
+[3200/15600]	[L1: 0.4759]	11.1+0.1s
+[4800/15600]	[L1: 0.4766]	11.0+0.1s
+[6400/15600]	[L1: 0.4785]	12.5+0.1s
+[8000/15600]	[L1: 0.4784]	12.1+0.1s
+[9600/15600]	[L1: 0.4783]	10.5+0.1s
+[11200/15600]	[L1: 0.4781]	10.1+0.1s
+[12800/15600]	[L1: 0.4780]	12.8+0.1s
+[14400/15600]	[L1: 0.4794]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.890 (Best: 54.404 @epoch 208)
+Forward: 65.14s
+
+Saving...
+Total: 65.64s
+
+[Epoch 213]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4759]	11.0+0.7s
+[3200/15600]	[L1: 0.4849]	11.0+0.1s
+[4800/15600]	[L1: 0.4820]	13.0+0.1s
+[6400/15600]	[L1: 0.4848]	11.2+0.1s
+[8000/15600]	[L1: 0.4830]	10.7+0.1s
+[9600/15600]	[L1: 0.4853]	10.9+0.1s
+[11200/15600]	[L1: 0.4855]	13.7+0.1s
+[12800/15600]	[L1: 0.4872]	10.8+0.1s
+[14400/15600]	[L1: 0.4868]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.378 (Best: 54.404 @epoch 208)
+Forward: 63.27s
+
+Saving...
+Total: 63.74s
+
+[Epoch 214]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4807]	11.7+0.7s
+[3200/15600]	[L1: 0.4753]	12.9+0.1s
+[4800/15600]	[L1: 0.4812]	10.9+0.1s
+[6400/15600]	[L1: 0.4773]	11.1+0.1s
+[8000/15600]	[L1: 0.4798]	13.6+0.1s
+[9600/15600]	[L1: 0.4803]	10.4+0.1s
+[11200/15600]	[L1: 0.4801]	10.0+0.1s
+[12800/15600]	[L1: 0.4815]	13.0+0.1s
+[14400/15600]	[L1: 0.4795]	10.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.266 (Best: 54.404 @epoch 208)
+Forward: 63.98s
+
+Saving...
+Total: 64.76s
+
+[Epoch 215]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4825]	10.8+0.8s
+[3200/15600]	[L1: 0.4755]	9.7+0.1s
+[4800/15600]	[L1: 0.4813]	9.5+0.1s
+[6400/15600]	[L1: 0.4813]	13.3+0.1s
+[8000/15600]	[L1: 0.4807]	11.0+0.1s
+[9600/15600]	[L1: 0.4806]	9.7+0.1s
+[11200/15600]	[L1: 0.4810]	11.7+0.1s
+[12800/15600]	[L1: 0.4807]	10.2+0.1s
+[14400/15600]	[L1: 0.4809]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.089 (Best: 54.404 @epoch 208)
+Forward: 64.80s
+
+Saving...
+Total: 65.37s
+
+[Epoch 216]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4732]	10.9+0.7s
+[3200/15600]	[L1: 0.4755]	10.9+0.1s
+[4800/15600]	[L1: 0.4781]	13.3+0.1s
+[6400/15600]	[L1: 0.4769]	10.6+0.1s
+[8000/15600]	[L1: 0.4786]	10.3+0.1s
+[9600/15600]	[L1: 0.4830]	11.5+0.1s
+[11200/15600]	[L1: 0.4829]	10.9+0.1s
+[12800/15600]	[L1: 0.4825]	10.2+0.1s
+[14400/15600]	[L1: 0.4822]	9.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.345 (Best: 54.404 @epoch 208)
+Forward: 63.96s
+
+Saving...
+Total: 64.46s
+
+[Epoch 217]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4619]	10.0+0.7s
+[3200/15600]	[L1: 0.4660]	13.4+0.1s
+[4800/15600]	[L1: 0.4683]	10.9+0.1s
+[6400/15600]	[L1: 0.4714]	11.1+0.1s
+[8000/15600]	[L1: 0.4738]	13.7+0.1s
+[9600/15600]	[L1: 0.4744]	11.2+0.1s
+[11200/15600]	[L1: 0.4759]	10.6+0.1s
+[12800/15600]	[L1: 0.4753]	13.2+0.1s
+[14400/15600]	[L1: 0.4768]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.279 (Best: 54.404 @epoch 208)
+Forward: 64.36s
+
+Saving...
+Total: 65.20s
+
+[Epoch 218]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4733]	11.2+0.7s
+[3200/15600]	[L1: 0.4722]	10.9+0.1s
+[4800/15600]	[L1: 0.4738]	11.3+0.1s
+[6400/15600]	[L1: 0.4753]	12.9+0.1s
+[8000/15600]	[L1: 0.4739]	10.9+0.1s
+[9600/15600]	[L1: 0.4748]	10.8+0.1s
+[11200/15600]	[L1: 0.4774]	13.4+0.1s
+[12800/15600]	[L1: 0.4795]	10.9+0.1s
+[14400/15600]	[L1: 0.4792]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.365 (Best: 54.404 @epoch 208)
+Forward: 65.31s
+
+Saving...
+Total: 65.85s
+
+[Epoch 219]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4843]	12.1+0.7s
+[3200/15600]	[L1: 0.4872]	12.4+0.1s
+[4800/15600]	[L1: 0.4893]	11.0+0.1s
+[6400/15600]	[L1: 0.4888]	11.2+0.1s
+[8000/15600]	[L1: 0.4872]	13.5+0.1s
+[9600/15600]	[L1: 0.4883]	10.9+0.1s
+[11200/15600]	[L1: 0.4892]	11.0+0.1s
+[12800/15600]	[L1: 0.4884]	13.9+0.1s
+[14400/15600]	[L1: 0.4878]	10.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.940 (Best: 54.404 @epoch 208)
+Forward: 64.90s
+
+Saving...
+Total: 65.42s
+
+[Epoch 220]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4802]	11.3+0.6s
+[3200/15600]	[L1: 0.4790]	11.0+0.1s
+[4800/15600]	[L1: 0.4847]	12.5+0.1s
+[6400/15600]	[L1: 0.4840]	10.6+0.1s
+[8000/15600]	[L1: 0.4812]	10.1+0.1s
+[9600/15600]	[L1: 0.4816]	10.5+0.1s
+[11200/15600]	[L1: 0.4793]	11.3+0.1s
+[12800/15600]	[L1: 0.4796]	10.4+0.1s
+[14400/15600]	[L1: 0.4810]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.050 (Best: 54.404 @epoch 208)
+Forward: 63.92s
+
+Saving...
+Total: 64.59s
+
+[Epoch 221]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4824]	11.8+0.8s
+[3200/15600]	[L1: 0.4821]	11.5+0.1s
+[4800/15600]	[L1: 0.4836]	9.6+0.1s
+[6400/15600]	[L1: 0.4824]	10.1+0.1s
+[8000/15600]	[L1: 0.4817]	11.2+0.1s
+[9600/15600]	[L1: 0.4814]	9.1+0.1s
+[11200/15600]	[L1: 0.4816]	9.2+0.1s
+[12800/15600]	[L1: 0.4822]	9.8+0.1s
+[14400/15600]	[L1: 0.4825]	11.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.061 (Best: 54.404 @epoch 208)
+Forward: 65.21s
+
+Saving...
+Total: 65.91s
+
+[Epoch 222]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4654]	10.7+0.8s
+[3200/15600]	[L1: 0.4765]	11.1+0.1s
+[4800/15600]	[L1: 0.4807]	11.0+0.1s
+[6400/15600]	[L1: 0.4840]	12.8+0.1s
+[8000/15600]	[L1: 0.4831]	10.9+0.1s
+[9600/15600]	[L1: 0.4847]	11.0+0.1s
+[11200/15600]	[L1: 0.4856]	12.8+0.1s
+[12800/15600]	[L1: 0.4832]	10.7+0.1s
+[14400/15600]	[L1: 0.4825]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.188 (Best: 54.404 @epoch 208)
+Forward: 61.97s
+
+Saving...
+Total: 62.45s
+
+[Epoch 223]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4702]	12.4+0.6s
+[3200/15600]	[L1: 0.4713]	11.2+0.1s
+[4800/15600]	[L1: 0.4746]	10.2+0.1s
+[6400/15600]	[L1: 0.4748]	10.6+0.1s
+[8000/15600]	[L1: 0.4744]	10.9+0.1s
+[9600/15600]	[L1: 0.4743]	11.1+0.1s
+[11200/15600]	[L1: 0.4777]	10.9+0.1s
+[12800/15600]	[L1: 0.4770]	12.7+0.1s
+[14400/15600]	[L1: 0.4782]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.411 (Best: 54.411 @epoch 223)
+Forward: 64.73s
+
+Saving...
+Total: 65.26s
+
+[Epoch 224]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4728]	11.2+0.8s
+[3200/15600]	[L1: 0.4746]	11.2+0.1s
+[4800/15600]	[L1: 0.4761]	13.3+0.1s
+[6400/15600]	[L1: 0.4760]	11.0+0.1s
+[8000/15600]	[L1: 0.4767]	11.1+0.1s
+[9600/15600]	[L1: 0.4801]	13.6+0.1s
+[11200/15600]	[L1: 0.4797]	11.1+0.1s
+[12800/15600]	[L1: 0.4801]	10.9+0.1s
+[14400/15600]	[L1: 0.4809]	13.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.275 (Best: 54.411 @epoch 223)
+Forward: 63.22s
+
+Saving...
+Total: 63.72s
+
+[Epoch 225]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4822]	13.7+0.7s
+[3200/15600]	[L1: 0.4900]	10.8+0.1s
+[4800/15600]	[L1: 0.4845]	11.1+0.1s
+[6400/15600]	[L1: 0.4801]	13.7+0.1s
+[8000/15600]	[L1: 0.4802]	11.0+0.1s
+[9600/15600]	[L1: 0.4835]	11.1+0.1s
+[11200/15600]	[L1: 0.4832]	11.7+0.1s
+[12800/15600]	[L1: 0.4826]	12.5+0.1s
+[14400/15600]	[L1: 0.4825]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.204 (Best: 54.411 @epoch 223)
+Forward: 63.92s
+
+Saving...
+Total: 64.42s
+
+[Epoch 226]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4778]	11.2+0.6s
+[3200/15600]	[L1: 0.4756]	10.9+0.1s
+[4800/15600]	[L1: 0.4725]	13.1+0.1s
+[6400/15600]	[L1: 0.4726]	10.9+0.1s
+[8000/15600]	[L1: 0.4733]	11.3+0.1s
+[9600/15600]	[L1: 0.4760]	12.1+0.1s
+[11200/15600]	[L1: 0.4771]	9.7+0.1s
+[12800/15600]	[L1: 0.4756]	9.6+0.1s
+[14400/15600]	[L1: 0.4754]	9.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.187 (Best: 54.411 @epoch 223)
+Forward: 63.12s
+
+Saving...
+Total: 63.63s
+
+[Epoch 227]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4814]	11.3+0.8s
+[3200/15600]	[L1: 0.4833]	12.6+0.1s
+[4800/15600]	[L1: 0.4816]	11.1+0.1s
+[6400/15600]	[L1: 0.4812]	10.7+0.1s
+[8000/15600]	[L1: 0.4810]	11.9+0.1s
+[9600/15600]	[L1: 0.4830]	10.0+0.1s
+[11200/15600]	[L1: 0.4815]	10.2+0.1s
+[12800/15600]	[L1: 0.4801]	12.0+0.1s
+[14400/15600]	[L1: 0.4799]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.389 (Best: 54.411 @epoch 223)
+Forward: 63.02s
+
+Saving...
+Total: 63.52s
+
+[Epoch 228]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4756]	10.8+0.6s
+[3200/15600]	[L1: 0.4847]	10.9+0.1s
+[4800/15600]	[L1: 0.4798]	12.8+0.1s
+[6400/15600]	[L1: 0.4809]	11.1+0.1s
+[8000/15600]	[L1: 0.4831]	11.4+0.1s
+[9600/15600]	[L1: 0.4831]	12.7+0.1s
+[11200/15600]	[L1: 0.4826]	11.0+0.1s
+[12800/15600]	[L1: 0.4815]	10.5+0.1s
+[14400/15600]	[L1: 0.4824]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.487 (Best: 54.487 @epoch 228)
+Forward: 61.60s
+
+Saving...
+Total: 62.25s
+
+[Epoch 229]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4705]	13.9+0.7s
+[3200/15600]	[L1: 0.4726]	11.2+0.1s
+[4800/15600]	[L1: 0.4729]	11.0+0.1s
+[6400/15600]	[L1: 0.4767]	13.5+0.1s
+[8000/15600]	[L1: 0.4763]	10.8+0.1s
+[9600/15600]	[L1: 0.4755]	11.0+0.1s
+[11200/15600]	[L1: 0.4751]	13.7+0.1s
+[12800/15600]	[L1: 0.4752]	11.1+0.1s
+[14400/15600]	[L1: 0.4766]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.084 (Best: 54.487 @epoch 228)
+Forward: 64.10s
+
+Saving...
+Total: 64.58s
+
+[Epoch 230]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4784]	11.3+0.7s
+[3200/15600]	[L1: 0.4800]	11.1+0.1s
+[4800/15600]	[L1: 0.4777]	13.5+0.1s
+[6400/15600]	[L1: 0.4741]	11.0+0.1s
+[8000/15600]	[L1: 0.4756]	11.1+0.1s
+[9600/15600]	[L1: 0.4768]	13.6+0.1s
+[11200/15600]	[L1: 0.4770]	11.0+0.1s
+[12800/15600]	[L1: 0.4773]	11.1+0.1s
+[14400/15600]	[L1: 0.4772]	13.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.486 (Best: 54.487 @epoch 228)
+Forward: 61.88s
+
+Saving...
+Total: 62.43s
+
+[Epoch 231]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4823]	13.9+0.7s
+[3200/15600]	[L1: 0.4682]	10.9+0.1s
+[4800/15600]	[L1: 0.4700]	11.0+0.1s
+[6400/15600]	[L1: 0.4683]	13.6+0.1s
+[8000/15600]	[L1: 0.4712]	11.0+0.1s
+[9600/15600]	[L1: 0.4731]	11.1+0.1s
+[11200/15600]	[L1: 0.4747]	11.6+0.1s
+[12800/15600]	[L1: 0.4739]	13.0+0.1s
+[14400/15600]	[L1: 0.4744]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.503 (Best: 54.503 @epoch 231)
+Forward: 67.13s
+
+Saving...
+Total: 67.69s
+
+[Epoch 232]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4920]	11.4+0.7s
+[3200/15600]	[L1: 0.4769]	10.6+0.1s
+[4800/15600]	[L1: 0.4759]	12.1+0.1s
+[6400/15600]	[L1: 0.4773]	9.8+0.1s
+[8000/15600]	[L1: 0.4765]	9.7+0.1s
+[9600/15600]	[L1: 0.4756]	9.8+0.1s
+[11200/15600]	[L1: 0.4759]	12.0+0.1s
+[12800/15600]	[L1: 0.4790]	9.5+0.1s
+[14400/15600]	[L1: 0.4782]	9.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.368 (Best: 54.503 @epoch 231)
+Forward: 63.88s
+
+Saving...
+Total: 64.38s
+
+[Epoch 233]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4706]	11.0+0.6s
+[3200/15600]	[L1: 0.4718]	13.2+0.1s
+[4800/15600]	[L1: 0.4758]	10.8+0.1s
+[6400/15600]	[L1: 0.4763]	11.1+0.1s
+[8000/15600]	[L1: 0.4762]	11.5+0.1s
+[9600/15600]	[L1: 0.4761]	13.1+0.1s
+[11200/15600]	[L1: 0.4751]	10.3+0.1s
+[12800/15600]	[L1: 0.4758]	11.0+0.1s
+[14400/15600]	[L1: 0.4769]	13.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.277 (Best: 54.503 @epoch 231)
+Forward: 61.65s
+
+Saving...
+Total: 62.50s
+
+[Epoch 234]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4798]	11.5+0.6s
+[3200/15600]	[L1: 0.4776]	10.6+0.1s
+[4800/15600]	[L1: 0.4769]	11.7+0.1s
+[6400/15600]	[L1: 0.4730]	11.9+0.1s
+[8000/15600]	[L1: 0.4729]	10.9+0.1s
+[9600/15600]	[L1: 0.4732]	10.9+0.1s
+[11200/15600]	[L1: 0.4736]	13.1+0.1s
+[12800/15600]	[L1: 0.4742]	10.9+0.1s
+[14400/15600]	[L1: 0.4742]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.852 (Best: 54.503 @epoch 231)
+Forward: 63.97s
+
+Saving...
+Total: 64.52s
+
+[Epoch 235]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4745]	13.7+0.8s
+[3200/15600]	[L1: 0.4796]	11.0+0.1s
+[4800/15600]	[L1: 0.4787]	11.0+0.1s
+[6400/15600]	[L1: 0.4780]	11.0+0.1s
+[8000/15600]	[L1: 0.4794]	13.7+0.1s
+[9600/15600]	[L1: 0.4786]	11.0+0.1s
+[11200/15600]	[L1: 0.4774]	11.0+0.1s
+[12800/15600]	[L1: 0.4790]	13.5+0.1s
+[14400/15600]	[L1: 0.4786]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.224 (Best: 54.503 @epoch 231)
+Forward: 63.42s
+
+Saving...
+Total: 63.90s
+
+[Epoch 236]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4890]	11.3+0.7s
+[3200/15600]	[L1: 0.4780]	10.1+0.1s
+[4800/15600]	[L1: 0.4761]	11.6+0.1s
+[6400/15600]	[L1: 0.4756]	9.9+0.1s
+[8000/15600]	[L1: 0.4753]	10.1+0.1s
+[9600/15600]	[L1: 0.4780]	9.6+0.1s
+[11200/15600]	[L1: 0.4760]	11.1+0.1s
+[12800/15600]	[L1: 0.4771]	10.0+0.1s
+[14400/15600]	[L1: 0.4766]	10.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.357 (Best: 54.503 @epoch 231)
+Forward: 66.54s
+
+Saving...
+Total: 67.05s
+
+[Epoch 237]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4777]	10.9+0.6s
+[3200/15600]	[L1: 0.4784]	12.8+0.1s
+[4800/15600]	[L1: 0.4769]	11.0+0.1s
+[6400/15600]	[L1: 0.4798]	10.8+0.1s
+[8000/15600]	[L1: 0.4820]	12.0+0.1s
+[9600/15600]	[L1: 0.4810]	11.1+0.1s
+[11200/15600]	[L1: 0.4798]	10.9+0.1s
+[12800/15600]	[L1: 0.4793]	10.9+0.1s
+[14400/15600]	[L1: 0.4784]	12.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.437 (Best: 54.503 @epoch 231)
+Forward: 66.61s
+
+Saving...
+Total: 67.20s
+
+[Epoch 238]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4842]	10.8+0.8s
+[3200/15600]	[L1: 0.4848]	11.3+0.1s
+[4800/15600]	[L1: 0.4875]	13.0+0.1s
+[6400/15600]	[L1: 0.4851]	11.8+0.1s
+[8000/15600]	[L1: 0.4844]	10.4+0.1s
+[9600/15600]	[L1: 0.4825]	11.0+0.1s
+[11200/15600]	[L1: 0.4843]	13.3+0.1s
+[12800/15600]	[L1: 0.4811]	11.1+0.1s
+[14400/15600]	[L1: 0.4804]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.363 (Best: 54.503 @epoch 231)
+Forward: 60.44s
+
+Saving...
+Total: 60.96s
+
+[Epoch 239]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4671]	10.3+0.7s
+[3200/15600]	[L1: 0.4688]	13.1+0.1s
+[4800/15600]	[L1: 0.4657]	10.4+0.1s
+[6400/15600]	[L1: 0.4707]	9.9+0.1s
+[8000/15600]	[L1: 0.4703]	13.3+0.1s
+[9600/15600]	[L1: 0.4735]	10.9+0.1s
+[11200/15600]	[L1: 0.4736]	11.0+0.1s
+[12800/15600]	[L1: 0.4728]	11.3+0.1s
+[14400/15600]	[L1: 0.4723]	13.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.263 (Best: 54.503 @epoch 231)
+Forward: 64.55s
+
+Saving...
+Total: 65.38s
+
+[Epoch 240]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4801]	11.2+1.0s
+[3200/15600]	[L1: 0.4831]	11.1+0.1s
+[4800/15600]	[L1: 0.4793]	12.0+0.1s
+[6400/15600]	[L1: 0.4773]	12.6+0.1s
+[8000/15600]	[L1: 0.4765]	11.5+0.1s
+[9600/15600]	[L1: 0.4783]	11.2+0.1s
+[11200/15600]	[L1: 0.4773]	14.0+0.1s
+[12800/15600]	[L1: 0.4762]	11.3+0.1s
+[14400/15600]	[L1: 0.4746]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.306 (Best: 54.503 @epoch 231)
+Forward: 60.94s
+
+Saving...
+Total: 61.46s
+
+[Epoch 241]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4622]	11.4+0.7s
+[3200/15600]	[L1: 0.4695]	13.2+0.1s
+[4800/15600]	[L1: 0.4694]	10.9+0.1s
+[6400/15600]	[L1: 0.4709]	10.8+0.1s
+[8000/15600]	[L1: 0.4704]	13.5+0.1s
+[9600/15600]	[L1: 0.4701]	11.1+0.1s
+[11200/15600]	[L1: 0.4696]	10.9+0.1s
+[12800/15600]	[L1: 0.4711]	13.7+0.1s
+[14400/15600]	[L1: 0.4712]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.346 (Best: 54.503 @epoch 231)
+Forward: 66.15s
+
+Saving...
+Total: 66.65s
+
+[Epoch 242]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4716]	11.1+0.7s
+[3200/15600]	[L1: 0.4762]	11.3+0.1s
+[4800/15600]	[L1: 0.4736]	13.8+0.1s
+[6400/15600]	[L1: 0.4733]	11.1+0.1s
+[8000/15600]	[L1: 0.4737]	10.9+0.1s
+[9600/15600]	[L1: 0.4728]	12.1+0.1s
+[11200/15600]	[L1: 0.4715]	12.7+0.1s
+[12800/15600]	[L1: 0.4743]	10.8+0.1s
+[14400/15600]	[L1: 0.4756]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.737 (Best: 54.503 @epoch 231)
+Forward: 62.66s
+
+Saving...
+Total: 63.15s
+
+[Epoch 243]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4668]	13.1+0.7s
+[3200/15600]	[L1: 0.4714]	11.8+0.1s
+[4800/15600]	[L1: 0.4691]	10.8+0.1s
+[6400/15600]	[L1: 0.4690]	11.2+0.1s
+[8000/15600]	[L1: 0.4672]	13.8+0.1s
+[9600/15600]	[L1: 0.4700]	10.9+0.1s
+[11200/15600]	[L1: 0.4710]	11.0+0.1s
+[12800/15600]	[L1: 0.4715]	13.6+0.1s
+[14400/15600]	[L1: 0.4722]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.465 (Best: 54.503 @epoch 231)
+Forward: 65.66s
+
+Saving...
+Total: 66.16s
+
+[Epoch 244]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4699]	11.4+0.7s
+[3200/15600]	[L1: 0.4839]	11.0+0.1s
+[4800/15600]	[L1: 0.4837]	13.2+0.1s
+[6400/15600]	[L1: 0.4804]	10.9+0.1s
+[8000/15600]	[L1: 0.4771]	10.6+0.1s
+[9600/15600]	[L1: 0.4763]	12.1+0.1s
+[11200/15600]	[L1: 0.4771]	12.6+0.1s
+[12800/15600]	[L1: 0.4761]	11.1+0.1s
+[14400/15600]	[L1: 0.4772]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.119 (Best: 54.503 @epoch 231)
+Forward: 64.56s
+
+Saving...
+Total: 65.05s
+
+[Epoch 245]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4665]	14.0+0.8s
+[3200/15600]	[L1: 0.4715]	10.9+0.1s
+[4800/15600]	[L1: 0.4688]	11.0+0.1s
+[6400/15600]	[L1: 0.4726]	12.5+0.1s
+[8000/15600]	[L1: 0.4728]	12.3+0.1s
+[9600/15600]	[L1: 0.4725]	11.1+0.1s
+[11200/15600]	[L1: 0.4740]	11.0+0.1s
+[12800/15600]	[L1: 0.4729]	13.8+0.1s
+[14400/15600]	[L1: 0.4738]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.244 (Best: 54.503 @epoch 231)
+Forward: 65.98s
+
+Saving...
+Total: 66.49s
+
+[Epoch 246]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4775]	11.0+0.7s
+[3200/15600]	[L1: 0.4759]	11.1+0.1s
+[4800/15600]	[L1: 0.4774]	13.6+0.1s
+[6400/15600]	[L1: 0.4804]	11.2+0.1s
+[8000/15600]	[L1: 0.4797]	11.2+0.1s
+[9600/15600]	[L1: 0.4790]	13.6+0.1s
+[11200/15600]	[L1: 0.4780]	11.2+0.1s
+[12800/15600]	[L1: 0.4786]	11.2+0.1s
+[14400/15600]	[L1: 0.4790]	13.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.200 (Best: 54.503 @epoch 231)
+Forward: 62.03s
+
+Saving...
+Total: 62.55s
+
+[Epoch 247]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4720]	13.8+0.7s
+[3200/15600]	[L1: 0.4709]	11.2+0.1s
+[4800/15600]	[L1: 0.4731]	10.9+0.1s
+[6400/15600]	[L1: 0.4699]	13.6+0.1s
+[8000/15600]	[L1: 0.4719]	11.0+0.1s
+[9600/15600]	[L1: 0.4695]	11.0+0.1s
+[11200/15600]	[L1: 0.4695]	11.5+0.1s
+[12800/15600]	[L1: 0.4709]	13.1+0.1s
+[14400/15600]	[L1: 0.4713]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.856 (Best: 54.503 @epoch 231)
+Forward: 65.64s
+
+Saving...
+Total: 66.16s
+
+[Epoch 248]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4758]	11.5+0.7s
+[3200/15600]	[L1: 0.4746]	11.1+0.1s
+[4800/15600]	[L1: 0.4731]	13.7+0.1s
+[6400/15600]	[L1: 0.4763]	11.0+0.1s
+[8000/15600]	[L1: 0.4745]	11.0+0.1s
+[9600/15600]	[L1: 0.4736]	13.4+0.1s
+[11200/15600]	[L1: 0.4725]	10.9+0.1s
+[12800/15600]	[L1: 0.4717]	10.9+0.1s
+[14400/15600]	[L1: 0.4722]	13.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.805 (Best: 54.503 @epoch 231)
+Forward: 61.13s
+
+Saving...
+Total: 61.80s
+
+[Epoch 249]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4841]	13.6+0.7s
+[3200/15600]	[L1: 0.4796]	10.8+0.1s
+[4800/15600]	[L1: 0.4765]	10.8+0.1s
+[6400/15600]	[L1: 0.4728]	13.4+0.1s
+[8000/15600]	[L1: 0.4744]	11.0+0.1s
+[9600/15600]	[L1: 0.4709]	10.3+0.1s
+[11200/15600]	[L1: 0.4702]	10.5+0.1s
+[12800/15600]	[L1: 0.4712]	12.5+0.1s
+[14400/15600]	[L1: 0.4711]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.273 (Best: 54.503 @epoch 231)
+Forward: 65.42s
+
+Saving...
+Total: 65.91s
+
+[Epoch 250]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4697]	11.2+0.7s
+[3200/15600]	[L1: 0.4695]	10.8+0.1s
+[4800/15600]	[L1: 0.4720]	13.0+0.1s
+[6400/15600]	[L1: 0.4713]	10.5+0.1s
+[8000/15600]	[L1: 0.4730]	11.0+0.1s
+[9600/15600]	[L1: 0.4736]	10.3+0.1s
+[11200/15600]	[L1: 0.4746]	13.1+0.1s
+[12800/15600]	[L1: 0.4744]	10.9+0.1s
+[14400/15600]	[L1: 0.4758]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.439 (Best: 54.503 @epoch 231)
+Forward: 62.90s
+
+Saving...
+Total: 63.39s
+
+[Epoch 251]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4738]	11.4+0.7s
+[3200/15600]	[L1: 0.4742]	13.4+0.1s
+[4800/15600]	[L1: 0.4706]	10.9+0.1s
+[6400/15600]	[L1: 0.4682]	11.1+0.1s
+[8000/15600]	[L1: 0.4696]	13.3+0.1s
+[9600/15600]	[L1: 0.4705]	11.2+0.1s
+[11200/15600]	[L1: 0.4710]	11.0+0.1s
+[12800/15600]	[L1: 0.4734]	13.4+0.1s
+[14400/15600]	[L1: 0.4726]	9.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.265 (Best: 54.503 @epoch 231)
+Forward: 63.88s
+
+Saving...
+Total: 64.55s
+
+[Epoch 252]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4843]	11.0+0.7s
+[3200/15600]	[L1: 0.4777]	10.7+0.1s
+[4800/15600]	[L1: 0.4787]	10.3+0.1s
+[6400/15600]	[L1: 0.4770]	12.0+0.1s
+[8000/15600]	[L1: 0.4749]	9.8+0.1s
+[9600/15600]	[L1: 0.4732]	10.4+0.1s
+[11200/15600]	[L1: 0.4756]	12.1+0.1s
+[12800/15600]	[L1: 0.4742]	11.2+0.1s
+[14400/15600]	[L1: 0.4746]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.360 (Best: 54.503 @epoch 231)
+Forward: 65.48s
+
+Saving...
+Total: 66.01s
+
+[Epoch 253]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4641]	11.1+0.8s
+[3200/15600]	[L1: 0.4744]	10.0+0.1s
+[4800/15600]	[L1: 0.4759]	13.6+0.1s
+[6400/15600]	[L1: 0.4748]	11.1+0.1s
+[8000/15600]	[L1: 0.4748]	10.1+0.1s
+[9600/15600]	[L1: 0.4729]	13.7+0.1s
+[11200/15600]	[L1: 0.4734]	10.9+0.1s
+[12800/15600]	[L1: 0.4733]	10.2+0.1s
+[14400/15600]	[L1: 0.4735]	12.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.293 (Best: 54.503 @epoch 231)
+Forward: 62.62s
+
+Saving...
+Total: 63.14s
+
+[Epoch 254]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4675]	13.1+0.6s
+[3200/15600]	[L1: 0.4792]	10.1+0.1s
+[4800/15600]	[L1: 0.4806]	9.7+0.1s
+[6400/15600]	[L1: 0.4777]	10.5+0.1s
+[8000/15600]	[L1: 0.4770]	11.8+0.1s
+[9600/15600]	[L1: 0.4758]	10.6+0.1s
+[11200/15600]	[L1: 0.4736]	9.9+0.1s
+[12800/15600]	[L1: 0.4759]	12.7+0.1s
+[14400/15600]	[L1: 0.4768]	10.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.605 (Best: 54.605 @epoch 254)
+Forward: 62.70s
+
+Saving...
+Total: 63.23s
+
+[Epoch 255]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4809]	10.9+0.5s
+[3200/15600]	[L1: 0.4753]	11.2+0.1s
+[4800/15600]	[L1: 0.4731]	13.0+0.1s
+[6400/15600]	[L1: 0.4708]	11.0+0.1s
+[8000/15600]	[L1: 0.4696]	11.2+0.1s
+[9600/15600]	[L1: 0.4700]	13.0+0.1s
+[11200/15600]	[L1: 0.4717]	11.0+0.1s
+[12800/15600]	[L1: 0.4707]	11.1+0.1s
+[14400/15600]	[L1: 0.4710]	12.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.383 (Best: 54.605 @epoch 254)
+Forward: 63.80s
+
+Saving...
+Total: 64.30s
+
+[Epoch 256]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4748]	13.4+0.6s
+[3200/15600]	[L1: 0.4808]	11.0+0.1s
+[4800/15600]	[L1: 0.4773]	11.1+0.1s
+[6400/15600]	[L1: 0.4746]	13.0+0.1s
+[8000/15600]	[L1: 0.4740]	10.9+0.1s
+[9600/15600]	[L1: 0.4736]	11.1+0.1s
+[11200/15600]	[L1: 0.4742]	12.8+0.1s
+[12800/15600]	[L1: 0.4722]	10.9+0.1s
+[14400/15600]	[L1: 0.4719]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.182 (Best: 54.605 @epoch 254)
+Forward: 62.05s
+
+Saving...
+Total: 62.60s
+
+[Epoch 257]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4697]	10.5+0.6s
+[3200/15600]	[L1: 0.4712]	10.8+0.1s
+[4800/15600]	[L1: 0.4765]	9.0+0.1s
+[6400/15600]	[L1: 0.4735]	9.2+0.1s
+[8000/15600]	[L1: 0.4718]	9.1+0.1s
+[9600/15600]	[L1: 0.4751]	10.6+0.1s
+[11200/15600]	[L1: 0.4763]	9.2+0.1s
+[12800/15600]	[L1: 0.4755]	9.9+0.1s
+[14400/15600]	[L1: 0.4764]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.524 (Best: 54.605 @epoch 254)
+Forward: 64.05s
+
+Saving...
+Total: 64.61s
+
+[Epoch 258]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4765]	12.7+0.6s
+[3200/15600]	[L1: 0.4682]	10.9+0.1s
+[4800/15600]	[L1: 0.4696]	10.7+0.1s
+[6400/15600]	[L1: 0.4687]	13.1+0.1s
+[8000/15600]	[L1: 0.4699]	10.8+0.1s
+[9600/15600]	[L1: 0.4699]	10.5+0.1s
+[11200/15600]	[L1: 0.4697]	12.1+0.1s
+[12800/15600]	[L1: 0.4697]	11.7+0.1s
+[14400/15600]	[L1: 0.4708]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.362 (Best: 54.605 @epoch 254)
+Forward: 63.23s
+
+Saving...
+Total: 63.89s
+
+[Epoch 259]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4771]	11.3+0.6s
+[3200/15600]	[L1: 0.4733]	12.6+0.1s
+[4800/15600]	[L1: 0.4710]	11.0+0.1s
+[6400/15600]	[L1: 0.4723]	10.9+0.1s
+[8000/15600]	[L1: 0.4723]	11.5+0.1s
+[9600/15600]	[L1: 0.4718]	12.1+0.1s
+[11200/15600]	[L1: 0.4726]	10.9+0.1s
+[12800/15600]	[L1: 0.4711]	10.7+0.1s
+[14400/15600]	[L1: 0.4708]	12.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.263 (Best: 54.605 @epoch 254)
+Forward: 65.44s
+
+Saving...
+Total: 66.09s
+
+[Epoch 260]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4864]	11.2+0.6s
+[3200/15600]	[L1: 0.4834]	11.1+0.1s
+[4800/15600]	[L1: 0.4793]	11.4+0.1s
+[6400/15600]	[L1: 0.4768]	12.5+0.1s
+[8000/15600]	[L1: 0.4752]	11.1+0.1s
+[9600/15600]	[L1: 0.4746]	11.0+0.1s
+[11200/15600]	[L1: 0.4732]	13.1+0.1s
+[12800/15600]	[L1: 0.4734]	10.5+0.1s
+[14400/15600]	[L1: 0.4715]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.391 (Best: 54.605 @epoch 254)
+Forward: 61.56s
+
+Saving...
+Total: 62.06s
+
+[Epoch 261]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4838]	11.5+0.6s
+[3200/15600]	[L1: 0.4758]	12.3+0.1s
+[4800/15600]	[L1: 0.4728]	11.0+0.1s
+[6400/15600]	[L1: 0.4764]	11.1+0.1s
+[8000/15600]	[L1: 0.4759]	13.0+0.1s
+[9600/15600]	[L1: 0.4753]	11.1+0.1s
+[11200/15600]	[L1: 0.4769]	11.1+0.1s
+[12800/15600]	[L1: 0.4754]	12.3+0.1s
+[14400/15600]	[L1: 0.4747]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.432 (Best: 54.605 @epoch 254)
+Forward: 62.57s
+
+Saving...
+Total: 63.06s
+
+[Epoch 262]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4837]	11.2+0.6s
+[3200/15600]	[L1: 0.4791]	10.9+0.1s
+[4800/15600]	[L1: 0.4731]	12.7+0.1s
+[6400/15600]	[L1: 0.4720]	10.9+0.1s
+[8000/15600]	[L1: 0.4739]	10.9+0.1s
+[9600/15600]	[L1: 0.4723]	12.5+0.1s
+[11200/15600]	[L1: 0.4738]	10.7+0.1s
+[12800/15600]	[L1: 0.4729]	11.0+0.1s
+[14400/15600]	[L1: 0.4730]	11.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.479 (Best: 54.605 @epoch 254)
+Forward: 61.59s
+
+Saving...
+Total: 62.22s
+
+[Epoch 263]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4854]	12.5+0.6s
+[3200/15600]	[L1: 0.4873]	10.9+0.1s
+[4800/15600]	[L1: 0.4780]	10.4+0.1s
+[6400/15600]	[L1: 0.4776]	12.4+0.1s
+[8000/15600]	[L1: 0.4743]	10.8+0.1s
+[9600/15600]	[L1: 0.4764]	9.8+0.1s
+[11200/15600]	[L1: 0.4752]	10.9+0.1s
+[12800/15600]	[L1: 0.4744]	12.4+0.1s
+[14400/15600]	[L1: 0.4751]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.173 (Best: 54.605 @epoch 254)
+Forward: 63.36s
+
+Saving...
+Total: 63.86s
+
+[Epoch 264]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4689]	10.8+0.7s
+[3200/15600]	[L1: 0.4729]	9.8+0.1s
+[4800/15600]	[L1: 0.4715]	11.8+0.1s
+[6400/15600]	[L1: 0.4712]	10.1+0.1s
+[8000/15600]	[L1: 0.4745]	10.1+0.1s
+[9600/15600]	[L1: 0.4722]	12.1+0.1s
+[11200/15600]	[L1: 0.4713]	10.5+0.1s
+[12800/15600]	[L1: 0.4712]	10.2+0.1s
+[14400/15600]	[L1: 0.4716]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.244 (Best: 54.605 @epoch 254)
+Forward: 60.91s
+
+Saving...
+Total: 61.44s
+
+[Epoch 265]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4713]	12.7+0.6s
+[3200/15600]	[L1: 0.4633]	10.9+0.1s
+[4800/15600]	[L1: 0.4650]	10.9+0.1s
+[6400/15600]	[L1: 0.4652]	12.1+0.1s
+[8000/15600]	[L1: 0.4651]	11.8+0.1s
+[9600/15600]	[L1: 0.4644]	10.8+0.1s
+[11200/15600]	[L1: 0.4662]	11.1+0.1s
+[12800/15600]	[L1: 0.4682]	12.7+0.1s
+[14400/15600]	[L1: 0.4688]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.524 (Best: 54.605 @epoch 254)
+Forward: 65.00s
+
+Saving...
+Total: 65.64s
+
+[Epoch 266]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4781]	11.2+0.9s
+[3200/15600]	[L1: 0.4755]	11.1+0.1s
+[4800/15600]	[L1: 0.4741]	13.4+0.1s
+[6400/15600]	[L1: 0.4709]	11.1+0.1s
+[8000/15600]	[L1: 0.4716]	11.0+0.1s
+[9600/15600]	[L1: 0.4727]	13.5+0.1s
+[11200/15600]	[L1: 0.4716]	11.0+0.1s
+[12800/15600]	[L1: 0.4700]	11.1+0.1s
+[14400/15600]	[L1: 0.4718]	13.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.436 (Best: 54.605 @epoch 254)
+Forward: 63.15s
+
+Saving...
+Total: 63.64s
+
+[Epoch 267]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4648]	14.1+0.7s
+[3200/15600]	[L1: 0.4721]	11.3+0.1s
+[4800/15600]	[L1: 0.4702]	11.6+0.1s
+[6400/15600]	[L1: 0.4710]	13.9+0.1s
+[8000/15600]	[L1: 0.4711]	11.2+0.1s
+[9600/15600]	[L1: 0.4725]	11.2+0.1s
+[11200/15600]	[L1: 0.4745]	13.7+0.1s
+[12800/15600]	[L1: 0.4736]	11.0+0.1s
+[14400/15600]	[L1: 0.4740]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.997 (Best: 54.605 @epoch 254)
+Forward: 64.77s
+
+Saving...
+Total: 65.43s
+
+[Epoch 268]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4603]	10.9+0.7s
+[3200/15600]	[L1: 0.4636]	10.7+0.1s
+[4800/15600]	[L1: 0.4661]	13.3+0.1s
+[6400/15600]	[L1: 0.4631]	10.8+0.1s
+[8000/15600]	[L1: 0.4614]	11.0+0.1s
+[9600/15600]	[L1: 0.4620]	13.3+0.1s
+[11200/15600]	[L1: 0.4635]	10.8+0.1s
+[12800/15600]	[L1: 0.4652]	10.9+0.1s
+[14400/15600]	[L1: 0.4659]	13.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.375 (Best: 54.605 @epoch 254)
+Forward: 62.74s
+
+Saving...
+Total: 63.24s
+
+[Epoch 269]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4724]	13.3+0.7s
+[3200/15600]	[L1: 0.4736]	10.8+0.1s
+[4800/15600]	[L1: 0.4704]	10.2+0.1s
+[6400/15600]	[L1: 0.4726]	12.3+0.1s
+[8000/15600]	[L1: 0.4714]	10.4+0.1s
+[9600/15600]	[L1: 0.4712]	10.0+0.1s
+[11200/15600]	[L1: 0.4715]	10.1+0.1s
+[12800/15600]	[L1: 0.4730]	12.1+0.1s
+[14400/15600]	[L1: 0.4713]	9.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.294 (Best: 54.605 @epoch 254)
+Forward: 65.68s
+
+Saving...
+Total: 66.17s
+
+[Epoch 270]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4683]	10.3+0.7s
+[3200/15600]	[L1: 0.4667]	10.0+0.1s
+[4800/15600]	[L1: 0.4646]	10.4+0.1s
+[6400/15600]	[L1: 0.4637]	13.6+0.1s
+[8000/15600]	[L1: 0.4630]	11.0+0.1s
+[9600/15600]	[L1: 0.4633]	11.1+0.1s
+[11200/15600]	[L1: 0.4642]	13.7+0.1s
+[12800/15600]	[L1: 0.4649]	11.0+0.1s
+[14400/15600]	[L1: 0.4636]	11.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.530 (Best: 54.605 @epoch 254)
+Forward: 62.36s
+
+Saving...
+Total: 62.86s
+
+[Epoch 271]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4641]	11.2+0.7s
+[3200/15600]	[L1: 0.4701]	13.2+0.1s
+[4800/15600]	[L1: 0.4713]	10.9+0.1s
+[6400/15600]	[L1: 0.4712]	11.3+0.1s
+[8000/15600]	[L1: 0.4702]	13.5+0.1s
+[9600/15600]	[L1: 0.4714]	11.0+0.1s
+[11200/15600]	[L1: 0.4693]	11.0+0.1s
+[12800/15600]	[L1: 0.4687]	13.7+0.1s
+[14400/15600]	[L1: 0.4682]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.349 (Best: 54.605 @epoch 254)
+Forward: 64.29s
+
+Saving...
+Total: 64.91s
+
+[Epoch 272]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4821]	11.3+0.7s
+[3200/15600]	[L1: 0.4808]	10.2+0.1s
+[4800/15600]	[L1: 0.4717]	9.7+0.1s
+[6400/15600]	[L1: 0.4695]	12.7+0.1s
+[8000/15600]	[L1: 0.4703]	10.4+0.1s
+[9600/15600]	[L1: 0.4714]	11.3+0.1s
+[11200/15600]	[L1: 0.4717]	13.8+0.1s
+[12800/15600]	[L1: 0.4723]	11.1+0.1s
+[14400/15600]	[L1: 0.4726]	11.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.407 (Best: 54.605 @epoch 254)
+Forward: 62.72s
+
+Saving...
+Total: 63.21s
+
+[Epoch 273]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4601]	11.3+0.7s
+[3200/15600]	[L1: 0.4604]	13.5+0.1s
+[4800/15600]	[L1: 0.4664]	11.0+0.1s
+[6400/15600]	[L1: 0.4666]	11.1+0.1s
+[8000/15600]	[L1: 0.4683]	13.4+0.1s
+[9600/15600]	[L1: 0.4698]	10.5+0.1s
+[11200/15600]	[L1: 0.4695]	11.0+0.1s
+[12800/15600]	[L1: 0.4712]	11.1+0.1s
+[14400/15600]	[L1: 0.4714]	13.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.334 (Best: 54.605 @epoch 254)
+Forward: 64.21s
+
+Saving...
+Total: 65.12s
+
+[Epoch 274]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4683]	11.4+1.0s
+[3200/15600]	[L1: 0.4710]	11.4+0.1s
+[4800/15600]	[L1: 0.4714]	11.4+0.1s
+[6400/15600]	[L1: 0.4692]	13.6+0.1s
+[8000/15600]	[L1: 0.4706]	10.9+0.1s
+[9600/15600]	[L1: 0.4690]	11.0+0.1s
+[11200/15600]	[L1: 0.4699]	13.5+0.1s
+[12800/15600]	[L1: 0.4680]	10.9+0.1s
+[14400/15600]	[L1: 0.4677]	11.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.392 (Best: 54.605 @epoch 254)
+Forward: 63.10s
+
+Saving...
+Total: 63.59s
+
+[Epoch 275]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4765]	11.2+0.7s
+[3200/15600]	[L1: 0.4742]	13.3+0.1s
+[4800/15600]	[L1: 0.4734]	10.8+0.1s
+[6400/15600]	[L1: 0.4717]	11.0+0.1s
+[8000/15600]	[L1: 0.4699]	13.4+0.1s
+[9600/15600]	[L1: 0.4692]	11.0+0.1s
+[11200/15600]	[L1: 0.4692]	10.9+0.1s
+[12800/15600]	[L1: 0.4685]	13.5+0.1s
+[14400/15600]	[L1: 0.4705]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.386 (Best: 54.605 @epoch 254)
+Forward: 62.09s
+
+Saving...
+Total: 63.07s
+
+[Epoch 276]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4636]	11.3+0.9s
+[3200/15600]	[L1: 0.4627]	10.9+0.1s
+[4800/15600]	[L1: 0.4656]	11.9+0.1s
+[6400/15600]	[L1: 0.4661]	12.4+0.1s
+[8000/15600]	[L1: 0.4683]	11.1+0.1s
+[9600/15600]	[L1: 0.4682]	11.0+0.1s
+[11200/15600]	[L1: 0.4679]	13.6+0.1s
+[12800/15600]	[L1: 0.4677]	10.9+0.1s
+[14400/15600]	[L1: 0.4681]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.516 (Best: 54.605 @epoch 254)
+Forward: 62.61s
+
+Saving...
+Total: 63.12s
+
+[Epoch 277]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4608]	11.5+0.6s
+[3200/15600]	[L1: 0.4625]	12.7+0.1s
+[4800/15600]	[L1: 0.4619]	10.7+0.1s
+[6400/15600]	[L1: 0.4626]	11.2+0.1s
+[8000/15600]	[L1: 0.4623]	12.8+0.1s
+[9600/15600]	[L1: 0.4635]	11.1+0.1s
+[11200/15600]	[L1: 0.4648]	10.8+0.1s
+[12800/15600]	[L1: 0.4642]	12.8+0.1s
+[14400/15600]	[L1: 0.4636]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.660 (Best: 54.660 @epoch 277)
+Forward: 63.37s
+
+Saving...
+Total: 63.92s
+
+[Epoch 278]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4665]	11.3+0.6s
+[3200/15600]	[L1: 0.4687]	11.0+0.1s
+[4800/15600]	[L1: 0.4692]	12.9+0.1s
+[6400/15600]	[L1: 0.4704]	10.8+0.1s
+[8000/15600]	[L1: 0.4694]	10.9+0.1s
+[9600/15600]	[L1: 0.4692]	12.9+0.1s
+[11200/15600]	[L1: 0.4682]	10.9+0.1s
+[12800/15600]	[L1: 0.4680]	11.1+0.1s
+[14400/15600]	[L1: 0.4671]	11.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.521 (Best: 54.660 @epoch 277)
+Forward: 62.14s
+
+Saving...
+Total: 62.64s
+
+[Epoch 279]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4720]	13.7+0.8s
+[3200/15600]	[L1: 0.4717]	10.9+0.1s
+[4800/15600]	[L1: 0.4724]	11.1+0.1s
+[6400/15600]	[L1: 0.4759]	13.7+0.1s
+[8000/15600]	[L1: 0.4746]	11.0+0.1s
+[9600/15600]	[L1: 0.4739]	11.0+0.1s
+[11200/15600]	[L1: 0.4734]	11.0+0.1s
+[12800/15600]	[L1: 0.4731]	13.5+0.1s
+[14400/15600]	[L1: 0.4734]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.253 (Best: 54.660 @epoch 277)
+Forward: 62.96s
+
+Saving...
+Total: 63.61s
+
+[Epoch 280]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4796]	10.7+0.6s
+[3200/15600]	[L1: 0.4755]	10.9+0.1s
+[4800/15600]	[L1: 0.4765]	13.6+0.1s
+[6400/15600]	[L1: 0.4721]	10.7+0.1s
+[8000/15600]	[L1: 0.4716]	10.2+0.1s
+[9600/15600]	[L1: 0.4712]	11.5+0.1s
+[11200/15600]	[L1: 0.4718]	9.8+0.1s
+[12800/15600]	[L1: 0.4703]	9.6+0.1s
+[14400/15600]	[L1: 0.4699]	9.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.485 (Best: 54.660 @epoch 277)
+Forward: 63.05s
+
+Saving...
+Total: 63.55s
+
+[Epoch 281]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4638]	11.6+0.8s
+[3200/15600]	[L1: 0.4640]	13.3+0.1s
+[4800/15600]	[L1: 0.4683]	10.9+0.1s
+[6400/15600]	[L1: 0.4708]	10.9+0.1s
+[8000/15600]	[L1: 0.4746]	13.1+0.1s
+[9600/15600]	[L1: 0.4738]	10.7+0.1s
+[11200/15600]	[L1: 0.4731]	10.6+0.1s
+[12800/15600]	[L1: 0.4714]	13.5+0.1s
+[14400/15600]	[L1: 0.4707]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.420 (Best: 54.660 @epoch 277)
+Forward: 65.27s
+
+Saving...
+Total: 65.75s
+
+[Epoch 282]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4553]	11.2+0.7s
+[3200/15600]	[L1: 0.4615]	11.1+0.1s
+[4800/15600]	[L1: 0.4619]	11.8+0.1s
+[6400/15600]	[L1: 0.4645]	12.9+0.1s
+[8000/15600]	[L1: 0.4656]	11.4+0.1s
+[9600/15600]	[L1: 0.4686]	11.3+0.1s
+[11200/15600]	[L1: 0.4685]	13.7+0.1s
+[12800/15600]	[L1: 0.4681]	10.9+0.1s
+[14400/15600]	[L1: 0.4699]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.505 (Best: 54.660 @epoch 277)
+Forward: 63.68s
+
+Saving...
+Total: 64.18s
+
+[Epoch 283]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4677]	10.6+0.7s
+[3200/15600]	[L1: 0.4691]	13.1+0.1s
+[4800/15600]	[L1: 0.4674]	10.0+0.1s
+[6400/15600]	[L1: 0.4671]	10.1+0.1s
+[8000/15600]	[L1: 0.4649]	12.8+0.1s
+[9600/15600]	[L1: 0.4644]	10.8+0.1s
+[11200/15600]	[L1: 0.4648]	11.1+0.1s
+[12800/15600]	[L1: 0.4649]	12.1+0.1s
+[14400/15600]	[L1: 0.4652]	12.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.410 (Best: 54.660 @epoch 277)
+Forward: 63.92s
+
+Saving...
+Total: 64.85s
+
+[Epoch 284]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4615]	10.6+0.9s
+[3200/15600]	[L1: 0.4666]	9.8+0.1s
+[4800/15600]	[L1: 0.4651]	9.7+0.1s
+[6400/15600]	[L1: 0.4685]	12.1+0.1s
+[8000/15600]	[L1: 0.4672]	11.0+0.1s
+[9600/15600]	[L1: 0.4670]	11.0+0.1s
+[11200/15600]	[L1: 0.4660]	13.4+0.1s
+[12800/15600]	[L1: 0.4667]	11.2+0.1s
+[14400/15600]	[L1: 0.4662]	11.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.071 (Best: 54.660 @epoch 277)
+Forward: 64.89s
+
+Saving...
+Total: 65.41s
+
+[Epoch 285]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4713]	10.4+0.6s
+[3200/15600]	[L1: 0.4644]	9.8+0.1s
+[4800/15600]	[L1: 0.4602]	11.5+0.1s
+[6400/15600]	[L1: 0.4637]	9.3+0.1s
+[8000/15600]	[L1: 0.4667]	9.1+0.1s
+[9600/15600]	[L1: 0.4668]	9.4+0.1s
+[11200/15600]	[L1: 0.4654]	12.3+0.1s
+[12800/15600]	[L1: 0.4656]	9.9+0.1s
+[14400/15600]	[L1: 0.4652]	9.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.395 (Best: 54.660 @epoch 277)
+Forward: 63.83s
+
+Saving...
+Total: 64.36s
+
+[Epoch 286]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4632]	9.8+0.6s
+[3200/15600]	[L1: 0.4661]	12.2+0.1s
+[4800/15600]	[L1: 0.4678]	10.2+0.1s
+[6400/15600]	[L1: 0.4697]	10.1+0.1s
+[8000/15600]	[L1: 0.4686]	9.5+0.1s
+[9600/15600]	[L1: 0.4683]	12.2+0.1s
+[11200/15600]	[L1: 0.4685]	9.5+0.1s
+[12800/15600]	[L1: 0.4677]	10.2+0.1s
+[14400/15600]	[L1: 0.4682]	10.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.175 (Best: 54.660 @epoch 277)
+Forward: 64.85s
+
+Saving...
+Total: 65.36s
+
+[Epoch 287]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4703]	12.7+0.6s
+[3200/15600]	[L1: 0.4652]	10.0+0.1s
+[4800/15600]	[L1: 0.4647]	9.4+0.1s
+[6400/15600]	[L1: 0.4626]	9.3+0.1s
+[8000/15600]	[L1: 0.4629]	11.7+0.1s
+[9600/15600]	[L1: 0.4640]	10.3+0.1s
+[11200/15600]	[L1: 0.4642]	9.1+0.1s
+[12800/15600]	[L1: 0.4645]	10.8+0.1s
+[14400/15600]	[L1: 0.4660]	12.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.312 (Best: 54.660 @epoch 277)
+Forward: 66.29s
+
+Saving...
+Total: 66.99s
+
+[Epoch 288]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4739]	11.3+0.7s
+[3200/15600]	[L1: 0.4658]	10.8+0.1s
+[4800/15600]	[L1: 0.4691]	12.4+0.1s
+[6400/15600]	[L1: 0.4676]	12.1+0.1s
+[8000/15600]	[L1: 0.4633]	11.0+0.1s
+[9600/15600]	[L1: 0.4636]	11.0+0.1s
+[11200/15600]	[L1: 0.4648]	13.7+0.1s
+[12800/15600]	[L1: 0.4657]	11.0+0.1s
+[14400/15600]	[L1: 0.4643]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.637 (Best: 54.660 @epoch 277)
+Forward: 61.12s
+
+Saving...
+Total: 61.68s
+
+[Epoch 289]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4524]	11.2+0.6s
+[3200/15600]	[L1: 0.4626]	11.7+0.1s
+[4800/15600]	[L1: 0.4683]	9.6+0.1s
+[6400/15600]	[L1: 0.4653]	10.9+0.1s
+[8000/15600]	[L1: 0.4641]	12.6+0.1s
+[9600/15600]	[L1: 0.4645]	9.8+0.1s
+[11200/15600]	[L1: 0.4649]	9.1+0.1s
+[12800/15600]	[L1: 0.4647]	10.1+0.1s
+[14400/15600]	[L1: 0.4650]	13.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.332 (Best: 54.660 @epoch 277)
+Forward: 66.20s
+
+Saving...
+Total: 67.03s
+
+[Epoch 290]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4606]	10.7+1.1s
+[3200/15600]	[L1: 0.4635]	10.9+0.1s
+[4800/15600]	[L1: 0.4675]	10.8+0.1s
+[6400/15600]	[L1: 0.4654]	13.3+0.1s
+[8000/15600]	[L1: 0.4652]	10.9+0.1s
+[9600/15600]	[L1: 0.4636]	11.1+0.1s
+[11200/15600]	[L1: 0.4657]	12.5+0.1s
+[12800/15600]	[L1: 0.4656]	10.7+0.1s
+[14400/15600]	[L1: 0.4649]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.210 (Best: 54.660 @epoch 277)
+Forward: 63.89s
+
+Saving...
+Total: 64.46s
+
+[Epoch 291]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4637]	11.1+0.7s
+[3200/15600]	[L1: 0.4657]	13.6+0.1s
+[4800/15600]	[L1: 0.4647]	11.0+0.1s
+[6400/15600]	[L1: 0.4631]	11.0+0.1s
+[8000/15600]	[L1: 0.4654]	11.5+0.1s
+[9600/15600]	[L1: 0.4646]	13.1+0.1s
+[11200/15600]	[L1: 0.4625]	11.0+0.1s
+[12800/15600]	[L1: 0.4619]	11.1+0.1s
+[14400/15600]	[L1: 0.4630]	13.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.274 (Best: 54.660 @epoch 277)
+Forward: 63.51s
+
+Saving...
+Total: 64.56s
+
+[Epoch 292]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4494]	11.2+1.0s
+[3200/15600]	[L1: 0.4560]	11.0+0.1s
+[4800/15600]	[L1: 0.4610]	11.3+0.1s
+[6400/15600]	[L1: 0.4613]	13.0+0.1s
+[8000/15600]	[L1: 0.4617]	11.0+0.1s
+[9600/15600]	[L1: 0.4645]	11.0+0.1s
+[11200/15600]	[L1: 0.4652]	13.6+0.1s
+[12800/15600]	[L1: 0.4660]	10.9+0.1s
+[14400/15600]	[L1: 0.4642]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.354 (Best: 54.660 @epoch 277)
+Forward: 64.38s
+
+Saving...
+Total: 64.88s
+
+[Epoch 293]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4659]	11.3+0.7s
+[3200/15600]	[L1: 0.4707]	13.1+0.1s
+[4800/15600]	[L1: 0.4694]	10.1+0.1s
+[6400/15600]	[L1: 0.4672]	10.8+0.1s
+[8000/15600]	[L1: 0.4694]	13.1+0.1s
+[9600/15600]	[L1: 0.4689]	10.2+0.1s
+[11200/15600]	[L1: 0.4685]	10.9+0.1s
+[12800/15600]	[L1: 0.4690]	10.7+0.1s
+[14400/15600]	[L1: 0.4690]	13.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.633 (Best: 54.660 @epoch 277)
+Forward: 64.10s
+
+Saving...
+Total: 64.64s
+
+[Epoch 294]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4716]	11.5+0.6s
+[3200/15600]	[L1: 0.4742]	10.1+0.1s
+[4800/15600]	[L1: 0.4699]	11.3+0.1s
+[6400/15600]	[L1: 0.4697]	13.0+0.1s
+[8000/15600]	[L1: 0.4673]	10.5+0.1s
+[9600/15600]	[L1: 0.4666]	10.9+0.1s
+[11200/15600]	[L1: 0.4666]	12.2+0.1s
+[12800/15600]	[L1: 0.4663]	10.2+0.1s
+[14400/15600]	[L1: 0.4656]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.546 (Best: 54.660 @epoch 277)
+Forward: 62.27s
+
+Saving...
+Total: 62.79s
+
+[Epoch 295]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4641]	12.0+0.6s
+[3200/15600]	[L1: 0.4636]	10.9+0.1s
+[4800/15600]	[L1: 0.4606]	10.9+0.1s
+[6400/15600]	[L1: 0.4606]	11.0+0.1s
+[8000/15600]	[L1: 0.4601]	12.4+0.1s
+[9600/15600]	[L1: 0.4609]	11.0+0.1s
+[11200/15600]	[L1: 0.4624]	10.9+0.1s
+[12800/15600]	[L1: 0.4621]	12.9+0.1s
+[14400/15600]	[L1: 0.4626]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.401 (Best: 54.660 @epoch 277)
+Forward: 62.56s
+
+Saving...
+Total: 63.06s
+
+[Epoch 296]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4741]	10.9+0.6s
+[3200/15600]	[L1: 0.4758]	11.0+0.1s
+[4800/15600]	[L1: 0.4707]	12.2+0.1s
+[6400/15600]	[L1: 0.4682]	10.8+0.1s
+[8000/15600]	[L1: 0.4676]	10.9+0.1s
+[9600/15600]	[L1: 0.4664]	12.5+0.1s
+[11200/15600]	[L1: 0.4660]	10.9+0.1s
+[12800/15600]	[L1: 0.4675]	10.8+0.1s
+[14400/15600]	[L1: 0.4670]	13.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.416 (Best: 54.660 @epoch 277)
+Forward: 62.65s
+
+Saving...
+Total: 63.16s
+
+[Epoch 297]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4646]	13.6+0.9s
+[3200/15600]	[L1: 0.4649]	11.2+0.1s
+[4800/15600]	[L1: 0.4605]	10.8+0.1s
+[6400/15600]	[L1: 0.4611]	13.6+0.1s
+[8000/15600]	[L1: 0.4618]	10.9+0.1s
+[9600/15600]	[L1: 0.4622]	11.0+0.1s
+[11200/15600]	[L1: 0.4630]	13.5+0.1s
+[12800/15600]	[L1: 0.4643]	11.1+0.1s
+[14400/15600]	[L1: 0.4636]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.417 (Best: 54.660 @epoch 277)
+Forward: 61.58s
+
+Saving...
+Total: 62.08s
+
+[Epoch 298]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4591]	10.9+0.6s
+[3200/15600]	[L1: 0.4652]	12.4+0.1s
+[4800/15600]	[L1: 0.4647]	11.5+0.1s
+[6400/15600]	[L1: 0.4664]	10.5+0.1s
+[8000/15600]	[L1: 0.4667]	10.4+0.1s
+[9600/15600]	[L1: 0.4671]	12.6+0.1s
+[11200/15600]	[L1: 0.4655]	10.4+0.1s
+[12800/15600]	[L1: 0.4662]	10.4+0.1s
+[14400/15600]	[L1: 0.4655]	12.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.224 (Best: 54.660 @epoch 277)
+Forward: 64.01s
+
+Saving...
+Total: 64.51s
+
+[Epoch 299]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4672]	13.2+0.8s
+[3200/15600]	[L1: 0.4618]	11.1+0.1s
+[4800/15600]	[L1: 0.4568]	11.0+0.1s
+[6400/15600]	[L1: 0.4571]	13.5+0.1s
+[8000/15600]	[L1: 0.4592]	10.2+0.1s
+[9600/15600]	[L1: 0.4588]	11.1+0.1s
+[11200/15600]	[L1: 0.4608]	11.4+0.1s
+[12800/15600]	[L1: 0.4621]	13.3+0.1s
+[14400/15600]	[L1: 0.4648]	11.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.543 (Best: 54.660 @epoch 277)
+Forward: 64.72s
+
+Saving...
+Total: 65.38s
+
diff --git a/experiment/smgarn/loss.pt b/experiment/smgarn/loss.pt
new file mode 100644
index 0000000000000000000000000000000000000000..59f6a29a9635b3267d0ac413274009a99633732d
--- /dev/null
+++ b/experiment/smgarn/loss.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8fe8e68621fb412dbae5e7473a290f0fd3da4bc4bdc9eca595a8f09a7358ae7
+size 980
diff --git a/experiment/smgarn/loss_L1.pdf b/experiment/smgarn/loss_L1.pdf
new file mode 100644
index 0000000000000000000000000000000000000000..f8b8c539e93cd85a867f84ec249d87e1daed3c72
Binary files /dev/null and b/experiment/smgarn/loss_L1.pdf differ
diff --git a/experiment/smgarn/loss_log.pt b/experiment/smgarn/loss_log.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3414910fb9e3130d9a2cd12c2344e1f5de7fb119
--- /dev/null
+++ b/experiment/smgarn/loss_log.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4512aee0adbdf076eca9c481a1c59c849dfa2f8a2930057ca4386bccee500e36
+size 2337
diff --git a/experiment/smgarn/model/model_best.pt b/experiment/smgarn/model/model_best.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0ce792af563dcb24491147ee9f9f030e03d94271
--- /dev/null
+++ b/experiment/smgarn/model/model_best.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac8d67dd933093af434f2ee9ba804c3a99fd8030bb616584ae923d9a18acd426
+size 8580304
diff --git a/experiment/smgarn/model/model_latest.pt b/experiment/smgarn/model/model_latest.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0ea1fc77bb71e1563226e680555e5aa957570408
--- /dev/null
+++ b/experiment/smgarn/model/model_latest.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d951676c2fc36938e959d5d2dadd930bdc492be8250c22f7eff6b89e2e3b403f
+size 8580604
diff --git a/experiment/smgarn/optimizer.pt b/experiment/smgarn/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fe9e59a4c03adb8a5034e919c4002c575289a38f
--- /dev/null
+++ b/experiment/smgarn/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ec5afef8869df59652b80994da1671f4d9ac464a5d75abf7788d69ad7efdde3
+size 14534714
diff --git a/experiment/smgarn/psnr_log.pt b/experiment/smgarn/psnr_log.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8254f5ae9417baccbf9cd575b995cedf5a0f7add
--- /dev/null
+++ b/experiment/smgarn/psnr_log.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a25231581865769f2dd5cc96133d43066632a048c4d4edb3bffc1a358a1515d
+size 2337
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0059.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0059.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..28dc803c73d3273b2900a46b95c9eca9b1ad7ce5
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0059.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0060.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0060.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..41cc4b1f239dfe3ef869fd838f6932f975ef347c
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0060.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0061.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0061.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..65a515669f2077d18d4e31db3ecdbed49a6d9989
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0061.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0062.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0062.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..a6dcfd4d1245e4a3a2f847ad21cb4ac70d3ecc0c
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0062.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0063.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0063.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..ae290ad19de52be187797e3fec8d4c64181ff0f0
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0063.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0064.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0064.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..292289d49bf0448a6addaf6742d7b125123bcf72
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0064.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0065.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0065.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..67a5393d280c35e7b225b5da79ea3517703c9a14
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0065.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0066.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0066.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..7034062d72b83b50601352af1d93b33443fcc651
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0066.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0067.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0067.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..a9ff9f001fcc0d25ee4c48d0dc91cd4e27eea859
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0067.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0068.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0068.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..71641864e799baae90a8b4d50ee32e6372f74136
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0068.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0069.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0069.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..01bdc5df8c0a89a80edacf8052524f227ae005f1
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0069.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0070.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0070.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..2b3f31b5abc62fa263e5b187376ca5c41c2ffafc
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0070.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0071.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0071.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..c8d66c77c571209ad2a56dfc7514d345ea01380d
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0071.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0072.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0072.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..62d0e0d57239a30d0a15871066d21e93b6d770eb
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0072.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0073.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0073.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..24fdcc76a6beae1b3a694955028e9189ef97c6c1
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0073.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0074.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0074.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..4fd9364d64a0ed91e24ce4e3d5ac7692bf451d30
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0074.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0075.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0075.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..aee50d3de2c7ec2bd3f5d905fa412de9203975d1
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0075.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0076.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0076.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..50ebce61ea529f6e6b432a119f5782831d74310d
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0076.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0077.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0077.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..55d21cd3e4d156efe81c042e6235fc7e31b450d7
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0077.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0078.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0078.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..cc19b4608e39d262dd8efb8d487e9e6c4f895e13
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0078.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0079.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0079.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..9f2fa88237fea4a149eef145a52df3a2a34d8068
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0079.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0080.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0080.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..1840630173a2e60afdbcde9602c62733299805a5
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0080.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0081.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0081.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..bec684a5ec8a74458135e8039a9ffa9575737525
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0081.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0082.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0082.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..65880012a9750e524b8c29797cd3ce143de081bd
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0082.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0083.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0083.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..6fd0d0498494cf7f03fba429fe1baabdf0deeabf
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0083.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0084.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0084.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..d3a89e27c977d9cb43b74261019dc9f5d8f76c2a
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0084.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0085.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0085.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..850ca3ce9518d939f76957fe135feb78b28b0b99
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0085.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0086.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0086.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..bbdf206d722dbd68c5e8b2983a79c789ebba0e78
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0086.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0087.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0087.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..2b66a569847e31cfbbb89031c1fab7635a0d9120
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0087.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0088.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0088.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..62251cc8915aa24c19a2c492c9114d5a279cb18c
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0088.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0089.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0089.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..e830c50078347d003a44313f839d517f4393fec5
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0089.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0090.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0090.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..a6e5a485f711b297343cef2c2f951813c906b38f
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0090.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0091.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0091.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..79f19e5d161e6db20d9d410727a1eea669c26f59
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0091.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0092.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0092.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..30ef83e7fc547700a1fa428d79f14ec4c4818626
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0092.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0093.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0093.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..79fc63dd8fd9eb10b8c4c3a62e3587b13b0bce74
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0093.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0094.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0094.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..957ee8174bb61d288a3224007c459c4829750319
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0094.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0095.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0095.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..6760d9a06e1254786a650d0de51ec18f7d63d01a
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0095.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0096.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0096.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..e3ae8ecd986cfe5b939f41bc119ed47eda56cd67
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0096.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0097.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0097.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..33ab3641f62d3d1d3c8057dfb4f5552bea71c726
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0097.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0098.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0098.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..2a0e921d77989c73a282a8a329ad8efe8149d44d
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0098.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0099.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0099.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..ac1c48fab84ad9fb82a6e2c94f8ea6dd521a1bc9
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0099.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0100.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0100.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..18422d0e524e2ec9d38eb1d99e32e698fd562840
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0100.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0101.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0101.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..a83d6f5510b2b190b2d842665b9942a5d6481620
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0101.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0102.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0102.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..d494a7c1edd193820ab2363a9916d382b48f7566
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0102.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0103.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0103.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..56e9a7b46c4e848375b00b06e0815f3ac6b96a6e
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0103.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0104.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0104.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..23ca7c6547b808b3355d7720dda6fc39d8a0d364
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0104.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0105.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0105.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..83c8a61da107ea14a16b50c582e5016528545952
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0105.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0106.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0106.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..62470eec35457988b882033966bbd6fe90666784
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0106.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0107.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0107.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..fb064dd019e0264b5aa54412bde8afb0268dfe45
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0107.jpg differ
diff --git a/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0108.jpg b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0108.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..7f7da54f5df221c87bc543f2642f6cfb54b449f0
Binary files /dev/null and b/experiment/smgarn/results-DIV2K/4k_camry_3_frame_0108.jpg differ
diff --git a/experiment/smgarn/test_DIV2K.pdf b/experiment/smgarn/test_DIV2K.pdf
new file mode 100644
index 0000000000000000000000000000000000000000..449eb0a3610562f0160ac104eb7a21c9b1f38ff4
Binary files /dev/null and b/experiment/smgarn/test_DIV2K.pdf differ
diff --git a/experiment/smgarn_1/config.txt b/experiment/smgarn_1/config.txt
new file mode 100644
index 0000000000000000000000000000000000000000..028d0cc3abc7cda92712f2710d71935f6e98a5a0
--- /dev/null
+++ b/experiment/smgarn_1/config.txt
@@ -0,0 +1,868 @@
+2025-01-03-22:35:21
+
+debug: False
+template: .
+n_threads: 6
+cpu: False
+n_GPUs: 4
+seed: 1
+dir_data: /data/dataset_snow100k/
+dir_demo: ../test
+data_train: ['DIV2K']
+data_test: ['DIV2K']
+data_range: 1-50000/50001-50050
+ext: sep_reset
+scale: [1]
+patch_size: 64
+rgb_range: 255
+n_colors: 3
+chop: False
+no_augment: False
+model: SMGARN
+act: relu
+pre_train: 
+extend: .
+n_resblocks: 16
+n_feats: 64
+res_scale: 1
+shift_mean: True
+dilation: False
+precision: single
+G0: 64
+RDNkSize: 3
+RDNconfig: B
+n_resgroups: 10
+reduction: 16
+reset: False
+test_every: 1000
+epochs: 1000
+batch_size: 16
+split_batch: 1
+self_ensemble: False
+test_only: False
+gan_k: 1
+lr: 0.0001
+decay: 100
+gamma: 0.5
+optimizer: ADAM
+momentum: 0.9
+betas: (0.9, 0.999)
+epsilon: 1e-08
+weight_decay: 0
+gclip: 0
+loss: 1*L1
+skip_threshold: 100000000.0
+save: smgarn
+load: 
+resume: 0
+save_models: False
+print_every: 100
+save_results: True
+save_gt: False
+
+2025-01-03-22:35:46
+
+debug: False
+template: .
+n_threads: 6
+cpu: False
+n_GPUs: 4
+seed: 1
+dir_data: /data/dataset_snow100k/
+dir_demo: ../test
+data_train: ['DIV2K']
+data_test: ['DIV2K']
+data_range: 1-50000/50001-50050
+ext: sep_reset
+scale: [1]
+patch_size: 64
+rgb_range: 255
+n_colors: 3
+chop: False
+no_augment: False
+model: SMGARN
+act: relu
+pre_train: 
+extend: .
+n_resblocks: 16
+n_feats: 64
+res_scale: 1
+shift_mean: True
+dilation: False
+precision: single
+G0: 64
+RDNkSize: 3
+RDNconfig: B
+n_resgroups: 10
+reduction: 16
+reset: False
+test_every: 1000
+epochs: 1000
+batch_size: 16
+split_batch: 1
+self_ensemble: False
+test_only: False
+gan_k: 1
+lr: 0.0001
+decay: 100
+gamma: 0.5
+optimizer: ADAM
+momentum: 0.9
+betas: (0.9, 0.999)
+epsilon: 1e-08
+weight_decay: 0
+gclip: 0
+loss: 1*L1
+skip_threshold: 100000000.0
+save: smgarn
+load: 
+resume: 0
+save_models: False
+print_every: 100
+save_results: True
+save_gt: False
+
+2025-01-03-22:37:45
+
+debug: False
+template: .
+n_threads: 6
+cpu: False
+n_GPUs: 4
+seed: 1
+dir_data: ../dataset
+dir_demo: ../test
+data_train: ['DIV2K']
+data_test: ['DIV2K']
+data_range: 1-50000/50001-50050
+ext: sep_reset
+scale: [1]
+patch_size: 64
+rgb_range: 255
+n_colors: 3
+chop: False
+no_augment: False
+model: SMGARN
+act: relu
+pre_train: 
+extend: .
+n_resblocks: 16
+n_feats: 64
+res_scale: 1
+shift_mean: True
+dilation: False
+precision: single
+G0: 64
+RDNkSize: 3
+RDNconfig: B
+n_resgroups: 10
+reduction: 16
+reset: False
+test_every: 1000
+epochs: 1000
+batch_size: 16
+split_batch: 1
+self_ensemble: False
+test_only: False
+gan_k: 1
+lr: 0.0001
+decay: 100
+gamma: 0.5
+optimizer: ADAM
+momentum: 0.9
+betas: (0.9, 0.999)
+epsilon: 1e-08
+weight_decay: 0
+gclip: 0
+loss: 1*L1
+skip_threshold: 100000000.0
+save: smgarn
+load: 
+resume: 0
+save_models: False
+print_every: 100
+save_results: True
+save_gt: False
+
+2025-01-03-22:39:55
+
+debug: False
+template: .
+n_threads: 6
+cpu: False
+n_GPUs: 4
+seed: 1
+dir_data: ../dataset
+dir_demo: ../test
+data_train: ['DIV2K']
+data_test: ['DIV2K']
+data_range: 1-50000/50001-50050
+ext: sep_reset
+scale: [1]
+patch_size: 64
+rgb_range: 255
+n_colors: 3
+chop: False
+no_augment: False
+model: SMGARN
+act: relu
+pre_train: 
+extend: .
+n_resblocks: 16
+n_feats: 64
+res_scale: 1
+shift_mean: True
+dilation: False
+precision: single
+G0: 64
+RDNkSize: 3
+RDNconfig: B
+n_resgroups: 10
+reduction: 16
+reset: False
+test_every: 1000
+epochs: 1000
+batch_size: 16
+split_batch: 1
+self_ensemble: False
+test_only: False
+gan_k: 1
+lr: 0.0001
+decay: 100
+gamma: 0.5
+optimizer: ADAM
+momentum: 0.9
+betas: (0.9, 0.999)
+epsilon: 1e-08
+weight_decay: 0
+gclip: 0
+loss: 1*L1
+skip_threshold: 100000000.0
+save: smgarn
+load: 
+resume: 0
+save_models: False
+print_every: 100
+save_results: True
+save_gt: False
+
+2025-01-03-22:40:18
+
+debug: False
+template: .
+n_threads: 6
+cpu: False
+n_GPUs: 4
+seed: 1
+dir_data: ../dataset
+dir_demo: ../test
+data_train: ['DIV2K']
+data_test: ['DIV2K']
+data_range: 1-50000/50001-50050
+ext: sep_reset
+scale: [1]
+patch_size: 64
+rgb_range: 255
+n_colors: 3
+chop: False
+no_augment: False
+model: SMGARN
+act: relu
+pre_train: 
+extend: .
+n_resblocks: 16
+n_feats: 64
+res_scale: 1
+shift_mean: True
+dilation: False
+precision: single
+G0: 64
+RDNkSize: 3
+RDNconfig: B
+n_resgroups: 10
+reduction: 16
+reset: False
+test_every: 1000
+epochs: 1000
+batch_size: 16
+split_batch: 1
+self_ensemble: False
+test_only: False
+gan_k: 1
+lr: 0.0001
+decay: 100
+gamma: 0.5
+optimizer: ADAM
+momentum: 0.9
+betas: (0.9, 0.999)
+epsilon: 1e-08
+weight_decay: 0
+gclip: 0
+loss: 1*L1
+skip_threshold: 100000000.0
+save: smgarn
+load: 
+resume: 0
+save_models: False
+print_every: 100
+save_results: True
+save_gt: False
+
+2025-01-04-08:02:40
+
+debug: False
+template: .
+n_threads: 6
+cpu: False
+n_GPUs: 4
+seed: 1
+dir_data: ../dataset
+dir_demo: ../test
+data_train: ['DIV2K']
+data_test: ['DIV2K']
+data_range: 1-50000/50001-50050
+ext: sep_reset
+scale: [1]
+patch_size: 64
+rgb_range: 255
+n_colors: 3
+chop: False
+no_augment: False
+model: EWT
+act: relu
+pre_train: 
+extend: .
+n_resblocks: 16
+n_feats: 64
+res_scale: 1
+shift_mean: True
+dilation: False
+precision: single
+G0: 64
+RDNkSize: 3
+RDNconfig: B
+n_resgroups: 10
+reduction: 16
+reset: False
+test_every: 1000
+epochs: 1000
+batch_size: 16
+split_batch: 1
+self_ensemble: False
+test_only: False
+gan_k: 1
+lr: 0.0001
+decay: 100
+gamma: 0.5
+optimizer: ADAM
+momentum: 0.9
+betas: (0.9, 0.999)
+epsilon: 1e-08
+weight_decay: 0
+gclip: 0
+loss: 1*L1
+skip_threshold: 100000000.0
+save: smgarn
+load: 
+resume: 0
+save_models: False
+print_every: 100
+save_results: True
+save_gt: False
+
+2025-01-04-08:20:40
+
+debug: False
+template: .
+n_threads: 6
+cpu: False
+n_GPUs: 4
+seed: 1
+dir_data: ../dataset
+dir_demo: ../test
+data_train: ['DIV2K']
+data_test: ['DIV2K']
+data_range: 1-50000/50001-50050
+ext: sep_reset
+scale: [1]
+patch_size: 64
+rgb_range: 255
+n_colors: 3
+chop: False
+no_augment: False
+model: EWT
+act: relu
+pre_train: 
+extend: .
+n_resblocks: 16
+n_feats: 64
+res_scale: 1
+shift_mean: True
+dilation: False
+precision: single
+G0: 64
+RDNkSize: 3
+RDNconfig: B
+n_resgroups: 10
+reduction: 16
+reset: False
+test_every: 1000
+epochs: 1000
+batch_size: 16
+split_batch: 1
+self_ensemble: False
+test_only: False
+gan_k: 1
+lr: 0.0001
+decay: 100
+gamma: 0.5
+optimizer: ADAM
+momentum: 0.9
+betas: (0.9, 0.999)
+epsilon: 1e-08
+weight_decay: 0
+gclip: 0
+loss: 1*L1
+skip_threshold: 100000000.0
+save: smgarn
+load: 
+resume: 0
+save_models: False
+print_every: 100
+save_results: True
+save_gt: False
+
+2025-01-04-08:27:03
+
+debug: False
+template: .
+n_threads: 6
+cpu: False
+n_GPUs: 4
+seed: 1
+dir_data: ../dataset
+dir_demo: ../test
+data_train: ['DIV2K']
+data_test: ['DIV2K']
+data_range: 1-50000/50001-50050
+ext: sep_reset
+scale: [1]
+patch_size: 64
+rgb_range: 255
+n_colors: 3
+chop: False
+no_augment: False
+model: EWT
+act: relu
+pre_train: 
+extend: .
+n_resblocks: 16
+n_feats: 64
+res_scale: 1
+shift_mean: True
+dilation: False
+precision: single
+G0: 64
+RDNkSize: 3
+RDNconfig: B
+n_resgroups: 10
+reduction: 16
+reset: False
+test_every: 1000
+epochs: 1000
+batch_size: 16
+split_batch: 1
+self_ensemble: False
+test_only: False
+gan_k: 1
+lr: 0.0001
+decay: 100
+gamma: 0.5
+optimizer: ADAM
+momentum: 0.9
+betas: (0.9, 0.999)
+epsilon: 1e-08
+weight_decay: 0
+gclip: 0
+loss: 1*L1
+skip_threshold: 100000000.0
+save: smgarn
+load: 
+resume: 0
+save_models: False
+print_every: 100
+save_results: True
+save_gt: False
+
+2025-01-04-08:30:42
+
+debug: False
+template: .
+n_threads: 6
+cpu: False
+n_GPUs: 4
+seed: 1
+dir_data: ../dataset
+dir_demo: ../test
+data_train: ['DIV2K']
+data_test: ['DIV2K']
+data_range: 1-50000/50001-50050
+ext: sep
+scale: [1]
+patch_size: 64
+rgb_range: 255
+n_colors: 3
+chop: False
+no_augment: False
+model: EWT
+act: relu
+pre_train: 
+extend: .
+n_resblocks: 16
+n_feats: 64
+res_scale: 1
+shift_mean: True
+dilation: False
+precision: single
+G0: 64
+RDNkSize: 3
+RDNconfig: B
+n_resgroups: 10
+reduction: 16
+reset: False
+test_every: 1000
+epochs: 1000
+batch_size: 16
+split_batch: 1
+self_ensemble: False
+test_only: False
+gan_k: 1
+lr: 0.0001
+decay: 100
+gamma: 0.5
+optimizer: ADAM
+momentum: 0.9
+betas: (0.9, 0.999)
+epsilon: 1e-08
+weight_decay: 0
+gclip: 0
+loss: 1*L1
+skip_threshold: 100000000.0
+save: smgarn
+load: 
+resume: 0
+save_models: False
+print_every: 100
+save_results: True
+save_gt: False
+
+2025-01-04-08:31:16
+
+debug: False
+template: .
+n_threads: 6
+cpu: False
+n_GPUs: 4
+seed: 1
+dir_data: ../dataset
+dir_demo: ../test
+data_train: ['DIV2K']
+data_test: ['DIV2K']
+data_range: 1-50000/50001-50050
+ext: sep
+scale: [1]
+patch_size: 64
+rgb_range: 255
+n_colors: 3
+chop: False
+no_augment: False
+model: EWT
+act: relu
+pre_train: 
+extend: .
+n_resblocks: 16
+n_feats: 64
+res_scale: 1
+shift_mean: True
+dilation: False
+precision: single
+G0: 64
+RDNkSize: 3
+RDNconfig: B
+n_resgroups: 10
+reduction: 16
+reset: False
+test_every: 1000
+epochs: 1000
+batch_size: 16
+split_batch: 1
+self_ensemble: False
+test_only: False
+gan_k: 1
+lr: 0.0001
+decay: 100
+gamma: 0.5
+optimizer: ADAM
+momentum: 0.9
+betas: (0.9, 0.999)
+epsilon: 1e-08
+weight_decay: 0
+gclip: 0
+loss: 1*L1
+skip_threshold: 100000000.0
+save: smgarn
+load: 
+resume: 0
+save_models: False
+print_every: 100
+save_results: True
+save_gt: False
+
+2025-01-04-08:42:00
+
+debug: False
+template: .
+n_threads: 6
+cpu: False
+n_GPUs: 4
+seed: 1
+dir_data: ../dataset
+dir_demo: ../test
+data_train: ['DIV2K']
+data_test: ['DIV2K']
+data_range: 1-50000/50001-50050
+ext: sep
+scale: [1]
+patch_size: 64
+rgb_range: 255
+n_colors: 3
+chop: False
+no_augment: False
+model: EWT
+act: relu
+pre_train: 
+extend: .
+n_resblocks: 16
+n_feats: 64
+res_scale: 1
+shift_mean: True
+dilation: False
+precision: single
+G0: 64
+RDNkSize: 3
+RDNconfig: B
+n_resgroups: 10
+reduction: 16
+reset: False
+test_every: 1000
+epochs: 1000
+batch_size: 16
+split_batch: 1
+self_ensemble: False
+test_only: False
+gan_k: 1
+lr: 0.0001
+decay: 100
+gamma: 0.5
+optimizer: ADAM
+momentum: 0.9
+betas: (0.9, 0.999)
+epsilon: 1e-08
+weight_decay: 0
+gclip: 0
+loss: 1*L1
+skip_threshold: 100000000.0
+save: smgarn
+load: 
+resume: 0
+save_models: False
+print_every: 100
+save_results: True
+save_gt: False
+
+2025-01-04-08:42:29
+
+debug: False
+template: .
+n_threads: 6
+cpu: False
+n_GPUs: 2
+seed: 1
+dir_data: ../dataset
+dir_demo: ../test
+data_train: ['DIV2K']
+data_test: ['DIV2K']
+data_range: 1-50000/50001-50050
+ext: sep
+scale: [1]
+patch_size: 64
+rgb_range: 255
+n_colors: 3
+chop: False
+no_augment: False
+model: EWT
+act: relu
+pre_train: 
+extend: .
+n_resblocks: 16
+n_feats: 64
+res_scale: 1
+shift_mean: True
+dilation: False
+precision: single
+G0: 64
+RDNkSize: 3
+RDNconfig: B
+n_resgroups: 10
+reduction: 16
+reset: False
+test_every: 1000
+epochs: 1000
+batch_size: 16
+split_batch: 1
+self_ensemble: False
+test_only: False
+gan_k: 1
+lr: 0.0001
+decay: 100
+gamma: 0.5
+optimizer: ADAM
+momentum: 0.9
+betas: (0.9, 0.999)
+epsilon: 1e-08
+weight_decay: 0
+gclip: 0
+loss: 1*L1
+skip_threshold: 100000000.0
+save: smgarn
+load: 
+resume: 0
+save_models: False
+print_every: 100
+save_results: True
+save_gt: False
+
+2025-01-04-08:48:24
+
+debug: False
+template: .
+n_threads: 6
+cpu: False
+n_GPUs: 2
+seed: 1
+dir_data: ../dataset
+dir_demo: ../test
+data_train: ['DIV2K']
+data_test: ['DIV2K']
+data_range: 1-50000/50001-50050
+ext: sep_reset
+scale: [1]
+patch_size: 64
+rgb_range: 255
+n_colors: 3
+chop: False
+no_augment: False
+model: EWT
+act: relu
+pre_train: 
+extend: .
+n_resblocks: 16
+n_feats: 64
+res_scale: 1
+shift_mean: True
+dilation: False
+precision: single
+G0: 64
+RDNkSize: 3
+RDNconfig: B
+n_resgroups: 10
+reduction: 16
+reset: False
+test_every: 1000
+epochs: 300
+batch_size: 16
+split_batch: 1
+self_ensemble: False
+test_only: False
+gan_k: 1
+lr: 0.0001
+decay: 100
+gamma: 0.5
+optimizer: ADAM
+momentum: 0.9
+betas: (0.9, 0.999)
+epsilon: 1e-08
+weight_decay: 0
+gclip: 0
+loss: 1*L1
+skip_threshold: 100000000.0
+save: smgarn
+load: 
+resume: 0
+save_models: False
+print_every: 100
+save_results: True
+save_gt: False
+
+2025-01-04-21:31:18
+
+debug: False
+template: .
+n_threads: 6
+cpu: False
+n_GPUs: 2
+seed: 1
+dir_data: ../dataset
+dir_demo: ../test
+data_train: ['DIV2K']
+data_test: ['DIV2K']
+data_range: 1-520/521-570
+ext: sep_reset
+scale: [1]
+patch_size: 64
+rgb_range: 255
+n_colors: 3
+chop: False
+no_augment: False
+model: EWT
+act: relu
+pre_train: 
+extend: .
+n_resblocks: 16
+n_feats: 64
+res_scale: 1
+shift_mean: True
+dilation: False
+precision: single
+G0: 64
+RDNkSize: 3
+RDNconfig: B
+n_resgroups: 10
+reduction: 16
+reset: False
+test_every: 1000
+epochs: 300
+batch_size: 16
+split_batch: 1
+self_ensemble: False
+test_only: False
+gan_k: 1
+lr: 0.0001
+decay: 100
+gamma: 0.5
+optimizer: ADAM
+momentum: 0.9
+betas: (0.9, 0.999)
+epsilon: 1e-08
+weight_decay: 0
+gclip: 0
+loss: 1*L1
+skip_threshold: 100000000.0
+save: smgarn
+load: 
+resume: 0
+save_models: False
+print_every: 100
+save_results: True
+save_gt: False
+
diff --git a/experiment/smgarn_1/log.txt b/experiment/smgarn_1/log.txt
new file mode 100644
index 0000000000000000000000000000000000000000..cfd1cdda378756df600d3f2a4d610c4deaadd021
--- /dev/null
+++ b/experiment/smgarn_1/log.txt
@@ -0,0 +1,12530 @@
+SMGARN(
+  (Stage_I): Mask_Net(
+    (head): Sequential(
+      (0): Conv2d(3, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      (1): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    )
+    (g_mp1): SnowMaskBlock(
+      (smblock): MaskBlock(
+        (act): ReLU(inplace=True)
+        (conv_head): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv_self): Conv2d(112, 112, kernel_size=(1, 1), stride=(1, 1))
+        (conv1): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv1_1): Conv2d(112, 112, kernel_size=(1, 1), stride=(1, 1))
+        (conv1_2): Conv2d(112, 112, kernel_size=(1, 1), stride=(1, 1))
+        (conv_tail): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      )
+      (conv3): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      (norm): LayerNorm((112,), eps=1e-05, elementwise_affine=True)
+    )
+    (conv_out1): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (conv_out2): Conv2d(112, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+  )
+  (Stage_II): ReconstructNet(
+    (fusion): FusionBlock(
+      (act): ReLU(inplace=True)
+      (conv_1): Conv2d(3, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      (conv_2): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      (conv_1_2): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      (conv_2_2): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      (ru_1): ResUnit(
+        (act): ReLU(inplace=True)
+        (conv1): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv2): Conv2d(112, 224, kernel_size=(1, 1), stride=(1, 1))
+        (conv3): Conv2d(224, 112, kernel_size=(1, 1), stride=(1, 1))
+      )
+      (ru_2): ResUnit(
+        (act): ReLU(inplace=True)
+        (conv1): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv2): Conv2d(112, 224, kernel_size=(1, 1), stride=(1, 1))
+        (conv3): Conv2d(224, 112, kernel_size=(1, 1), stride=(1, 1))
+      )
+      (ru_1_1): ResUnit(
+        (act): ReLU(inplace=True)
+        (conv1): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv2): Conv2d(112, 224, kernel_size=(1, 1), stride=(1, 1))
+        (conv3): Conv2d(224, 112, kernel_size=(1, 1), stride=(1, 1))
+      )
+      (ru_2_1): ResUnit(
+        (act): ReLU(inplace=True)
+        (conv1): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv2): Conv2d(112, 224, kernel_size=(1, 1), stride=(1, 1))
+        (conv3): Conv2d(224, 112, kernel_size=(1, 1), stride=(1, 1))
+      )
+      (ru): ResUnit(
+        (act): ReLU(inplace=True)
+        (conv1): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv2): Conv2d(112, 224, kernel_size=(1, 1), stride=(1, 1))
+        (conv3): Conv2d(224, 112, kernel_size=(1, 1), stride=(1, 1))
+      )
+      (ru_): ResUnit(
+        (act): ReLU(inplace=True)
+        (conv1): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv2): Conv2d(112, 224, kernel_size=(1, 1), stride=(1, 1))
+        (conv3): Conv2d(224, 112, kernel_size=(1, 1), stride=(1, 1))
+      )
+      (conv_tail_1): Conv2d(224, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      (conv_tail_2): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    )
+    (recon): Sequential(
+      (0): MARB(
+        (act): ReLU(inplace=True)
+        (conv_dl2): Conv2d(112, 112, kernel_size=(1, 1), stride=(1, 1))
+        (conv_dl3): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv_dl5): Conv2d(112, 112, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
+        (conv1_1): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv1_2): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv1_3): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv2_1): Conv2d(224, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv2_2): Conv2d(224, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv_tail): Conv2d(224, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      )
+      (1): MARB(
+        (act): ReLU(inplace=True)
+        (conv_dl2): Conv2d(112, 112, kernel_size=(1, 1), stride=(1, 1))
+        (conv_dl3): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv_dl5): Conv2d(112, 112, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
+        (conv1_1): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv1_2): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv1_3): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv2_1): Conv2d(224, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv2_2): Conv2d(224, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv_tail): Conv2d(224, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      )
+      (2): MARB(
+        (act): ReLU(inplace=True)
+        (conv_dl2): Conv2d(112, 112, kernel_size=(1, 1), stride=(1, 1))
+        (conv_dl3): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv_dl5): Conv2d(112, 112, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
+        (conv1_1): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv1_2): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv1_3): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv2_1): Conv2d(224, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv2_2): Conv2d(224, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (conv_tail): Conv2d(224, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      )
+    )
+    (tail): Sequential(
+      (0): Conv2d(112, 112, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      (1): ReLU(inplace=True)
+      (2): Conv2d(112, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    )
+  )
+)
+[Epoch 1]	Learning rate: 1.00e-4
+[1600/16000]	[L1: 47.8929]	14.1+2.4s
+[3200/16000]	[L1: 39.1485]	10.5+2.0s
+[4800/16000]	[L1: 36.0881]	11.5+2.0s
+[6400/16000]	[L1: 33.8624]	10.2+2.3s
+[8000/16000]	[L1: 32.3248]	10.2+2.4s
+[9600/16000]	[L1: 31.3261]	11.2+2.1s
+[11200/16000]	[L1: 30.6030]	10.2+2.4s
+[12800/16000]	[L1: 29.9444]	10.1+2.3s
+[14400/16000]	[L1: 29.2442]	11.2+2.1s
+[16000/16000]	[L1: 28.5621]	10.4+2.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.56s
+
+Saving...
+Total: 2.21s
+
+[Epoch 2]	Learning rate: 1.00e-4
+[1600/16000]	[L1: 22.9611]	11.6+1.9s
+[3200/16000]	[L1: 22.8063]	10.5+2.0s
+[4800/16000]	[L1: 22.5382]	10.3+2.1s
+[6400/16000]	[L1: 22.3339]	11.0+2.2s
+[8000/16000]	[L1: 22.4234]	10.0+2.5s
+[9600/16000]	[L1: 22.1952]	10.3+2.2s
+[11200/16000]	[L1: 22.0444]	11.7+1.7s
+[12800/16000]	[L1: 22.0328]	10.8+1.8s
+[14400/16000]	[L1: 22.0057]	12.0+1.5s
+[16000/16000]	[L1: 21.8648]	10.7+1.8s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.49s
+
+Saving...
+Total: 1.12s
+
+[Epoch 3]	Learning rate: 1.00e-4
+EWT(
+  (DWT): DWT()
+  (IWT): IWT()
+  (trans): MFAM(
+    (conv_first): Conv2d(24, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (patch_embed): PatchEmbed(
+      (norm): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+    )
+    (patch_unembed): PatchUnEmbed()
+    (pos_drop): Dropout(p=0.0, inplace=False)
+    (layers): ModuleList(
+      (0): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): Identity()
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.014)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+      (1): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.029)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.043)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+      (2): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.057)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.071)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (2): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.086)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (3): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.100)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+    )
+    (norm): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+    (conv_after_body): ResBlock(
+      (body): Sequential(
+        (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (1): ReLU(inplace=True)
+        (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      )
+    )
+    (conv_last): Conv2d(96, 12, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+  )
+)
+EWT(
+  (DWT): DWT()
+  (IWT): IWT()
+  (trans): MFAM(
+    (conv_first): Conv2d(24, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (patch_embed): PatchEmbed(
+      (norm): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+    )
+    (patch_unembed): PatchUnEmbed()
+    (pos_drop): Dropout(p=0.0, inplace=False)
+    (layers): ModuleList(
+      (0): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): Identity()
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.014)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+      (1): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.029)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.043)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+      (2): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.057)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.071)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (2): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.086)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (3): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.100)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+    )
+    (norm): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+    (conv_after_body): ResBlock(
+      (body): Sequential(
+        (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (1): ReLU(inplace=True)
+        (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      )
+    )
+    (conv_last): Conv2d(96, 12, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+  )
+)
+EWT(
+  (DWT): DWT()
+  (IWT): IWT()
+  (trans): MFAM(
+    (conv_first): Conv2d(24, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (patch_embed): PatchEmbed(
+      (norm): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+    )
+    (patch_unembed): PatchUnEmbed()
+    (pos_drop): Dropout(p=0.0, inplace=False)
+    (layers): ModuleList(
+      (0): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): Identity()
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.014)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+      (1): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.029)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.043)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+      (2): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.057)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.071)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (2): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.086)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (3): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.100)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+    )
+    (norm): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+    (conv_after_body): ResBlock(
+      (body): Sequential(
+        (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (1): ReLU(inplace=True)
+        (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      )
+    )
+    (conv_last): Conv2d(96, 12, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+  )
+)
+[Epoch 1]	Learning rate: 1.00e-4
+EWT(
+  (DWT): DWT()
+  (IWT): IWT()
+  (trans): MFAM(
+    (conv_first): Conv2d(24, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (patch_embed): PatchEmbed(
+      (norm): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+    )
+    (patch_unembed): PatchUnEmbed()
+    (pos_drop): Dropout(p=0.0, inplace=False)
+    (layers): ModuleList(
+      (0): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): Identity()
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.014)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+      (1): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.029)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.043)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+      (2): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.057)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.071)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (2): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.086)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (3): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.100)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+    )
+    (norm): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+    (conv_after_body): ResBlock(
+      (body): Sequential(
+        (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (1): ReLU(inplace=True)
+        (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      )
+    )
+    (conv_last): Conv2d(96, 12, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+  )
+)
+[Epoch 1]	Learning rate: 1.00e-4
+EWT(
+  (DWT): DWT()
+  (IWT): IWT()
+  (trans): MFAM(
+    (conv_first): Conv2d(24, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (patch_embed): PatchEmbed(
+      (norm): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+    )
+    (patch_unembed): PatchUnEmbed()
+    (pos_drop): Dropout(p=0.0, inplace=False)
+    (layers): ModuleList(
+      (0): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): Identity()
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.014)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+      (1): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.029)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.043)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+      (2): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.057)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.071)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (2): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.086)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (3): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.100)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+    )
+    (norm): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+    (conv_after_body): ResBlock(
+      (body): Sequential(
+        (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (1): ReLU(inplace=True)
+        (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      )
+    )
+    (conv_last): Conv2d(96, 12, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+  )
+)
+[Epoch 1]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 38.9428]	12.2+0.5s
+[3200/15960]	[L1: 28.3258]	8.8+0.1s
+[4800/15960]	[L1: 23.4237]	8.9+0.1s
+[6400/15960]	[L1: 20.4574]	9.7+0.1s
+[8000/15960]	[L1: 18.3574]	8.9+0.1s
+[9600/15960]	[L1: 16.5629]	9.1+0.1s
+[11200/15960]	[L1: 14.9812]	9.9+0.1s
+[12800/15960]	[L1: 13.6646]	9.3+0.1s
+EWT(
+  (DWT): DWT()
+  (IWT): IWT()
+  (trans): MFAM(
+    (conv_first): Conv2d(24, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (patch_embed): PatchEmbed(
+      (norm): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+    )
+    (patch_unembed): PatchUnEmbed()
+    (pos_drop): Dropout(p=0.0, inplace=False)
+    (layers): ModuleList(
+      (0): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): Identity()
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.014)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+      (1): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.029)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.043)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+      (2): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.057)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.071)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (2): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.086)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (3): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.100)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+    )
+    (norm): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+    (conv_after_body): ResBlock(
+      (body): Sequential(
+        (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (1): ReLU(inplace=True)
+        (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      )
+    )
+    (conv_last): Conv2d(96, 12, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+  )
+)
+[Epoch 1]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 38.9420]	12.8+0.8s
+[3200/15960]	[L1: 28.3252]	10.5+0.1s
+[4800/15960]	[L1: 23.4234]	9.7+0.1s
+[6400/15960]	[L1: 20.4573]	9.8+0.1s
+[8000/15960]	[L1: 18.3851]	10.1+0.1s
+[9600/15960]	[L1: 16.6325]	10.9+0.1s
+[11200/15960]	[L1: 15.0731]	10.7+0.1s
+[12800/15960]	[L1: 13.7582]	9.9+0.1s
+[14400/15960]	[L1: 12.6943]	9.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.27s
+
+Saving...
+Total: 1.83s
+
+[Epoch 2]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 3.6983]	11.1+0.6s
+[3200/15960]	[L1: 3.7069]	11.0+0.1s
+[4800/15960]	[L1: 3.6397]	10.7+0.1s
+[6400/15960]	[L1: 3.5733]	10.8+0.1s
+[8000/15960]	[L1: 3.5244]	10.9+0.1s
+[9600/15960]	[L1: 3.4789]	10.3+0.1s
+[11200/15960]	[L1: 3.4246]	10.7+0.1s
+[12800/15960]	[L1: 3.3866]	10.8+0.1s
+[14400/15960]	[L1: 3.3513]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.29s
+
+Saving...
+Total: 1.73s
+
+[Epoch 3]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 2.9079]	11.0+0.6s
+[3200/15960]	[L1: 2.8305]	10.7+0.1s
+[4800/15960]	[L1: 2.8430]	10.8+0.1s
+[6400/15960]	[L1: 2.8255]	9.8+0.1s
+[8000/15960]	[L1: 2.7963]	10.7+0.1s
+[9600/15960]	[L1: 2.7725]	10.5+0.1s
+[11200/15960]	[L1: 2.7511]	9.8+0.1s
+[12800/15960]	[L1: 2.7186]	9.9+0.1s
+[14400/15960]	[L1: 2.6918]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.28s
+
+Saving...
+Total: 1.68s
+
+[Epoch 4]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 2.4157]	11.2+0.6s
+[3200/15960]	[L1: 2.4057]	11.0+0.1s
+[4800/15960]	[L1: 2.4011]	11.0+0.1s
+[6400/15960]	[L1: 2.3932]	10.8+0.1s
+[8000/15960]	[L1: 2.3647]	10.7+0.1s
+[9600/15960]	[L1: 2.3345]	10.8+0.1s
+[11200/15960]	[L1: 2.3276]	10.8+0.1s
+[12800/15960]	[L1: 2.3122]	10.7+0.1s
+[14400/15960]	[L1: 2.2911]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.70s
+
+[Epoch 5]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 2.1575]	11.1+0.6s
+[3200/15960]	[L1: 2.1519]	10.9+0.1s
+[4800/15960]	[L1: 2.1478]	10.9+0.1s
+[6400/15960]	[L1: 2.1352]	10.5+0.1s
+[8000/15960]	[L1: 2.1115]	11.1+0.1s
+[9600/15960]	[L1: 2.0912]	11.3+0.1s
+[11200/15960]	[L1: 2.0813]	10.9+0.1s
+[12800/15960]	[L1: 2.0727]	10.9+0.1s
+[14400/15960]	[L1: 2.0572]	10.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.71s
+
+[Epoch 6]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 1.8861]	11.1+0.6s
+[3200/15960]	[L1: 1.9382]	10.7+0.1s
+[4800/15960]	[L1: 1.9322]	10.7+0.1s
+[6400/15960]	[L1: 1.9300]	10.1+0.1s
+[8000/15960]	[L1: 1.9217]	10.9+0.1s
+[9600/15960]	[L1: 1.9021]	10.6+0.1s
+[11200/15960]	[L1: 1.8806]	10.5+0.1s
+[12800/15960]	[L1: 1.8709]	11.0+0.1s
+[14400/15960]	[L1: 1.8670]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.29s
+
+Saving...
+Total: 1.71s
+
+[Epoch 7]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 1.7570]	11.0+0.6s
+[3200/15960]	[L1: 1.7700]	10.9+0.1s
+[4800/15960]	[L1: 1.7694]	10.7+0.1s
+[6400/15960]	[L1: 1.7587]	10.8+0.1s
+[8000/15960]	[L1: 1.7544]	10.7+0.1s
+[9600/15960]	[L1: 1.7551]	10.8+0.1s
+[11200/15960]	[L1: 1.7459]	10.7+0.1s
+[12800/15960]	[L1: 1.7297]	10.9+0.1s
+[14400/15960]	[L1: 1.7208]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 0.72s
+
+[Epoch 8]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 1.6361]	10.8+0.5s
+[3200/15960]	[L1: 1.6477]	10.7+0.1s
+[4800/15960]	[L1: 1.6361]	10.7+0.1s
+[6400/15960]	[L1: 1.6118]	10.8+0.1s
+[8000/15960]	[L1: 1.6054]	10.6+0.1s
+[9600/15960]	[L1: 1.5998]	10.6+0.1s
+[11200/15960]	[L1: 1.6011]	10.6+0.1s
+[12800/15960]	[L1: 1.5952]	11.0+0.1s
+[14400/15960]	[L1: 1.5922]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.71s
+
+[Epoch 9]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 1.4958]	11.3+0.6s
+[3200/15960]	[L1: 1.4818]	10.9+0.1s
+[4800/15960]	[L1: 1.4851]	10.9+0.1s
+[6400/15960]	[L1: 1.5465]	11.1+0.1s
+[8000/15960]	[L1: 1.5282]	10.8+0.1s
+[9600/15960]	[L1: 1.5154]	11.1+0.1s
+[11200/15960]	[L1: 1.5128]	10.9+0.1s
+[12800/15960]	[L1: 1.5099]	11.1+0.1s
+[14400/15960]	[L1: 1.5061]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.90s
+
+[Epoch 10]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 1.4520]	11.2+0.6s
+[3200/15960]	[L1: 1.4491]	11.0+0.1s
+[4800/15960]	[L1: 1.4614]	10.5+0.1s
+[6400/15960]	[L1: 1.4519]	10.1+0.1s
+[8000/15960]	[L1: 1.4420]	10.3+0.1s
+[9600/15960]	[L1: 1.4342]	10.4+0.1s
+[11200/15960]	[L1: 1.4233]	10.3+0.1s
+[12800/15960]	[L1: 1.4161]	9.6+0.1s
+[14400/15960]	[L1: 1.4089]	9.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.70s
+
+[Epoch 11]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 1.3887]	11.1+0.6s
+[3200/15960]	[L1: 1.3857]	11.1+0.1s
+[4800/15960]	[L1: 1.3828]	10.8+0.1s
+[6400/15960]	[L1: 1.3922]	11.1+0.1s
+[8000/15960]	[L1: 1.3814]	11.1+0.1s
+[9600/15960]	[L1: 1.3933]	11.0+0.1s
+[11200/15960]	[L1: 1.3831]	10.4+0.1s
+[12800/15960]	[L1: 1.3691]	10.7+0.1s
+[14400/15960]	[L1: 1.3671]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.74s
+
+[Epoch 12]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 1.3377]	11.1+0.6s
+[3200/15960]	[L1: 1.3461]	11.1+0.1s
+[4800/15960]	[L1: 1.3558]	11.0+0.1s
+[6400/15960]	[L1: 1.3292]	11.0+0.1s
+[8000/15960]	[L1: 1.3217]	11.0+0.1s
+[9600/15960]	[L1: 1.3114]	11.1+0.1s
+[11200/15960]	[L1: 1.3097]	11.0+0.1s
+[12800/15960]	[L1: 1.3020]	11.0+0.1s
+[14400/15960]	[L1: 1.3004]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.29s
+
+Saving...
+Total: 1.69s
+
+[Epoch 13]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 1.2745]	10.2+0.5s
+[3200/15960]	[L1: 1.2774]	10.5+0.1s
+[4800/15960]	[L1: 1.2784]	10.3+0.1s
+[6400/15960]	[L1: 1.2646]	10.8+0.1s
+[8000/15960]	[L1: 1.2646]	10.5+0.1s
+[9600/15960]	[L1: 1.2606]	9.9+0.1s
+[11200/15960]	[L1: 1.2568]	10.2+0.1s
+[12800/15960]	[L1: 1.2578]	10.2+0.1s
+[14400/15960]	[L1: 1.2537]	9.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.29s
+
+Saving...
+Total: 1.67s
+
+[Epoch 14]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 1.2125]	11.1+0.5s
+[3200/15960]	[L1: 1.1873]	10.9+0.1s
+[4800/15960]	[L1: 1.2245]	10.9+0.1s
+[6400/15960]	[L1: 1.2298]	10.8+0.1s
+[8000/15960]	[L1: 1.2156]	10.7+0.1s
+[9600/15960]	[L1: 1.2063]	10.8+0.1s
+[11200/15960]	[L1: 1.2107]	10.6+0.1s
+[12800/15960]	[L1: 1.2068]	10.8+0.1s
+[14400/15960]	[L1: 1.2013]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.72s
+
+[Epoch 15]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 1.1775]	11.1+0.6s
+[3200/15960]	[L1: 1.1935]	10.7+0.1s
+[4800/15960]	[L1: 1.1770]	10.7+0.1s
+[6400/15960]	[L1: 1.1866]	10.9+0.1s
+[8000/15960]	[L1: 1.1921]	10.7+0.1s
+[9600/15960]	[L1: 1.1801]	11.0+0.1s
+[11200/15960]	[L1: 1.1734]	11.0+0.1s
+[12800/15960]	[L1: 1.1694]	11.1+0.1s
+[14400/15960]	[L1: 1.1652]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 0.76s
+
+[Epoch 16]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 1.0795]	11.2+0.6s
+[3200/15960]	[L1: 1.1053]	11.0+0.1s
+[4800/15960]	[L1: 1.1239]	11.1+0.1s
+[6400/15960]	[L1: 1.1242]	11.0+0.1s
+[8000/15960]	[L1: 1.1197]	11.1+0.1s
+[9600/15960]	[L1: 1.1207]	10.9+0.1s
+[11200/15960]	[L1: 1.1174]	10.8+0.1s
+[12800/15960]	[L1: 1.1111]	10.8+0.1s
+[14400/15960]	[L1: 1.1123]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.28s
+
+Saving...
+Total: 1.69s
+
+[Epoch 17]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 1.1130]	9.9+0.5s
+[3200/15960]	[L1: 1.1171]	10.7+0.1s
+[4800/15960]	[L1: 1.1032]	10.1+0.1s
+[6400/15960]	[L1: 1.0958]	10.1+0.1s
+[8000/15960]	[L1: 1.0980]	10.4+0.1s
+[9600/15960]	[L1: 1.0969]	10.5+0.1s
+[11200/15960]	[L1: 1.0922]	10.2+0.1s
+[12800/15960]	[L1: 1.0848]	10.8+0.1s
+[14400/15960]	[L1: 1.0855]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.70s
+
+[Epoch 18]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 1.1244]	11.1+0.5s
+[3200/15960]	[L1: 1.1172]	10.9+0.1s
+[4800/15960]	[L1: 1.0872]	10.8+0.1s
+[6400/15960]	[L1: 1.0643]	10.9+0.1s
+[8000/15960]	[L1: 1.0794]	10.9+0.1s
+[9600/15960]	[L1: 1.0696]	10.8+0.1s
+[11200/15960]	[L1: 1.0654]	10.9+0.1s
+[12800/15960]	[L1: 1.0585]	10.9+0.1s
+[14400/15960]	[L1: 1.0674]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.72s
+
+[Epoch 19]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 1.0598]	11.0+0.6s
+[3200/15960]	[L1: 1.0623]	11.0+0.1s
+[4800/15960]	[L1: 1.0658]	10.8+0.1s
+[6400/15960]	[L1: 1.0611]	10.7+0.1s
+[8000/15960]	[L1: 1.0471]	10.7+0.1s
+[9600/15960]	[L1: 1.0444]	10.9+0.1s
+[11200/15960]	[L1: 1.0435]	10.7+0.1s
+[12800/15960]	[L1: 1.0392]	10.7+0.1s
+[14400/15960]	[L1: 1.0341]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 0.75s
+
+[Epoch 20]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.9785]	11.2+0.5s
+[3200/15960]	[L1: 0.9945]	11.0+0.1s
+[4800/15960]	[L1: 1.0242]	11.0+0.1s
+[6400/15960]	[L1: 1.0295]	11.1+0.1s
+[8000/15960]	[L1: 1.0315]	10.9+0.1s
+[9600/15960]	[L1: 1.0310]	10.8+0.1s
+[11200/15960]	[L1: 1.0283]	10.8+0.1s
+[12800/15960]	[L1: 1.0337]	11.0+0.1s
+[14400/15960]	[L1: 1.0321]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.29s
+
+Saving...
+Total: 1.70s
+
+[Epoch 21]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 1.0225]	10.0+0.5s
+[3200/15960]	[L1: 1.0289]	9.6+0.1s
+[4800/15960]	[L1: 1.0155]	9.9+0.1s
+[6400/15960]	[L1: 1.0139]	9.4+0.1s
+[8000/15960]	[L1: 1.0110]	9.6+0.1s
+[9600/15960]	[L1: 1.0113]	10.7+0.1s
+[11200/15960]	[L1: 1.0023]	10.6+0.1s
+[12800/15960]	[L1: 1.0021]	10.5+0.1s
+[14400/15960]	[L1: 1.0018]	9.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.71s
+
+[Epoch 22]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.9714]	11.1+0.5s
+[3200/15960]	[L1: 0.9848]	10.8+0.1s
+[4800/15960]	[L1: 0.9824]	10.4+0.1s
+[6400/15960]	[L1: 0.9770]	9.6+0.1s
+[8000/15960]	[L1: 0.9755]	10.5+0.1s
+[9600/15960]	[L1: 0.9789]	10.5+0.1s
+[11200/15960]	[L1: 0.9924]	10.2+0.1s
+[12800/15960]	[L1: 0.9992]	10.7+0.1s
+[14400/15960]	[L1: 0.9942]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 0.70s
+
+[Epoch 23]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.9646]	11.3+0.5s
+[3200/15960]	[L1: 0.9526]	11.0+0.1s
+[4800/15960]	[L1: 0.9704]	11.1+0.1s
+[6400/15960]	[L1: 0.9648]	11.0+0.1s
+[8000/15960]	[L1: 0.9726]	11.0+0.1s
+[9600/15960]	[L1: 0.9749]	11.1+0.1s
+[11200/15960]	[L1: 0.9743]	11.0+0.1s
+[12800/15960]	[L1: 0.9717]	10.7+0.1s
+[14400/15960]	[L1: 0.9672]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.74s
+
+[Epoch 24]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.9944]	10.9+0.5s
+[3200/15960]	[L1: 0.9708]	11.0+0.1s
+[4800/15960]	[L1: 0.9480]	11.0+0.1s
+[6400/15960]	[L1: 0.9474]	10.7+0.1s
+[8000/15960]	[L1: 0.9456]	10.6+0.1s
+[9600/15960]	[L1: 0.9484]	11.0+0.1s
+[11200/15960]	[L1: 0.9550]	10.7+0.1s
+[12800/15960]	[L1: 0.9552]	10.3+0.1s
+[14400/15960]	[L1: 0.9635]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.69s
+
+[Epoch 25]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.9474]	11.1+0.5s
+[3200/15960]	[L1: 0.9202]	10.5+0.1s
+[4800/15960]	[L1: 0.9305]	11.1+0.1s
+[6400/15960]	[L1: 0.9359]	10.8+0.1s
+[8000/15960]	[L1: 0.9365]	10.9+0.1s
+[9600/15960]	[L1: 0.9371]	10.9+0.1s
+[11200/15960]	[L1: 0.9443]	11.0+0.1s
+[12800/15960]	[L1: 0.9394]	10.8+0.1s
+[14400/15960]	[L1: 0.9423]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.67s
+
+[Epoch 26]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.9282]	10.7+0.6s
+[3200/15960]	[L1: 0.9404]	9.4+0.1s
+[4800/15960]	[L1: 0.9403]	10.8+0.1s
+[6400/15960]	[L1: 0.9248]	11.0+0.1s
+[8000/15960]	[L1: 0.9191]	10.9+0.1s
+[9600/15960]	[L1: 0.9139]	10.7+0.1s
+[11200/15960]	[L1: 0.9064]	10.7+0.1s
+[12800/15960]	[L1: 0.9095]	10.8+0.1s
+[14400/15960]	[L1: 0.9109]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.70s
+
+[Epoch 27]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 1.0293]	10.5+0.6s
+[3200/15960]	[L1: 0.9743]	10.6+0.1s
+[4800/15960]	[L1: 0.9594]	10.6+0.1s
+[6400/15960]	[L1: 0.9377]	10.7+0.1s
+[8000/15960]	[L1: 0.9263]	10.8+0.1s
+[9600/15960]	[L1: 0.9270]	10.8+0.1s
+[11200/15960]	[L1: 0.9239]	10.7+0.1s
+[12800/15960]	[L1: 0.9184]	10.8+0.1s
+[14400/15960]	[L1: 0.9226]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 0.75s
+
+[Epoch 28]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.8785]	11.1+0.6s
+[3200/15960]	[L1: 0.8891]	10.9+0.1s
+[4800/15960]	[L1: 0.8959]	10.8+0.1s
+[6400/15960]	[L1: 0.8921]	10.7+0.1s
+[8000/15960]	[L1: 0.8860]	10.9+0.1s
+[9600/15960]	[L1: 0.8833]	10.9+0.1s
+[11200/15960]	[L1: 0.8822]	10.7+0.1s
+[12800/15960]	[L1: 0.8858]	10.7+0.1s
+[14400/15960]	[L1: 0.8868]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.70s
+
+[Epoch 29]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.8982]	10.9+0.6s
+[3200/15960]	[L1: 0.8982]	10.9+0.1s
+[4800/15960]	[L1: 0.9099]	10.7+0.1s
+[6400/15960]	[L1: 0.8960]	10.8+0.1s
+[8000/15960]	[L1: 0.8974]	10.7+0.1s
+[9600/15960]	[L1: 0.8930]	11.0+0.1s
+[11200/15960]	[L1: 0.8924]	10.8+0.1s
+[12800/15960]	[L1: 0.8853]	11.0+0.1s
+[14400/15960]	[L1: 0.8823]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.73s
+
+[Epoch 30]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.9256]	10.8+0.6s
+[3200/15960]	[L1: 0.9091]	11.1+0.1s
+[4800/15960]	[L1: 0.8949]	11.0+0.1s
+[6400/15960]	[L1: 0.8837]	11.1+0.1s
+[8000/15960]	[L1: 0.8832]	10.7+0.1s
+[9600/15960]	[L1: 0.8803]	11.0+0.1s
+[11200/15960]	[L1: 0.8792]	10.2+0.1s
+[12800/15960]	[L1: 0.8773]	10.1+0.1s
+[14400/15960]	[L1: 0.8767]	10.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.71s
+
+[Epoch 31]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.8495]	11.2+0.5s
+[3200/15960]	[L1: 0.8540]	11.2+0.1s
+[4800/15960]	[L1: 0.8529]	11.0+0.1s
+[6400/15960]	[L1: 0.8721]	10.7+0.1s
+[8000/15960]	[L1: 0.8663]	10.8+0.1s
+[9600/15960]	[L1: 0.8653]	10.9+0.1s
+[11200/15960]	[L1: 0.8643]	10.8+0.1s
+[12800/15960]	[L1: 0.8709]	10.8+0.1s
+[14400/15960]	[L1: 0.8718]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.70s
+
+[Epoch 32]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.8321]	11.1+0.6s
+[3200/15960]	[L1: 0.8398]	11.2+0.1s
+[4800/15960]	[L1: 0.8389]	11.3+0.1s
+[6400/15960]	[L1: 0.8537]	11.0+0.1s
+[8000/15960]	[L1: 0.8571]	11.1+0.1s
+[9600/15960]	[L1: 0.8582]	11.1+0.1s
+[11200/15960]	[L1: 0.8538]	11.0+0.1s
+[12800/15960]	[L1: 0.8540]	11.0+0.1s
+[14400/15960]	[L1: 0.8552]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 0.76s
+
+[Epoch 33]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.8221]	10.9+0.6s
+[3200/15960]	[L1: 0.8368]	10.9+0.1s
+[4800/15960]	[L1: 0.8575]	10.8+0.1s
+[6400/15960]	[L1: 0.8509]	10.8+0.1s
+[8000/15960]	[L1: 0.8477]	10.8+0.1s
+[9600/15960]	[L1: 0.8520]	10.8+0.1s
+[11200/15960]	[L1: 0.8615]	10.7+0.1s
+[12800/15960]	[L1: 0.8641]	10.7+0.1s
+[14400/15960]	[L1: 0.8618]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.76s
+
+[Epoch 34]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.8210]	11.1+0.6s
+[3200/15960]	[L1: 0.8519]	10.8+0.1s
+[4800/15960]	[L1: 0.8559]	10.8+0.1s
+[6400/15960]	[L1: 0.8515]	11.2+0.1s
+[8000/15960]	[L1: 0.8421]	10.9+0.1s
+[9600/15960]	[L1: 0.8419]	10.9+0.1s
+[11200/15960]	[L1: 0.8504]	10.9+0.1s
+[12800/15960]	[L1: 0.8450]	11.2+0.1s
+[14400/15960]	[L1: 0.8404]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.70s
+
+[Epoch 35]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.8519]	11.2+0.6s
+[3200/15960]	[L1: 0.8712]	10.7+0.1s
+[4800/15960]	[L1: 0.8642]	10.9+0.1s
+[6400/15960]	[L1: 0.8552]	10.9+0.1s
+[8000/15960]	[L1: 0.8406]	10.9+0.1s
+[9600/15960]	[L1: 0.8344]	10.8+0.1s
+[11200/15960]	[L1: 0.8436]	10.8+0.1s
+[12800/15960]	[L1: 0.8396]	11.1+0.1s
+[14400/15960]	[L1: 0.8464]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.69s
+
+[Epoch 36]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.8047]	10.9+0.5s
+[3200/15960]	[L1: 0.8114]	10.7+0.1s
+[4800/15960]	[L1: 0.8087]	10.9+0.1s
+[6400/15960]	[L1: 0.8161]	10.8+0.1s
+[8000/15960]	[L1: 0.8105]	10.7+0.1s
+[9600/15960]	[L1: 0.8184]	10.7+0.1s
+[11200/15960]	[L1: 0.8254]	10.7+0.1s
+[12800/15960]	[L1: 0.8273]	10.8+0.1s
+[14400/15960]	[L1: 0.8219]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.29s
+
+Saving...
+Total: 1.70s
+
+[Epoch 37]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7874]	11.0+0.5s
+[3200/15960]	[L1: 0.8270]	10.7+0.1s
+[4800/15960]	[L1: 0.8422]	10.9+0.1s
+[6400/15960]	[L1: 0.8248]	10.7+0.1s
+[8000/15960]	[L1: 0.8177]	10.8+0.1s
+[9600/15960]	[L1: 0.8148]	10.7+0.1s
+[11200/15960]	[L1: 0.8143]	10.8+0.1s
+[12800/15960]	[L1: 0.8132]	10.8+0.1s
+[14400/15960]	[L1: 0.8230]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.71s
+
+[Epoch 38]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.8464]	10.6+0.6s
+[3200/15960]	[L1: 0.8226]	10.6+0.1s
+[4800/15960]	[L1: 0.8139]	10.7+0.1s
+[6400/15960]	[L1: 0.8243]	10.8+0.1s
+[8000/15960]	[L1: 0.8206]	10.7+0.1s
+[9600/15960]	[L1: 0.8197]	10.8+0.1s
+[11200/15960]	[L1: 0.8219]	10.6+0.1s
+[12800/15960]	[L1: 0.8185]	10.7+0.1s
+[14400/15960]	[L1: 0.8208]	10.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.74s
+
+[Epoch 39]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7935]	11.1+0.6s
+[3200/15960]	[L1: 0.7932]	11.0+0.1s
+[4800/15960]	[L1: 0.7961]	10.6+0.1s
+[6400/15960]	[L1: 0.8015]	10.9+0.1s
+[8000/15960]	[L1: 0.8026]	10.9+0.1s
+[9600/15960]	[L1: 0.8047]	10.8+0.1s
+[11200/15960]	[L1: 0.7998]	10.9+0.1s
+[12800/15960]	[L1: 0.8011]	10.9+0.1s
+[14400/15960]	[L1: 0.8012]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 0.72s
+
+[Epoch 40]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.8273]	10.7+0.5s
+[3200/15960]	[L1: 0.8074]	10.7+0.1s
+[4800/15960]	[L1: 0.8085]	10.9+0.1s
+[6400/15960]	[L1: 0.8153]	10.9+0.1s
+[8000/15960]	[L1: 0.8050]	10.8+0.1s
+[9600/15960]	[L1: 0.8016]	10.9+0.1s
+[11200/15960]	[L1: 0.7967]	10.9+0.1s
+[12800/15960]	[L1: 0.7920]	10.8+0.1s
+[14400/15960]	[L1: 0.7868]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.69s
+
+[Epoch 41]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.8047]	10.9+0.6s
+[3200/15960]	[L1: 0.8025]	10.9+0.1s
+[4800/15960]	[L1: 0.7928]	10.7+0.1s
+[6400/15960]	[L1: 0.8012]	10.9+0.1s
+[8000/15960]	[L1: 0.7965]	10.8+0.1s
+[9600/15960]	[L1: 0.7943]	10.7+0.1s
+[11200/15960]	[L1: 0.7976]	10.9+0.1s
+[12800/15960]	[L1: 0.7937]	10.8+0.1s
+[14400/15960]	[L1: 0.7905]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.69s
+
+[Epoch 42]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7597]	11.2+0.5s
+[3200/15960]	[L1: 0.7911]	10.9+0.1s
+[4800/15960]	[L1: 0.7838]	11.0+0.1s
+[6400/15960]	[L1: 0.7786]	10.8+0.1s
+[8000/15960]	[L1: 0.7765]	11.0+0.1s
+[9600/15960]	[L1: 0.7736]	10.8+0.1s
+[11200/15960]	[L1: 0.7772]	10.7+0.1s
+[12800/15960]	[L1: 0.7774]	11.0+0.1s
+[14400/15960]	[L1: 0.7800]	10.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 0.72s
+
+[Epoch 43]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.8084]	10.2+0.5s
+[3200/15960]	[L1: 0.8366]	10.2+0.1s
+[4800/15960]	[L1: 0.8135]	10.1+0.1s
+[6400/15960]	[L1: 0.8010]	9.8+0.1s
+[8000/15960]	[L1: 0.7887]	10.2+0.1s
+[9600/15960]	[L1: 0.7817]	10.4+0.1s
+[11200/15960]	[L1: 0.7837]	9.7+0.1s
+[12800/15960]	[L1: 0.7837]	10.5+0.1s
+[14400/15960]	[L1: 0.7836]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 0.71s
+
+[Epoch 44]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7850]	11.1+0.6s
+[3200/15960]	[L1: 0.7968]	10.6+0.1s
+[4800/15960]	[L1: 0.7895]	9.7+0.1s
+[6400/15960]	[L1: 0.7986]	10.6+0.1s
+[8000/15960]	[L1: 0.7914]	11.0+0.1s
+[9600/15960]	[L1: 0.7895]	10.8+0.1s
+[11200/15960]	[L1: 0.7824]	10.9+0.1s
+[12800/15960]	[L1: 0.7842]	10.9+0.1s
+[14400/15960]	[L1: 0.7852]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.71s
+
+[Epoch 45]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7254]	10.7+0.5s
+[3200/15960]	[L1: 0.7436]	10.3+0.1s
+[4800/15960]	[L1: 0.7500]	10.4+0.1s
+[6400/15960]	[L1: 0.7431]	9.8+0.1s
+[8000/15960]	[L1: 0.7437]	10.2+0.1s
+[9600/15960]	[L1: 0.7495]	9.9+0.1s
+[11200/15960]	[L1: 0.7557]	10.4+0.1s
+[12800/15960]	[L1: 0.7530]	9.7+0.1s
+[14400/15960]	[L1: 0.7500]	9.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 2.01s
+
+[Epoch 46]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7480]	10.9+0.6s
+[3200/15960]	[L1: 0.7485]	10.3+0.1s
+[4800/15960]	[L1: 0.7515]	10.4+0.1s
+[6400/15960]	[L1: 0.7607]	9.9+0.1s
+[8000/15960]	[L1: 0.7634]	9.9+0.1s
+[9600/15960]	[L1: 0.7722]	9.7+0.1s
+[11200/15960]	[L1: 0.7731]	10.1+0.1s
+[12800/15960]	[L1: 0.7732]	9.5+0.1s
+[14400/15960]	[L1: 0.7723]	10.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.73s
+
+[Epoch 47]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.8009]	9.9+0.5s
+[3200/15960]	[L1: 0.7685]	9.7+0.1s
+[4800/15960]	[L1: 0.7592]	10.9+0.1s
+[6400/15960]	[L1: 0.7555]	10.9+0.1s
+[8000/15960]	[L1: 0.7572]	9.7+0.1s
+[9600/15960]	[L1: 0.7577]	9.9+0.1s
+[11200/15960]	[L1: 0.7593]	11.1+0.1s
+[12800/15960]	[L1: 0.7623]	10.5+0.1s
+[14400/15960]	[L1: 0.7639]	10.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.67s
+
+[Epoch 48]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7930]	11.3+0.6s
+[3200/15960]	[L1: 0.7741]	10.9+0.1s
+[4800/15960]	[L1: 0.7607]	10.9+0.1s
+[6400/15960]	[L1: 0.7511]	10.9+0.1s
+[8000/15960]	[L1: 0.7477]	10.8+0.1s
+[9600/15960]	[L1: 0.7449]	10.6+0.1s
+[11200/15960]	[L1: 0.7474]	10.7+0.1s
+[12800/15960]	[L1: 0.7465]	11.2+0.1s
+[14400/15960]	[L1: 0.7485]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.73s
+
+[Epoch 49]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7535]	11.1+0.6s
+[3200/15960]	[L1: 0.7504]	10.8+0.1s
+[4800/15960]	[L1: 0.7458]	10.8+0.1s
+[6400/15960]	[L1: 0.7492]	10.9+0.1s
+[8000/15960]	[L1: 0.7501]	10.7+0.1s
+[9600/15960]	[L1: 0.7541]	10.9+0.1s
+[11200/15960]	[L1: 0.7559]	10.7+0.1s
+[12800/15960]	[L1: 0.7552]	10.9+0.1s
+[14400/15960]	[L1: 0.7593]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.73s
+
+[Epoch 50]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7431]	10.9+0.6s
+[3200/15960]	[L1: 0.7256]	10.9+0.1s
+[4800/15960]	[L1: 0.7243]	10.8+0.1s
+[6400/15960]	[L1: 0.7319]	10.7+0.1s
+[8000/15960]	[L1: 0.7439]	10.9+0.1s
+[9600/15960]	[L1: 0.7485]	10.8+0.1s
+[11200/15960]	[L1: 0.7434]	10.9+0.1s
+[12800/15960]	[L1: 0.7479]	10.8+0.1s
+[14400/15960]	[L1: 0.7464]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 0.71s
+
+[Epoch 51]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7980]	10.9+0.5s
+[3200/15960]	[L1: 0.7729]	9.5+0.1s
+[4800/15960]	[L1: 0.7653]	10.9+0.1s
+[6400/15960]	[L1: 0.7598]	10.9+0.1s
+[8000/15960]	[L1: 0.7559]	10.8+0.1s
+[9600/15960]	[L1: 0.7508]	10.9+0.1s
+[11200/15960]	[L1: 0.7423]	11.0+0.1s
+[12800/15960]	[L1: 0.7375]	10.8+0.1s
+[14400/15960]	[L1: 0.7380]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 0.82s
+
+[Epoch 52]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7240]	10.9+0.5s
+[3200/15960]	[L1: 0.7244]	10.9+0.1s
+[4800/15960]	[L1: 0.7440]	10.9+0.1s
+[6400/15960]	[L1: 0.7355]	10.7+0.1s
+[8000/15960]	[L1: 0.7358]	10.9+0.1s
+[9600/15960]	[L1: 0.7425]	10.7+0.1s
+[11200/15960]	[L1: 0.7366]	10.0+0.1s
+[12800/15960]	[L1: 0.7368]	10.0+0.1s
+[14400/15960]	[L1: 0.7379]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.73s
+
+[Epoch 53]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7100]	11.2+0.6s
+[3200/15960]	[L1: 0.7403]	10.9+0.1s
+[4800/15960]	[L1: 0.7281]	10.9+0.1s
+[6400/15960]	[L1: 0.7173]	10.9+0.1s
+[8000/15960]	[L1: 0.7236]	11.0+0.1s
+[9600/15960]	[L1: 0.7184]	10.9+0.1s
+[11200/15960]	[L1: 0.7382]	10.9+0.1s
+[12800/15960]	[L1: 0.7353]	10.8+0.1s
+[14400/15960]	[L1: 0.7368]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.71s
+
+[Epoch 54]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7921]	11.0+0.6s
+[3200/15960]	[L1: 0.7598]	11.0+0.1s
+[4800/15960]	[L1: 0.7409]	10.7+0.1s
+[6400/15960]	[L1: 0.7347]	10.9+0.1s
+[8000/15960]	[L1: 0.7268]	10.8+0.1s
+[9600/15960]	[L1: 0.7189]	10.9+0.1s
+[11200/15960]	[L1: 0.7198]	10.8+0.1s
+[12800/15960]	[L1: 0.7250]	10.8+0.1s
+[14400/15960]	[L1: 0.7226]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.72s
+
+[Epoch 55]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7451]	11.2+0.6s
+[3200/15960]	[L1: 0.7279]	10.8+0.1s
+[4800/15960]	[L1: 0.7120]	10.7+0.1s
+[6400/15960]	[L1: 0.7068]	10.9+0.1s
+[8000/15960]	[L1: 0.7046]	10.3+0.1s
+[9600/15960]	[L1: 0.7134]	9.6+0.1s
+[11200/15960]	[L1: 0.7145]	10.2+0.1s
+[12800/15960]	[L1: 0.7133]	10.1+0.1s
+[14400/15960]	[L1: 0.7137]	10.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.71s
+
+[Epoch 56]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7359]	10.0+0.6s
+[3200/15960]	[L1: 0.7120]	10.0+0.1s
+[4800/15960]	[L1: 0.7111]	10.9+0.1s
+[6400/15960]	[L1: 0.7283]	9.9+0.1s
+[8000/15960]	[L1: 0.7350]	10.7+0.1s
+[9600/15960]	[L1: 0.7307]	10.8+0.1s
+[11200/15960]	[L1: 0.7323]	11.0+0.1s
+[12800/15960]	[L1: 0.7287]	10.8+0.1s
+[14400/15960]	[L1: 0.7224]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.71s
+
+[Epoch 57]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7225]	10.0+0.5s
+[3200/15960]	[L1: 0.6998]	10.7+0.1s
+[4800/15960]	[L1: 0.6986]	11.0+0.1s
+[6400/15960]	[L1: 0.7115]	10.9+0.1s
+[8000/15960]	[L1: 0.7160]	11.0+0.1s
+[9600/15960]	[L1: 0.7088]	10.6+0.1s
+[11200/15960]	[L1: 0.7069]	11.0+0.1s
+[12800/15960]	[L1: 0.7101]	10.9+0.1s
+[14400/15960]	[L1: 0.7166]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.68s
+
+[Epoch 58]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7144]	11.0+0.6s
+[3200/15960]	[L1: 0.6975]	9.6+0.1s
+[4800/15960]	[L1: 0.6952]	10.2+0.1s
+[6400/15960]	[L1: 0.7062]	10.2+0.1s
+[8000/15960]	[L1: 0.7020]	10.8+0.1s
+[9600/15960]	[L1: 0.7076]	9.8+0.1s
+[11200/15960]	[L1: 0.7098]	9.6+0.1s
+[12800/15960]	[L1: 0.7151]	10.4+0.1s
+[14400/15960]	[L1: 0.7162]	9.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.72s
+
+[Epoch 59]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7097]	10.9+0.5s
+[3200/15960]	[L1: 0.7045]	11.0+0.1s
+[4800/15960]	[L1: 0.7067]	10.7+0.1s
+[6400/15960]	[L1: 0.7020]	10.8+0.1s
+[8000/15960]	[L1: 0.7005]	10.8+0.1s
+[9600/15960]	[L1: 0.7049]	10.7+0.1s
+[11200/15960]	[L1: 0.7062]	10.9+0.1s
+[12800/15960]	[L1: 0.7086]	10.7+0.1s
+[14400/15960]	[L1: 0.7092]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.71s
+
+[Epoch 60]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7200]	11.3+0.6s
+[3200/15960]	[L1: 0.7291]	11.0+0.1s
+[4800/15960]	[L1: 0.7260]	11.1+0.1s
+[6400/15960]	[L1: 0.7192]	11.1+0.1s
+[8000/15960]	[L1: 0.7143]	11.0+0.1s
+[9600/15960]	[L1: 0.7093]	11.1+0.1s
+[11200/15960]	[L1: 0.7063]	11.1+0.1s
+[12800/15960]	[L1: 0.7057]	11.0+0.1s
+[14400/15960]	[L1: 0.7085]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.75s
+
+[Epoch 61]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6785]	10.1+0.5s
+[3200/15960]	[L1: 0.7017]	10.2+0.1s
+[4800/15960]	[L1: 0.6963]	9.5+0.1s
+[6400/15960]	[L1: 0.6976]	10.4+0.1s
+[8000/15960]	[L1: 0.6991]	10.7+0.1s
+[9600/15960]	[L1: 0.7014]	10.7+0.1s
+[11200/15960]	[L1: 0.6984]	10.8+0.1s
+[12800/15960]	[L1: 0.6997]	10.7+0.1s
+[14400/15960]	[L1: 0.7001]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.69s
+
+[Epoch 62]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7276]	11.2+0.6s
+[3200/15960]	[L1: 0.6976]	11.1+0.1s
+[4800/15960]	[L1: 0.6995]	10.3+0.1s
+[6400/15960]	[L1: 0.6931]	10.9+0.1s
+[8000/15960]	[L1: 0.6919]	11.0+0.1s
+[9600/15960]	[L1: 0.6878]	10.9+0.1s
+[11200/15960]	[L1: 0.6888]	11.0+0.1s
+[12800/15960]	[L1: 0.6896]	10.8+0.1s
+[14400/15960]	[L1: 0.6932]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.68s
+
+[Epoch 63]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7848]	10.9+0.6s
+[3200/15960]	[L1: 0.7373]	11.2+0.1s
+[4800/15960]	[L1: 0.7318]	11.0+0.1s
+[6400/15960]	[L1: 0.7287]	10.9+0.1s
+[8000/15960]	[L1: 0.7253]	11.0+0.1s
+[9600/15960]	[L1: 0.7159]	11.0+0.1s
+[11200/15960]	[L1: 0.7074]	10.8+0.1s
+[12800/15960]	[L1: 0.6990]	10.9+0.1s
+[14400/15960]	[L1: 0.6980]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.29s
+
+Saving...
+Total: 1.82s
+
+[Epoch 64]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7266]	11.2+0.6s
+[3200/15960]	[L1: 0.7123]	11.0+0.1s
+[4800/15960]	[L1: 0.7314]	10.9+0.1s
+[6400/15960]	[L1: 0.7172]	10.9+0.1s
+[8000/15960]	[L1: 0.7148]	11.1+0.1s
+[9600/15960]	[L1: 0.7119]	10.8+0.1s
+[11200/15960]	[L1: 0.7121]	10.9+0.1s
+[12800/15960]	[L1: 0.7089]	10.9+0.1s
+[14400/15960]	[L1: 0.7065]	10.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.68s
+
+[Epoch 65]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7160]	11.0+0.6s
+[3200/15960]	[L1: 0.7432]	11.1+0.1s
+[4800/15960]	[L1: 0.7219]	10.9+0.1s
+[6400/15960]	[L1: 0.7049]	10.9+0.1s
+[8000/15960]	[L1: 0.7006]	10.8+0.1s
+[9600/15960]	[L1: 0.6912]	10.9+0.1s
+[11200/15960]	[L1: 0.6859]	10.8+0.1s
+[12800/15960]	[L1: 0.6839]	10.8+0.1s
+[14400/15960]	[L1: 0.6828]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 0.81s
+
+[Epoch 66]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.7131]	11.3+0.5s
+[3200/15960]	[L1: 0.7254]	10.9+0.1s
+[4800/15960]	[L1: 0.7042]	10.4+0.1s
+[6400/15960]	[L1: 0.7065]	11.0+0.1s
+[8000/15960]	[L1: 0.7019]	11.1+0.1s
+[9600/15960]	[L1: 0.6986]	10.9+0.1s
+[11200/15960]	[L1: 0.6948]	10.5+0.1s
+[12800/15960]	[L1: 0.6983]	10.6+0.1s
+[14400/15960]	[L1: 0.6969]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 0.74s
+
+[Epoch 67]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6528]	11.0+0.5s
+[3200/15960]	[L1: 0.6624]	10.9+0.1s
+[4800/15960]	[L1: 0.6651]	10.8+0.1s
+[6400/15960]	[L1: 0.6721]	10.8+0.1s
+[8000/15960]	[L1: 0.6710]	10.8+0.1s
+[9600/15960]	[L1: 0.6753]	10.7+0.1s
+[11200/15960]	[L1: 0.6778]	10.8+0.1s
+[12800/15960]	[L1: 0.6795]	10.7+0.1s
+[14400/15960]	[L1: 0.6798]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.71s
+
+[Epoch 68]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6824]	11.2+0.7s
+[3200/15960]	[L1: 0.6872]	10.8+0.1s
+[4800/15960]	[L1: 0.6635]	11.0+0.1s
+[6400/15960]	[L1: 0.6754]	10.9+0.1s
+[8000/15960]	[L1: 0.6774]	10.9+0.1s
+[9600/15960]	[L1: 0.6847]	10.9+0.1s
+[11200/15960]	[L1: 0.6886]	11.0+0.1s
+[12800/15960]	[L1: 0.6878]	11.0+0.1s
+[14400/15960]	[L1: 0.6865]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.72s
+
+[Epoch 69]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6820]	11.1+0.6s
+[3200/15960]	[L1: 0.6920]	10.8+0.1s
+[4800/15960]	[L1: 0.6843]	10.0+0.1s
+[6400/15960]	[L1: 0.6712]	10.8+0.1s
+[8000/15960]	[L1: 0.6702]	10.8+0.1s
+[9600/15960]	[L1: 0.6778]	10.9+0.1s
+[11200/15960]	[L1: 0.6775]	10.8+0.1s
+[12800/15960]	[L1: 0.6724]	11.1+0.1s
+[14400/15960]	[L1: 0.6737]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.70s
+
+[Epoch 70]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6859]	11.1+0.6s
+[3200/15960]	[L1: 0.6516]	10.9+0.1s
+[4800/15960]	[L1: 0.6530]	10.4+0.1s
+[6400/15960]	[L1: 0.6545]	10.8+0.1s
+[8000/15960]	[L1: 0.6637]	10.1+0.1s
+[9600/15960]	[L1: 0.6714]	9.4+0.1s
+[11200/15960]	[L1: 0.6742]	9.6+0.1s
+[12800/15960]	[L1: 0.6770]	9.6+0.1s
+[14400/15960]	[L1: 0.6777]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.72s
+
+[Epoch 71]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6440]	10.5+0.5s
+[3200/15960]	[L1: 0.6547]	10.9+0.1s
+[4800/15960]	[L1: 0.6607]	10.2+0.1s
+[6400/15960]	[L1: 0.6669]	10.1+0.1s
+[8000/15960]	[L1: 0.6628]	10.8+0.1s
+[9600/15960]	[L1: 0.6628]	10.5+0.1s
+[11200/15960]	[L1: 0.6631]	9.9+0.1s
+[12800/15960]	[L1: 0.6629]	10.8+0.1s
+[14400/15960]	[L1: 0.6637]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.72s
+
+[Epoch 72]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6745]	11.2+0.6s
+[3200/15960]	[L1: 0.6604]	11.0+0.1s
+[4800/15960]	[L1: 0.6891]	10.8+0.1s
+[6400/15960]	[L1: 0.6914]	11.0+0.1s
+[8000/15960]	[L1: 0.6906]	10.9+0.1s
+[9600/15960]	[L1: 0.6885]	10.8+0.1s
+[11200/15960]	[L1: 0.6820]	10.9+0.1s
+[12800/15960]	[L1: 0.6771]	11.0+0.1s
+[14400/15960]	[L1: 0.6854]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.73s
+
+[Epoch 73]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6582]	9.7+0.6s
+[3200/15960]	[L1: 0.6718]	9.8+0.1s
+[4800/15960]	[L1: 0.6692]	10.2+0.1s
+[6400/15960]	[L1: 0.6685]	9.9+0.1s
+[8000/15960]	[L1: 0.6666]	9.6+0.1s
+[9600/15960]	[L1: 0.6638]	10.6+0.1s
+[11200/15960]	[L1: 0.6673]	9.8+0.1s
+[12800/15960]	[L1: 0.6720]	10.3+0.1s
+[14400/15960]	[L1: 0.6724]	9.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.74s
+
+[Epoch 74]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6436]	11.1+0.6s
+[3200/15960]	[L1: 0.6396]	10.8+0.1s
+[4800/15960]	[L1: 0.6623]	10.9+0.1s
+[6400/15960]	[L1: 0.6613]	10.9+0.1s
+[8000/15960]	[L1: 0.6575]	10.4+0.1s
+[9600/15960]	[L1: 0.6636]	10.3+0.1s
+[11200/15960]	[L1: 0.6623]	10.8+0.1s
+[12800/15960]	[L1: 0.6600]	11.1+0.1s
+[14400/15960]	[L1: 0.6580]	10.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.71s
+
+[Epoch 75]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6646]	10.9+0.6s
+[3200/15960]	[L1: 0.6613]	10.3+0.1s
+[4800/15960]	[L1: 0.6617]	9.9+0.1s
+[6400/15960]	[L1: 0.6636]	9.8+0.1s
+[8000/15960]	[L1: 0.6578]	9.6+0.1s
+[9600/15960]	[L1: 0.6639]	10.0+0.1s
+[11200/15960]	[L1: 0.6639]	9.6+0.1s
+[12800/15960]	[L1: 0.6631]	9.5+0.1s
+[14400/15960]	[L1: 0.6617]	9.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 0.75s
+
+[Epoch 76]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6435]	11.0+0.5s
+[3200/15960]	[L1: 0.6359]	10.9+0.1s
+[4800/15960]	[L1: 0.6408]	10.3+0.1s
+[6400/15960]	[L1: 0.6451]	10.3+0.1s
+[8000/15960]	[L1: 0.6487]	10.9+0.1s
+[9600/15960]	[L1: 0.6511]	10.8+0.1s
+[11200/15960]	[L1: 0.6491]	10.4+0.1s
+[12800/15960]	[L1: 0.6486]	10.5+0.1s
+[14400/15960]	[L1: 0.6510]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.81s
+
+[Epoch 77]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6744]	10.7+0.6s
+[3200/15960]	[L1: 0.6659]	10.8+0.1s
+[4800/15960]	[L1: 0.6703]	10.6+0.1s
+[6400/15960]	[L1: 0.6687]	10.8+0.1s
+[8000/15960]	[L1: 0.6690]	10.3+0.1s
+[9600/15960]	[L1: 0.6778]	9.6+0.1s
+[11200/15960]	[L1: 0.6715]	10.3+0.1s
+[12800/15960]	[L1: 0.6724]	9.9+0.1s
+[14400/15960]	[L1: 0.6675]	9.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.72s
+
+[Epoch 78]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6589]	11.1+0.6s
+[3200/15960]	[L1: 0.6666]	10.8+0.1s
+[4800/15960]	[L1: 0.6583]	10.7+0.1s
+[6400/15960]	[L1: 0.6517]	10.1+0.1s
+[8000/15960]	[L1: 0.6481]	10.3+0.1s
+[9600/15960]	[L1: 0.6493]	9.7+0.1s
+[11200/15960]	[L1: 0.6463]	10.3+0.1s
+[12800/15960]	[L1: 0.6460]	10.7+0.1s
+[14400/15960]	[L1: 0.6470]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 0.79s
+
+[Epoch 79]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6204]	11.1+0.6s
+[3200/15960]	[L1: 0.6324]	10.9+0.1s
+[4800/15960]	[L1: 0.6411]	10.8+0.1s
+[6400/15960]	[L1: 0.6475]	10.9+0.1s
+[8000/15960]	[L1: 0.6488]	10.8+0.1s
+[9600/15960]	[L1: 0.6486]	10.9+0.1s
+[11200/15960]	[L1: 0.6472]	10.9+0.1s
+[12800/15960]	[L1: 0.6478]	10.8+0.1s
+[14400/15960]	[L1: 0.6477]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.72s
+
+[Epoch 80]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6330]	11.2+0.5s
+[3200/15960]	[L1: 0.6408]	11.2+0.1s
+[4800/15960]	[L1: 0.6356]	11.1+0.1s
+[6400/15960]	[L1: 0.6436]	11.2+0.1s
+[8000/15960]	[L1: 0.6492]	11.0+0.1s
+[9600/15960]	[L1: 0.6530]	10.9+0.1s
+[11200/15960]	[L1: 0.6546]	11.1+0.1s
+[12800/15960]	[L1: 0.6564]	11.2+0.1s
+[14400/15960]	[L1: 0.6575]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.70s
+
+[Epoch 81]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6364]	10.6+0.6s
+[3200/15960]	[L1: 0.6324]	11.0+0.1s
+[4800/15960]	[L1: 0.6449]	10.8+0.1s
+[6400/15960]	[L1: 0.6505]	10.9+0.1s
+[8000/15960]	[L1: 0.6561]	10.7+0.1s
+[9600/15960]	[L1: 0.6493]	10.9+0.1s
+[11200/15960]	[L1: 0.6492]	10.8+0.1s
+[12800/15960]	[L1: 0.6534]	10.8+0.1s
+[14400/15960]	[L1: 0.6557]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.69s
+
+[Epoch 82]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6725]	11.2+0.6s
+[3200/15960]	[L1: 0.6685]	11.1+0.1s
+[4800/15960]	[L1: 0.6486]	11.0+0.1s
+[6400/15960]	[L1: 0.6460]	10.9+0.1s
+[8000/15960]	[L1: 0.6416]	10.8+0.1s
+[9600/15960]	[L1: 0.6416]	10.8+0.1s
+[11200/15960]	[L1: 0.6459]	10.2+0.1s
+[12800/15960]	[L1: 0.6470]	9.8+0.1s
+[14400/15960]	[L1: 0.6452]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.71s
+
+[Epoch 83]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6449]	9.9+0.6s
+[3200/15960]	[L1: 0.6470]	10.1+0.1s
+[4800/15960]	[L1: 0.6386]	10.1+0.1s
+[6400/15960]	[L1: 0.6422]	10.1+0.1s
+[8000/15960]	[L1: 0.6425]	10.1+0.1s
+[9600/15960]	[L1: 0.6382]	10.9+0.1s
+[11200/15960]	[L1: 0.6378]	11.0+0.1s
+[12800/15960]	[L1: 0.6366]	11.0+0.1s
+[14400/15960]	[L1: 0.6375]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.70s
+
+[Epoch 84]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6349]	11.2+0.5s
+[3200/15960]	[L1: 0.6737]	10.4+0.1s
+[4800/15960]	[L1: 0.6594]	10.4+0.1s
+[6400/15960]	[L1: 0.6588]	10.4+0.1s
+[8000/15960]	[L1: 0.6553]	10.8+0.1s
+[9600/15960]	[L1: 0.6548]	10.2+0.1s
+[11200/15960]	[L1: 0.6505]	9.7+0.1s
+[12800/15960]	[L1: 0.6465]	9.8+0.1s
+[14400/15960]	[L1: 0.6480]	9.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.72s
+
+[Epoch 85]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6295]	11.2+0.6s
+[3200/15960]	[L1: 0.6517]	10.9+0.1s
+[4800/15960]	[L1: 0.6508]	10.8+0.1s
+[6400/15960]	[L1: 0.6420]	10.9+0.1s
+[8000/15960]	[L1: 0.6385]	10.8+0.1s
+[9600/15960]	[L1: 0.6351]	10.8+0.1s
+[11200/15960]	[L1: 0.6372]	10.9+0.1s
+[12800/15960]	[L1: 0.6362]	10.8+0.1s
+[14400/15960]	[L1: 0.6418]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.72s
+
+[Epoch 86]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6307]	11.0+0.6s
+[3200/15960]	[L1: 0.6421]	10.9+0.1s
+[4800/15960]	[L1: 0.6284]	10.8+0.1s
+[6400/15960]	[L1: 0.6279]	10.8+0.1s
+[8000/15960]	[L1: 0.6264]	10.8+0.1s
+[9600/15960]	[L1: 0.6264]	10.9+0.1s
+[11200/15960]	[L1: 0.6235]	10.8+0.1s
+[12800/15960]	[L1: 0.6295]	10.8+0.1s
+[14400/15960]	[L1: 0.6284]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.68s
+
+[Epoch 87]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6711]	11.1+0.6s
+[3200/15960]	[L1: 0.6667]	11.0+0.1s
+[4800/15960]	[L1: 0.6572]	11.0+0.1s
+[6400/15960]	[L1: 0.6520]	11.1+0.1s
+[8000/15960]	[L1: 0.6414]	10.9+0.1s
+[9600/15960]	[L1: 0.6464]	11.0+0.1s
+[11200/15960]	[L1: 0.6416]	11.0+0.1s
+[12800/15960]	[L1: 0.6407]	11.1+0.1s
+[14400/15960]	[L1: 0.6359]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.71s
+
+[Epoch 88]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6316]	11.0+0.5s
+[3200/15960]	[L1: 0.6210]	10.9+0.1s
+[4800/15960]	[L1: 0.6316]	11.1+0.1s
+[6400/15960]	[L1: 0.6380]	11.1+0.1s
+[8000/15960]	[L1: 0.6364]	11.0+0.1s
+[9600/15960]	[L1: 0.6603]	11.0+0.1s
+[11200/15960]	[L1: 0.6606]	10.9+0.1s
+[12800/15960]	[L1: 0.6560]	10.8+0.1s
+[14400/15960]	[L1: 0.6513]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.70s
+
+[Epoch 89]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6126]	10.9+0.5s
+[3200/15960]	[L1: 0.6104]	10.7+0.1s
+[4800/15960]	[L1: 0.6095]	10.7+0.1s
+[6400/15960]	[L1: 0.6124]	11.0+0.1s
+[8000/15960]	[L1: 0.6226]	10.8+0.1s
+[9600/15960]	[L1: 0.6201]	10.9+0.1s
+[11200/15960]	[L1: 0.6285]	10.8+0.1s
+[12800/15960]	[L1: 0.6273]	10.9+0.1s
+[14400/15960]	[L1: 0.6328]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.71s
+
+[Epoch 90]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6101]	10.1+0.5s
+[3200/15960]	[L1: 0.6127]	10.6+0.1s
+[4800/15960]	[L1: 0.6265]	10.9+0.1s
+[6400/15960]	[L1: 0.6354]	10.9+0.1s
+[8000/15960]	[L1: 0.6324]	10.8+0.1s
+[9600/15960]	[L1: 0.6356]	10.9+0.1s
+[11200/15960]	[L1: 0.6357]	10.9+0.1s
+[12800/15960]	[L1: 0.6325]	10.8+0.1s
+[14400/15960]	[L1: 0.6319]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.86s
+
+[Epoch 91]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6518]	11.0+0.5s
+[3200/15960]	[L1: 0.6391]	10.9+0.1s
+[4800/15960]	[L1: 0.6272]	10.9+0.1s
+[6400/15960]	[L1: 0.6268]	10.9+0.1s
+[8000/15960]	[L1: 0.6291]	11.1+0.1s
+[9600/15960]	[L1: 0.6370]	11.0+0.1s
+[11200/15960]	[L1: 0.6336]	11.0+0.1s
+[12800/15960]	[L1: 0.6293]	11.0+0.1s
+[14400/15960]	[L1: 0.6291]	11.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 0.76s
+
+[Epoch 92]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6017]	11.0+0.5s
+[3200/15960]	[L1: 0.6016]	10.9+0.1s
+[4800/15960]	[L1: 0.5979]	10.8+0.1s
+[6400/15960]	[L1: 0.5997]	11.1+0.1s
+[8000/15960]	[L1: 0.6086]	11.0+0.1s
+[9600/15960]	[L1: 0.6140]	11.2+0.1s
+[11200/15960]	[L1: 0.6133]	11.0+0.1s
+[12800/15960]	[L1: 0.6193]	11.1+0.1s
+[14400/15960]	[L1: 0.6180]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 0.71s
+
+[Epoch 93]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6566]	11.1+0.6s
+[3200/15960]	[L1: 0.6352]	11.1+0.1s
+[4800/15960]	[L1: 0.6195]	10.9+0.1s
+[6400/15960]	[L1: 0.6182]	10.8+0.1s
+[8000/15960]	[L1: 0.6218]	11.1+0.1s
+[9600/15960]	[L1: 0.6261]	10.9+0.1s
+[11200/15960]	[L1: 0.6227]	11.0+0.1s
+[12800/15960]	[L1: 0.6198]	10.8+0.1s
+[14400/15960]	[L1: 0.6248]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.67s
+
+[Epoch 94]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6640]	11.1+0.5s
+[3200/15960]	[L1: 0.6544]	10.8+0.1s
+[4800/15960]	[L1: 0.6477]	10.0+0.1s
+[6400/15960]	[L1: 0.6401]	9.5+0.1s
+[8000/15960]	[L1: 0.6395]	10.4+0.1s
+[9600/15960]	[L1: 0.6414]	10.3+0.1s
+[11200/15960]	[L1: 0.6401]	10.1+0.1s
+[12800/15960]	[L1: 0.6375]	10.7+0.1s
+[14400/15960]	[L1: 0.6350]	9.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.71s
+
+[Epoch 95]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6115]	11.1+0.5s
+[3200/15960]	[L1: 0.6385]	10.8+0.1s
+[4800/15960]	[L1: 0.6404]	10.9+0.1s
+[6400/15960]	[L1: 0.6313]	10.7+0.1s
+[8000/15960]	[L1: 0.6238]	10.9+0.1s
+[9600/15960]	[L1: 0.6232]	10.8+0.1s
+[11200/15960]	[L1: 0.6235]	10.8+0.1s
+[12800/15960]	[L1: 0.6207]	10.9+0.1s
+[14400/15960]	[L1: 0.6170]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.71s
+
+[Epoch 96]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6340]	10.9+0.5s
+[3200/15960]	[L1: 0.6283]	10.9+0.1s
+[4800/15960]	[L1: 0.6259]	10.8+0.1s
+[6400/15960]	[L1: 0.6235]	10.9+0.1s
+[8000/15960]	[L1: 0.6234]	9.6+0.1s
+[9600/15960]	[L1: 0.6275]	9.5+0.1s
+[11200/15960]	[L1: 0.6282]	9.8+0.1s
+[12800/15960]	[L1: 0.6265]	9.9+0.1s
+[14400/15960]	[L1: 0.6228]	9.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.73s
+
+[Epoch 97]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6037]	11.3+0.5s
+[3200/15960]	[L1: 0.6267]	10.9+0.1s
+[4800/15960]	[L1: 0.6267]	10.8+0.1s
+[6400/15960]	[L1: 0.6256]	10.7+0.1s
+[8000/15960]	[L1: 0.6236]	10.9+0.1s
+[9600/15960]	[L1: 0.6200]	10.7+0.1s
+[11200/15960]	[L1: 0.6187]	10.8+0.1s
+[12800/15960]	[L1: 0.6226]	10.7+0.1s
+[14400/15960]	[L1: 0.6284]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.69s
+
+[Epoch 98]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6446]	11.1+0.6s
+[3200/15960]	[L1: 0.6287]	11.1+0.1s
+[4800/15960]	[L1: 0.6251]	11.3+0.1s
+[6400/15960]	[L1: 0.6114]	11.3+0.1s
+[8000/15960]	[L1: 0.6129]	11.5+0.1s
+[9600/15960]	[L1: 0.6117]	11.5+0.1s
+[11200/15960]	[L1: 0.6146]	11.0+0.1s
+[12800/15960]	[L1: 0.6174]	11.1+0.1s
+[14400/15960]	[L1: 0.6175]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.70s
+
+[Epoch 99]	Learning rate: 1.00e-4
+[1600/15960]	[L1: 0.6206]	11.5+0.5s
+[3200/15960]	[L1: 0.6240]	11.5+0.1s
+[4800/15960]	[L1: 0.6076]	11.3+0.1s
+[6400/15960]	[L1: 0.6165]	11.0+0.1s
+[8000/15960]	[L1: 0.6113]	11.0+0.1s
+[9600/15960]	[L1: 0.6121]	11.1+0.1s
+[11200/15960]	[L1: 0.6123]	11.0+0.1s
+[12800/15960]	[L1: 0.6124]	10.9+0.1s
+[14400/15960]	[L1: 0.6119]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.72s
+
+[Epoch 100]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5478]	10.9+0.6s
+[3200/15960]	[L1: 0.5429]	10.8+0.1s
+[4800/15960]	[L1: 0.5431]	10.7+0.1s
+[6400/15960]	[L1: 0.5404]	10.9+0.1s
+[8000/15960]	[L1: 0.5423]	10.7+0.1s
+[9600/15960]	[L1: 0.5435]	10.8+0.1s
+[11200/15960]	[L1: 0.5442]	10.8+0.1s
+[12800/15960]	[L1: 0.5421]	10.9+0.1s
+[14400/15960]	[L1: 0.5403]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.72s
+
+[Epoch 101]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5321]	11.3+0.5s
+[3200/15960]	[L1: 0.5394]	11.2+0.1s
+[4800/15960]	[L1: 0.5432]	11.2+0.1s
+[6400/15960]	[L1: 0.5419]	10.6+0.1s
+[8000/15960]	[L1: 0.5448]	11.0+0.1s
+[9600/15960]	[L1: 0.5440]	11.1+0.1s
+[11200/15960]	[L1: 0.5437]	10.5+0.1s
+[12800/15960]	[L1: 0.5442]	10.7+0.1s
+[14400/15960]	[L1: 0.5435]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.69s
+
+[Epoch 102]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5566]	11.0+0.5s
+[3200/15960]	[L1: 0.5492]	10.7+0.1s
+[4800/15960]	[L1: 0.5435]	10.0+0.1s
+[6400/15960]	[L1: 0.5467]	10.8+0.1s
+[8000/15960]	[L1: 0.5458]	10.8+0.1s
+[9600/15960]	[L1: 0.5461]	10.8+0.1s
+[11200/15960]	[L1: 0.5455]	11.1+0.1s
+[12800/15960]	[L1: 0.5453]	11.0+0.1s
+[14400/15960]	[L1: 0.5448]	10.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.72s
+
+[Epoch 103]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5367]	11.0+0.6s
+[3200/15960]	[L1: 0.5425]	10.8+0.1s
+[4800/15960]	[L1: 0.5409]	10.9+0.1s
+[6400/15960]	[L1: 0.5410]	10.9+0.1s
+[8000/15960]	[L1: 0.5397]	10.8+0.1s
+[9600/15960]	[L1: 0.5376]	10.9+0.1s
+[11200/15960]	[L1: 0.5369]	11.0+0.1s
+[12800/15960]	[L1: 0.5367]	10.8+0.1s
+[14400/15960]	[L1: 0.5385]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.87s
+
+[Epoch 104]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5369]	11.1+0.6s
+[3200/15960]	[L1: 0.5559]	10.7+0.1s
+[4800/15960]	[L1: 0.5533]	10.5+0.1s
+[6400/15960]	[L1: 0.5543]	10.8+0.1s
+[8000/15960]	[L1: 0.5514]	10.9+0.1s
+[9600/15960]	[L1: 0.5488]	10.8+0.1s
+[11200/15960]	[L1: 0.5485]	10.9+0.1s
+[12800/15960]	[L1: 0.5458]	10.8+0.1s
+[14400/15960]	[L1: 0.5452]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 0.88s
+
+[Epoch 105]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5335]	11.1+0.5s
+[3200/15960]	[L1: 0.5261]	10.8+0.1s
+[4800/15960]	[L1: 0.5300]	10.9+0.1s
+[6400/15960]	[L1: 0.5294]	11.1+0.1s
+[8000/15960]	[L1: 0.5310]	10.9+0.1s
+[9600/15960]	[L1: 0.5345]	11.0+0.1s
+[11200/15960]	[L1: 0.5361]	11.0+0.1s
+[12800/15960]	[L1: 0.5375]	11.3+0.1s
+[14400/15960]	[L1: 0.5366]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.69s
+
+[Epoch 106]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5321]	11.2+0.6s
+[3200/15960]	[L1: 0.5345]	10.3+0.1s
+[4800/15960]	[L1: 0.5423]	9.7+0.1s
+[6400/15960]	[L1: 0.5387]	9.7+0.1s
+[8000/15960]	[L1: 0.5398]	10.2+0.1s
+[9600/15960]	[L1: 0.5380]	10.4+0.1s
+[11200/15960]	[L1: 0.5389]	10.9+0.1s
+[12800/15960]	[L1: 0.5384]	9.9+0.1s
+[14400/15960]	[L1: 0.5368]	9.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.73s
+
+[Epoch 107]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5249]	10.3+0.6s
+[3200/15960]	[L1: 0.5231]	9.9+0.1s
+[4800/15960]	[L1: 0.5266]	9.5+0.1s
+[6400/15960]	[L1: 0.5248]	9.7+0.1s
+[8000/15960]	[L1: 0.5256]	9.5+0.1s
+[9600/15960]	[L1: 0.5306]	9.7+0.1s
+[11200/15960]	[L1: 0.5320]	9.5+0.1s
+[12800/15960]	[L1: 0.5305]	10.7+0.1s
+[14400/15960]	[L1: 0.5322]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.72s
+
+[Epoch 108]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5355]	11.3+0.6s
+[3200/15960]	[L1: 0.5457]	11.0+0.1s
+[4800/15960]	[L1: 0.5423]	11.0+0.1s
+[6400/15960]	[L1: 0.5418]	11.0+0.1s
+[8000/15960]	[L1: 0.5413]	11.1+0.1s
+[9600/15960]	[L1: 0.5396]	11.0+0.1s
+[11200/15960]	[L1: 0.5412]	11.0+0.1s
+[12800/15960]	[L1: 0.5387]	11.0+0.1s
+[14400/15960]	[L1: 0.5372]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.87s
+
+[Epoch 109]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5288]	11.1+0.6s
+[3200/15960]	[L1: 0.5317]	11.0+0.1s
+[4800/15960]	[L1: 0.5297]	10.9+0.1s
+[6400/15960]	[L1: 0.5331]	10.8+0.1s
+[8000/15960]	[L1: 0.5325]	10.9+0.1s
+[9600/15960]	[L1: 0.5325]	10.9+0.1s
+[11200/15960]	[L1: 0.5375]	10.8+0.1s
+[12800/15960]	[L1: 0.5381]	10.9+0.1s
+[14400/15960]	[L1: 0.5414]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.74s
+
+[Epoch 110]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5412]	10.1+0.6s
+[3200/15960]	[L1: 0.5438]	10.7+0.1s
+[4800/15960]	[L1: 0.5388]	10.6+0.1s
+[6400/15960]	[L1: 0.5340]	10.6+0.1s
+[8000/15960]	[L1: 0.5357]	10.6+0.1s
+[9600/15960]	[L1: 0.5326]	10.8+0.1s
+[11200/15960]	[L1: 0.5297]	10.6+0.1s
+[12800/15960]	[L1: 0.5291]	10.7+0.1s
+[14400/15960]	[L1: 0.5295]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 0.76s
+
+[Epoch 111]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5345]	10.0+0.6s
+[3200/15960]	[L1: 0.5350]	10.7+0.1s
+[4800/15960]	[L1: 0.5387]	10.6+0.1s
+[6400/15960]	[L1: 0.5376]	10.4+0.1s
+[8000/15960]	[L1: 0.5379]	10.0+0.1s
+[9600/15960]	[L1: 0.5383]	9.6+0.1s
+[11200/15960]	[L1: 0.5378]	9.6+0.1s
+[12800/15960]	[L1: 0.5368]	9.7+0.1s
+[14400/15960]	[L1: 0.5367]	9.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.70s
+
+[Epoch 112]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5303]	10.3+0.5s
+[3200/15960]	[L1: 0.5287]	9.9+0.1s
+[4800/15960]	[L1: 0.5222]	10.8+0.1s
+[6400/15960]	[L1: 0.5202]	10.9+0.1s
+[8000/15960]	[L1: 0.5215]	10.2+0.1s
+[9600/15960]	[L1: 0.5236]	10.0+0.1s
+[11200/15960]	[L1: 0.5247]	9.5+0.1s
+[12800/15960]	[L1: 0.5239]	10.1+0.1s
+[14400/15960]	[L1: 0.5255]	9.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 0.76s
+
+[Epoch 113]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5275]	9.7+0.6s
+[3200/15960]	[L1: 0.5295]	10.3+0.1s
+[4800/15960]	[L1: 0.5245]	10.9+0.1s
+[6400/15960]	[L1: 0.5282]	10.1+0.1s
+[8000/15960]	[L1: 0.5287]	10.2+0.1s
+[9600/15960]	[L1: 0.5294]	9.7+0.1s
+[11200/15960]	[L1: 0.5291]	10.6+0.1s
+[12800/15960]	[L1: 0.5261]	9.5+0.1s
+[14400/15960]	[L1: 0.5268]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.73s
+
+[Epoch 114]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5359]	11.1+0.5s
+[3200/15960]	[L1: 0.5319]	11.0+0.1s
+[4800/15960]	[L1: 0.5278]	11.0+0.1s
+[6400/15960]	[L1: 0.5288]	10.9+0.1s
+[8000/15960]	[L1: 0.5325]	10.8+0.1s
+[9600/15960]	[L1: 0.5316]	10.9+0.1s
+[11200/15960]	[L1: 0.5315]	10.9+0.1s
+[12800/15960]	[L1: 0.5287]	10.8+0.1s
+[14400/15960]	[L1: 0.5294]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.87s
+
+[Epoch 115]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5174]	11.1+0.6s
+[3200/15960]	[L1: 0.5300]	10.9+0.1s
+[4800/15960]	[L1: 0.5298]	11.0+0.1s
+[6400/15960]	[L1: 0.5284]	10.9+0.1s
+[8000/15960]	[L1: 0.5264]	10.7+0.1s
+[9600/15960]	[L1: 0.5261]	10.8+0.1s
+[11200/15960]	[L1: 0.5268]	10.9+0.1s
+[12800/15960]	[L1: 0.5267]	10.3+0.1s
+[14400/15960]	[L1: 0.5283]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.73s
+
+[Epoch 116]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5377]	10.9+0.5s
+[3200/15960]	[L1: 0.5293]	10.1+0.1s
+[4800/15960]	[L1: 0.5243]	10.3+0.1s
+[6400/15960]	[L1: 0.5230]	10.7+0.1s
+[8000/15960]	[L1: 0.5276]	10.1+0.1s
+[9600/15960]	[L1: 0.5248]	10.5+0.1s
+[11200/15960]	[L1: 0.5250]	10.3+0.1s
+[12800/15960]	[L1: 0.5260]	10.9+0.1s
+[14400/15960]	[L1: 0.5262]	9.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.71s
+
+[Epoch 117]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5121]	10.2+0.5s
+[3200/15960]	[L1: 0.5263]	9.7+0.1s
+[4800/15960]	[L1: 0.5204]	10.7+0.1s
+[6400/15960]	[L1: 0.5184]	9.9+0.1s
+[8000/15960]	[L1: 0.5210]	10.0+0.1s
+[9600/15960]	[L1: 0.5172]	9.8+0.1s
+[11200/15960]	[L1: 0.5184]	10.1+0.1s
+[12800/15960]	[L1: 0.5195]	10.5+0.1s
+[14400/15960]	[L1: 0.5207]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.70s
+
+[Epoch 118]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5319]	11.2+0.5s
+[3200/15960]	[L1: 0.5336]	11.1+0.1s
+[4800/15960]	[L1: 0.5301]	10.5+0.1s
+[6400/15960]	[L1: 0.5278]	9.7+0.1s
+[8000/15960]	[L1: 0.5282]	10.2+0.1s
+[9600/15960]	[L1: 0.5277]	11.1+0.1s
+[11200/15960]	[L1: 0.5276]	10.9+0.1s
+[12800/15960]	[L1: 0.5260]	10.9+0.1s
+[14400/15960]	[L1: 0.5262]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.92s
+
+[Epoch 119]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5276]	11.3+0.5s
+[3200/15960]	[L1: 0.5378]	11.1+0.1s
+[4800/15960]	[L1: 0.5295]	10.7+0.1s
+[6400/15960]	[L1: 0.5278]	10.4+0.1s
+[8000/15960]	[L1: 0.5251]	11.2+0.1s
+[9600/15960]	[L1: 0.5250]	11.0+0.1s
+[11200/15960]	[L1: 0.5263]	11.2+0.1s
+[12800/15960]	[L1: 0.5236]	11.0+0.1s
+[14400/15960]	[L1: 0.5242]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.75s
+
+[Epoch 120]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5126]	11.0+0.5s
+[3200/15960]	[L1: 0.5157]	10.7+0.1s
+[4800/15960]	[L1: 0.5131]	10.9+0.1s
+[6400/15960]	[L1: 0.5148]	10.3+0.1s
+[8000/15960]	[L1: 0.5173]	9.9+0.1s
+[9600/15960]	[L1: 0.5183]	10.9+0.1s
+[11200/15960]	[L1: 0.5208]	11.0+0.1s
+[12800/15960]	[L1: 0.5216]	10.6+0.1s
+[14400/15960]	[L1: 0.5207]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.71s
+
+[Epoch 121]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5296]	11.3+0.6s
+[3200/15960]	[L1: 0.5290]	11.2+0.1s
+[4800/15960]	[L1: 0.5312]	11.0+0.1s
+[6400/15960]	[L1: 0.5306]	11.1+0.1s
+[8000/15960]	[L1: 0.5309]	11.0+0.1s
+[9600/15960]	[L1: 0.5270]	10.9+0.1s
+[11200/15960]	[L1: 0.5249]	10.9+0.1s
+[12800/15960]	[L1: 0.5226]	10.8+0.1s
+[14400/15960]	[L1: 0.5247]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.71s
+
+[Epoch 122]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5183]	11.1+0.5s
+[3200/15960]	[L1: 0.5191]	10.5+0.1s
+[4800/15960]	[L1: 0.5230]	10.8+0.1s
+[6400/15960]	[L1: 0.5218]	10.9+0.1s
+[8000/15960]	[L1: 0.5222]	11.1+0.1s
+[9600/15960]	[L1: 0.5229]	10.2+0.1s
+[11200/15960]	[L1: 0.5245]	10.0+0.1s
+[12800/15960]	[L1: 0.5207]	9.8+0.1s
+[14400/15960]	[L1: 0.5223]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 0.76s
+
+[Epoch 123]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5385]	11.2+0.6s
+[3200/15960]	[L1: 0.5305]	10.8+0.1s
+[4800/15960]	[L1: 0.5322]	11.0+0.1s
+[6400/15960]	[L1: 0.5286]	11.0+0.1s
+[8000/15960]	[L1: 0.5241]	10.8+0.1s
+[9600/15960]	[L1: 0.5217]	10.6+0.1s
+[11200/15960]	[L1: 0.5195]	10.6+0.1s
+[12800/15960]	[L1: 0.5205]	10.0+0.1s
+[14400/15960]	[L1: 0.5211]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 0.76s
+
+[Epoch 124]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5289]	10.8+0.5s
+[3200/15960]	[L1: 0.5212]	10.5+0.1s
+[4800/15960]	[L1: 0.5157]	10.3+0.1s
+[6400/15960]	[L1: 0.5126]	10.8+0.1s
+[8000/15960]	[L1: 0.5135]	11.0+0.1s
+[9600/15960]	[L1: 0.5165]	10.8+0.1s
+[11200/15960]	[L1: 0.5159]	10.4+0.1s
+[12800/15960]	[L1: 0.5168]	10.4+0.1s
+[14400/15960]	[L1: 0.5186]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.71s
+
+[Epoch 125]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4989]	11.3+0.6s
+[3200/15960]	[L1: 0.5120]	11.0+0.1s
+[4800/15960]	[L1: 0.5146]	11.1+0.1s
+[6400/15960]	[L1: 0.5169]	11.1+0.1s
+[8000/15960]	[L1: 0.5205]	11.0+0.1s
+[9600/15960]	[L1: 0.5246]	11.1+0.1s
+[11200/15960]	[L1: 0.5235]	11.1+0.1s
+[12800/15960]	[L1: 0.5249]	10.9+0.1s
+[14400/15960]	[L1: 0.5233]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.69s
+
+[Epoch 126]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4988]	11.2+0.5s
+[3200/15960]	[L1: 0.5152]	10.9+0.1s
+[4800/15960]	[L1: 0.5135]	11.1+0.1s
+[6400/15960]	[L1: 0.5177]	11.0+0.1s
+[8000/15960]	[L1: 0.5185]	11.1+0.1s
+[9600/15960]	[L1: 0.5189]	11.0+0.1s
+[11200/15960]	[L1: 0.5187]	9.9+0.1s
+[12800/15960]	[L1: 0.5186]	9.9+0.1s
+[14400/15960]	[L1: 0.5169]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.75s
+
+[Epoch 127]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5490]	11.1+0.5s
+[3200/15960]	[L1: 0.5308]	10.8+0.1s
+[4800/15960]	[L1: 0.5308]	10.8+0.1s
+[6400/15960]	[L1: 0.5290]	10.9+0.1s
+[8000/15960]	[L1: 0.5256]	10.6+0.1s
+[9600/15960]	[L1: 0.5240]	10.9+0.1s
+[11200/15960]	[L1: 0.5240]	10.8+0.1s
+[12800/15960]	[L1: 0.5232]	10.9+0.1s
+[14400/15960]	[L1: 0.5237]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.85s
+
+[Epoch 128]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5256]	11.2+0.6s
+[3200/15960]	[L1: 0.5197]	11.0+0.1s
+[4800/15960]	[L1: 0.5168]	9.8+0.1s
+[6400/15960]	[L1: 0.5150]	9.5+0.1s
+[8000/15960]	[L1: 0.5117]	9.8+0.1s
+[9600/15960]	[L1: 0.5119]	10.0+0.1s
+[11200/15960]	[L1: 0.5112]	10.6+0.1s
+[12800/15960]	[L1: 0.5124]	10.8+0.1s
+[14400/15960]	[L1: 0.5116]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.69s
+
+[Epoch 129]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5270]	10.8+0.5s
+[3200/15960]	[L1: 0.5228]	11.0+0.1s
+[4800/15960]	[L1: 0.5229]	11.1+0.1s
+[6400/15960]	[L1: 0.5226]	10.3+0.1s
+[8000/15960]	[L1: 0.5227]	10.2+0.1s
+[9600/15960]	[L1: 0.5249]	10.5+0.1s
+[11200/15960]	[L1: 0.5245]	10.6+0.1s
+[12800/15960]	[L1: 0.5212]	10.7+0.1s
+[14400/15960]	[L1: 0.5212]	10.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.71s
+
+[Epoch 130]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5068]	10.9+0.6s
+[3200/15960]	[L1: 0.5194]	11.0+0.1s
+[4800/15960]	[L1: 0.5154]	10.9+0.1s
+[6400/15960]	[L1: 0.5098]	10.8+0.1s
+[8000/15960]	[L1: 0.5076]	11.0+0.1s
+[9600/15960]	[L1: 0.5094]	10.8+0.1s
+[11200/15960]	[L1: 0.5109]	10.7+0.1s
+[12800/15960]	[L1: 0.5115]	10.8+0.1s
+[14400/15960]	[L1: 0.5115]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.30s
+
+Saving...
+Total: 1.72s
+
+[Epoch 131]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5046]	10.3+0.6s
+[3200/15960]	[L1: 0.5201]	10.9+0.1s
+[4800/15960]	[L1: 0.5202]	10.8+0.1s
+[6400/15960]	[L1: 0.5278]	10.9+0.1s
+[8000/15960]	[L1: 0.5270]	10.7+0.1s
+[9600/15960]	[L1: 0.5245]	9.7+0.1s
+[11200/15960]	[L1: 0.5233]	9.6+0.1s
+[12800/15960]	[L1: 0.5232]	9.5+0.1s
+[14400/15960]	[L1: 0.5200]	9.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.69s
+
+[Epoch 132]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5118]	10.3+0.5s
+[3200/15960]	[L1: 0.5205]	10.2+0.1s
+[4800/15960]	[L1: 0.5192]	10.3+0.1s
+[6400/15960]	[L1: 0.5181]	10.3+0.1s
+[8000/15960]	[L1: 0.5150]	10.1+0.1s
+[9600/15960]	[L1: 0.5138]	10.0+0.1s
+[11200/15960]	[L1: 0.5171]	10.2+0.1s
+[12800/15960]	[L1: 0.5188]	10.3+0.1s
+[14400/15960]	[L1: 0.5196]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.71s
+
+[Epoch 133]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5051]	11.4+0.6s
+[3200/15960]	[L1: 0.5080]	11.0+0.1s
+[4800/15960]	[L1: 0.5117]	11.1+0.1s
+[6400/15960]	[L1: 0.5174]	10.7+0.1s
+[8000/15960]	[L1: 0.5171]	10.9+0.1s
+[9600/15960]	[L1: 0.5180]	10.9+0.1s
+[11200/15960]	[L1: 0.5164]	10.8+0.1s
+[12800/15960]	[L1: 0.5177]	10.9+0.1s
+[14400/15960]	[L1: 0.5175]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.76s
+
+[Epoch 134]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5063]	11.3+0.6s
+[3200/15960]	[L1: 0.5048]	11.0+0.1s
+[4800/15960]	[L1: 0.5088]	11.0+0.1s
+[6400/15960]	[L1: 0.5106]	11.0+0.1s
+[8000/15960]	[L1: 0.5082]	11.1+0.1s
+[9600/15960]	[L1: 0.5069]	10.9+0.1s
+[11200/15960]	[L1: 0.5085]	10.8+0.1s
+[12800/15960]	[L1: 0.5061]	11.2+0.1s
+[14400/15960]	[L1: 0.5082]	11.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.71s
+
+[Epoch 135]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5339]	11.0+0.5s
+[3200/15960]	[L1: 0.5202]	11.0+0.1s
+[4800/15960]	[L1: 0.5193]	10.5+0.1s
+[6400/15960]	[L1: 0.5206]	10.7+0.1s
+[8000/15960]	[L1: 0.5205]	11.0+0.1s
+[9600/15960]	[L1: 0.5194]	11.0+0.1s
+[11200/15960]	[L1: 0.5164]	11.1+0.1s
+[12800/15960]	[L1: 0.5144]	11.0+0.1s
+[14400/15960]	[L1: 0.5148]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 0.74s
+
+[Epoch 136]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5009]	10.5+0.6s
+[3200/15960]	[L1: 0.5074]	11.1+0.1s
+[4800/15960]	[L1: 0.5056]	10.7+0.1s
+[6400/15960]	[L1: 0.5133]	11.0+0.1s
+[8000/15960]	[L1: 0.5156]	11.1+0.1s
+[9600/15960]	[L1: 0.5130]	11.0+0.1s
+[11200/15960]	[L1: 0.5132]	11.2+0.1s
+[12800/15960]	[L1: 0.5138]	11.0+0.1s
+[14400/15960]	[L1: 0.5117]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.73s
+
+[Epoch 137]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5160]	11.0+0.6s
+[3200/15960]	[L1: 0.5079]	11.0+0.1s
+[4800/15960]	[L1: 0.5115]	10.8+0.1s
+[6400/15960]	[L1: 0.5144]	11.0+0.1s
+[8000/15960]	[L1: 0.5154]	10.8+0.1s
+[9600/15960]	[L1: 0.5146]	10.8+0.1s
+[11200/15960]	[L1: 0.5136]	10.9+0.1s
+[12800/15960]	[L1: 0.5130]	10.8+0.1s
+[14400/15960]	[L1: 0.5120]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.74s
+
+[Epoch 138]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5298]	11.3+0.6s
+[3200/15960]	[L1: 0.5150]	11.1+0.1s
+[4800/15960]	[L1: 0.5102]	11.0+0.1s
+[6400/15960]	[L1: 0.5135]	11.1+0.1s
+[8000/15960]	[L1: 0.5117]	10.9+0.1s
+[9600/15960]	[L1: 0.5141]	11.1+0.1s
+[11200/15960]	[L1: 0.5148]	11.1+0.1s
+[12800/15960]	[L1: 0.5121]	10.9+0.1s
+[14400/15960]	[L1: 0.5113]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.74s
+
+[Epoch 139]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5272]	10.9+0.5s
+[3200/15960]	[L1: 0.5157]	10.9+0.1s
+[4800/15960]	[L1: 0.5087]	10.8+0.1s
+[6400/15960]	[L1: 0.5095]	10.8+0.1s
+[8000/15960]	[L1: 0.5091]	10.7+0.1s
+[9600/15960]	[L1: 0.5071]	10.4+0.1s
+[11200/15960]	[L1: 0.5065]	10.8+0.1s
+[12800/15960]	[L1: 0.5086]	10.7+0.1s
+[14400/15960]	[L1: 0.5069]	10.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.73s
+
+[Epoch 140]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5373]	11.0+0.6s
+[3200/15960]	[L1: 0.5365]	10.9+0.1s
+[4800/15960]	[L1: 0.5367]	10.8+0.1s
+[6400/15960]	[L1: 0.5248]	10.8+0.1s
+[8000/15960]	[L1: 0.5213]	10.7+0.1s
+[9600/15960]	[L1: 0.5179]	10.8+0.1s
+[11200/15960]	[L1: 0.5179]	10.9+0.1s
+[12800/15960]	[L1: 0.5155]	10.7+0.1s
+[14400/15960]	[L1: 0.5144]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.72s
+
+[Epoch 141]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5132]	11.0+0.6s
+[3200/15960]	[L1: 0.5032]	11.0+0.1s
+[4800/15960]	[L1: 0.5076]	10.8+0.1s
+[6400/15960]	[L1: 0.5089]	10.9+0.1s
+[8000/15960]	[L1: 0.5112]	10.7+0.1s
+[9600/15960]	[L1: 0.5119]	10.8+0.1s
+[11200/15960]	[L1: 0.5098]	10.9+0.1s
+[12800/15960]	[L1: 0.5110]	10.8+0.1s
+[14400/15960]	[L1: 0.5106]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.75s
+
+[Epoch 142]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5054]	11.4+0.6s
+[3200/15960]	[L1: 0.5048]	11.3+0.1s
+[4800/15960]	[L1: 0.5153]	11.1+0.1s
+[6400/15960]	[L1: 0.5123]	11.1+0.1s
+[8000/15960]	[L1: 0.5115]	11.0+0.1s
+[9600/15960]	[L1: 0.5114]	11.1+0.1s
+[11200/15960]	[L1: 0.5132]	11.1+0.1s
+[12800/15960]	[L1: 0.5115]	11.0+0.1s
+[14400/15960]	[L1: 0.5127]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 0.76s
+
+[Epoch 143]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5081]	11.2+0.5s
+[3200/15960]	[L1: 0.5035]	11.1+0.1s
+[4800/15960]	[L1: 0.5041]	10.1+0.1s
+[6400/15960]	[L1: 0.5065]	10.9+0.1s
+[8000/15960]	[L1: 0.5064]	10.0+0.1s
+[9600/15960]	[L1: 0.5056]	10.0+0.1s
+[11200/15960]	[L1: 0.5048]	10.1+0.1s
+[12800/15960]	[L1: 0.5045]	9.9+0.1s
+[14400/15960]	[L1: 0.5014]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.73s
+
+[Epoch 144]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5143]	11.3+0.6s
+[3200/15960]	[L1: 0.5185]	11.1+0.1s
+[4800/15960]	[L1: 0.5144]	11.0+0.1s
+[6400/15960]	[L1: 0.5104]	11.2+0.1s
+[8000/15960]	[L1: 0.5086]	11.1+0.1s
+[9600/15960]	[L1: 0.5069]	10.1+0.1s
+[11200/15960]	[L1: 0.5051]	10.6+0.1s
+[12800/15960]	[L1: 0.5076]	10.7+0.1s
+[14400/15960]	[L1: 0.5107]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.76s
+
+[Epoch 145]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4996]	11.0+0.5s
+[3200/15960]	[L1: 0.5025]	10.8+0.1s
+[4800/15960]	[L1: 0.5111]	10.6+0.1s
+[6400/15960]	[L1: 0.5177]	10.6+0.1s
+[8000/15960]	[L1: 0.5145]	10.5+0.1s
+[9600/15960]	[L1: 0.5145]	10.5+0.1s
+[11200/15960]	[L1: 0.5120]	10.6+0.1s
+[12800/15960]	[L1: 0.5105]	10.3+0.1s
+[14400/15960]	[L1: 0.5097]	10.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.71s
+
+[Epoch 146]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5107]	11.0+0.6s
+[3200/15960]	[L1: 0.5102]	10.8+0.1s
+[4800/15960]	[L1: 0.5069]	10.6+0.1s
+[6400/15960]	[L1: 0.5097]	10.8+0.1s
+[8000/15960]	[L1: 0.5108]	10.6+0.1s
+[9600/15960]	[L1: 0.5120]	10.8+0.1s
+[11200/15960]	[L1: 0.5127]	10.8+0.1s
+[12800/15960]	[L1: 0.5109]	10.6+0.1s
+[14400/15960]	[L1: 0.5114]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.73s
+
+[Epoch 147]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5001]	10.9+0.6s
+[3200/15960]	[L1: 0.5026]	10.9+0.1s
+[4800/15960]	[L1: 0.5039]	10.7+0.1s
+[6400/15960]	[L1: 0.5091]	10.7+0.1s
+[8000/15960]	[L1: 0.5055]	10.9+0.1s
+[9600/15960]	[L1: 0.5042]	10.8+0.1s
+[11200/15960]	[L1: 0.5040]	10.9+0.1s
+[12800/15960]	[L1: 0.5033]	10.7+0.1s
+[14400/15960]	[L1: 0.5033]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.71s
+
+[Epoch 148]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5122]	11.2+0.6s
+[3200/15960]	[L1: 0.5015]	10.8+0.1s
+[4800/15960]	[L1: 0.5065]	11.0+0.1s
+[6400/15960]	[L1: 0.5060]	10.8+0.1s
+[8000/15960]	[L1: 0.5070]	10.9+0.1s
+[9600/15960]	[L1: 0.5077]	11.0+0.1s
+[11200/15960]	[L1: 0.5047]	10.5+0.1s
+[12800/15960]	[L1: 0.5050]	11.0+0.1s
+[14400/15960]	[L1: 0.5057]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.74s
+
+[Epoch 149]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5068]	11.0+0.6s
+[3200/15960]	[L1: 0.5053]	10.7+0.1s
+[4800/15960]	[L1: 0.5118]	10.8+0.1s
+[6400/15960]	[L1: 0.5032]	10.9+0.1s
+[8000/15960]	[L1: 0.5050]	10.8+0.1s
+[9600/15960]	[L1: 0.5067]	10.8+0.1s
+[11200/15960]	[L1: 0.5069]	10.9+0.1s
+[12800/15960]	[L1: 0.5057]	11.1+0.1s
+[14400/15960]	[L1: 0.5060]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 0.77s
+
+[Epoch 150]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4976]	11.2+0.6s
+[3200/15960]	[L1: 0.5022]	11.0+0.1s
+[4800/15960]	[L1: 0.5024]	10.8+0.1s
+[6400/15960]	[L1: 0.5051]	11.0+0.1s
+[8000/15960]	[L1: 0.5063]	10.8+0.1s
+[9600/15960]	[L1: 0.5081]	11.1+0.1s
+[11200/15960]	[L1: 0.5066]	10.9+0.1s
+[12800/15960]	[L1: 0.5029]	11.0+0.1s
+[14400/15960]	[L1: 0.5063]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.88s
+
+[Epoch 151]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5064]	11.1+0.5s
+[3200/15960]	[L1: 0.5123]	11.1+0.1s
+[4800/15960]	[L1: 0.5164]	10.9+0.1s
+[6400/15960]	[L1: 0.5106]	10.9+0.1s
+[8000/15960]	[L1: 0.5053]	10.9+0.1s
+[9600/15960]	[L1: 0.5055]	10.8+0.1s
+[11200/15960]	[L1: 0.5045]	10.9+0.1s
+[12800/15960]	[L1: 0.5047]	10.9+0.1s
+[14400/15960]	[L1: 0.5053]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 0.73s
+
+[Epoch 152]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5099]	11.1+0.6s
+[3200/15960]	[L1: 0.5088]	9.6+0.1s
+[4800/15960]	[L1: 0.5095]	11.0+0.1s
+[6400/15960]	[L1: 0.5115]	11.0+0.1s
+[8000/15960]	[L1: 0.5124]	10.7+0.1s
+[9600/15960]	[L1: 0.5116]	10.7+0.1s
+[11200/15960]	[L1: 0.5098]	10.9+0.1s
+[12800/15960]	[L1: 0.5080]	10.7+0.1s
+[14400/15960]	[L1: 0.5076]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.75s
+
+[Epoch 153]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4963]	11.2+0.5s
+[3200/15960]	[L1: 0.5025]	10.9+0.1s
+[4800/15960]	[L1: 0.5071]	11.0+0.1s
+[6400/15960]	[L1: 0.5106]	10.9+0.1s
+[8000/15960]	[L1: 0.5081]	10.9+0.1s
+[9600/15960]	[L1: 0.5062]	10.6+0.1s
+[11200/15960]	[L1: 0.5047]	11.0+0.1s
+[12800/15960]	[L1: 0.5069]	10.9+0.1s
+[14400/15960]	[L1: 0.5054]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.73s
+
+[Epoch 154]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5099]	10.7+0.6s
+[3200/15960]	[L1: 0.5137]	9.8+0.1s
+[4800/15960]	[L1: 0.5075]	10.2+0.1s
+[6400/15960]	[L1: 0.5075]	10.7+0.1s
+[8000/15960]	[L1: 0.5058]	10.8+0.1s
+[9600/15960]	[L1: 0.5085]	10.9+0.1s
+[11200/15960]	[L1: 0.5072]	10.7+0.1s
+[12800/15960]	[L1: 0.5060]	9.8+0.1s
+[14400/15960]	[L1: 0.5058]	10.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.73s
+
+[Epoch 155]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4884]	11.2+0.5s
+[3200/15960]	[L1: 0.5134]	11.0+0.1s
+[4800/15960]	[L1: 0.5180]	10.9+0.1s
+[6400/15960]	[L1: 0.5208]	11.0+0.1s
+[8000/15960]	[L1: 0.5158]	10.9+0.1s
+[9600/15960]	[L1: 0.5119]	10.7+0.1s
+[11200/15960]	[L1: 0.5110]	10.8+0.1s
+[12800/15960]	[L1: 0.5083]	10.8+0.1s
+[14400/15960]	[L1: 0.5091]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.73s
+
+[Epoch 156]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4921]	11.0+0.6s
+[3200/15960]	[L1: 0.4955]	10.9+0.1s
+[4800/15960]	[L1: 0.4984]	10.8+0.1s
+[6400/15960]	[L1: 0.4942]	10.9+0.1s
+[8000/15960]	[L1: 0.4973]	10.8+0.1s
+[9600/15960]	[L1: 0.4996]	10.8+0.1s
+[11200/15960]	[L1: 0.5049]	10.9+0.1s
+[12800/15960]	[L1: 0.5061]	10.8+0.1s
+[14400/15960]	[L1: 0.5090]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.73s
+
+[Epoch 157]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5200]	10.1+0.5s
+[3200/15960]	[L1: 0.5155]	10.6+0.1s
+[4800/15960]	[L1: 0.5082]	10.9+0.1s
+[6400/15960]	[L1: 0.5056]	10.2+0.1s
+[8000/15960]	[L1: 0.5013]	10.3+0.1s
+[9600/15960]	[L1: 0.5046]	10.6+0.1s
+[11200/15960]	[L1: 0.5039]	10.7+0.1s
+[12800/15960]	[L1: 0.5035]	10.8+0.1s
+[14400/15960]	[L1: 0.5035]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.74s
+
+[Epoch 158]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4964]	11.0+0.6s
+[3200/15960]	[L1: 0.5016]	10.7+0.1s
+[4800/15960]	[L1: 0.4980]	10.8+0.1s
+[6400/15960]	[L1: 0.4937]	10.9+0.1s
+[8000/15960]	[L1: 0.4900]	11.0+0.1s
+[9600/15960]	[L1: 0.4920]	10.3+0.1s
+[11200/15960]	[L1: 0.4932]	9.5+0.1s
+[12800/15960]	[L1: 0.4930]	10.3+0.1s
+[14400/15960]	[L1: 0.4921]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.75s
+
+[Epoch 159]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5079]	11.1+0.6s
+[3200/15960]	[L1: 0.5092]	10.8+0.1s
+[4800/15960]	[L1: 0.5069]	10.9+0.1s
+[6400/15960]	[L1: 0.5065]	10.8+0.1s
+[8000/15960]	[L1: 0.5035]	10.8+0.1s
+[9600/15960]	[L1: 0.5047]	10.9+0.1s
+[11200/15960]	[L1: 0.5039]	10.8+0.1s
+[12800/15960]	[L1: 0.5038]	10.9+0.1s
+[14400/15960]	[L1: 0.5017]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.71s
+
+[Epoch 160]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5003]	11.1+0.5s
+[3200/15960]	[L1: 0.4929]	11.0+0.1s
+[4800/15960]	[L1: 0.4942]	11.0+0.1s
+[6400/15960]	[L1: 0.4946]	11.1+0.1s
+[8000/15960]	[L1: 0.4942]	11.0+0.1s
+[9600/15960]	[L1: 0.4937]	11.0+0.1s
+[11200/15960]	[L1: 0.4949]	11.0+0.1s
+[12800/15960]	[L1: 0.4960]	11.1+0.1s
+[14400/15960]	[L1: 0.4966]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 0.78s
+
+[Epoch 161]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5205]	11.3+0.6s
+[3200/15960]	[L1: 0.5143]	11.0+0.1s
+[4800/15960]	[L1: 0.5063]	10.9+0.1s
+[6400/15960]	[L1: 0.5039]	11.1+0.1s
+[8000/15960]	[L1: 0.5025]	10.9+0.1s
+[9600/15960]	[L1: 0.5017]	11.1+0.1s
+[11200/15960]	[L1: 0.5003]	11.0+0.1s
+[12800/15960]	[L1: 0.5003]	11.1+0.1s
+[14400/15960]	[L1: 0.5004]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 2.06s
+
+[Epoch 162]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5100]	10.5+0.5s
+[3200/15960]	[L1: 0.5004]	10.8+0.1s
+[4800/15960]	[L1: 0.4985]	11.0+0.1s
+[6400/15960]	[L1: 0.5016]	9.9+0.1s
+[8000/15960]	[L1: 0.5009]	10.6+0.1s
+[9600/15960]	[L1: 0.5008]	9.7+0.1s
+[11200/15960]	[L1: 0.4994]	9.8+0.1s
+[12800/15960]	[L1: 0.4987]	10.3+0.1s
+[14400/15960]	[L1: 0.5013]	10.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.74s
+
+[Epoch 163]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4988]	10.1+0.5s
+[3200/15960]	[L1: 0.4982]	10.1+0.1s
+[4800/15960]	[L1: 0.4968]	9.9+0.1s
+[6400/15960]	[L1: 0.4949]	10.0+0.1s
+[8000/15960]	[L1: 0.4947]	9.9+0.1s
+[9600/15960]	[L1: 0.4978]	9.9+0.1s
+[11200/15960]	[L1: 0.4973]	9.9+0.1s
+[12800/15960]	[L1: 0.4976]	10.2+0.1s
+[14400/15960]	[L1: 0.4979]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 0.75s
+
+[Epoch 164]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4852]	11.2+0.5s
+[3200/15960]	[L1: 0.4864]	10.8+0.1s
+[4800/15960]	[L1: 0.4892]	10.4+0.1s
+[6400/15960]	[L1: 0.4985]	10.6+0.1s
+[8000/15960]	[L1: 0.4972]	10.2+0.1s
+[9600/15960]	[L1: 0.4960]	10.4+0.1s
+[11200/15960]	[L1: 0.4959]	10.6+0.1s
+[12800/15960]	[L1: 0.4949]	11.1+0.1s
+[14400/15960]	[L1: 0.4946]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.73s
+
+[Epoch 165]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5213]	11.1+0.7s
+[3200/15960]	[L1: 0.5066]	11.2+0.1s
+[4800/15960]	[L1: 0.5004]	10.8+0.1s
+[6400/15960]	[L1: 0.5011]	11.0+0.1s
+[8000/15960]	[L1: 0.5003]	9.9+0.1s
+[9600/15960]	[L1: 0.5031]	10.5+0.1s
+[11200/15960]	[L1: 0.5008]	9.6+0.1s
+[12800/15960]	[L1: 0.5009]	10.2+0.1s
+[14400/15960]	[L1: 0.4991]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.70s
+
+[Epoch 166]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4854]	11.2+0.6s
+[3200/15960]	[L1: 0.4989]	10.9+0.1s
+[4800/15960]	[L1: 0.4983]	10.8+0.1s
+[6400/15960]	[L1: 0.4931]	11.0+0.1s
+[8000/15960]	[L1: 0.4908]	11.0+0.1s
+[9600/15960]	[L1: 0.4933]	10.8+0.1s
+[11200/15960]	[L1: 0.4936]	10.9+0.1s
+[12800/15960]	[L1: 0.4955]	10.8+0.1s
+[14400/15960]	[L1: 0.4986]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.70s
+
+[Epoch 167]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4973]	11.1+0.6s
+[3200/15960]	[L1: 0.5021]	10.7+0.1s
+[4800/15960]	[L1: 0.5016]	9.9+0.1s
+[6400/15960]	[L1: 0.5034]	10.6+0.1s
+[8000/15960]	[L1: 0.4989]	10.0+0.1s
+[9600/15960]	[L1: 0.4995]	10.8+0.1s
+[11200/15960]	[L1: 0.4982]	10.7+0.1s
+[12800/15960]	[L1: 0.4986]	10.8+0.1s
+[14400/15960]	[L1: 0.4985]	10.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.72s
+
+[Epoch 168]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5014]	10.9+0.5s
+[3200/15960]	[L1: 0.4992]	10.6+0.1s
+[4800/15960]	[L1: 0.4961]	10.5+0.1s
+[6400/15960]	[L1: 0.4950]	10.6+0.1s
+[8000/15960]	[L1: 0.4988]	10.2+0.1s
+[9600/15960]	[L1: 0.4980]	10.3+0.1s
+[11200/15960]	[L1: 0.4986]	10.3+0.1s
+[12800/15960]	[L1: 0.4998]	10.2+0.1s
+[14400/15960]	[L1: 0.5008]	9.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.73s
+
+[Epoch 169]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4879]	10.6+0.7s
+[3200/15960]	[L1: 0.4926]	10.8+0.1s
+[4800/15960]	[L1: 0.4982]	9.7+0.1s
+[6400/15960]	[L1: 0.4950]	10.9+0.1s
+[8000/15960]	[L1: 0.4917]	10.8+0.1s
+[9600/15960]	[L1: 0.4953]	10.8+0.1s
+[11200/15960]	[L1: 0.4968]	10.9+0.1s
+[12800/15960]	[L1: 0.4949]	10.8+0.1s
+[14400/15960]	[L1: 0.4950]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.84s
+
+[Epoch 170]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4944]	11.3+0.6s
+[3200/15960]	[L1: 0.5034]	10.9+0.1s
+[4800/15960]	[L1: 0.5050]	10.8+0.1s
+[6400/15960]	[L1: 0.5002]	10.9+0.1s
+[8000/15960]	[L1: 0.4972]	10.8+0.1s
+[9600/15960]	[L1: 0.4979]	11.0+0.1s
+[11200/15960]	[L1: 0.4966]	10.9+0.1s
+[12800/15960]	[L1: 0.4986]	10.8+0.1s
+[14400/15960]	[L1: 0.4989]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.72s
+
+[Epoch 171]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5179]	11.0+0.5s
+[3200/15960]	[L1: 0.5033]	11.1+0.1s
+[4800/15960]	[L1: 0.5042]	10.9+0.1s
+[6400/15960]	[L1: 0.5052]	10.9+0.1s
+[8000/15960]	[L1: 0.5046]	11.1+0.1s
+[9600/15960]	[L1: 0.5028]	10.9+0.1s
+[11200/15960]	[L1: 0.5019]	11.0+0.1s
+[12800/15960]	[L1: 0.5019]	10.9+0.1s
+[14400/15960]	[L1: 0.5025]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.71s
+
+[Epoch 172]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5095]	10.5+0.6s
+[3200/15960]	[L1: 0.4944]	10.8+0.1s
+[4800/15960]	[L1: 0.4961]	11.0+0.1s
+[6400/15960]	[L1: 0.4936]	11.0+0.1s
+[8000/15960]	[L1: 0.4962]	10.8+0.1s
+[9600/15960]	[L1: 0.4998]	11.0+0.1s
+[11200/15960]	[L1: 0.4977]	10.9+0.1s
+[12800/15960]	[L1: 0.4987]	10.7+0.1s
+[14400/15960]	[L1: 0.4979]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 0.75s
+
+[Epoch 173]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4998]	11.1+0.6s
+[3200/15960]	[L1: 0.5062]	10.9+0.1s
+[4800/15960]	[L1: 0.5046]	10.8+0.1s
+[6400/15960]	[L1: 0.5003]	10.5+0.1s
+[8000/15960]	[L1: 0.4996]	10.8+0.1s
+[9600/15960]	[L1: 0.4974]	10.8+0.1s
+[11200/15960]	[L1: 0.4961]	11.0+0.1s
+[12800/15960]	[L1: 0.4959]	10.9+0.1s
+[14400/15960]	[L1: 0.4958]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.71s
+
+[Epoch 174]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4928]	10.1+0.5s
+[3200/15960]	[L1: 0.5069]	10.7+0.1s
+[4800/15960]	[L1: 0.5034]	10.2+0.1s
+[6400/15960]	[L1: 0.5020]	11.0+0.1s
+[8000/15960]	[L1: 0.4994]	10.9+0.1s
+[9600/15960]	[L1: 0.4978]	11.0+0.1s
+[11200/15960]	[L1: 0.4973]	10.9+0.1s
+[12800/15960]	[L1: 0.4969]	11.0+0.1s
+[14400/15960]	[L1: 0.4959]	10.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.82s
+
+[Epoch 175]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4879]	10.6+0.5s
+[3200/15960]	[L1: 0.4969]	10.1+0.1s
+[4800/15960]	[L1: 0.4952]	9.6+0.1s
+[6400/15960]	[L1: 0.4957]	9.7+0.1s
+[8000/15960]	[L1: 0.4944]	9.7+0.1s
+[9600/15960]	[L1: 0.4919]	9.6+0.1s
+[11200/15960]	[L1: 0.4918]	9.7+0.1s
+[12800/15960]	[L1: 0.4945]	9.9+0.1s
+[14400/15960]	[L1: 0.4957]	9.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 0.80s
+
+[Epoch 176]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5110]	10.2+0.5s
+[3200/15960]	[L1: 0.4939]	9.6+0.1s
+[4800/15960]	[L1: 0.4957]	9.8+0.1s
+[6400/15960]	[L1: 0.4957]	9.7+0.1s
+[8000/15960]	[L1: 0.4968]	9.5+0.1s
+[9600/15960]	[L1: 0.4959]	10.7+0.1s
+[11200/15960]	[L1: 0.4957]	10.8+0.1s
+[12800/15960]	[L1: 0.4961]	10.7+0.1s
+[14400/15960]	[L1: 0.4945]	9.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.74s
+
+[Epoch 177]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4851]	11.1+0.5s
+[3200/15960]	[L1: 0.4884]	10.8+0.1s
+[4800/15960]	[L1: 0.4917]	10.9+0.1s
+[6400/15960]	[L1: 0.4914]	10.7+0.1s
+[8000/15960]	[L1: 0.4878]	11.0+0.1s
+[9600/15960]	[L1: 0.4912]	10.8+0.1s
+[11200/15960]	[L1: 0.4947]	10.8+0.1s
+[12800/15960]	[L1: 0.4925]	10.9+0.1s
+[14400/15960]	[L1: 0.4926]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.77s
+
+[Epoch 178]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5018]	11.1+0.5s
+[3200/15960]	[L1: 0.5049]	11.0+0.1s
+[4800/15960]	[L1: 0.5057]	10.8+0.1s
+[6400/15960]	[L1: 0.5017]	10.9+0.1s
+[8000/15960]	[L1: 0.4974]	10.8+0.1s
+[9600/15960]	[L1: 0.4951]	10.9+0.1s
+[11200/15960]	[L1: 0.4951]	10.8+0.1s
+[12800/15960]	[L1: 0.4951]	10.8+0.1s
+[14400/15960]	[L1: 0.4961]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.72s
+
+[Epoch 179]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4856]	9.7+0.5s
+[3200/15960]	[L1: 0.4966]	9.4+0.1s
+[4800/15960]	[L1: 0.4976]	9.4+0.1s
+[6400/15960]	[L1: 0.4958]	9.7+0.1s
+[8000/15960]	[L1: 0.5001]	10.4+0.1s
+[9600/15960]	[L1: 0.4988]	10.0+0.1s
+[11200/15960]	[L1: 0.4988]	10.2+0.1s
+[12800/15960]	[L1: 0.4990]	9.7+0.1s
+[14400/15960]	[L1: 0.4977]	9.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.74s
+
+[Epoch 180]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4693]	11.1+0.6s
+[3200/15960]	[L1: 0.4855]	11.1+0.1s
+[4800/15960]	[L1: 0.4888]	11.0+0.1s
+[6400/15960]	[L1: 0.4907]	11.1+0.1s
+[8000/15960]	[L1: 0.4927]	10.9+0.1s
+[9600/15960]	[L1: 0.4925]	11.1+0.1s
+[11200/15960]	[L1: 0.4936]	9.9+0.1s
+[12800/15960]	[L1: 0.4921]	9.9+0.1s
+[14400/15960]	[L1: 0.4930]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.74s
+
+[Epoch 181]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4953]	11.2+0.6s
+[3200/15960]	[L1: 0.5017]	11.5+0.1s
+[4800/15960]	[L1: 0.4995]	10.0+0.1s
+[6400/15960]	[L1: 0.5022]	10.7+0.1s
+[8000/15960]	[L1: 0.4966]	10.0+0.1s
+[9600/15960]	[L1: 0.4938]	10.9+0.1s
+[11200/15960]	[L1: 0.4952]	11.0+0.1s
+[12800/15960]	[L1: 0.4949]	10.8+0.1s
+[14400/15960]	[L1: 0.4942]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.73s
+
+[Epoch 182]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4994]	11.1+0.6s
+[3200/15960]	[L1: 0.4970]	11.1+0.1s
+[4800/15960]	[L1: 0.4977]	10.9+0.1s
+[6400/15960]	[L1: 0.4982]	11.0+0.1s
+[8000/15960]	[L1: 0.4983]	10.9+0.1s
+[9600/15960]	[L1: 0.4981]	11.0+0.1s
+[11200/15960]	[L1: 0.4993]	10.9+0.1s
+[12800/15960]	[L1: 0.4973]	11.0+0.1s
+[14400/15960]	[L1: 0.4966]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.74s
+
+[Epoch 183]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4787]	11.2+0.6s
+[3200/15960]	[L1: 0.4806]	11.0+0.1s
+[4800/15960]	[L1: 0.4895]	10.9+0.1s
+[6400/15960]	[L1: 0.4882]	11.0+0.1s
+[8000/15960]	[L1: 0.4887]	11.1+0.1s
+[9600/15960]	[L1: 0.4886]	10.9+0.1s
+[11200/15960]	[L1: 0.4882]	11.0+0.1s
+[12800/15960]	[L1: 0.4870]	10.9+0.1s
+[14400/15960]	[L1: 0.4885]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 0.76s
+
+[Epoch 184]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4921]	10.7+0.5s
+[3200/15960]	[L1: 0.4864]	10.6+0.1s
+[4800/15960]	[L1: 0.4874]	10.3+0.1s
+[6400/15960]	[L1: 0.4875]	10.4+0.1s
+[8000/15960]	[L1: 0.4881]	10.2+0.1s
+[9600/15960]	[L1: 0.4883]	10.2+0.1s
+[11200/15960]	[L1: 0.4879]	10.3+0.1s
+[12800/15960]	[L1: 0.4877]	10.1+0.1s
+[14400/15960]	[L1: 0.4887]	10.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.75s
+
+[Epoch 185]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4761]	11.0+0.7s
+[3200/15960]	[L1: 0.4894]	10.9+0.1s
+[4800/15960]	[L1: 0.4885]	10.7+0.1s
+[6400/15960]	[L1: 0.4876]	10.8+0.1s
+[8000/15960]	[L1: 0.4874]	10.8+0.1s
+[9600/15960]	[L1: 0.4871]	10.8+0.1s
+[11200/15960]	[L1: 0.4874]	10.9+0.1s
+[12800/15960]	[L1: 0.4896]	10.8+0.1s
+[14400/15960]	[L1: 0.4903]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.75s
+
+[Epoch 186]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4751]	11.0+0.6s
+[3200/15960]	[L1: 0.4762]	10.9+0.1s
+[4800/15960]	[L1: 0.4834]	10.7+0.1s
+[6400/15960]	[L1: 0.4897]	10.8+0.1s
+[8000/15960]	[L1: 0.4882]	10.8+0.1s
+[9600/15960]	[L1: 0.4900]	10.8+0.1s
+[11200/15960]	[L1: 0.4895]	10.8+0.1s
+[12800/15960]	[L1: 0.4913]	10.6+0.1s
+[14400/15960]	[L1: 0.4900]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 0.78s
+
+[Epoch 187]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4835]	11.1+0.6s
+[3200/15960]	[L1: 0.4871]	10.1+0.1s
+[4800/15960]	[L1: 0.4879]	10.5+0.1s
+[6400/15960]	[L1: 0.4901]	11.0+0.1s
+[8000/15960]	[L1: 0.4929]	10.8+0.1s
+[9600/15960]	[L1: 0.4924]	10.9+0.1s
+[11200/15960]	[L1: 0.4909]	10.9+0.1s
+[12800/15960]	[L1: 0.4903]	10.8+0.1s
+[14400/15960]	[L1: 0.4905]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.71s
+
+[Epoch 188]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4966]	10.6+0.5s
+[3200/15960]	[L1: 0.4883]	10.1+0.1s
+[4800/15960]	[L1: 0.4906]	10.2+0.1s
+[6400/15960]	[L1: 0.4870]	10.2+0.1s
+[8000/15960]	[L1: 0.4890]	10.3+0.1s
+[9600/15960]	[L1: 0.4890]	10.8+0.1s
+[11200/15960]	[L1: 0.4944]	9.8+0.1s
+[12800/15960]	[L1: 0.4925]	9.6+0.1s
+[14400/15960]	[L1: 0.4920]	9.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 0.74s
+
+[Epoch 189]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5047]	11.2+0.6s
+[3200/15960]	[L1: 0.4972]	10.6+0.1s
+[4800/15960]	[L1: 0.4851]	10.3+0.1s
+[6400/15960]	[L1: 0.4844]	10.9+0.1s
+[8000/15960]	[L1: 0.4829]	10.2+0.1s
+[9600/15960]	[L1: 0.4849]	10.2+0.1s
+[11200/15960]	[L1: 0.4840]	10.0+0.1s
+[12800/15960]	[L1: 0.4846]	9.4+0.1s
+[14400/15960]	[L1: 0.4861]	9.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.75s
+
+[Epoch 190]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4919]	10.9+0.6s
+[3200/15960]	[L1: 0.4939]	10.8+0.1s
+[4800/15960]	[L1: 0.4930]	10.8+0.1s
+[6400/15960]	[L1: 0.4965]	10.8+0.1s
+[8000/15960]	[L1: 0.4934]	11.0+0.1s
+[9600/15960]	[L1: 0.4964]	10.8+0.1s
+[11200/15960]	[L1: 0.4968]	11.0+0.1s
+[12800/15960]	[L1: 0.4968]	10.8+0.1s
+[14400/15960]	[L1: 0.4952]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.72s
+
+[Epoch 191]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4900]	10.8+0.6s
+[3200/15960]	[L1: 0.4881]	10.2+0.1s
+[4800/15960]	[L1: 0.4891]	10.2+0.1s
+[6400/15960]	[L1: 0.4892]	10.9+0.1s
+[8000/15960]	[L1: 0.4854]	10.8+0.1s
+[9600/15960]	[L1: 0.4878]	10.9+0.1s
+[11200/15960]	[L1: 0.4853]	10.9+0.1s
+[12800/15960]	[L1: 0.4872]	10.7+0.1s
+[14400/15960]	[L1: 0.4885]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.76s
+
+[Epoch 192]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4826]	11.0+0.6s
+[3200/15960]	[L1: 0.4888]	10.9+0.1s
+[4800/15960]	[L1: 0.4947]	10.7+0.1s
+[6400/15960]	[L1: 0.4949]	10.4+0.1s
+[8000/15960]	[L1: 0.4927]	11.0+0.1s
+[9600/15960]	[L1: 0.4917]	10.6+0.1s
+[11200/15960]	[L1: 0.4905]	11.0+0.1s
+[12800/15960]	[L1: 0.4907]	10.8+0.1s
+[14400/15960]	[L1: 0.4913]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.74s
+
+[Epoch 193]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4745]	10.0+0.5s
+[3200/15960]	[L1: 0.4753]	9.6+0.1s
+[4800/15960]	[L1: 0.4826]	10.5+0.1s
+[6400/15960]	[L1: 0.4884]	11.0+0.1s
+[8000/15960]	[L1: 0.4904]	10.1+0.1s
+[9600/15960]	[L1: 0.4885]	9.7+0.1s
+[11200/15960]	[L1: 0.4897]	9.5+0.1s
+[12800/15960]	[L1: 0.4889]	10.1+0.1s
+[14400/15960]	[L1: 0.4904]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.76s
+
+[Epoch 194]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.5242]	10.8+0.6s
+[3200/15960]	[L1: 0.5111]	9.9+0.1s
+[4800/15960]	[L1: 0.4997]	9.6+0.1s
+[6400/15960]	[L1: 0.4956]	10.1+0.1s
+[8000/15960]	[L1: 0.4925]	10.4+0.1s
+[9600/15960]	[L1: 0.4908]	9.5+0.1s
+[11200/15960]	[L1: 0.4872]	10.4+0.1s
+[12800/15960]	[L1: 0.4880]	10.9+0.1s
+[14400/15960]	[L1: 0.4878]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.74s
+
+[Epoch 195]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4716]	10.9+0.6s
+[3200/15960]	[L1: 0.4815]	10.9+0.1s
+[4800/15960]	[L1: 0.4795]	10.7+0.1s
+[6400/15960]	[L1: 0.4838]	10.7+0.1s
+[8000/15960]	[L1: 0.4891]	10.9+0.1s
+[9600/15960]	[L1: 0.4883]	10.9+0.1s
+[11200/15960]	[L1: 0.4875]	10.7+0.1s
+[12800/15960]	[L1: 0.4855]	10.8+0.1s
+[14400/15960]	[L1: 0.4857]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.86s
+
+[Epoch 196]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4944]	11.0+0.6s
+[3200/15960]	[L1: 0.4878]	10.8+0.1s
+[4800/15960]	[L1: 0.4922]	10.8+0.1s
+[6400/15960]	[L1: 0.4897]	10.8+0.1s
+[8000/15960]	[L1: 0.4874]	11.0+0.1s
+[9600/15960]	[L1: 0.4878]	10.4+0.1s
+[11200/15960]	[L1: 0.4890]	10.4+0.1s
+[12800/15960]	[L1: 0.4893]	11.0+0.1s
+[14400/15960]	[L1: 0.4898]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.72s
+
+[Epoch 197]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4854]	10.1+0.6s
+[3200/15960]	[L1: 0.4865]	10.6+0.1s
+[4800/15960]	[L1: 0.4886]	10.2+0.1s
+[6400/15960]	[L1: 0.4891]	10.7+0.1s
+[8000/15960]	[L1: 0.4888]	10.5+0.1s
+[9600/15960]	[L1: 0.4888]	10.9+0.1s
+[11200/15960]	[L1: 0.4878]	10.8+0.1s
+[12800/15960]	[L1: 0.4883]	10.8+0.1s
+[14400/15960]	[L1: 0.4881]	10.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 0.78s
+
+[Epoch 198]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4949]	11.4+0.6s
+[3200/15960]	[L1: 0.5033]	11.1+0.1s
+[4800/15960]	[L1: 0.4979]	11.0+0.1s
+[6400/15960]	[L1: 0.4909]	11.1+0.1s
+[8000/15960]	[L1: 0.4862]	11.1+0.1s
+[9600/15960]	[L1: 0.4885]	11.0+0.1s
+[11200/15960]	[L1: 0.4886]	11.1+0.1s
+[12800/15960]	[L1: 0.4863]	11.1+0.1s
+[14400/15960]	[L1: 0.4850]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.74s
+
+[Epoch 199]	Learning rate: 5.00e-5
+[1600/15960]	[L1: 0.4626]	11.1+0.6s
+[3200/15960]	[L1: 0.4757]	11.0+0.1s
+[4800/15960]	[L1: 0.4813]	10.7+0.1s
+[6400/15960]	[L1: 0.4859]	11.1+0.1s
+[8000/15960]	[L1: 0.4849]	11.0+0.1s
+[9600/15960]	[L1: 0.4847]	10.8+0.1s
+[11200/15960]	[L1: 0.4848]	10.7+0.1s
+[12800/15960]	[L1: 0.4845]	10.7+0.1s
+[14400/15960]	[L1: 0.4839]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 0.80s
+
+[Epoch 200]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4640]	11.2+0.6s
+[3200/15960]	[L1: 0.4618]	11.0+0.1s
+[4800/15960]	[L1: 0.4610]	10.9+0.1s
+[6400/15960]	[L1: 0.4557]	11.1+0.1s
+[8000/15960]	[L1: 0.4564]	10.6+0.1s
+[9600/15960]	[L1: 0.4559]	10.1+0.1s
+[11200/15960]	[L1: 0.4543]	10.9+0.1s
+[12800/15960]	[L1: 0.4526]	10.2+0.1s
+[14400/15960]	[L1: 0.4523]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 0.78s
+
+[Epoch 201]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4523]	10.1+0.5s
+[3200/15960]	[L1: 0.4488]	10.7+0.1s
+[4800/15960]	[L1: 0.4502]	10.8+0.1s
+[6400/15960]	[L1: 0.4513]	9.9+0.1s
+[8000/15960]	[L1: 0.4501]	10.7+0.1s
+[9600/15960]	[L1: 0.4520]	10.9+0.1s
+[11200/15960]	[L1: 0.4506]	10.8+0.1s
+[12800/15960]	[L1: 0.4513]	10.8+0.1s
+[14400/15960]	[L1: 0.4511]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 0.85s
+
+[Epoch 202]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4617]	10.9+0.6s
+[3200/15960]	[L1: 0.4621]	11.0+0.1s
+[4800/15960]	[L1: 0.4651]	10.8+0.1s
+[6400/15960]	[L1: 0.4621]	9.9+0.1s
+[8000/15960]	[L1: 0.4630]	9.7+0.1s
+[9600/15960]	[L1: 0.4618]	10.3+0.1s
+[11200/15960]	[L1: 0.4601]	10.9+0.1s
+[12800/15960]	[L1: 0.4607]	10.9+0.1s
+[14400/15960]	[L1: 0.4605]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.72s
+
+[Epoch 203]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4583]	11.0+0.6s
+[3200/15960]	[L1: 0.4533]	11.1+0.1s
+[4800/15960]	[L1: 0.4498]	10.8+0.1s
+[6400/15960]	[L1: 0.4514]	10.9+0.1s
+[8000/15960]	[L1: 0.4527]	10.8+0.1s
+[9600/15960]	[L1: 0.4533]	11.0+0.1s
+[11200/15960]	[L1: 0.4526]	10.8+0.1s
+[12800/15960]	[L1: 0.4519]	10.8+0.1s
+[14400/15960]	[L1: 0.4524]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 0.81s
+
+[Epoch 204]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4607]	11.3+0.5s
+[3200/15960]	[L1: 0.4528]	11.1+0.1s
+[4800/15960]	[L1: 0.4535]	11.0+0.1s
+[6400/15960]	[L1: 0.4575]	11.1+0.1s
+[8000/15960]	[L1: 0.4564]	11.1+0.1s
+[9600/15960]	[L1: 0.4568]	11.0+0.1s
+[11200/15960]	[L1: 0.4566]	11.1+0.1s
+[12800/15960]	[L1: 0.4566]	11.1+0.1s
+[14400/15960]	[L1: 0.4560]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 0.77s
+
+[Epoch 205]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4511]	10.7+0.5s
+[3200/15960]	[L1: 0.4505]	11.0+0.1s
+[4800/15960]	[L1: 0.4526]	10.5+0.1s
+[6400/15960]	[L1: 0.4544]	10.5+0.1s
+[8000/15960]	[L1: 0.4572]	9.9+0.1s
+[9600/15960]	[L1: 0.4563]	10.8+0.1s
+[11200/15960]	[L1: 0.4581]	10.4+0.1s
+[12800/15960]	[L1: 0.4584]	10.8+0.1s
+[14400/15960]	[L1: 0.4571]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 0.77s
+
+[Epoch 206]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4506]	11.2+0.5s
+[3200/15960]	[L1: 0.4536]	11.1+0.1s
+[4800/15960]	[L1: 0.4555]	10.9+0.1s
+[6400/15960]	[L1: 0.4545]	11.0+0.1s
+[8000/15960]	[L1: 0.4554]	10.9+0.1s
+[9600/15960]	[L1: 0.4571]	10.8+0.1s
+[11200/15960]	[L1: 0.4566]	11.0+0.1s
+[12800/15960]	[L1: 0.4578]	11.0+0.1s
+[14400/15960]	[L1: 0.4573]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.73s
+
+[Epoch 207]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4636]	10.9+0.6s
+[3200/15960]	[L1: 0.4667]	10.8+0.1s
+[4800/15960]	[L1: 0.4623]	10.0+0.1s
+[6400/15960]	[L1: 0.4647]	9.7+0.1s
+[8000/15960]	[L1: 0.4646]	10.1+0.1s
+[9600/15960]	[L1: 0.4646]	9.6+0.1s
+[11200/15960]	[L1: 0.4634]	9.6+0.1s
+[12800/15960]	[L1: 0.4621]	10.8+0.1s
+[14400/15960]	[L1: 0.4605]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.72s
+
+[Epoch 208]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4477]	10.3+0.5s
+[3200/15960]	[L1: 0.4518]	10.9+0.1s
+[4800/15960]	[L1: 0.4546]	10.6+0.1s
+[6400/15960]	[L1: 0.4558]	10.9+0.1s
+[8000/15960]	[L1: 0.4571]	10.9+0.1s
+[9600/15960]	[L1: 0.4555]	10.8+0.1s
+[11200/15960]	[L1: 0.4539]	11.0+0.1s
+[12800/15960]	[L1: 0.4536]	10.8+0.1s
+[14400/15960]	[L1: 0.4537]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 0.74s
+
+[Epoch 209]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4480]	10.9+0.6s
+[3200/15960]	[L1: 0.4443]	10.4+0.1s
+[4800/15960]	[L1: 0.4466]	10.7+0.1s
+[6400/15960]	[L1: 0.4478]	10.8+0.1s
+[8000/15960]	[L1: 0.4457]	10.7+0.1s
+[9600/15960]	[L1: 0.4481]	10.7+0.1s
+[11200/15960]	[L1: 0.4479]	10.7+0.1s
+[12800/15960]	[L1: 0.4480]	10.8+0.1s
+[14400/15960]	[L1: 0.4489]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.73s
+
+[Epoch 210]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4502]	10.5+0.5s
+[3200/15960]	[L1: 0.4437]	10.7+0.1s
+[4800/15960]	[L1: 0.4471]	10.5+0.1s
+[6400/15960]	[L1: 0.4474]	11.1+0.1s
+[8000/15960]	[L1: 0.4471]	10.9+0.1s
+[9600/15960]	[L1: 0.4463]	10.9+0.1s
+[11200/15960]	[L1: 0.4461]	10.9+0.1s
+[12800/15960]	[L1: 0.4466]	10.9+0.1s
+[14400/15960]	[L1: 0.4459]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.74s
+
+[Epoch 211]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4514]	10.7+0.5s
+[3200/15960]	[L1: 0.4494]	11.0+0.1s
+[4800/15960]	[L1: 0.4529]	10.2+0.1s
+[6400/15960]	[L1: 0.4540]	9.9+0.1s
+[8000/15960]	[L1: 0.4518]	9.9+0.1s
+[9600/15960]	[L1: 0.4519]	10.0+0.1s
+[11200/15960]	[L1: 0.4533]	10.1+0.1s
+[12800/15960]	[L1: 0.4523]	10.1+0.1s
+[14400/15960]	[L1: 0.4528]	9.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.74s
+
+[Epoch 212]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4595]	10.9+0.6s
+[3200/15960]	[L1: 0.4567]	11.0+0.1s
+[4800/15960]	[L1: 0.4585]	10.8+0.1s
+[6400/15960]	[L1: 0.4581]	10.8+0.1s
+[8000/15960]	[L1: 0.4586]	10.4+0.1s
+[9600/15960]	[L1: 0.4591]	10.5+0.1s
+[11200/15960]	[L1: 0.4578]	10.4+0.1s
+[12800/15960]	[L1: 0.4608]	10.3+0.1s
+[14400/15960]	[L1: 0.4599]	11.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.76s
+
+[Epoch 213]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4444]	11.0+0.6s
+[3200/15960]	[L1: 0.4571]	9.5+0.1s
+[4800/15960]	[L1: 0.4585]	9.7+0.1s
+[6400/15960]	[L1: 0.4574]	10.3+0.1s
+[8000/15960]	[L1: 0.4580]	9.6+0.1s
+[9600/15960]	[L1: 0.4577]	10.4+0.1s
+[11200/15960]	[L1: 0.4582]	10.8+0.1s
+[12800/15960]	[L1: 0.4594]	10.9+0.1s
+[14400/15960]	[L1: 0.4603]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 0.73s
+
+[Epoch 214]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4529]	11.3+0.5s
+[3200/15960]	[L1: 0.4503]	11.0+0.1s
+[4800/15960]	[L1: 0.4536]	11.1+0.1s
+[6400/15960]	[L1: 0.4543]	11.2+0.1s
+[8000/15960]	[L1: 0.4514]	10.3+0.1s
+[9600/15960]	[L1: 0.4529]	10.4+0.1s
+[11200/15960]	[L1: 0.4527]	10.5+0.1s
+[12800/15960]	[L1: 0.4527]	10.4+0.1s
+[14400/15960]	[L1: 0.4519]	10.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.85s
+
+[Epoch 215]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4499]	11.4+0.6s
+[3200/15960]	[L1: 0.4455]	10.9+0.1s
+[4800/15960]	[L1: 0.4443]	11.0+0.1s
+[6400/15960]	[L1: 0.4451]	11.0+0.1s
+[8000/15960]	[L1: 0.4431]	11.1+0.1s
+[9600/15960]	[L1: 0.4468]	10.3+0.1s
+[11200/15960]	[L1: 0.4473]	10.9+0.1s
+[12800/15960]	[L1: 0.4484]	10.4+0.1s
+[14400/15960]	[L1: 0.4499]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.73s
+
+[Epoch 216]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4568]	11.2+0.6s
+[3200/15960]	[L1: 0.4490]	11.2+0.1s
+[4800/15960]	[L1: 0.4487]	11.0+0.1s
+[6400/15960]	[L1: 0.4487]	11.1+0.1s
+[8000/15960]	[L1: 0.4472]	11.0+0.1s
+[9600/15960]	[L1: 0.4486]	11.1+0.1s
+[11200/15960]	[L1: 0.4513]	11.0+0.1s
+[12800/15960]	[L1: 0.4512]	11.1+0.1s
+[14400/15960]	[L1: 0.4496]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 1.71s
+
+[Epoch 217]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4499]	10.5+0.5s
+[3200/15960]	[L1: 0.4523]	10.9+0.1s
+[4800/15960]	[L1: 0.4540]	10.9+0.1s
+[6400/15960]	[L1: 0.4540]	10.9+0.1s
+[8000/15960]	[L1: 0.4536]	11.0+0.1s
+[9600/15960]	[L1: 0.4506]	10.7+0.1s
+[11200/15960]	[L1: 0.4500]	10.8+0.1s
+[12800/15960]	[L1: 0.4492]	10.8+0.1s
+[14400/15960]	[L1: 0.4483]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 0.79s
+
+[Epoch 218]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4495]	11.3+0.6s
+[3200/15960]	[L1: 0.4498]	10.9+0.1s
+[4800/15960]	[L1: 0.4444]	11.1+0.1s
+[6400/15960]	[L1: 0.4464]	10.9+0.1s
+[8000/15960]	[L1: 0.4485]	11.1+0.1s
+[9600/15960]	[L1: 0.4474]	11.1+0.1s
+[11200/15960]	[L1: 0.4472]	10.9+0.1s
+[12800/15960]	[L1: 0.4476]	11.1+0.1s
+[14400/15960]	[L1: 0.4487]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.70s
+
+[Epoch 219]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4608]	11.1+0.5s
+[3200/15960]	[L1: 0.4590]	10.8+0.1s
+[4800/15960]	[L1: 0.4513]	10.9+0.1s
+[6400/15960]	[L1: 0.4533]	10.8+0.1s
+[8000/15960]	[L1: 0.4540]	10.9+0.1s
+[9600/15960]	[L1: 0.4544]	10.8+0.1s
+[11200/15960]	[L1: 0.4542]	10.8+0.1s
+[12800/15960]	[L1: 0.4530]	10.9+0.1s
+[14400/15960]	[L1: 0.4517]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.71s
+
+[Epoch 220]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4490]	10.9+0.5s
+[3200/15960]	[L1: 0.4503]	11.0+0.1s
+[4800/15960]	[L1: 0.4523]	10.9+0.1s
+[6400/15960]	[L1: 0.4507]	10.8+0.1s
+[8000/15960]	[L1: 0.4503]	11.1+0.1s
+[9600/15960]	[L1: 0.4476]	11.0+0.1s
+[11200/15960]	[L1: 0.4460]	10.8+0.1s
+[12800/15960]	[L1: 0.4468]	10.9+0.1s
+[14400/15960]	[L1: 0.4473]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.73s
+
+[Epoch 221]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4432]	11.2+0.6s
+[3200/15960]	[L1: 0.4414]	11.0+0.1s
+[4800/15960]	[L1: 0.4461]	11.0+0.1s
+[6400/15960]	[L1: 0.4484]	10.9+0.1s
+[8000/15960]	[L1: 0.4481]	11.1+0.1s
+[9600/15960]	[L1: 0.4492]	10.9+0.1s
+[11200/15960]	[L1: 0.4494]	10.9+0.1s
+[12800/15960]	[L1: 0.4489]	10.8+0.1s
+[14400/15960]	[L1: 0.4488]	10.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.70s
+
+[Epoch 222]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4524]	10.9+0.6s
+[3200/15960]	[L1: 0.4561]	10.3+0.1s
+[4800/15960]	[L1: 0.4557]	10.2+0.1s
+[6400/15960]	[L1: 0.4506]	10.7+0.1s
+[8000/15960]	[L1: 0.4514]	10.6+0.1s
+[9600/15960]	[L1: 0.4527]	10.6+0.1s
+[11200/15960]	[L1: 0.4524]	11.0+0.1s
+[12800/15960]	[L1: 0.4522]	10.7+0.1s
+[14400/15960]	[L1: 0.4506]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.75s
+
+[Epoch 223]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4461]	10.6+0.6s
+[3200/15960]	[L1: 0.4455]	10.5+0.1s
+[4800/15960]	[L1: 0.4466]	9.6+0.1s
+[6400/15960]	[L1: 0.4438]	10.3+0.1s
+[8000/15960]	[L1: 0.4423]	10.8+0.1s
+[9600/15960]	[L1: 0.4448]	10.1+0.1s
+[11200/15960]	[L1: 0.4449]	10.5+0.1s
+[12800/15960]	[L1: 0.4446]	10.6+0.1s
+[14400/15960]	[L1: 0.4460]	9.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 0.75s
+
+[Epoch 224]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4434]	10.9+0.6s
+[3200/15960]	[L1: 0.4528]	10.9+0.1s
+[4800/15960]	[L1: 0.4489]	11.5+0.1s
+[6400/15960]	[L1: 0.4460]	11.0+0.1s
+[8000/15960]	[L1: 0.4468]	10.8+0.1s
+[9600/15960]	[L1: 0.4478]	10.8+0.1s
+[11200/15960]	[L1: 0.4483]	10.8+0.1s
+[12800/15960]	[L1: 0.4478]	11.1+0.1s
+[14400/15960]	[L1: 0.4472]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 0.75s
+
+[Epoch 225]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4516]	10.9+0.6s
+[3200/15960]	[L1: 0.4503]	11.0+0.1s
+[4800/15960]	[L1: 0.4481]	11.1+0.1s
+[6400/15960]	[L1: 0.4448]	11.1+0.1s
+[8000/15960]	[L1: 0.4424]	10.9+0.1s
+[9600/15960]	[L1: 0.4469]	11.1+0.1s
+[11200/15960]	[L1: 0.4487]	10.7+0.1s
+[12800/15960]	[L1: 0.4480]	10.8+0.1s
+[14400/15960]	[L1: 0.4469]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.72s
+
+[Epoch 226]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4564]	10.0+0.5s
+[3200/15960]	[L1: 0.4503]	9.5+0.1s
+[4800/15960]	[L1: 0.4455]	9.6+0.1s
+[6400/15960]	[L1: 0.4472]	10.5+0.1s
+[8000/15960]	[L1: 0.4486]	10.7+0.1s
+[9600/15960]	[L1: 0.4490]	10.5+0.1s
+[11200/15960]	[L1: 0.4507]	9.5+0.1s
+[12800/15960]	[L1: 0.4513]	10.7+0.1s
+[14400/15960]	[L1: 0.4511]	10.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.70s
+
+[Epoch 227]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4478]	11.4+0.6s
+[3200/15960]	[L1: 0.4499]	11.3+0.1s
+[4800/15960]	[L1: 0.4521]	10.5+0.1s
+[6400/15960]	[L1: 0.4514]	10.5+0.1s
+[8000/15960]	[L1: 0.4513]	10.8+0.1s
+[9600/15960]	[L1: 0.4495]	10.2+0.1s
+[11200/15960]	[L1: 0.4504]	10.6+0.1s
+[12800/15960]	[L1: 0.4501]	9.7+0.1s
+[14400/15960]	[L1: 0.4502]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.88s
+
+[Epoch 228]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4510]	10.7+0.6s
+[3200/15960]	[L1: 0.4459]	10.4+0.1s
+[4800/15960]	[L1: 0.4433]	10.4+0.1s
+[6400/15960]	[L1: 0.4432]	10.4+0.1s
+[8000/15960]	[L1: 0.4437]	10.6+0.1s
+[9600/15960]	[L1: 0.4458]	10.4+0.1s
+[11200/15960]	[L1: 0.4480]	10.4+0.1s
+[12800/15960]	[L1: 0.4494]	10.4+0.1s
+[14400/15960]	[L1: 0.4502]	10.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 0.75s
+
+[Epoch 229]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4570]	10.2+0.6s
+[3200/15960]	[L1: 0.4522]	9.5+0.1s
+[4800/15960]	[L1: 0.4555]	9.9+0.1s
+[6400/15960]	[L1: 0.4530]	10.5+0.1s
+[8000/15960]	[L1: 0.4512]	10.3+0.1s
+[9600/15960]	[L1: 0.4517]	10.9+0.1s
+[11200/15960]	[L1: 0.4516]	10.7+0.1s
+[12800/15960]	[L1: 0.4515]	10.9+0.1s
+[14400/15960]	[L1: 0.4511]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.70s
+
+[Epoch 230]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4405]	10.9+0.5s
+[3200/15960]	[L1: 0.4377]	10.7+0.1s
+[4800/15960]	[L1: 0.4389]	10.8+0.1s
+[6400/15960]	[L1: 0.4393]	10.7+0.1s
+[8000/15960]	[L1: 0.4417]	10.9+0.1s
+[9600/15960]	[L1: 0.4431]	10.7+0.1s
+[11200/15960]	[L1: 0.4444]	10.8+0.1s
+[12800/15960]	[L1: 0.4447]	10.7+0.1s
+[14400/15960]	[L1: 0.4456]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 0.72s
+
+[Epoch 231]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4631]	11.0+0.6s
+[3200/15960]	[L1: 0.4608]	10.8+0.1s
+[4800/15960]	[L1: 0.4603]	11.0+0.1s
+[6400/15960]	[L1: 0.4569]	10.8+0.1s
+[8000/15960]	[L1: 0.4530]	11.0+0.1s
+[9600/15960]	[L1: 0.4522]	10.3+0.1s
+[11200/15960]	[L1: 0.4523]	9.6+0.1s
+[12800/15960]	[L1: 0.4524]	10.2+0.1s
+[14400/15960]	[L1: 0.4516]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.31s
+
+Saving...
+Total: 0.74s
+
+[Epoch 232]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4568]	10.6+0.6s
+[3200/15960]	[L1: 0.4489]	10.0+0.1s
+[4800/15960]	[L1: 0.4471]	10.0+0.1s
+[6400/15960]	[L1: 0.4459]	10.7+0.1s
+[8000/15960]	[L1: 0.4472]	10.2+0.1s
+[9600/15960]	[L1: 0.4492]	10.4+0.1s
+[11200/15960]	[L1: 0.4481]	10.9+0.1s
+[12800/15960]	[L1: 0.4480]	11.1+0.1s
+[14400/15960]	[L1: 0.4468]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.70s
+
+[Epoch 233]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4428]	10.3+0.6s
+[3200/15960]	[L1: 0.4455]	10.2+0.1s
+[4800/15960]	[L1: 0.4483]	10.5+0.1s
+[6400/15960]	[L1: 0.4493]	10.0+0.1s
+[8000/15960]	[L1: 0.4504]	10.1+0.1s
+[9600/15960]	[L1: 0.4496]	10.1+0.1s
+[11200/15960]	[L1: 0.4494]	10.0+0.1s
+[12800/15960]	[L1: 0.4490]	10.9+0.1s
+[14400/15960]	[L1: 0.4495]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 0.74s
+
+[Epoch 234]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4510]	11.2+0.6s
+[3200/15960]	[L1: 0.4425]	11.1+0.1s
+[4800/15960]	[L1: 0.4413]	10.9+0.1s
+[6400/15960]	[L1: 0.4403]	10.8+0.1s
+[8000/15960]	[L1: 0.4414]	10.8+0.1s
+[9600/15960]	[L1: 0.4415]	11.1+0.1s
+[11200/15960]	[L1: 0.4418]	10.9+0.1s
+[12800/15960]	[L1: 0.4416]	10.9+0.1s
+[14400/15960]	[L1: 0.4423]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.73s
+
+[Epoch 235]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4406]	10.9+0.6s
+[3200/15960]	[L1: 0.4410]	10.9+0.1s
+[4800/15960]	[L1: 0.4404]	10.8+0.1s
+[6400/15960]	[L1: 0.4433]	10.8+0.1s
+[8000/15960]	[L1: 0.4449]	11.0+0.1s
+[9600/15960]	[L1: 0.4448]	10.8+0.1s
+[11200/15960]	[L1: 0.4468]	11.0+0.1s
+[12800/15960]	[L1: 0.4460]	10.5+0.1s
+[14400/15960]	[L1: 0.4454]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.74s
+
+[Epoch 236]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4498]	11.1+0.6s
+[3200/15960]	[L1: 0.4459]	11.0+0.1s
+[4800/15960]	[L1: 0.4438]	11.0+0.1s
+[6400/15960]	[L1: 0.4451]	10.9+0.1s
+[8000/15960]	[L1: 0.4479]	11.0+0.1s
+[9600/15960]	[L1: 0.4479]	11.0+0.1s
+[11200/15960]	[L1: 0.4496]	10.8+0.1s
+[12800/15960]	[L1: 0.4493]	10.8+0.1s
+[14400/15960]	[L1: 0.4490]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.70s
+
+[Epoch 237]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4483]	10.9+0.5s
+[3200/15960]	[L1: 0.4440]	10.8+0.1s
+[4800/15960]	[L1: 0.4487]	11.0+0.1s
+[6400/15960]	[L1: 0.4505]	11.2+0.1s
+[8000/15960]	[L1: 0.4493]	11.0+0.1s
+[9600/15960]	[L1: 0.4513]	11.0+0.1s
+[11200/15960]	[L1: 0.4501]	11.0+0.1s
+[12800/15960]	[L1: 0.4501]	11.0+0.1s
+[14400/15960]	[L1: 0.4501]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.34s
+
+Saving...
+Total: 0.76s
+
+[Epoch 238]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4472]	10.8+0.5s
+[3200/15960]	[L1: 0.4582]	10.8+0.1s
+[4800/15960]	[L1: 0.4577]	10.6+0.1s
+[6400/15960]	[L1: 0.4558]	10.5+0.1s
+[8000/15960]	[L1: 0.4544]	10.2+0.1s
+[9600/15960]	[L1: 0.4518]	10.4+0.1s
+[11200/15960]	[L1: 0.4499]	10.9+0.1s
+[12800/15960]	[L1: 0.4483]	10.8+0.1s
+[14400/15960]	[L1: 0.4479]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.70s
+
+[Epoch 239]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4531]	11.2+0.5s
+[3200/15960]	[L1: 0.4547]	10.9+0.1s
+[4800/15960]	[L1: 0.4531]	11.0+0.1s
+[6400/15960]	[L1: 0.4541]	10.9+0.1s
+[8000/15960]	[L1: 0.4504]	11.0+0.1s
+[9600/15960]	[L1: 0.4487]	10.7+0.1s
+[11200/15960]	[L1: 0.4489]	10.9+0.1s
+[12800/15960]	[L1: 0.4490]	10.9+0.1s
+[14400/15960]	[L1: 0.4484]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.73s
+
+[Epoch 240]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4543]	11.3+0.5s
+[3200/15960]	[L1: 0.4503]	11.0+0.1s
+[4800/15960]	[L1: 0.4504]	11.1+0.1s
+[6400/15960]	[L1: 0.4508]	11.0+0.1s
+[8000/15960]	[L1: 0.4489]	11.2+0.1s
+[9600/15960]	[L1: 0.4477]	11.1+0.1s
+[11200/15960]	[L1: 0.4480]	11.0+0.1s
+[12800/15960]	[L1: 0.4480]	11.1+0.1s
+[14400/15960]	[L1: 0.4490]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.77s
+
+[Epoch 241]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4531]	11.4+0.6s
+[3200/15960]	[L1: 0.4457]	11.1+0.1s
+[4800/15960]	[L1: 0.4474]	11.1+0.1s
+[6400/15960]	[L1: 0.4455]	11.0+0.1s
+[8000/15960]	[L1: 0.4459]	11.2+0.1s
+[9600/15960]	[L1: 0.4437]	10.9+0.1s
+[11200/15960]	[L1: 0.4439]	10.8+0.1s
+[12800/15960]	[L1: 0.4451]	10.9+0.1s
+[14400/15960]	[L1: 0.4460]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.73s
+
+[Epoch 242]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4362]	11.1+0.6s
+[3200/15960]	[L1: 0.4413]	11.1+0.1s
+[4800/15960]	[L1: 0.4415]	11.0+0.1s
+[6400/15960]	[L1: 0.4394]	11.0+0.1s
+[8000/15960]	[L1: 0.4404]	10.9+0.1s
+[9600/15960]	[L1: 0.4414]	10.9+0.1s
+[11200/15960]	[L1: 0.4408]	11.0+0.1s
+[12800/15960]	[L1: 0.4424]	10.9+0.1s
+[14400/15960]	[L1: 0.4430]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.34s
+
+Saving...
+Total: 0.79s
+
+[Epoch 243]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4462]	11.3+0.6s
+[3200/15960]	[L1: 0.4420]	11.0+0.1s
+[4800/15960]	[L1: 0.4404]	11.0+0.1s
+[6400/15960]	[L1: 0.4414]	10.5+0.1s
+[8000/15960]	[L1: 0.4430]	11.1+0.1s
+[9600/15960]	[L1: 0.4452]	11.0+0.1s
+[11200/15960]	[L1: 0.4452]	11.0+0.1s
+[12800/15960]	[L1: 0.4461]	11.0+0.1s
+[14400/15960]	[L1: 0.4447]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.71s
+
+[Epoch 244]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4501]	11.2+0.6s
+[3200/15960]	[L1: 0.4536]	11.2+0.1s
+[4800/15960]	[L1: 0.4537]	11.0+0.1s
+[6400/15960]	[L1: 0.4534]	11.0+0.1s
+[8000/15960]	[L1: 0.4510]	11.1+0.1s
+[9600/15960]	[L1: 0.4502]	11.1+0.1s
+[11200/15960]	[L1: 0.4503]	10.9+0.1s
+[12800/15960]	[L1: 0.4512]	11.0+0.1s
+[14400/15960]	[L1: 0.4508]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.72s
+
+[Epoch 245]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4541]	10.0+0.6s
+[3200/15960]	[L1: 0.4538]	10.0+0.1s
+[4800/15960]	[L1: 0.4474]	9.6+0.1s
+[6400/15960]	[L1: 0.4483]	10.2+0.1s
+[8000/15960]	[L1: 0.4463]	10.9+0.1s
+[9600/15960]	[L1: 0.4462]	10.9+0.1s
+[11200/15960]	[L1: 0.4461]	10.8+0.1s
+[12800/15960]	[L1: 0.4461]	10.8+0.1s
+[14400/15960]	[L1: 0.4467]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.76s
+
+[Epoch 246]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4530]	10.6+0.6s
+[3200/15960]	[L1: 0.4486]	10.0+0.1s
+[4800/15960]	[L1: 0.4441]	10.9+0.1s
+[6400/15960]	[L1: 0.4476]	11.1+0.1s
+[8000/15960]	[L1: 0.4464]	10.7+0.1s
+[9600/15960]	[L1: 0.4495]	9.7+0.1s
+[11200/15960]	[L1: 0.4491]	9.9+0.1s
+[12800/15960]	[L1: 0.4489]	10.3+0.1s
+[14400/15960]	[L1: 0.4475]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 0.79s
+
+[Epoch 247]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4500]	10.4+0.5s
+[3200/15960]	[L1: 0.4514]	9.9+0.1s
+[4800/15960]	[L1: 0.4512]	9.6+0.1s
+[6400/15960]	[L1: 0.4475]	11.0+0.1s
+[8000/15960]	[L1: 0.4479]	10.8+0.1s
+[9600/15960]	[L1: 0.4453]	11.0+0.1s
+[11200/15960]	[L1: 0.4458]	10.8+0.1s
+[12800/15960]	[L1: 0.4455]	10.9+0.1s
+[14400/15960]	[L1: 0.4466]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.74s
+
+[Epoch 248]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4360]	11.1+0.6s
+[3200/15960]	[L1: 0.4412]	10.8+0.1s
+[4800/15960]	[L1: 0.4430]	10.9+0.1s
+[6400/15960]	[L1: 0.4463]	10.7+0.1s
+[8000/15960]	[L1: 0.4460]	10.9+0.1s
+[9600/15960]	[L1: 0.4448]	10.8+0.1s
+[11200/15960]	[L1: 0.4454]	11.0+0.1s
+[12800/15960]	[L1: 0.4447]	10.9+0.1s
+[14400/15960]	[L1: 0.4444]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.69s
+
+[Epoch 249]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4444]	11.6+0.6s
+[3200/15960]	[L1: 0.4456]	11.2+0.1s
+[4800/15960]	[L1: 0.4452]	11.1+0.1s
+[6400/15960]	[L1: 0.4471]	10.8+0.1s
+[8000/15960]	[L1: 0.4447]	11.3+0.1s
+[9600/15960]	[L1: 0.4452]	11.5+0.1s
+[11200/15960]	[L1: 0.4451]	11.7+0.1s
+[12800/15960]	[L1: 0.4443]	11.3+0.1s
+[14400/15960]	[L1: 0.4438]	11.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.85s
+
+[Epoch 250]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4498]	10.4+0.5s
+[3200/15960]	[L1: 0.4460]	10.6+0.1s
+[4800/15960]	[L1: 0.4473]	10.6+0.1s
+[6400/15960]	[L1: 0.4517]	10.4+0.1s
+[8000/15960]	[L1: 0.4516]	10.6+0.1s
+[9600/15960]	[L1: 0.4503]	10.7+0.1s
+[11200/15960]	[L1: 0.4505]	10.7+0.1s
+[12800/15960]	[L1: 0.4489]	10.8+0.1s
+[14400/15960]	[L1: 0.4473]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 0.76s
+
+[Epoch 251]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4618]	11.0+0.6s
+[3200/15960]	[L1: 0.4515]	10.9+0.1s
+[4800/15960]	[L1: 0.4503]	10.1+0.1s
+[6400/15960]	[L1: 0.4490]	9.6+0.1s
+[8000/15960]	[L1: 0.4493]	9.6+0.1s
+[9600/15960]	[L1: 0.4493]	9.8+0.1s
+[11200/15960]	[L1: 0.4472]	9.5+0.1s
+[12800/15960]	[L1: 0.4472]	9.8+0.1s
+[14400/15960]	[L1: 0.4457]	9.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 0.73s
+
+[Epoch 252]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4431]	9.9+0.5s
+[3200/15960]	[L1: 0.4515]	10.5+0.1s
+[4800/15960]	[L1: 0.4498]	10.6+0.1s
+[6400/15960]	[L1: 0.4504]	10.3+0.1s
+[8000/15960]	[L1: 0.4515]	10.1+0.1s
+[9600/15960]	[L1: 0.4521]	10.7+0.1s
+[11200/15960]	[L1: 0.4504]	10.3+0.1s
+[12800/15960]	[L1: 0.4503]	10.6+0.1s
+[14400/15960]	[L1: 0.4499]	9.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 0.77s
+
+[Epoch 253]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4509]	10.0+0.5s
+[3200/15960]	[L1: 0.4467]	9.6+0.1s
+[4800/15960]	[L1: 0.4453]	10.8+0.1s
+[6400/15960]	[L1: 0.4418]	10.5+0.1s
+[8000/15960]	[L1: 0.4426]	9.7+0.1s
+[9600/15960]	[L1: 0.4416]	9.6+0.1s
+[11200/15960]	[L1: 0.4402]	9.9+0.1s
+[12800/15960]	[L1: 0.4413]	9.8+0.1s
+[14400/15960]	[L1: 0.4407]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.71s
+
+[Epoch 254]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4350]	11.2+0.6s
+[3200/15960]	[L1: 0.4403]	10.9+0.1s
+[4800/15960]	[L1: 0.4457]	10.9+0.1s
+[6400/15960]	[L1: 0.4453]	10.9+0.1s
+[8000/15960]	[L1: 0.4459]	11.2+0.1s
+[9600/15960]	[L1: 0.4464]	10.9+0.1s
+[11200/15960]	[L1: 0.4462]	10.8+0.1s
+[12800/15960]	[L1: 0.4453]	10.8+0.1s
+[14400/15960]	[L1: 0.4445]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.75s
+
+[Epoch 255]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4503]	11.1+0.6s
+[3200/15960]	[L1: 0.4424]	10.7+0.1s
+[4800/15960]	[L1: 0.4404]	10.8+0.1s
+[6400/15960]	[L1: 0.4402]	10.1+0.1s
+[8000/15960]	[L1: 0.4408]	10.3+0.1s
+[9600/15960]	[L1: 0.4430]	10.6+0.1s
+[11200/15960]	[L1: 0.4432]	11.2+0.1s
+[12800/15960]	[L1: 0.4428]	10.9+0.1s
+[14400/15960]	[L1: 0.4420]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 0.78s
+
+[Epoch 256]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4336]	11.3+0.6s
+[3200/15960]	[L1: 0.4329]	10.9+0.1s
+[4800/15960]	[L1: 0.4373]	10.9+0.1s
+[6400/15960]	[L1: 0.4375]	10.9+0.1s
+[8000/15960]	[L1: 0.4371]	11.1+0.1s
+[9600/15960]	[L1: 0.4376]	10.9+0.1s
+[11200/15960]	[L1: 0.4369]	10.7+0.1s
+[12800/15960]	[L1: 0.4388]	10.8+0.1s
+[14400/15960]	[L1: 0.4404]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.71s
+
+[Epoch 257]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4429]	11.0+0.6s
+[3200/15960]	[L1: 0.4442]	11.0+0.1s
+[4800/15960]	[L1: 0.4403]	10.7+0.1s
+[6400/15960]	[L1: 0.4396]	10.3+0.1s
+[8000/15960]	[L1: 0.4390]	10.9+0.1s
+[9600/15960]	[L1: 0.4375]	10.7+0.1s
+[11200/15960]	[L1: 0.4390]	10.8+0.1s
+[12800/15960]	[L1: 0.4396]	10.3+0.1s
+[14400/15960]	[L1: 0.4411]	9.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.74s
+
+[Epoch 258]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4328]	10.5+0.6s
+[3200/15960]	[L1: 0.4379]	9.9+0.1s
+[4800/15960]	[L1: 0.4425]	10.4+0.1s
+[6400/15960]	[L1: 0.4417]	9.8+0.1s
+[8000/15960]	[L1: 0.4392]	9.9+0.1s
+[9600/15960]	[L1: 0.4421]	10.3+0.1s
+[11200/15960]	[L1: 0.4409]	10.7+0.1s
+[12800/15960]	[L1: 0.4418]	10.6+0.1s
+[14400/15960]	[L1: 0.4420]	9.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 0.79s
+
+[Epoch 259]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4438]	11.1+0.6s
+[3200/15960]	[L1: 0.4451]	11.1+0.1s
+[4800/15960]	[L1: 0.4430]	11.0+0.1s
+[6400/15960]	[L1: 0.4450]	11.0+0.1s
+[8000/15960]	[L1: 0.4450]	11.1+0.1s
+[9600/15960]	[L1: 0.4429]	10.9+0.1s
+[11200/15960]	[L1: 0.4422]	11.1+0.1s
+[12800/15960]	[L1: 0.4411]	11.0+0.1s
+[14400/15960]	[L1: 0.4424]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.88s
+
+[Epoch 260]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4409]	10.3+0.5s
+[3200/15960]	[L1: 0.4399]	10.3+0.1s
+[4800/15960]	[L1: 0.4385]	10.9+0.1s
+[6400/15960]	[L1: 0.4388]	10.0+0.1s
+[8000/15960]	[L1: 0.4424]	11.3+0.1s
+[9600/15960]	[L1: 0.4434]	10.9+0.1s
+[11200/15960]	[L1: 0.4425]	10.8+0.1s
+[12800/15960]	[L1: 0.4410]	10.6+0.1s
+[14400/15960]	[L1: 0.4418]	10.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.71s
+
+[Epoch 261]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4418]	11.1+0.6s
+[3200/15960]	[L1: 0.4466]	11.1+0.1s
+[4800/15960]	[L1: 0.4478]	10.9+0.1s
+[6400/15960]	[L1: 0.4495]	10.9+0.1s
+[8000/15960]	[L1: 0.4473]	10.9+0.1s
+[9600/15960]	[L1: 0.4456]	10.8+0.1s
+[11200/15960]	[L1: 0.4455]	10.6+0.1s
+[12800/15960]	[L1: 0.4446]	10.7+0.1s
+[14400/15960]	[L1: 0.4443]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.71s
+
+[Epoch 262]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4488]	11.0+0.6s
+[3200/15960]	[L1: 0.4413]	10.7+0.1s
+[4800/15960]	[L1: 0.4419]	10.7+0.1s
+[6400/15960]	[L1: 0.4455]	10.7+0.1s
+[8000/15960]	[L1: 0.4460]	10.6+0.1s
+[9600/15960]	[L1: 0.4457]	10.8+0.1s
+[11200/15960]	[L1: 0.4440]	10.9+0.1s
+[12800/15960]	[L1: 0.4448]	10.8+0.1s
+[14400/15960]	[L1: 0.4453]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.75s
+
+[Epoch 263]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4488]	10.9+0.6s
+[3200/15960]	[L1: 0.4473]	10.9+0.1s
+[4800/15960]	[L1: 0.4453]	10.8+0.1s
+[6400/15960]	[L1: 0.4425]	10.8+0.1s
+[8000/15960]	[L1: 0.4407]	10.9+0.1s
+[9600/15960]	[L1: 0.4415]	10.8+0.1s
+[11200/15960]	[L1: 0.4417]	10.9+0.1s
+[12800/15960]	[L1: 0.4413]	10.8+0.1s
+[14400/15960]	[L1: 0.4404]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.34s
+
+Saving...
+Total: 1.72s
+
+[Epoch 264]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4487]	11.3+0.6s
+[3200/15960]	[L1: 0.4469]	11.0+0.1s
+[4800/15960]	[L1: 0.4441]	11.2+0.1s
+[6400/15960]	[L1: 0.4439]	10.9+0.1s
+[8000/15960]	[L1: 0.4432]	10.5+0.1s
+[9600/15960]	[L1: 0.4453]	11.1+0.1s
+[11200/15960]	[L1: 0.4445]	11.1+0.1s
+[12800/15960]	[L1: 0.4456]	11.0+0.1s
+[14400/15960]	[L1: 0.4468]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 0.90s
+
+[Epoch 265]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4420]	11.1+0.6s
+[3200/15960]	[L1: 0.4383]	10.9+0.1s
+[4800/15960]	[L1: 0.4379]	11.0+0.1s
+[6400/15960]	[L1: 0.4376]	10.7+0.1s
+[8000/15960]	[L1: 0.4374]	10.9+0.1s
+[9600/15960]	[L1: 0.4376]	10.9+0.1s
+[11200/15960]	[L1: 0.4389]	11.1+0.1s
+[12800/15960]	[L1: 0.4399]	10.8+0.1s
+[14400/15960]	[L1: 0.4409]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.34s
+
+Saving...
+Total: 1.75s
+
+[Epoch 266]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4484]	11.3+0.5s
+[3200/15960]	[L1: 0.4413]	11.0+0.1s
+[4800/15960]	[L1: 0.4438]	11.1+0.1s
+[6400/15960]	[L1: 0.4430]	10.9+0.1s
+[8000/15960]	[L1: 0.4421]	10.6+0.1s
+[9600/15960]	[L1: 0.4411]	10.5+0.1s
+[11200/15960]	[L1: 0.4408]	9.7+0.1s
+[12800/15960]	[L1: 0.4430]	10.1+0.1s
+[14400/15960]	[L1: 0.4437]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.73s
+
+[Epoch 267]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4460]	11.3+0.5s
+[3200/15960]	[L1: 0.4450]	10.9+0.1s
+[4800/15960]	[L1: 0.4406]	10.9+0.1s
+[6400/15960]	[L1: 0.4435]	11.0+0.1s
+[8000/15960]	[L1: 0.4407]	11.1+0.1s
+[9600/15960]	[L1: 0.4432]	10.9+0.1s
+[11200/15960]	[L1: 0.4433]	10.9+0.1s
+[12800/15960]	[L1: 0.4431]	10.9+0.1s
+[14400/15960]	[L1: 0.4437]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.71s
+
+[Epoch 268]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4400]	11.5+0.5s
+[3200/15960]	[L1: 0.4386]	11.2+0.1s
+[4800/15960]	[L1: 0.4356]	11.1+0.1s
+[6400/15960]	[L1: 0.4399]	11.4+0.1s
+[8000/15960]	[L1: 0.4391]	11.0+0.1s
+[9600/15960]	[L1: 0.4405]	11.1+0.1s
+[11200/15960]	[L1: 0.4391]	10.6+0.1s
+[12800/15960]	[L1: 0.4412]	11.1+0.1s
+[14400/15960]	[L1: 0.4424]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.71s
+
+[Epoch 269]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4316]	11.2+0.5s
+[3200/15960]	[L1: 0.4302]	10.9+0.1s
+[4800/15960]	[L1: 0.4324]	10.9+0.1s
+[6400/15960]	[L1: 0.4315]	10.9+0.1s
+[8000/15960]	[L1: 0.4331]	10.8+0.1s
+[9600/15960]	[L1: 0.4352]	10.3+0.1s
+[11200/15960]	[L1: 0.4347]	10.0+0.1s
+[12800/15960]	[L1: 0.4352]	9.6+0.1s
+[14400/15960]	[L1: 0.4350]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.75s
+
+[Epoch 270]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4330]	10.3+0.5s
+[3200/15960]	[L1: 0.4446]	9.7+0.1s
+[4800/15960]	[L1: 0.4463]	10.7+0.1s
+[6400/15960]	[L1: 0.4474]	10.9+0.1s
+[8000/15960]	[L1: 0.4460]	9.8+0.1s
+[9600/15960]	[L1: 0.4433]	10.7+0.1s
+[11200/15960]	[L1: 0.4431]	9.8+0.1s
+[12800/15960]	[L1: 0.4440]	9.9+0.1s
+[14400/15960]	[L1: 0.4433]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.74s
+
+[Epoch 271]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4431]	11.1+0.6s
+[3200/15960]	[L1: 0.4434]	11.0+0.1s
+[4800/15960]	[L1: 0.4442]	10.4+0.1s
+[6400/15960]	[L1: 0.4411]	10.8+0.1s
+[8000/15960]	[L1: 0.4413]	10.0+0.1s
+[9600/15960]	[L1: 0.4408]	10.5+0.1s
+[11200/15960]	[L1: 0.4403]	9.6+0.1s
+[12800/15960]	[L1: 0.4395]	9.4+0.1s
+[14400/15960]	[L1: 0.4410]	9.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 0.75s
+
+[Epoch 272]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4431]	10.2+0.5s
+[3200/15960]	[L1: 0.4516]	10.1+0.1s
+[4800/15960]	[L1: 0.4492]	10.1+0.1s
+[6400/15960]	[L1: 0.4485]	10.0+0.1s
+[8000/15960]	[L1: 0.4490]	10.2+0.1s
+[9600/15960]	[L1: 0.4476]	10.4+0.1s
+[11200/15960]	[L1: 0.4445]	10.6+0.1s
+[12800/15960]	[L1: 0.4434]	11.0+0.1s
+[14400/15960]	[L1: 0.4437]	10.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 0.77s
+
+[Epoch 273]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4436]	11.2+0.6s
+[3200/15960]	[L1: 0.4475]	11.1+0.1s
+[4800/15960]	[L1: 0.4479]	11.0+0.1s
+[6400/15960]	[L1: 0.4472]	11.0+0.1s
+[8000/15960]	[L1: 0.4456]	11.0+0.1s
+[9600/15960]	[L1: 0.4460]	11.2+0.1s
+[11200/15960]	[L1: 0.4465]	11.0+0.1s
+[12800/15960]	[L1: 0.4474]	11.0+0.1s
+[14400/15960]	[L1: 0.4463]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 0.80s
+
+[Epoch 274]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4444]	10.6+0.6s
+[3200/15960]	[L1: 0.4461]	11.0+0.1s
+[4800/15960]	[L1: 0.4446]	10.9+0.1s
+[6400/15960]	[L1: 0.4437]	11.1+0.1s
+[8000/15960]	[L1: 0.4430]	10.8+0.1s
+[9600/15960]	[L1: 0.4429]	10.9+0.1s
+[11200/15960]	[L1: 0.4443]	10.9+0.1s
+[12800/15960]	[L1: 0.4433]	10.5+0.1s
+[14400/15960]	[L1: 0.4427]	9.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.89s
+
+[Epoch 275]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4519]	10.9+0.5s
+[3200/15960]	[L1: 0.4447]	9.7+0.1s
+[4800/15960]	[L1: 0.4465]	9.7+0.1s
+[6400/15960]	[L1: 0.4465]	9.8+0.1s
+[8000/15960]	[L1: 0.4444]	9.7+0.1s
+[9600/15960]	[L1: 0.4445]	9.8+0.1s
+[11200/15960]	[L1: 0.4442]	9.7+0.1s
+[12800/15960]	[L1: 0.4415]	10.9+0.1s
+[14400/15960]	[L1: 0.4420]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 0.92s
+
+[Epoch 276]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4415]	11.0+0.6s
+[3200/15960]	[L1: 0.4380]	10.8+0.1s
+[4800/15960]	[L1: 0.4411]	10.8+0.1s
+[6400/15960]	[L1: 0.4387]	10.9+0.1s
+[8000/15960]	[L1: 0.4390]	11.0+0.1s
+[9600/15960]	[L1: 0.4390]	10.9+0.1s
+[11200/15960]	[L1: 0.4410]	10.8+0.1s
+[12800/15960]	[L1: 0.4408]	10.8+0.1s
+[14400/15960]	[L1: 0.4411]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.74s
+
+[Epoch 277]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4401]	10.9+0.6s
+[3200/15960]	[L1: 0.4461]	10.0+0.1s
+[4800/15960]	[L1: 0.4437]	9.9+0.1s
+[6400/15960]	[L1: 0.4473]	10.6+0.1s
+[8000/15960]	[L1: 0.4429]	10.3+0.1s
+[9600/15960]	[L1: 0.4407]	10.3+0.1s
+[11200/15960]	[L1: 0.4409]	9.9+0.1s
+[12800/15960]	[L1: 0.4407]	10.9+0.1s
+[14400/15960]	[L1: 0.4389]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 0.77s
+
+[Epoch 278]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4273]	9.9+0.6s
+[3200/15960]	[L1: 0.4351]	11.1+0.1s
+[4800/15960]	[L1: 0.4383]	10.0+0.1s
+[6400/15960]	[L1: 0.4387]	10.5+0.1s
+[8000/15960]	[L1: 0.4387]	10.2+0.1s
+[9600/15960]	[L1: 0.4384]	11.0+0.1s
+[11200/15960]	[L1: 0.4380]	11.1+0.1s
+[12800/15960]	[L1: 0.4377]	9.9+0.1s
+[14400/15960]	[L1: 0.4373]	9.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 0.78s
+
+[Epoch 279]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4392]	11.3+0.6s
+[3200/15960]	[L1: 0.4407]	11.0+0.1s
+[4800/15960]	[L1: 0.4376]	11.1+0.1s
+[6400/15960]	[L1: 0.4387]	10.1+0.1s
+[8000/15960]	[L1: 0.4352]	9.7+0.1s
+[9600/15960]	[L1: 0.4364]	9.8+0.1s
+[11200/15960]	[L1: 0.4365]	10.4+0.1s
+[12800/15960]	[L1: 0.4384]	10.3+0.1s
+[14400/15960]	[L1: 0.4389]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.34s
+
+Saving...
+Total: 1.73s
+
+[Epoch 280]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4436]	11.2+0.6s
+[3200/15960]	[L1: 0.4394]	10.8+0.1s
+[4800/15960]	[L1: 0.4399]	10.8+0.1s
+[6400/15960]	[L1: 0.4380]	10.8+0.1s
+[8000/15960]	[L1: 0.4390]	10.9+0.1s
+[9600/15960]	[L1: 0.4420]	10.7+0.1s
+[11200/15960]	[L1: 0.4418]	10.7+0.1s
+[12800/15960]	[L1: 0.4399]	10.7+0.1s
+[14400/15960]	[L1: 0.4389]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.74s
+
+[Epoch 281]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4462]	10.0+0.5s
+[3200/15960]	[L1: 0.4412]	10.3+0.1s
+[4800/15960]	[L1: 0.4422]	10.8+0.1s
+[6400/15960]	[L1: 0.4438]	10.9+0.1s
+[8000/15960]	[L1: 0.4434]	9.8+0.1s
+[9600/15960]	[L1: 0.4424]	9.6+0.1s
+[11200/15960]	[L1: 0.4417]	9.6+0.1s
+[12800/15960]	[L1: 0.4394]	9.5+0.1s
+[14400/15960]	[L1: 0.4399]	9.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.71s
+
+[Epoch 282]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4340]	11.1+0.6s
+[3200/15960]	[L1: 0.4333]	10.8+0.1s
+[4800/15960]	[L1: 0.4366]	10.7+0.1s
+[6400/15960]	[L1: 0.4378]	10.5+0.1s
+[8000/15960]	[L1: 0.4351]	10.8+0.1s
+[9600/15960]	[L1: 0.4355]	10.9+0.1s
+[11200/15960]	[L1: 0.4363]	10.7+0.1s
+[12800/15960]	[L1: 0.4369]	10.8+0.1s
+[14400/15960]	[L1: 0.4360]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.73s
+
+[Epoch 283]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4304]	11.0+0.6s
+[3200/15960]	[L1: 0.4403]	10.9+0.1s
+[4800/15960]	[L1: 0.4408]	10.7+0.1s
+[6400/15960]	[L1: 0.4420]	10.8+0.1s
+[8000/15960]	[L1: 0.4397]	10.7+0.1s
+[9600/15960]	[L1: 0.4392]	10.2+0.1s
+[11200/15960]	[L1: 0.4377]	10.9+0.1s
+[12800/15960]	[L1: 0.4375]	10.4+0.1s
+[14400/15960]	[L1: 0.4377]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.34s
+
+Saving...
+Total: 1.73s
+
+[Epoch 284]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4482]	11.2+0.6s
+[3200/15960]	[L1: 0.4382]	10.8+0.1s
+[4800/15960]	[L1: 0.4360]	10.6+0.1s
+[6400/15960]	[L1: 0.4358]	10.5+0.1s
+[8000/15960]	[L1: 0.4363]	10.7+0.1s
+[9600/15960]	[L1: 0.4352]	10.8+0.1s
+[11200/15960]	[L1: 0.4351]	11.2+0.1s
+[12800/15960]	[L1: 0.4351]	10.8+0.1s
+[14400/15960]	[L1: 0.4360]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.74s
+
+[Epoch 285]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4276]	11.1+0.6s
+[3200/15960]	[L1: 0.4348]	11.1+0.1s
+[4800/15960]	[L1: 0.4344]	11.0+0.1s
+[6400/15960]	[L1: 0.4354]	10.9+0.1s
+[8000/15960]	[L1: 0.4357]	11.1+0.1s
+[9600/15960]	[L1: 0.4361]	11.0+0.1s
+[11200/15960]	[L1: 0.4343]	11.1+0.1s
+[12800/15960]	[L1: 0.4346]	11.1+0.1s
+[14400/15960]	[L1: 0.4360]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.73s
+
+[Epoch 286]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4380]	10.5+0.5s
+[3200/15960]	[L1: 0.4399]	10.6+0.1s
+[4800/15960]	[L1: 0.4372]	10.3+0.1s
+[6400/15960]	[L1: 0.4376]	10.4+0.1s
+[8000/15960]	[L1: 0.4355]	10.2+0.1s
+[9600/15960]	[L1: 0.4353]	10.3+0.1s
+[11200/15960]	[L1: 0.4357]	10.2+0.1s
+[12800/15960]	[L1: 0.4356]	10.1+0.1s
+[14400/15960]	[L1: 0.4359]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.34s
+
+Saving...
+Total: 1.87s
+
+[Epoch 287]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4389]	10.7+0.6s
+[3200/15960]	[L1: 0.4466]	10.6+0.1s
+[4800/15960]	[L1: 0.4463]	11.0+0.1s
+[6400/15960]	[L1: 0.4441]	10.8+0.1s
+[8000/15960]	[L1: 0.4413]	10.1+0.1s
+[9600/15960]	[L1: 0.4417]	11.0+0.1s
+[11200/15960]	[L1: 0.4407]	10.8+0.1s
+[12800/15960]	[L1: 0.4395]	11.4+0.1s
+[14400/15960]	[L1: 0.4402]	11.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.73s
+
+[Epoch 288]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4567]	10.9+0.6s
+[3200/15960]	[L1: 0.4472]	11.2+0.1s
+[4800/15960]	[L1: 0.4445]	11.0+0.1s
+[6400/15960]	[L1: 0.4410]	11.1+0.1s
+[8000/15960]	[L1: 0.4400]	11.0+0.1s
+[9600/15960]	[L1: 0.4396]	11.3+0.1s
+[11200/15960]	[L1: 0.4389]	11.2+0.1s
+[12800/15960]	[L1: 0.4386]	11.1+0.1s
+[14400/15960]	[L1: 0.4389]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.89s
+
+[Epoch 289]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4289]	11.2+0.6s
+[3200/15960]	[L1: 0.4373]	11.1+0.1s
+[4800/15960]	[L1: 0.4355]	11.1+0.1s
+[6400/15960]	[L1: 0.4358]	11.5+0.1s
+[8000/15960]	[L1: 0.4340]	11.1+0.1s
+[9600/15960]	[L1: 0.4341]	11.0+0.1s
+[11200/15960]	[L1: 0.4334]	11.1+0.1s
+[12800/15960]	[L1: 0.4332]	11.1+0.1s
+[14400/15960]	[L1: 0.4338]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.89s
+
+[Epoch 290]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4444]	11.1+0.5s
+[3200/15960]	[L1: 0.4416]	11.0+0.1s
+[4800/15960]	[L1: 0.4398]	11.1+0.1s
+[6400/15960]	[L1: 0.4392]	11.0+0.1s
+[8000/15960]	[L1: 0.4381]	11.0+0.1s
+[9600/15960]	[L1: 0.4370]	10.6+0.1s
+[11200/15960]	[L1: 0.4377]	11.0+0.1s
+[12800/15960]	[L1: 0.4372]	11.2+0.1s
+[14400/15960]	[L1: 0.4384]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.72s
+
+[Epoch 291]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4395]	9.9+0.6s
+[3200/15960]	[L1: 0.4366]	9.6+0.1s
+[4800/15960]	[L1: 0.4369]	9.7+0.1s
+[6400/15960]	[L1: 0.4354]	9.6+0.1s
+[8000/15960]	[L1: 0.4389]	9.7+0.1s
+[9600/15960]	[L1: 0.4417]	10.2+0.1s
+[11200/15960]	[L1: 0.4410]	10.3+0.1s
+[12800/15960]	[L1: 0.4400]	10.0+0.1s
+[14400/15960]	[L1: 0.4395]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 0.78s
+
+[Epoch 292]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4335]	11.1+0.6s
+[3200/15960]	[L1: 0.4381]	11.1+0.1s
+[4800/15960]	[L1: 0.4377]	10.9+0.1s
+[6400/15960]	[L1: 0.4353]	11.0+0.1s
+[8000/15960]	[L1: 0.4357]	11.1+0.1s
+[9600/15960]	[L1: 0.4371]	11.1+0.1s
+[11200/15960]	[L1: 0.4367]	9.9+0.1s
+[12800/15960]	[L1: 0.4387]	10.4+0.1s
+[14400/15960]	[L1: 0.4380]	10.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 0.76s
+
+[Epoch 293]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4253]	11.4+0.6s
+[3200/15960]	[L1: 0.4261]	11.1+0.1s
+[4800/15960]	[L1: 0.4277]	11.0+0.1s
+[6400/15960]	[L1: 0.4304]	11.1+0.1s
+[8000/15960]	[L1: 0.4348]	11.1+0.1s
+[9600/15960]	[L1: 0.4347]	11.0+0.1s
+[11200/15960]	[L1: 0.4345]	11.1+0.1s
+[12800/15960]	[L1: 0.4354]	10.7+0.1s
+[14400/15960]	[L1: 0.4354]	9.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.74s
+
+[Epoch 294]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4443]	10.0+0.5s
+[3200/15960]	[L1: 0.4408]	11.1+0.1s
+[4800/15960]	[L1: 0.4437]	10.9+0.1s
+[6400/15960]	[L1: 0.4411]	10.9+0.1s
+[8000/15960]	[L1: 0.4401]	10.9+0.1s
+[9600/15960]	[L1: 0.4380]	10.9+0.1s
+[11200/15960]	[L1: 0.4378]	10.8+0.1s
+[12800/15960]	[L1: 0.4375]	10.9+0.1s
+[14400/15960]	[L1: 0.4366]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.34s
+
+Saving...
+Total: 0.78s
+
+[Epoch 295]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4392]	11.1+0.6s
+[3200/15960]	[L1: 0.4425]	10.6+0.1s
+[4800/15960]	[L1: 0.4380]	9.7+0.1s
+[6400/15960]	[L1: 0.4349]	9.9+0.1s
+[8000/15960]	[L1: 0.4354]	9.8+0.1s
+[9600/15960]	[L1: 0.4381]	9.9+0.1s
+[11200/15960]	[L1: 0.4364]	10.0+0.1s
+[12800/15960]	[L1: 0.4370]	10.3+0.1s
+[14400/15960]	[L1: 0.4358]	9.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.72s
+
+[Epoch 296]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4283]	9.6+0.6s
+[3200/15960]	[L1: 0.4267]	10.1+0.1s
+[4800/15960]	[L1: 0.4291]	10.7+0.1s
+[6400/15960]	[L1: 0.4316]	10.7+0.1s
+[8000/15960]	[L1: 0.4335]	10.6+0.1s
+[9600/15960]	[L1: 0.4340]	10.6+0.1s
+[11200/15960]	[L1: 0.4349]	10.7+0.1s
+[12800/15960]	[L1: 0.4359]	10.6+0.1s
+[14400/15960]	[L1: 0.4375]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 1.75s
+
+[Epoch 297]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4357]	11.3+0.6s
+[3200/15960]	[L1: 0.4320]	10.8+0.1s
+[4800/15960]	[L1: 0.4352]	11.0+0.1s
+[6400/15960]	[L1: 0.4349]	11.0+0.1s
+[8000/15960]	[L1: 0.4339]	10.7+0.1s
+[9600/15960]	[L1: 0.4358]	9.9+0.1s
+[11200/15960]	[L1: 0.4370]	10.0+0.1s
+[12800/15960]	[L1: 0.4378]	10.8+0.1s
+[14400/15960]	[L1: 0.4390]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 0.79s
+
+[Epoch 298]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4443]	11.0+0.6s
+[3200/15960]	[L1: 0.4387]	11.0+0.1s
+[4800/15960]	[L1: 0.4330]	9.7+0.1s
+[6400/15960]	[L1: 0.4362]	10.8+0.1s
+[8000/15960]	[L1: 0.4370]	11.0+0.1s
+[9600/15960]	[L1: 0.4392]	10.7+0.1s
+[11200/15960]	[L1: 0.4373]	11.0+0.1s
+[12800/15960]	[L1: 0.4381]	10.8+0.1s
+[14400/15960]	[L1: 0.4385]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.32s
+
+Saving...
+Total: 1.72s
+
+[Epoch 299]	Learning rate: 2.50e-5
+[1600/15960]	[L1: 0.4359]	11.1+0.5s
+[3200/15960]	[L1: 0.4345]	10.8+0.1s
+[4800/15960]	[L1: 0.4344]	11.0+0.1s
+[6400/15960]	[L1: 0.4356]	11.1+0.1s
+[8000/15960]	[L1: 0.4355]	10.8+0.1s
+[9600/15960]	[L1: 0.4348]	10.9+0.1s
+[11200/15960]	[L1: 0.4350]	10.9+0.1s
+[12800/15960]	[L1: 0.4356]	9.8+0.1s
+[14400/15960]	[L1: 0.4355]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: nan (Best: nan @epoch 1)
+Forward: 0.33s
+
+Saving...
+Total: 0.76s
+
+EWT(
+  (DWT): DWT()
+  (IWT): IWT()
+  (trans): MFAM(
+    (conv_first): Conv2d(24, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (patch_embed): PatchEmbed(
+      (norm): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+    )
+    (patch_unembed): PatchUnEmbed()
+    (pos_drop): Dropout(p=0.0, inplace=False)
+    (layers): ModuleList(
+      (0): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): Identity()
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.014)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+      (1): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.029)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.043)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+      (2): DoublebranchFeatureExtractionBlock(
+        (DFEB): DoubleBranchBlock(
+          (FIEB): ModuleList(
+            (0): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.057)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (1): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.071)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (2): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.086)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+            (3): SwinTransformerBlock(
+              (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (attn): WindowAttention(
+                dim=96, window_size=(8, 8), num_heads=6
+                (qkv): Linear(in_features=96, out_features=288, bias=True)
+                (attn_drop): Dropout(p=0.0, inplace=False)
+                (proj): Linear(in_features=96, out_features=96, bias=True)
+                (proj_drop): Dropout(p=0.0, inplace=False)
+                (softmax): Softmax(dim=-1)
+              )
+              (drop_path): DropPath(drop_prob=0.100)
+              (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+              (mlp): Mlp(
+                (fc1): Linear(in_features=96, out_features=192, bias=True)
+                (act): GELU(approximate='none')
+                (fc2): Linear(in_features=192, out_features=96, bias=True)
+                (drop): Dropout(p=0.0, inplace=False)
+              )
+            )
+          )
+          (SIEB): Sequential(
+            (0): ResBlock(
+              (body): Sequential(
+                (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+                (1): ReLU(inplace=True)
+                (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+              )
+            )
+          )
+        )
+        (conv): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (token_embed): PatchEmbed()
+        (token_unembed): PatchUnEmbed()
+      )
+    )
+    (norm): LayerNorm((96,), eps=1e-05, elementwise_affine=True)
+    (conv_after_body): ResBlock(
+      (body): Sequential(
+        (0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+        (1): ReLU(inplace=True)
+        (2): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      )
+    )
+    (conv_last): Conv2d(96, 12, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+  )
+)
+[Epoch 1]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 38.8606]	12.8+0.7s
+[3200/15600]	[L1: 28.3468]	11.0+0.1s
+[4800/15600]	[L1: 23.3180]	11.0+0.1s
+[6400/15600]	[L1: 20.3516]	11.0+0.1s
+[8000/15600]	[L1: 18.2679]	11.0+0.1s
+[9600/15600]	[L1: 16.5213]	11.0+0.1s
+[11200/15600]	[L1: 14.9782]	11.1+0.1s
+[12800/15600]	[L1: 13.6674]	11.1+0.1s
+[14400/15600]	[L1: 12.5963]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 38.615 (Best: 38.615 @epoch 1)
+Forward: 64.69s
+
+Saving...
+Total: 65.29s
+
+[Epoch 2]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 3.7693]	11.0+0.6s
+[3200/15600]	[L1: 3.7170]	11.8+0.1s
+[4800/15600]	[L1: 3.6269]	10.9+0.1s
+[6400/15600]	[L1: 3.5729]	11.3+0.1s
+[8000/15600]	[L1: 3.4993]	12.8+0.1s
+[9600/15600]	[L1: 3.4520]	11.0+0.1s
+[11200/15600]	[L1: 3.3999]	11.1+0.1s
+[12800/15600]	[L1: 3.3479]	12.2+0.1s
+[14400/15600]	[L1: 3.2995]	12.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 43.030 (Best: 43.030 @epoch 2)
+Forward: 60.76s
+
+Saving...
+Total: 61.28s
+
+[Epoch 3]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 2.7683]	11.2+0.6s
+[3200/15600]	[L1: 2.7799]	10.9+0.1s
+[4800/15600]	[L1: 2.7844]	12.2+0.1s
+[6400/15600]	[L1: 2.7709]	11.1+0.1s
+[8000/15600]	[L1: 2.7209]	10.7+0.1s
+[9600/15600]	[L1: 2.6915]	11.8+0.1s
+[11200/15600]	[L1: 2.6776]	11.1+0.1s
+[12800/15600]	[L1: 2.6568]	11.2+0.1s
+[14400/15600]	[L1: 2.6281]	11.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 43.301 (Best: 43.301 @epoch 3)
+Forward: 60.18s
+
+Saving...
+Total: 60.81s
+
+[Epoch 4]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 2.4075]	11.7+0.7s
+[3200/15600]	[L1: 2.4099]	11.1+0.1s
+[4800/15600]	[L1: 2.3713]	11.3+0.1s
+[6400/15600]	[L1: 2.3536]	12.1+0.1s
+[8000/15600]	[L1: 2.3439]	11.2+0.1s
+[9600/15600]	[L1: 2.3309]	11.2+0.1s
+[11200/15600]	[L1: 2.3095]	12.4+0.1s
+[12800/15600]	[L1: 2.2983]	11.1+0.1s
+[14400/15600]	[L1: 2.2804]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 44.695 (Best: 44.695 @epoch 4)
+Forward: 60.99s
+
+Saving...
+Total: 61.47s
+
+[Epoch 5]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 2.1003]	11.5+0.6s
+[3200/15600]	[L1: 2.1048]	9.7+0.1s
+[4800/15600]	[L1: 2.0923]	10.4+0.1s
+[6400/15600]	[L1: 2.0990]	10.9+0.1s
+[8000/15600]	[L1: 2.0756]	11.8+0.1s
+[9600/15600]	[L1: 2.0850]	10.5+0.1s
+[11200/15600]	[L1: 2.0724]	9.7+0.1s
+[12800/15600]	[L1: 2.0687]	12.0+0.1s
+[14400/15600]	[L1: 2.0562]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 45.200 (Best: 45.200 @epoch 5)
+Forward: 63.73s
+
+Saving...
+Total: 64.23s
+
+[Epoch 6]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.9312]	9.9+0.6s
+[3200/15600]	[L1: 1.9367]	11.0+0.1s
+[4800/15600]	[L1: 1.9256]	10.9+0.1s
+[6400/15600]	[L1: 1.9163]	10.6+0.1s
+[8000/15600]	[L1: 1.9087]	10.7+0.1s
+[9600/15600]	[L1: 1.8967]	12.2+0.1s
+[11200/15600]	[L1: 1.8817]	10.7+0.1s
+[12800/15600]	[L1: 1.8761]	10.7+0.1s
+[14400/15600]	[L1: 1.8697]	12.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 45.386 (Best: 45.386 @epoch 6)
+Forward: 61.62s
+
+Saving...
+Total: 62.16s
+
+[Epoch 7]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.7464]	9.9+0.5s
+[3200/15600]	[L1: 1.7443]	9.4+0.1s
+[4800/15600]	[L1: 1.7443]	9.4+0.1s
+[6400/15600]	[L1: 1.7504]	11.5+0.1s
+[8000/15600]	[L1: 1.7402]	10.7+0.1s
+[9600/15600]	[L1: 1.7378]	10.6+0.1s
+[11200/15600]	[L1: 1.7345]	12.2+0.1s
+[12800/15600]	[L1: 1.7256]	9.8+0.1s
+[14400/15600]	[L1: 1.7278]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 45.057 (Best: 45.386 @epoch 6)
+Forward: 61.60s
+
+Saving...
+Total: 62.06s
+
+[Epoch 8]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.7165]	11.0+0.6s
+[3200/15600]	[L1: 1.6879]	12.0+0.1s
+[4800/15600]	[L1: 1.6901]	10.9+0.1s
+[6400/15600]	[L1: 1.6685]	10.9+0.1s
+[8000/15600]	[L1: 1.6695]	12.4+0.1s
+[9600/15600]	[L1: 1.6569]	11.4+0.1s
+[11200/15600]	[L1: 1.6564]	10.8+0.1s
+[12800/15600]	[L1: 1.6427]	12.4+0.1s
+[14400/15600]	[L1: 1.6364]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 45.847 (Best: 45.847 @epoch 8)
+Forward: 60.60s
+
+Saving...
+Total: 61.10s
+
+[Epoch 9]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.6121]	11.3+0.6s
+[3200/15600]	[L1: 1.5759]	11.3+0.1s
+[4800/15600]	[L1: 1.5723]	12.3+0.1s
+[6400/15600]	[L1: 1.5867]	11.1+0.1s
+[8000/15600]	[L1: 1.5783]	11.1+0.1s
+[9600/15600]	[L1: 1.5686]	12.2+0.1s
+[11200/15600]	[L1: 1.5620]	10.9+0.1s
+[12800/15600]	[L1: 1.5555]	10.5+0.1s
+[14400/15600]	[L1: 1.5534]	11.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 46.500 (Best: 46.500 @epoch 9)
+Forward: 60.59s
+
+Saving...
+Total: 61.24s
+
+[Epoch 10]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.5011]	12.3+0.6s
+[3200/15600]	[L1: 1.4827]	10.8+0.1s
+[4800/15600]	[L1: 1.4907]	11.1+0.1s
+[6400/15600]	[L1: 1.4964]	12.3+0.1s
+[8000/15600]	[L1: 1.4850]	10.7+0.1s
+[9600/15600]	[L1: 1.4797]	10.9+0.1s
+[11200/15600]	[L1: 1.4820]	12.3+0.1s
+[12800/15600]	[L1: 1.4748]	10.9+0.1s
+[14400/15600]	[L1: 1.4659]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 45.577 (Best: 46.500 @epoch 9)
+Forward: 59.49s
+
+Saving...
+Total: 59.94s
+
+[Epoch 11]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.4499]	11.1+0.6s
+[3200/15600]	[L1: 1.4093]	12.0+0.1s
+[4800/15600]	[L1: 1.4017]	10.7+0.1s
+[6400/15600]	[L1: 1.3915]	10.8+0.1s
+[8000/15600]	[L1: 1.4009]	12.5+0.1s
+[9600/15600]	[L1: 1.4003]	11.0+0.1s
+[11200/15600]	[L1: 1.4030]	11.3+0.1s
+[12800/15600]	[L1: 1.3942]	11.9+0.1s
+[14400/15600]	[L1: 1.3949]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 46.941 (Best: 46.941 @epoch 11)
+Forward: 59.92s
+
+Saving...
+Total: 60.43s
+
+[Epoch 12]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.3767]	10.9+0.6s
+[3200/15600]	[L1: 1.3586]	11.7+0.1s
+[4800/15600]	[L1: 1.3551]	11.5+0.1s
+[6400/15600]	[L1: 1.3685]	11.1+0.1s
+[8000/15600]	[L1: 1.3618]	10.9+0.1s
+[9600/15600]	[L1: 1.3511]	11.3+0.1s
+[11200/15600]	[L1: 1.3443]	9.9+0.1s
+[12800/15600]	[L1: 1.3453]	10.2+0.1s
+[14400/15600]	[L1: 1.3396]	11.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 45.941 (Best: 46.941 @epoch 11)
+Forward: 61.13s
+
+Saving...
+Total: 61.59s
+
+[Epoch 13]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.2932]	11.2+0.6s
+[3200/15600]	[L1: 1.3008]	10.6+0.1s
+[4800/15600]	[L1: 1.2757]	12.0+0.1s
+[6400/15600]	[L1: 1.2736]	10.2+0.1s
+[8000/15600]	[L1: 1.2756]	10.3+0.1s
+[9600/15600]	[L1: 1.2832]	10.4+0.1s
+[11200/15600]	[L1: 1.2769]	12.0+0.1s
+[12800/15600]	[L1: 1.2635]	10.7+0.1s
+[14400/15600]	[L1: 1.2618]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 47.330 (Best: 47.330 @epoch 13)
+Forward: 61.34s
+
+Saving...
+Total: 61.85s
+
+[Epoch 14]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.2790]	11.8+0.5s
+[3200/15600]	[L1: 1.2277]	10.4+0.1s
+[4800/15600]	[L1: 1.2326]	10.4+0.1s
+[6400/15600]	[L1: 1.2283]	10.8+0.1s
+[8000/15600]	[L1: 1.2260]	10.5+0.1s
+[9600/15600]	[L1: 1.2277]	10.0+0.1s
+[11200/15600]	[L1: 1.2305]	10.2+0.1s
+[12800/15600]	[L1: 1.2268]	11.2+0.1s
+[14400/15600]	[L1: 1.2223]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 46.399 (Best: 47.330 @epoch 13)
+Forward: 63.36s
+
+Saving...
+Total: 63.83s
+
+[Epoch 15]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.1544]	10.8+0.7s
+[3200/15600]	[L1: 1.1992]	11.1+0.1s
+[4800/15600]	[L1: 1.1723]	10.3+0.1s
+[6400/15600]	[L1: 1.1846]	9.9+0.1s
+[8000/15600]	[L1: 1.1927]	11.0+0.1s
+[9600/15600]	[L1: 1.1948]	12.2+0.1s
+[11200/15600]	[L1: 1.1864]	10.9+0.1s
+[12800/15600]	[L1: 1.1891]	11.0+0.1s
+[14400/15600]	[L1: 1.1908]	12.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 47.342 (Best: 47.342 @epoch 15)
+Forward: 60.19s
+
+Saving...
+Total: 60.69s
+
+[Epoch 16]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.1129]	11.1+0.6s
+[3200/15600]	[L1: 1.1167]	11.2+0.1s
+[4800/15600]	[L1: 1.1095]	12.6+0.1s
+[6400/15600]	[L1: 1.1198]	10.3+0.1s
+[8000/15600]	[L1: 1.1148]	10.7+0.1s
+[9600/15600]	[L1: 1.1194]	12.2+0.1s
+[11200/15600]	[L1: 1.1205]	11.2+0.1s
+[12800/15600]	[L1: 1.1183]	11.1+0.1s
+[14400/15600]	[L1: 1.1231]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 45.916 (Best: 47.342 @epoch 15)
+Forward: 61.54s
+
+Saving...
+Total: 62.02s
+
+[Epoch 17]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.1546]	12.5+0.6s
+[3200/15600]	[L1: 1.1356]	11.1+0.1s
+[4800/15600]	[L1: 1.1351]	10.9+0.1s
+[6400/15600]	[L1: 1.1287]	12.4+0.1s
+[8000/15600]	[L1: 1.1197]	11.1+0.1s
+[9600/15600]	[L1: 1.1139]	11.0+0.1s
+[11200/15600]	[L1: 1.1156]	12.3+0.1s
+[12800/15600]	[L1: 1.1189]	11.1+0.1s
+[14400/15600]	[L1: 1.1171]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 47.541 (Best: 47.541 @epoch 17)
+Forward: 62.97s
+
+Saving...
+Total: 63.44s
+
+[Epoch 18]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.1029]	11.3+0.6s
+[3200/15600]	[L1: 1.0959]	11.6+0.1s
+[4800/15600]	[L1: 1.0942]	10.8+0.1s
+[6400/15600]	[L1: 1.0923]	10.7+0.1s
+[8000/15600]	[L1: 1.0916]	11.9+0.1s
+[9600/15600]	[L1: 1.0935]	10.7+0.1s
+[11200/15600]	[L1: 1.0864]	10.7+0.1s
+[12800/15600]	[L1: 1.0828]	11.7+0.1s
+[14400/15600]	[L1: 1.0802]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 48.013 (Best: 48.013 @epoch 18)
+Forward: 62.43s
+
+Saving...
+Total: 62.91s
+
+[Epoch 19]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.0629]	11.4+0.5s
+[3200/15600]	[L1: 1.0794]	12.0+0.1s
+[4800/15600]	[L1: 1.0667]	9.8+0.1s
+[6400/15600]	[L1: 1.0783]	9.8+0.1s
+[8000/15600]	[L1: 1.0769]	10.7+0.1s
+[9600/15600]	[L1: 1.0734]	10.6+0.1s
+[11200/15600]	[L1: 1.0658]	9.9+0.1s
+[12800/15600]	[L1: 1.0672]	9.1+0.1s
+[14400/15600]	[L1: 1.0638]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 48.402 (Best: 48.402 @epoch 19)
+Forward: 63.10s
+
+Saving...
+Total: 63.62s
+
+[Epoch 20]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.0655]	11.2+0.7s
+[3200/15600]	[L1: 1.0329]	11.2+0.1s
+[4800/15600]	[L1: 1.0349]	12.3+0.1s
+[6400/15600]	[L1: 1.0391]	11.3+0.1s
+[8000/15600]	[L1: 1.0470]	10.7+0.1s
+[9600/15600]	[L1: 1.0453]	10.8+0.1s
+[11200/15600]	[L1: 1.0463]	12.0+0.1s
+[12800/15600]	[L1: 1.0410]	10.8+0.1s
+[14400/15600]	[L1: 1.0413]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 48.049 (Best: 48.402 @epoch 19)
+Forward: 59.60s
+
+Saving...
+Total: 60.08s
+
+[Epoch 21]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.0601]	11.1+0.6s
+[3200/15600]	[L1: 1.0489]	9.7+0.1s
+[4800/15600]	[L1: 1.0412]	10.2+0.1s
+[6400/15600]	[L1: 1.0423]	10.3+0.1s
+[8000/15600]	[L1: 1.0343]	10.8+0.1s
+[9600/15600]	[L1: 1.0286]	10.7+0.1s
+[11200/15600]	[L1: 1.0252]	10.7+0.1s
+[12800/15600]	[L1: 1.0240]	11.3+0.1s
+[14400/15600]	[L1: 1.0206]	9.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 47.708 (Best: 48.402 @epoch 19)
+Forward: 64.99s
+
+Saving...
+Total: 65.46s
+
+[Epoch 22]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.0454]	11.1+0.6s
+[3200/15600]	[L1: 1.0465]	12.3+0.1s
+[4800/15600]	[L1: 1.0417]	11.2+0.1s
+[6400/15600]	[L1: 1.0267]	10.9+0.1s
+[8000/15600]	[L1: 1.0272]	12.3+0.1s
+[9600/15600]	[L1: 1.0219]	11.2+0.1s
+[11200/15600]	[L1: 1.0174]	10.8+0.1s
+[12800/15600]	[L1: 1.0175]	12.1+0.1s
+[14400/15600]	[L1: 1.0194]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 47.992 (Best: 48.402 @epoch 19)
+Forward: 61.84s
+
+Saving...
+Total: 62.28s
+
+[Epoch 23]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.9612]	10.9+0.6s
+[3200/15600]	[L1: 0.9724]	10.7+0.1s
+[4800/15600]	[L1: 0.9760]	11.9+0.1s
+[6400/15600]	[L1: 0.9954]	10.8+0.1s
+[8000/15600]	[L1: 1.0017]	10.6+0.1s
+[9600/15600]	[L1: 0.9954]	12.0+0.1s
+[11200/15600]	[L1: 0.9945]	10.9+0.1s
+[12800/15600]	[L1: 0.9930]	11.1+0.1s
+[14400/15600]	[L1: 0.9914]	12.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 47.628 (Best: 48.402 @epoch 19)
+Forward: 62.34s
+
+Saving...
+Total: 62.76s
+
+[Epoch 24]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 1.0027]	11.2+0.6s
+[3200/15600]	[L1: 1.0033]	11.4+0.1s
+[4800/15600]	[L1: 0.9895]	11.7+0.1s
+[6400/15600]	[L1: 0.9743]	11.0+0.1s
+[8000/15600]	[L1: 0.9707]	10.7+0.1s
+[9600/15600]	[L1: 0.9756]	11.3+0.1s
+[11200/15600]	[L1: 0.9776]	13.1+0.1s
+[12800/15600]	[L1: 0.9745]	10.9+0.1s
+[14400/15600]	[L1: 0.9740]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 48.430 (Best: 48.430 @epoch 24)
+Forward: 60.17s
+
+Saving...
+Total: 60.64s
+
+[Epoch 25]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.9874]	10.9+0.6s
+[3200/15600]	[L1: 0.9945]	13.1+0.1s
+[4800/15600]	[L1: 0.9822]	10.7+0.1s
+[6400/15600]	[L1: 0.9865]	10.7+0.1s
+[8000/15600]	[L1: 0.9908]	12.9+0.1s
+[9600/15600]	[L1: 0.9861]	10.9+0.1s
+[11200/15600]	[L1: 0.9785]	10.8+0.1s
+[12800/15600]	[L1: 0.9709]	13.0+0.1s
+[14400/15600]	[L1: 0.9711]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 48.122 (Best: 48.430 @epoch 24)
+Forward: 65.01s
+
+Saving...
+Total: 65.45s
+
+[Epoch 26]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.9303]	10.9+0.6s
+[3200/15600]	[L1: 0.9484]	10.6+0.1s
+[4800/15600]	[L1: 0.9299]	12.4+0.1s
+[6400/15600]	[L1: 0.9298]	10.5+0.1s
+[8000/15600]	[L1: 0.9279]	10.7+0.1s
+[9600/15600]	[L1: 0.9315]	10.7+0.1s
+[11200/15600]	[L1: 0.9363]	12.8+0.1s
+[12800/15600]	[L1: 0.9411]	10.8+0.1s
+[14400/15600]	[L1: 0.9460]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 48.517 (Best: 48.517 @epoch 26)
+Forward: 60.50s
+
+Saving...
+Total: 60.97s
+
+[Epoch 27]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8961]	10.9+0.6s
+[3200/15600]	[L1: 0.9741]	13.2+0.1s
+[4800/15600]	[L1: 0.9731]	10.9+0.1s
+[6400/15600]	[L1: 0.9568]	10.8+0.1s
+[8000/15600]	[L1: 0.9503]	13.0+0.1s
+[9600/15600]	[L1: 0.9389]	10.9+0.1s
+[11200/15600]	[L1: 0.9391]	11.1+0.1s
+[12800/15600]	[L1: 0.9385]	13.0+0.1s
+[14400/15600]	[L1: 0.9407]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 48.803 (Best: 48.803 @epoch 27)
+Forward: 61.68s
+
+Saving...
+Total: 62.18s
+
+[Epoch 28]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8834]	11.1+0.6s
+[3200/15600]	[L1: 0.9078]	10.6+0.1s
+[4800/15600]	[L1: 0.9070]	11.4+0.1s
+[6400/15600]	[L1: 0.9192]	12.5+0.1s
+[8000/15600]	[L1: 0.9132]	10.8+0.1s
+[9600/15600]	[L1: 0.9111]	10.7+0.1s
+[11200/15600]	[L1: 0.9100]	13.1+0.1s
+[12800/15600]	[L1: 0.9110]	10.9+0.1s
+[14400/15600]	[L1: 0.9093]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 48.369 (Best: 48.803 @epoch 27)
+Forward: 63.64s
+
+Saving...
+Total: 64.07s
+
+[Epoch 29]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.9284]	11.4+0.6s
+[3200/15600]	[L1: 0.8915]	12.7+0.1s
+[4800/15600]	[L1: 0.9177]	10.9+0.1s
+[6400/15600]	[L1: 0.9115]	10.9+0.1s
+[8000/15600]	[L1: 0.9196]	13.2+0.1s
+[9600/15600]	[L1: 0.9132]	10.8+0.1s
+[11200/15600]	[L1: 0.9128]	10.9+0.1s
+[12800/15600]	[L1: 0.9136]	13.0+0.1s
+[14400/15600]	[L1: 0.9125]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.415 (Best: 49.415 @epoch 29)
+Forward: 63.86s
+
+Saving...
+Total: 64.35s
+
+[Epoch 30]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8534]	11.3+0.5s
+[3200/15600]	[L1: 0.8789]	11.1+0.1s
+[4800/15600]	[L1: 0.8598]	12.4+0.1s
+[6400/15600]	[L1: 0.8631]	11.4+0.1s
+[8000/15600]	[L1: 0.8757]	11.2+0.1s
+[9600/15600]	[L1: 0.8860]	12.0+0.1s
+[11200/15600]	[L1: 0.8867]	11.0+0.1s
+[12800/15600]	[L1: 0.8815]	11.1+0.1s
+[14400/15600]	[L1: 0.8834]	12.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.844 (Best: 49.844 @epoch 30)
+Forward: 62.70s
+
+Saving...
+Total: 63.51s
+
+[Epoch 31]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8767]	12.9+0.7s
+[3200/15600]	[L1: 0.9158]	10.8+0.1s
+[4800/15600]	[L1: 0.9068]	11.0+0.1s
+[6400/15600]	[L1: 0.9012]	12.6+0.1s
+[8000/15600]	[L1: 0.8913]	10.8+0.1s
+[9600/15600]	[L1: 0.8937]	11.2+0.1s
+[11200/15600]	[L1: 0.8989]	13.4+0.1s
+[12800/15600]	[L1: 0.8937]	10.2+0.1s
+[14400/15600]	[L1: 0.8942]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 48.667 (Best: 49.844 @epoch 30)
+Forward: 63.02s
+
+Saving...
+Total: 63.50s
+
+[Epoch 32]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8499]	11.0+0.6s
+[3200/15600]	[L1: 0.8597]	12.9+0.1s
+[4800/15600]	[L1: 0.8780]	10.8+0.1s
+[6400/15600]	[L1: 0.8801]	11.0+0.1s
+[8000/15600]	[L1: 0.8791]	12.8+0.1s
+[9600/15600]	[L1: 0.8677]	10.5+0.1s
+[11200/15600]	[L1: 0.8667]	9.7+0.1s
+[12800/15600]	[L1: 0.8767]	10.0+0.1s
+[14400/15600]	[L1: 0.8718]	12.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.061 (Best: 50.061 @epoch 32)
+Forward: 59.90s
+
+Saving...
+Total: 60.71s
+
+[Epoch 33]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8527]	10.8+0.7s
+[3200/15600]	[L1: 0.8590]	10.2+0.1s
+[4800/15600]	[L1: 0.8727]	10.0+0.1s
+[6400/15600]	[L1: 0.8651]	12.3+0.1s
+[8000/15600]	[L1: 0.8756]	10.1+0.1s
+[9600/15600]	[L1: 0.8803]	10.1+0.1s
+[11200/15600]	[L1: 0.8827]	12.0+0.1s
+[12800/15600]	[L1: 0.8766]	10.0+0.1s
+[14400/15600]	[L1: 0.8764]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 48.934 (Best: 50.061 @epoch 32)
+Forward: 62.12s
+
+Saving...
+Total: 62.73s
+
+[Epoch 34]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8632]	10.9+0.7s
+[3200/15600]	[L1: 0.8757]	13.0+0.1s
+[4800/15600]	[L1: 0.8677]	10.7+0.1s
+[6400/15600]	[L1: 0.8598]	10.6+0.1s
+[8000/15600]	[L1: 0.8621]	11.9+0.1s
+[9600/15600]	[L1: 0.8599]	12.4+0.1s
+[11200/15600]	[L1: 0.8642]	10.3+0.1s
+[12800/15600]	[L1: 0.8689]	10.0+0.1s
+[14400/15600]	[L1: 0.8626]	12.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.471 (Best: 50.061 @epoch 32)
+Forward: 62.29s
+
+Saving...
+Total: 63.05s
+
+[Epoch 35]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8095]	13.6+0.8s
+[3200/15600]	[L1: 0.8557]	11.2+0.1s
+[4800/15600]	[L1: 0.8677]	10.7+0.1s
+[6400/15600]	[L1: 0.8597]	13.1+0.1s
+[8000/15600]	[L1: 0.8508]	11.0+0.1s
+[9600/15600]	[L1: 0.8599]	10.9+0.1s
+[11200/15600]	[L1: 0.8515]	12.7+0.1s
+[12800/15600]	[L1: 0.8505]	11.4+0.1s
+[14400/15600]	[L1: 0.8491]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.039 (Best: 50.061 @epoch 32)
+Forward: 64.05s
+
+Saving...
+Total: 64.55s
+
+[Epoch 36]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8458]	10.3+0.6s
+[3200/15600]	[L1: 0.8433]	12.7+0.1s
+[4800/15600]	[L1: 0.8546]	11.2+0.1s
+[6400/15600]	[L1: 0.8625]	11.1+0.1s
+[8000/15600]	[L1: 0.8685]	11.0+0.1s
+[9600/15600]	[L1: 0.8684]	13.3+0.1s
+[11200/15600]	[L1: 0.8631]	11.0+0.1s
+[12800/15600]	[L1: 0.8573]	11.1+0.1s
+[14400/15600]	[L1: 0.8536]	12.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 47.943 (Best: 50.061 @epoch 32)
+Forward: 60.91s
+
+Saving...
+Total: 61.52s
+
+[Epoch 37]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8855]	11.8+0.7s
+[3200/15600]	[L1: 0.8482]	10.8+0.1s
+[4800/15600]	[L1: 0.8286]	10.9+0.1s
+[6400/15600]	[L1: 0.8351]	13.4+0.1s
+[8000/15600]	[L1: 0.8310]	11.0+0.1s
+[9600/15600]	[L1: 0.8304]	10.9+0.1s
+[11200/15600]	[L1: 0.8310]	13.0+0.1s
+[12800/15600]	[L1: 0.8336]	11.1+0.1s
+[14400/15600]	[L1: 0.8303]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.545 (Best: 50.545 @epoch 37)
+Forward: 61.01s
+
+Saving...
+Total: 61.54s
+
+[Epoch 38]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8567]	10.9+0.6s
+[3200/15600]	[L1: 0.8485]	13.2+0.1s
+[4800/15600]	[L1: 0.8263]	10.8+0.1s
+[6400/15600]	[L1: 0.8265]	10.7+0.1s
+[8000/15600]	[L1: 0.8310]	11.9+0.1s
+[9600/15600]	[L1: 0.8263]	11.5+0.1s
+[11200/15600]	[L1: 0.8305]	11.1+0.1s
+[12800/15600]	[L1: 0.8288]	10.9+0.1s
+[14400/15600]	[L1: 0.8307]	13.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.696 (Best: 50.545 @epoch 37)
+Forward: 61.54s
+
+Saving...
+Total: 62.45s
+
+[Epoch 39]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7925]	13.0+0.7s
+[3200/15600]	[L1: 0.8034]	10.9+0.1s
+[4800/15600]	[L1: 0.8104]	11.0+0.1s
+[6400/15600]	[L1: 0.8107]	13.4+0.1s
+[8000/15600]	[L1: 0.8077]	11.1+0.1s
+[9600/15600]	[L1: 0.8130]	10.9+0.1s
+[11200/15600]	[L1: 0.8112]	13.0+0.1s
+[12800/15600]	[L1: 0.8082]	11.0+0.1s
+[14400/15600]	[L1: 0.8037]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.213 (Best: 50.545 @epoch 37)
+Forward: 62.87s
+
+Saving...
+Total: 63.37s
+
+[Epoch 40]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.9074]	11.0+0.6s
+[3200/15600]	[L1: 0.9044]	10.0+0.1s
+[4800/15600]	[L1: 0.8681]	12.6+0.1s
+[6400/15600]	[L1: 0.8449]	10.1+0.1s
+[8000/15600]	[L1: 0.8337]	11.4+0.1s
+[9600/15600]	[L1: 0.8311]	13.7+0.1s
+[11200/15600]	[L1: 0.8314]	10.9+0.1s
+[12800/15600]	[L1: 0.8248]	11.1+0.1s
+[14400/15600]	[L1: 0.8202]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.351 (Best: 50.545 @epoch 37)
+Forward: 61.49s
+
+Saving...
+Total: 62.01s
+
+[Epoch 41]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8430]	13.6+0.6s
+[3200/15600]	[L1: 0.8397]	11.0+0.1s
+[4800/15600]	[L1: 0.8292]	11.1+0.1s
+[6400/15600]	[L1: 0.8148]	11.5+0.1s
+[8000/15600]	[L1: 0.8197]	12.2+0.1s
+[9600/15600]	[L1: 0.8200]	10.8+0.1s
+[11200/15600]	[L1: 0.8204]	10.9+0.1s
+[12800/15600]	[L1: 0.8193]	13.1+0.1s
+[14400/15600]	[L1: 0.8174]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.471 (Best: 50.545 @epoch 37)
+Forward: 60.38s
+
+Saving...
+Total: 60.85s
+
+[Epoch 42]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7846]	11.0+0.6s
+[3200/15600]	[L1: 0.7842]	11.1+0.1s
+[4800/15600]	[L1: 0.7898]	13.5+0.1s
+[6400/15600]	[L1: 0.7849]	11.0+0.1s
+[8000/15600]	[L1: 0.7856]	11.1+0.1s
+[9600/15600]	[L1: 0.7886]	13.7+0.1s
+[11200/15600]	[L1: 0.7857]	11.0+0.1s
+[12800/15600]	[L1: 0.7828]	10.1+0.1s
+[14400/15600]	[L1: 0.7829]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.778 (Best: 50.778 @epoch 42)
+Forward: 60.77s
+
+Saving...
+Total: 61.24s
+
+[Epoch 43]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8601]	12.9+0.6s
+[3200/15600]	[L1: 0.8506]	11.1+0.1s
+[4800/15600]	[L1: 0.8267]	11.4+0.1s
+[6400/15600]	[L1: 0.8189]	13.4+0.1s
+[8000/15600]	[L1: 0.8138]	11.2+0.1s
+[9600/15600]	[L1: 0.8153]	11.2+0.1s
+[11200/15600]	[L1: 0.8197]	11.9+0.1s
+[12800/15600]	[L1: 0.8168]	12.7+0.1s
+[14400/15600]	[L1: 0.8173]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.043 (Best: 50.778 @epoch 42)
+Forward: 64.37s
+
+Saving...
+Total: 64.84s
+
+[Epoch 44]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8053]	11.0+0.6s
+[3200/15600]	[L1: 0.7927]	13.3+0.1s
+[4800/15600]	[L1: 0.7828]	11.1+0.1s
+[6400/15600]	[L1: 0.7786]	11.1+0.1s
+[8000/15600]	[L1: 0.7875]	10.9+0.1s
+[9600/15600]	[L1: 0.7865]	13.3+0.1s
+[11200/15600]	[L1: 0.7949]	11.1+0.1s
+[12800/15600]	[L1: 0.7957]	10.9+0.1s
+[14400/15600]	[L1: 0.7959]	13.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.949 (Best: 50.778 @epoch 42)
+Forward: 66.50s
+
+Saving...
+Total: 67.08s
+
+[Epoch 45]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8272]	13.0+0.6s
+[3200/15600]	[L1: 0.8170]	9.9+0.1s
+[4800/15600]	[L1: 0.8088]	10.1+0.1s
+[6400/15600]	[L1: 0.8098]	12.9+0.1s
+[8000/15600]	[L1: 0.8020]	10.0+0.1s
+[9600/15600]	[L1: 0.7946]	10.1+0.1s
+[11200/15600]	[L1: 0.7909]	10.1+0.1s
+[12800/15600]	[L1: 0.7863]	12.6+0.1s
+[14400/15600]	[L1: 0.7807]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.649 (Best: 50.778 @epoch 42)
+Forward: 61.54s
+
+Saving...
+Total: 61.97s
+
+[Epoch 46]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8158]	11.0+0.5s
+[3200/15600]	[L1: 0.7845]	10.6+0.1s
+[4800/15600]	[L1: 0.7793]	12.0+0.1s
+[6400/15600]	[L1: 0.7878]	10.8+0.1s
+[8000/15600]	[L1: 0.7863]	9.6+0.1s
+[9600/15600]	[L1: 0.7877]	10.8+0.1s
+[11200/15600]	[L1: 0.7868]	9.9+0.1s
+[12800/15600]	[L1: 0.7882]	11.1+0.1s
+[14400/15600]	[L1: 0.7829]	10.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.021 (Best: 50.778 @epoch 42)
+Forward: 61.97s
+
+Saving...
+Total: 62.42s
+
+[Epoch 47]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7673]	13.1+0.6s
+[3200/15600]	[L1: 0.7614]	11.3+0.1s
+[4800/15600]	[L1: 0.7604]	11.0+0.1s
+[6400/15600]	[L1: 0.7702]	11.8+0.1s
+[8000/15600]	[L1: 0.7750]	10.3+0.1s
+[9600/15600]	[L1: 0.7685]	10.2+0.1s
+[11200/15600]	[L1: 0.7710]	11.5+0.1s
+[12800/15600]	[L1: 0.7698]	9.9+0.1s
+[14400/15600]	[L1: 0.7746]	9.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.861 (Best: 50.861 @epoch 47)
+Forward: 63.79s
+
+Saving...
+Total: 64.28s
+
+[Epoch 48]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7780]	10.6+0.5s
+[3200/15600]	[L1: 0.7596]	10.9+0.1s
+[4800/15600]	[L1: 0.7625]	9.8+0.1s
+[6400/15600]	[L1: 0.7593]	10.7+0.1s
+[8000/15600]	[L1: 0.7596]	11.8+0.1s
+[9600/15600]	[L1: 0.7669]	10.6+0.1s
+[11200/15600]	[L1: 0.7621]	10.9+0.1s
+[12800/15600]	[L1: 0.7661]	10.9+0.1s
+[14400/15600]	[L1: 0.7693]	12.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.561 (Best: 51.561 @epoch 48)
+Forward: 63.21s
+
+Saving...
+Total: 63.76s
+
+[Epoch 49]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7473]	11.8+0.7s
+[3200/15600]	[L1: 0.7554]	11.1+0.1s
+[4800/15600]	[L1: 0.7588]	13.5+0.1s
+[6400/15600]	[L1: 0.7625]	9.7+0.1s
+[8000/15600]	[L1: 0.7647]	10.5+0.1s
+[9600/15600]	[L1: 0.7577]	12.4+0.1s
+[11200/15600]	[L1: 0.7560]	11.8+0.1s
+[12800/15600]	[L1: 0.7566]	10.9+0.1s
+[14400/15600]	[L1: 0.7566]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.298 (Best: 51.561 @epoch 48)
+Forward: 59.95s
+
+Saving...
+Total: 60.43s
+
+[Epoch 50]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7521]	11.3+0.6s
+[3200/15600]	[L1: 0.7641]	13.1+0.1s
+[4800/15600]	[L1: 0.7705]	10.9+0.1s
+[6400/15600]	[L1: 0.7591]	10.9+0.1s
+[8000/15600]	[L1: 0.7539]	13.2+0.1s
+[9600/15600]	[L1: 0.7555]	10.9+0.1s
+[11200/15600]	[L1: 0.7522]	11.1+0.1s
+[12800/15600]	[L1: 0.7532]	13.3+0.1s
+[14400/15600]	[L1: 0.7515]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.265 (Best: 51.561 @epoch 48)
+Forward: 58.38s
+
+Saving...
+Total: 59.12s
+
+[Epoch 51]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7572]	13.4+0.6s
+[3200/15600]	[L1: 0.7284]	11.0+0.1s
+[4800/15600]	[L1: 0.7369]	11.0+0.1s
+[6400/15600]	[L1: 0.7463]	13.1+0.1s
+[8000/15600]	[L1: 0.7453]	11.1+0.1s
+[9600/15600]	[L1: 0.7554]	11.1+0.1s
+[11200/15600]	[L1: 0.7605]	13.3+0.1s
+[12800/15600]	[L1: 0.7608]	11.1+0.1s
+[14400/15600]	[L1: 0.7544]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 47.573 (Best: 51.561 @epoch 48)
+Forward: 63.80s
+
+Saving...
+Total: 64.26s
+
+[Epoch 52]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.8290]	11.1+0.6s
+[3200/15600]	[L1: 0.7919]	12.1+0.1s
+[4800/15600]	[L1: 0.7951]	10.4+0.1s
+[6400/15600]	[L1: 0.7733]	10.3+0.1s
+[8000/15600]	[L1: 0.7668]	11.4+0.1s
+[9600/15600]	[L1: 0.7648]	11.1+0.1s
+[11200/15600]	[L1: 0.7693]	10.8+0.1s
+[12800/15600]	[L1: 0.7605]	12.2+0.1s
+[14400/15600]	[L1: 0.7614]	10.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.202 (Best: 51.561 @epoch 48)
+Forward: 65.73s
+
+Saving...
+Total: 66.20s
+
+[Epoch 53]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7401]	11.0+0.5s
+[3200/15600]	[L1: 0.7217]	10.9+0.1s
+[4800/15600]	[L1: 0.7348]	12.2+0.1s
+[6400/15600]	[L1: 0.7361]	10.2+0.1s
+[8000/15600]	[L1: 0.7353]	9.0+0.1s
+[9600/15600]	[L1: 0.7552]	10.3+0.1s
+[11200/15600]	[L1: 0.7566]	10.9+0.1s
+[12800/15600]	[L1: 0.7580]	10.4+0.1s
+[14400/15600]	[L1: 0.7505]	9.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.901 (Best: 51.561 @epoch 48)
+Forward: 61.04s
+
+Saving...
+Total: 61.52s
+
+[Epoch 54]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7100]	13.0+0.8s
+[3200/15600]	[L1: 0.7065]	11.9+0.1s
+[4800/15600]	[L1: 0.7238]	11.0+0.1s
+[6400/15600]	[L1: 0.7168]	11.1+0.1s
+[8000/15600]	[L1: 0.7158]	13.3+0.1s
+[9600/15600]	[L1: 0.7111]	11.0+0.1s
+[11200/15600]	[L1: 0.7162]	11.1+0.1s
+[12800/15600]	[L1: 0.7181]	13.4+0.1s
+[14400/15600]	[L1: 0.7215]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.378 (Best: 51.561 @epoch 48)
+Forward: 65.21s
+
+Saving...
+Total: 65.69s
+
+[Epoch 55]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7753]	10.6+0.6s
+[3200/15600]	[L1: 0.7639]	10.8+0.1s
+[4800/15600]	[L1: 0.7677]	13.0+0.1s
+[6400/15600]	[L1: 0.7557]	11.0+0.1s
+[8000/15600]	[L1: 0.7417]	11.1+0.1s
+[9600/15600]	[L1: 0.7479]	13.2+0.1s
+[11200/15600]	[L1: 0.7437]	11.0+0.1s
+[12800/15600]	[L1: 0.7404]	11.0+0.1s
+[14400/15600]	[L1: 0.7380]	13.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.864 (Best: 51.561 @epoch 48)
+Forward: 59.93s
+
+Saving...
+Total: 60.38s
+
+[Epoch 56]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7625]	12.8+0.6s
+[3200/15600]	[L1: 0.7400]	10.6+0.1s
+[4800/15600]	[L1: 0.7601]	10.4+0.1s
+[6400/15600]	[L1: 0.7629]	13.2+0.1s
+[8000/15600]	[L1: 0.7590]	10.7+0.1s
+[9600/15600]	[L1: 0.7486]	10.4+0.1s
+[11200/15600]	[L1: 0.7458]	12.4+0.1s
+[12800/15600]	[L1: 0.7431]	10.9+0.1s
+[14400/15600]	[L1: 0.7397]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.673 (Best: 51.673 @epoch 56)
+Forward: 63.32s
+
+Saving...
+Total: 63.81s
+
+[Epoch 57]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6884]	11.4+0.6s
+[3200/15600]	[L1: 0.7447]	13.4+0.1s
+[4800/15600]	[L1: 0.7436]	10.9+0.1s
+[6400/15600]	[L1: 0.7353]	10.9+0.1s
+[8000/15600]	[L1: 0.7290]	13.1+0.1s
+[9600/15600]	[L1: 0.7229]	11.1+0.1s
+[11200/15600]	[L1: 0.7216]	10.8+0.1s
+[12800/15600]	[L1: 0.7183]	10.3+0.1s
+[14400/15600]	[L1: 0.7170]	12.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.044 (Best: 51.673 @epoch 56)
+Forward: 61.93s
+
+Saving...
+Total: 62.50s
+
+[Epoch 58]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7335]	11.2+0.6s
+[3200/15600]	[L1: 0.7330]	11.1+0.1s
+[4800/15600]	[L1: 0.7382]	13.3+0.1s
+[6400/15600]	[L1: 0.7389]	10.8+0.1s
+[8000/15600]	[L1: 0.7331]	11.6+0.1s
+[9600/15600]	[L1: 0.7276]	10.1+0.1s
+[11200/15600]	[L1: 0.7200]	13.0+0.1s
+[12800/15600]	[L1: 0.7170]	10.5+0.1s
+[14400/15600]	[L1: 0.7191]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.391 (Best: 51.673 @epoch 56)
+Forward: 60.68s
+
+Saving...
+Total: 61.15s
+
+[Epoch 59]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7592]	13.4+0.7s
+[3200/15600]	[L1: 0.7341]	10.9+0.1s
+[4800/15600]	[L1: 0.7343]	11.1+0.1s
+[6400/15600]	[L1: 0.7293]	10.8+0.1s
+[8000/15600]	[L1: 0.7283]	12.8+0.1s
+[9600/15600]	[L1: 0.7327]	10.0+0.1s
+[11200/15600]	[L1: 0.7306]	9.5+0.1s
+[12800/15600]	[L1: 0.7284]	12.8+0.1s
+[14400/15600]	[L1: 0.7277]	9.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.097 (Best: 52.097 @epoch 59)
+Forward: 62.84s
+
+Saving...
+Total: 63.34s
+
+[Epoch 60]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6951]	11.0+0.6s
+[3200/15600]	[L1: 0.6779]	10.9+0.1s
+[4800/15600]	[L1: 0.6959]	12.9+0.1s
+[6400/15600]	[L1: 0.7042]	10.7+0.1s
+[8000/15600]	[L1: 0.6992]	10.8+0.1s
+[9600/15600]	[L1: 0.7065]	11.7+0.1s
+[11200/15600]	[L1: 0.7049]	12.6+0.1s
+[12800/15600]	[L1: 0.7012]	10.9+0.1s
+[14400/15600]	[L1: 0.7030]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.214 (Best: 52.097 @epoch 59)
+Forward: 62.15s
+
+Saving...
+Total: 62.61s
+
+[Epoch 61]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7339]	13.2+0.6s
+[3200/15600]	[L1: 0.7286]	10.9+0.1s
+[4800/15600]	[L1: 0.7098]	10.9+0.1s
+[6400/15600]	[L1: 0.7114]	12.9+0.1s
+[8000/15600]	[L1: 0.7155]	10.9+0.1s
+[9600/15600]	[L1: 0.7197]	10.9+0.1s
+[11200/15600]	[L1: 0.7156]	13.3+0.1s
+[12800/15600]	[L1: 0.7167]	11.1+0.1s
+[14400/15600]	[L1: 0.7177]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.332 (Best: 52.097 @epoch 59)
+Forward: 65.20s
+
+Saving...
+Total: 65.71s
+
+[Epoch 62]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7185]	11.2+0.6s
+[3200/15600]	[L1: 0.7334]	12.5+0.1s
+[4800/15600]	[L1: 0.7270]	10.8+0.1s
+[6400/15600]	[L1: 0.7305]	10.4+0.1s
+[8000/15600]	[L1: 0.7267]	12.5+0.1s
+[9600/15600]	[L1: 0.7246]	10.8+0.1s
+[11200/15600]	[L1: 0.7216]	10.1+0.1s
+[12800/15600]	[L1: 0.7178]	10.5+0.1s
+[14400/15600]	[L1: 0.7208]	11.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.585 (Best: 52.097 @epoch 59)
+Forward: 62.19s
+
+Saving...
+Total: 62.69s
+
+[Epoch 63]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7574]	11.6+0.6s
+[3200/15600]	[L1: 0.7311]	11.1+0.1s
+[4800/15600]	[L1: 0.7255]	13.1+0.1s
+[6400/15600]	[L1: 0.7198]	11.1+0.1s
+[8000/15600]	[L1: 0.7185]	11.1+0.1s
+[9600/15600]	[L1: 0.7133]	11.0+0.1s
+[11200/15600]	[L1: 0.7120]	13.8+0.1s
+[12800/15600]	[L1: 0.7107]	11.2+0.1s
+[14400/15600]	[L1: 0.7090]	11.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.598 (Best: 52.097 @epoch 59)
+Forward: 60.97s
+
+Saving...
+Total: 61.43s
+
+[Epoch 64]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7118]	12.5+0.6s
+[3200/15600]	[L1: 0.7165]	10.7+0.1s
+[4800/15600]	[L1: 0.7230]	11.0+0.1s
+[6400/15600]	[L1: 0.7163]	10.0+0.1s
+[8000/15600]	[L1: 0.7199]	12.6+0.1s
+[9600/15600]	[L1: 0.7171]	11.0+0.1s
+[11200/15600]	[L1: 0.7137]	11.1+0.1s
+[12800/15600]	[L1: 0.7116]	12.4+0.1s
+[14400/15600]	[L1: 0.7102]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.206 (Best: 52.097 @epoch 59)
+Forward: 64.12s
+
+Saving...
+Total: 64.60s
+
+[Epoch 65]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6854]	10.8+0.6s
+[3200/15600]	[L1: 0.7088]	10.6+0.1s
+[4800/15600]	[L1: 0.6982]	10.7+0.1s
+[6400/15600]	[L1: 0.7023]	11.7+0.1s
+[8000/15600]	[L1: 0.7040]	10.0+0.1s
+[9600/15600]	[L1: 0.7042]	9.5+0.1s
+[11200/15600]	[L1: 0.7018]	12.0+0.1s
+[12800/15600]	[L1: 0.7049]	10.5+0.1s
+[14400/15600]	[L1: 0.7026]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.341 (Best: 52.097 @epoch 59)
+Forward: 62.21s
+
+Saving...
+Total: 62.70s
+
+[Epoch 66]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6930]	11.3+0.6s
+[3200/15600]	[L1: 0.7027]	13.0+0.1s
+[4800/15600]	[L1: 0.6915]	10.7+0.1s
+[6400/15600]	[L1: 0.7011]	10.7+0.1s
+[8000/15600]	[L1: 0.6999]	10.9+0.1s
+[9600/15600]	[L1: 0.6985]	12.9+0.1s
+[11200/15600]	[L1: 0.6939]	11.0+0.1s
+[12800/15600]	[L1: 0.6934]	10.9+0.1s
+[14400/15600]	[L1: 0.6932]	13.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.351 (Best: 52.097 @epoch 59)
+Forward: 60.87s
+
+Saving...
+Total: 61.76s
+
+[Epoch 67]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7177]	11.0+0.7s
+[3200/15600]	[L1: 0.7081]	11.3+0.1s
+[4800/15600]	[L1: 0.6910]	12.7+0.1s
+[6400/15600]	[L1: 0.6957]	11.3+0.1s
+[8000/15600]	[L1: 0.6995]	10.8+0.1s
+[9600/15600]	[L1: 0.6940]	10.8+0.1s
+[11200/15600]	[L1: 0.6954]	13.2+0.1s
+[12800/15600]	[L1: 0.6964]	11.1+0.1s
+[14400/15600]	[L1: 0.6948]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 48.190 (Best: 52.097 @epoch 59)
+Forward: 62.45s
+
+Saving...
+Total: 62.94s
+
+[Epoch 68]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7062]	12.4+0.6s
+[3200/15600]	[L1: 0.6909]	11.8+0.1s
+[4800/15600]	[L1: 0.6930]	10.9+0.1s
+[6400/15600]	[L1: 0.6864]	10.8+0.1s
+[8000/15600]	[L1: 0.6873]	13.3+0.1s
+[9600/15600]	[L1: 0.6847]	11.2+0.1s
+[11200/15600]	[L1: 0.6847]	11.0+0.1s
+[12800/15600]	[L1: 0.6844]	13.1+0.1s
+[14400/15600]	[L1: 0.6854]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.145 (Best: 52.097 @epoch 59)
+Forward: 61.97s
+
+Saving...
+Total: 62.60s
+
+[Epoch 69]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6645]	11.1+0.6s
+[3200/15600]	[L1: 0.6690]	11.0+0.1s
+[4800/15600]	[L1: 0.6663]	13.2+0.1s
+[6400/15600]	[L1: 0.6859]	10.8+0.1s
+[8000/15600]	[L1: 0.6858]	10.7+0.1s
+[9600/15600]	[L1: 0.6856]	11.6+0.1s
+[11200/15600]	[L1: 0.6848]	10.1+0.1s
+[12800/15600]	[L1: 0.6886]	10.1+0.1s
+[14400/15600]	[L1: 0.6838]	9.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.390 (Best: 52.097 @epoch 59)
+Forward: 63.34s
+
+Saving...
+Total: 63.84s
+
+[Epoch 70]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6919]	11.9+0.6s
+[3200/15600]	[L1: 0.6787]	10.9+0.1s
+[4800/15600]	[L1: 0.6941]	11.1+0.1s
+[6400/15600]	[L1: 0.7028]	11.2+0.1s
+[8000/15600]	[L1: 0.7064]	11.2+0.1s
+[9600/15600]	[L1: 0.7062]	11.1+0.1s
+[11200/15600]	[L1: 0.7012]	11.7+0.1s
+[12800/15600]	[L1: 0.7009]	11.0+0.1s
+[14400/15600]	[L1: 0.6996]	10.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.909 (Best: 52.097 @epoch 59)
+Forward: 64.27s
+
+Saving...
+Total: 64.78s
+
+[Epoch 71]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6997]	11.1+0.5s
+[3200/15600]	[L1: 0.6979]	11.9+0.1s
+[4800/15600]	[L1: 0.6933]	11.1+0.1s
+[6400/15600]	[L1: 0.6927]	10.9+0.1s
+[8000/15600]	[L1: 0.6887]	11.9+0.1s
+[9600/15600]	[L1: 0.6846]	11.0+0.1s
+[11200/15600]	[L1: 0.6835]	10.8+0.1s
+[12800/15600]	[L1: 0.6838]	11.5+0.1s
+[14400/15600]	[L1: 0.6874]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.434 (Best: 52.097 @epoch 59)
+Forward: 64.12s
+
+Saving...
+Total: 64.61s
+
+[Epoch 72]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7221]	9.6+0.5s
+[3200/15600]	[L1: 0.6995]	10.7+0.1s
+[4800/15600]	[L1: 0.6848]	10.7+0.1s
+[6400/15600]	[L1: 0.6791]	11.0+0.1s
+[8000/15600]	[L1: 0.6794]	11.9+0.1s
+[9600/15600]	[L1: 0.6844]	11.0+0.1s
+[11200/15600]	[L1: 0.6858]	11.1+0.1s
+[12800/15600]	[L1: 0.6848]	12.2+0.1s
+[14400/15600]	[L1: 0.6866]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.054 (Best: 52.097 @epoch 59)
+Forward: 61.90s
+
+Saving...
+Total: 62.40s
+
+[Epoch 73]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6661]	11.4+0.7s
+[3200/15600]	[L1: 0.6712]	10.9+0.1s
+[4800/15600]	[L1: 0.6719]	13.1+0.1s
+[6400/15600]	[L1: 0.6625]	11.5+0.1s
+[8000/15600]	[L1: 0.6639]	11.3+0.1s
+[9600/15600]	[L1: 0.6633]	12.7+0.1s
+[11200/15600]	[L1: 0.6607]	9.5+0.1s
+[12800/15600]	[L1: 0.6673]	10.1+0.1s
+[14400/15600]	[L1: 0.6672]	12.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.391 (Best: 52.097 @epoch 59)
+Forward: 60.20s
+
+Saving...
+Total: 60.70s
+
+[Epoch 74]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.7369]	13.2+0.6s
+[3200/15600]	[L1: 0.7012]	10.7+0.1s
+[4800/15600]	[L1: 0.6996]	10.8+0.1s
+[6400/15600]	[L1: 0.7009]	12.9+0.1s
+[8000/15600]	[L1: 0.6954]	10.8+0.1s
+[9600/15600]	[L1: 0.6970]	10.9+0.1s
+[11200/15600]	[L1: 0.6985]	13.0+0.1s
+[12800/15600]	[L1: 0.6956]	11.0+0.1s
+[14400/15600]	[L1: 0.6916]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.187 (Best: 52.097 @epoch 59)
+Forward: 61.85s
+
+Saving...
+Total: 62.37s
+
+[Epoch 75]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6632]	10.7+0.6s
+[3200/15600]	[L1: 0.6732]	12.0+0.1s
+[4800/15600]	[L1: 0.6737]	9.9+0.1s
+[6400/15600]	[L1: 0.6645]	9.6+0.1s
+[8000/15600]	[L1: 0.6625]	9.7+0.1s
+[9600/15600]	[L1: 0.6643]	12.1+0.1s
+[11200/15600]	[L1: 0.6649]	9.8+0.1s
+[12800/15600]	[L1: 0.6690]	10.5+0.1s
+[14400/15600]	[L1: 0.6676]	12.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 49.757 (Best: 52.097 @epoch 59)
+Forward: 59.93s
+
+Saving...
+Total: 60.56s
+
+[Epoch 76]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6609]	12.1+0.8s
+[3200/15600]	[L1: 0.6701]	11.0+0.1s
+[4800/15600]	[L1: 0.6663]	11.1+0.1s
+[6400/15600]	[L1: 0.6743]	12.4+0.1s
+[8000/15600]	[L1: 0.6719]	9.5+0.1s
+[9600/15600]	[L1: 0.6741]	9.6+0.1s
+[11200/15600]	[L1: 0.6817]	11.7+0.1s
+[12800/15600]	[L1: 0.6781]	11.2+0.1s
+[14400/15600]	[L1: 0.6743]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.398 (Best: 52.097 @epoch 59)
+Forward: 62.62s
+
+Saving...
+Total: 63.17s
+
+[Epoch 77]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6519]	11.5+0.6s
+[3200/15600]	[L1: 0.6409]	12.1+0.1s
+[4800/15600]	[L1: 0.6483]	11.0+0.1s
+[6400/15600]	[L1: 0.6627]	10.9+0.1s
+[8000/15600]	[L1: 0.6643]	12.2+0.1s
+[9600/15600]	[L1: 0.6646]	11.0+0.1s
+[11200/15600]	[L1: 0.6779]	11.0+0.1s
+[12800/15600]	[L1: 0.6752]	12.1+0.1s
+[14400/15600]	[L1: 0.6760]	11.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.451 (Best: 52.451 @epoch 77)
+Forward: 62.47s
+
+Saving...
+Total: 63.11s
+
+[Epoch 78]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6436]	11.1+0.5s
+[3200/15600]	[L1: 0.6403]	12.0+0.1s
+[4800/15600]	[L1: 0.6534]	11.1+0.1s
+[6400/15600]	[L1: 0.6568]	10.9+0.1s
+[8000/15600]	[L1: 0.6662]	12.0+0.1s
+[9600/15600]	[L1: 0.6710]	10.4+0.1s
+[11200/15600]	[L1: 0.6763]	10.8+0.1s
+[12800/15600]	[L1: 0.6739]	11.7+0.1s
+[14400/15600]	[L1: 0.6705]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.305 (Best: 52.451 @epoch 77)
+Forward: 60.75s
+
+Saving...
+Total: 61.24s
+
+[Epoch 79]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6467]	11.2+0.8s
+[3200/15600]	[L1: 0.6605]	12.8+0.1s
+[4800/15600]	[L1: 0.6577]	11.2+0.1s
+[6400/15600]	[L1: 0.6568]	11.0+0.1s
+[8000/15600]	[L1: 0.6590]	11.7+0.1s
+[9600/15600]	[L1: 0.6561]	12.2+0.1s
+[11200/15600]	[L1: 0.6668]	11.0+0.1s
+[12800/15600]	[L1: 0.6683]	11.1+0.1s
+[14400/15600]	[L1: 0.6652]	12.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.975 (Best: 52.451 @epoch 77)
+Forward: 61.74s
+
+Saving...
+Total: 62.23s
+
+[Epoch 80]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6580]	11.2+0.6s
+[3200/15600]	[L1: 0.6601]	11.1+0.1s
+[4800/15600]	[L1: 0.6652]	12.5+0.1s
+[6400/15600]	[L1: 0.6557]	10.9+0.1s
+[8000/15600]	[L1: 0.6579]	10.8+0.1s
+[9600/15600]	[L1: 0.6571]	10.8+0.1s
+[11200/15600]	[L1: 0.6569]	12.8+0.1s
+[12800/15600]	[L1: 0.6578]	10.7+0.1s
+[14400/15600]	[L1: 0.6586]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.799 (Best: 52.451 @epoch 77)
+Forward: 61.80s
+
+Saving...
+Total: 62.29s
+
+[Epoch 81]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6913]	13.4+0.7s
+[3200/15600]	[L1: 0.6725]	11.0+0.1s
+[4800/15600]	[L1: 0.6655]	11.0+0.1s
+[6400/15600]	[L1: 0.6665]	13.0+0.1s
+[8000/15600]	[L1: 0.6619]	10.2+0.1s
+[9600/15600]	[L1: 0.6546]	11.1+0.1s
+[11200/15600]	[L1: 0.6577]	12.7+0.1s
+[12800/15600]	[L1: 0.6560]	11.2+0.1s
+[14400/15600]	[L1: 0.6525]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.214 (Best: 52.451 @epoch 77)
+Forward: 61.87s
+
+Saving...
+Total: 62.36s
+
+[Epoch 82]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6646]	11.4+0.6s
+[3200/15600]	[L1: 0.6558]	12.5+0.1s
+[4800/15600]	[L1: 0.6850]	10.8+0.1s
+[6400/15600]	[L1: 0.6766]	10.8+0.1s
+[8000/15600]	[L1: 0.6790]	12.7+0.1s
+[9600/15600]	[L1: 0.6793]	10.8+0.1s
+[11200/15600]	[L1: 0.6796]	10.7+0.1s
+[12800/15600]	[L1: 0.6760]	11.3+0.1s
+[14400/15600]	[L1: 0.6709]	11.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.462 (Best: 52.462 @epoch 82)
+Forward: 61.05s
+
+Saving...
+Total: 61.57s
+
+[Epoch 83]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6688]	11.1+0.6s
+[3200/15600]	[L1: 0.6540]	11.3+0.1s
+[4800/15600]	[L1: 0.6574]	10.9+0.1s
+[6400/15600]	[L1: 0.6562]	10.5+0.1s
+[8000/15600]	[L1: 0.6637]	9.8+0.1s
+[9600/15600]	[L1: 0.6699]	9.1+0.1s
+[11200/15600]	[L1: 0.6707]	11.6+0.1s
+[12800/15600]	[L1: 0.6663]	10.9+0.1s
+[14400/15600]	[L1: 0.6662]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.149 (Best: 52.462 @epoch 82)
+Forward: 61.91s
+
+Saving...
+Total: 62.36s
+
+[Epoch 84]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6871]	12.1+0.5s
+[3200/15600]	[L1: 0.6816]	10.9+0.1s
+[4800/15600]	[L1: 0.6731]	11.0+0.1s
+[6400/15600]	[L1: 0.6776]	12.2+0.1s
+[8000/15600]	[L1: 0.6681]	11.0+0.1s
+[9600/15600]	[L1: 0.6611]	11.1+0.1s
+[11200/15600]	[L1: 0.6550]	11.5+0.1s
+[12800/15600]	[L1: 0.6544]	10.6+0.1s
+[14400/15600]	[L1: 0.6537]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.857 (Best: 52.462 @epoch 82)
+Forward: 64.48s
+
+Saving...
+Total: 64.94s
+
+[Epoch 85]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6458]	11.5+0.5s
+[3200/15600]	[L1: 0.6737]	10.9+0.1s
+[4800/15600]	[L1: 0.6741]	10.9+0.1s
+[6400/15600]	[L1: 0.6653]	11.6+0.1s
+[8000/15600]	[L1: 0.6649]	11.4+0.1s
+[9600/15600]	[L1: 0.6667]	10.8+0.1s
+[11200/15600]	[L1: 0.6625]	10.9+0.1s
+[12800/15600]	[L1: 0.6618]	11.6+0.1s
+[14400/15600]	[L1: 0.6577]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.748 (Best: 52.462 @epoch 82)
+Forward: 65.09s
+
+Saving...
+Total: 65.59s
+
+[Epoch 86]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6672]	11.0+0.7s
+[3200/15600]	[L1: 0.6631]	11.5+0.1s
+[4800/15600]	[L1: 0.6672]	10.3+0.1s
+[6400/15600]	[L1: 0.6623]	10.4+0.1s
+[8000/15600]	[L1: 0.6560]	11.4+0.1s
+[9600/15600]	[L1: 0.6510]	10.2+0.1s
+[11200/15600]	[L1: 0.6493]	10.3+0.1s
+[12800/15600]	[L1: 0.6493]	11.2+0.1s
+[14400/15600]	[L1: 0.6525]	10.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.820 (Best: 52.462 @epoch 82)
+Forward: 61.32s
+
+Saving...
+Total: 61.83s
+
+[Epoch 87]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6501]	11.3+0.7s
+[3200/15600]	[L1: 0.6480]	11.0+0.1s
+[4800/15600]	[L1: 0.6515]	11.8+0.1s
+[6400/15600]	[L1: 0.6483]	10.6+0.1s
+[8000/15600]	[L1: 0.6483]	9.6+0.1s
+[9600/15600]	[L1: 0.6476]	11.3+0.1s
+[11200/15600]	[L1: 0.6416]	10.0+0.1s
+[12800/15600]	[L1: 0.6392]	10.7+0.1s
+[14400/15600]	[L1: 0.6373]	11.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.259 (Best: 52.462 @epoch 82)
+Forward: 63.47s
+
+Saving...
+Total: 64.27s
+
+[Epoch 88]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6943]	12.0+0.6s
+[3200/15600]	[L1: 0.7176]	10.8+0.1s
+[4800/15600]	[L1: 0.6917]	10.5+0.1s
+[6400/15600]	[L1: 0.6762]	11.8+0.1s
+[8000/15600]	[L1: 0.6722]	10.7+0.1s
+[9600/15600]	[L1: 0.6618]	11.0+0.1s
+[11200/15600]	[L1: 0.6614]	11.8+0.1s
+[12800/15600]	[L1: 0.6606]	11.0+0.1s
+[14400/15600]	[L1: 0.6590]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.344 (Best: 52.462 @epoch 82)
+Forward: 61.67s
+
+Saving...
+Total: 62.12s
+
+[Epoch 89]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6059]	12.4+0.7s
+[3200/15600]	[L1: 0.6210]	9.8+0.1s
+[4800/15600]	[L1: 0.6255]	9.5+0.1s
+[6400/15600]	[L1: 0.6412]	9.7+0.1s
+[8000/15600]	[L1: 0.6379]	10.4+0.1s
+[9600/15600]	[L1: 0.6369]	10.3+0.1s
+[11200/15600]	[L1: 0.6347]	10.0+0.1s
+[12800/15600]	[L1: 0.6423]	11.4+0.1s
+[14400/15600]	[L1: 0.6489]	10.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.978 (Best: 52.462 @epoch 82)
+Forward: 63.72s
+
+Saving...
+Total: 64.20s
+
+[Epoch 90]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6095]	11.2+0.6s
+[3200/15600]	[L1: 0.6449]	12.1+0.1s
+[4800/15600]	[L1: 0.6562]	10.3+0.1s
+[6400/15600]	[L1: 0.6534]	10.3+0.1s
+[8000/15600]	[L1: 0.6555]	11.4+0.1s
+[9600/15600]	[L1: 0.6506]	10.0+0.1s
+[11200/15600]	[L1: 0.6500]	10.3+0.1s
+[12800/15600]	[L1: 0.6468]	9.8+0.1s
+[14400/15600]	[L1: 0.6460]	11.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.535 (Best: 52.462 @epoch 82)
+Forward: 63.28s
+
+Saving...
+Total: 63.87s
+
+[Epoch 91]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6595]	10.9+0.5s
+[3200/15600]	[L1: 0.6195]	10.8+0.1s
+[4800/15600]	[L1: 0.6161]	12.0+0.1s
+[6400/15600]	[L1: 0.6246]	11.0+0.1s
+[8000/15600]	[L1: 0.6229]	11.0+0.1s
+[9600/15600]	[L1: 0.6281]	12.0+0.1s
+[11200/15600]	[L1: 0.6315]	10.4+0.1s
+[12800/15600]	[L1: 0.6299]	10.5+0.1s
+[14400/15600]	[L1: 0.6308]	11.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.647 (Best: 52.462 @epoch 82)
+Forward: 61.71s
+
+Saving...
+Total: 62.18s
+
+[Epoch 92]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6187]	11.2+0.8s
+[3200/15600]	[L1: 0.6354]	10.6+0.1s
+[4800/15600]	[L1: 0.6405]	11.6+0.1s
+[6400/15600]	[L1: 0.6475]	10.4+0.1s
+[8000/15600]	[L1: 0.6469]	10.2+0.1s
+[9600/15600]	[L1: 0.6465]	11.5+0.1s
+[11200/15600]	[L1: 0.6428]	10.3+0.1s
+[12800/15600]	[L1: 0.6420]	10.2+0.1s
+[14400/15600]	[L1: 0.6440]	10.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.329 (Best: 52.462 @epoch 82)
+Forward: 62.07s
+
+Saving...
+Total: 62.55s
+
+[Epoch 93]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6760]	11.8+0.7s
+[3200/15600]	[L1: 0.6546]	11.0+0.1s
+[4800/15600]	[L1: 0.6403]	10.8+0.1s
+[6400/15600]	[L1: 0.6448]	11.9+0.1s
+[8000/15600]	[L1: 0.6430]	10.8+0.1s
+[9600/15600]	[L1: 0.6395]	11.0+0.1s
+[11200/15600]	[L1: 0.6428]	12.0+0.1s
+[12800/15600]	[L1: 0.6373]	10.8+0.1s
+[14400/15600]	[L1: 0.6352]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.697 (Best: 52.697 @epoch 93)
+Forward: 62.96s
+
+Saving...
+Total: 64.17s
+
+[Epoch 94]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6257]	12.1+0.9s
+[3200/15600]	[L1: 0.6263]	10.9+0.1s
+[4800/15600]	[L1: 0.6372]	10.7+0.1s
+[6400/15600]	[L1: 0.6337]	12.4+0.1s
+[8000/15600]	[L1: 0.6380]	10.4+0.1s
+[9600/15600]	[L1: 0.6377]	10.1+0.1s
+[11200/15600]	[L1: 0.6411]	11.6+0.1s
+[12800/15600]	[L1: 0.6358]	10.7+0.1s
+[14400/15600]	[L1: 0.6371]	10.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.793 (Best: 52.793 @epoch 94)
+Forward: 61.75s
+
+Saving...
+Total: 62.30s
+
+[Epoch 95]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6405]	11.2+0.7s
+[3200/15600]	[L1: 0.6270]	12.7+0.1s
+[4800/15600]	[L1: 0.6390]	11.0+0.1s
+[6400/15600]	[L1: 0.6409]	10.9+0.1s
+[8000/15600]	[L1: 0.6505]	12.8+0.1s
+[9600/15600]	[L1: 0.6442]	11.0+0.1s
+[11200/15600]	[L1: 0.6359]	10.9+0.1s
+[12800/15600]	[L1: 0.6335]	12.1+0.1s
+[14400/15600]	[L1: 0.6337]	11.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.139 (Best: 52.793 @epoch 94)
+Forward: 61.87s
+
+Saving...
+Total: 62.33s
+
+[Epoch 96]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6445]	10.7+0.6s
+[3200/15600]	[L1: 0.6617]	10.4+0.1s
+[4800/15600]	[L1: 0.6615]	12.0+0.1s
+[6400/15600]	[L1: 0.6539]	11.0+0.1s
+[8000/15600]	[L1: 0.6467]	10.9+0.1s
+[9600/15600]	[L1: 0.6406]	11.0+0.1s
+[11200/15600]	[L1: 0.6404]	10.6+0.1s
+[12800/15600]	[L1: 0.6428]	9.3+0.1s
+[14400/15600]	[L1: 0.6435]	9.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.810 (Best: 52.810 @epoch 96)
+Forward: 61.11s
+
+Saving...
+Total: 61.73s
+
+[Epoch 97]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.5977]	11.0+0.7s
+[3200/15600]	[L1: 0.6086]	12.6+0.1s
+[4800/15600]	[L1: 0.6050]	11.0+0.1s
+[6400/15600]	[L1: 0.6167]	10.9+0.1s
+[8000/15600]	[L1: 0.6192]	12.8+0.1s
+[9600/15600]	[L1: 0.6239]	10.7+0.1s
+[11200/15600]	[L1: 0.6231]	9.6+0.1s
+[12800/15600]	[L1: 0.6203]	12.0+0.1s
+[14400/15600]	[L1: 0.6189]	9.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.939 (Best: 52.810 @epoch 96)
+Forward: 61.32s
+
+Saving...
+Total: 61.79s
+
+[Epoch 98]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6611]	10.1+0.6s
+[3200/15600]	[L1: 0.6491]	9.6+0.1s
+[4800/15600]	[L1: 0.6509]	10.7+0.1s
+[6400/15600]	[L1: 0.6406]	10.9+0.1s
+[8000/15600]	[L1: 0.6434]	10.2+0.1s
+[9600/15600]	[L1: 0.6329]	10.0+0.1s
+[11200/15600]	[L1: 0.6303]	11.9+0.1s
+[12800/15600]	[L1: 0.6279]	11.1+0.1s
+[14400/15600]	[L1: 0.6268]	10.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.527 (Best: 52.810 @epoch 96)
+Forward: 63.12s
+
+Saving...
+Total: 63.58s
+
+[Epoch 99]	Learning rate: 1.00e-4
+[1600/15600]	[L1: 0.6462]	10.5+0.6s
+[3200/15600]	[L1: 0.6430]	12.1+0.1s
+[4800/15600]	[L1: 0.6345]	10.0+0.1s
+[6400/15600]	[L1: 0.6368]	10.3+0.1s
+[8000/15600]	[L1: 0.6340]	12.7+0.1s
+[9600/15600]	[L1: 0.6391]	10.9+0.1s
+[11200/15600]	[L1: 0.6382]	10.7+0.1s
+[12800/15600]	[L1: 0.6364]	11.7+0.1s
+[14400/15600]	[L1: 0.6324]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.404 (Best: 52.810 @epoch 96)
+Forward: 65.12s
+
+Saving...
+Total: 65.76s
+
+[Epoch 100]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5774]	10.9+0.6s
+[3200/15600]	[L1: 0.5675]	11.1+0.1s
+[4800/15600]	[L1: 0.5534]	12.3+0.1s
+[6400/15600]	[L1: 0.5551]	11.0+0.1s
+[8000/15600]	[L1: 0.5528]	11.2+0.1s
+[9600/15600]	[L1: 0.5535]	12.1+0.1s
+[11200/15600]	[L1: 0.5537]	11.0+0.1s
+[12800/15600]	[L1: 0.5510]	10.9+0.1s
+[14400/15600]	[L1: 0.5504]	12.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.601 (Best: 53.601 @epoch 100)
+Forward: 64.89s
+
+Saving...
+Total: 65.45s
+
+[Epoch 101]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5519]	10.7+0.7s
+[3200/15600]	[L1: 0.5517]	9.8+0.1s
+[4800/15600]	[L1: 0.5497]	9.8+0.1s
+[6400/15600]	[L1: 0.5477]	10.9+0.1s
+[8000/15600]	[L1: 0.5499]	10.3+0.1s
+[9600/15600]	[L1: 0.5472]	10.3+0.1s
+[11200/15600]	[L1: 0.5467]	11.2+0.1s
+[12800/15600]	[L1: 0.5481]	10.2+0.1s
+[14400/15600]	[L1: 0.5461]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 50.826 (Best: 53.601 @epoch 100)
+Forward: 62.99s
+
+Saving...
+Total: 63.49s
+
+[Epoch 102]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5722]	11.0+0.6s
+[3200/15600]	[L1: 0.5539]	10.7+0.1s
+[4800/15600]	[L1: 0.5562]	10.0+0.1s
+[6400/15600]	[L1: 0.5572]	10.6+0.1s
+[8000/15600]	[L1: 0.5546]	9.6+0.1s
+[9600/15600]	[L1: 0.5530]	9.8+0.1s
+[11200/15600]	[L1: 0.5518]	9.6+0.1s
+[12800/15600]	[L1: 0.5540]	10.6+0.1s
+[14400/15600]	[L1: 0.5541]	9.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.482 (Best: 53.601 @epoch 100)
+Forward: 63.38s
+
+Saving...
+Total: 63.86s
+
+[Epoch 103]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5419]	11.2+0.7s
+[3200/15600]	[L1: 0.5478]	12.9+0.1s
+[4800/15600]	[L1: 0.5492]	10.8+0.1s
+[6400/15600]	[L1: 0.5482]	11.1+0.1s
+[8000/15600]	[L1: 0.5467]	12.6+0.1s
+[9600/15600]	[L1: 0.5454]	11.1+0.1s
+[11200/15600]	[L1: 0.5488]	11.0+0.1s
+[12800/15600]	[L1: 0.5484]	12.8+0.1s
+[14400/15600]	[L1: 0.5478]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.261 (Best: 53.601 @epoch 100)
+Forward: 61.61s
+
+Saving...
+Total: 62.10s
+
+[Epoch 104]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5557]	10.2+0.6s
+[3200/15600]	[L1: 0.5520]	10.2+0.1s
+[4800/15600]	[L1: 0.5507]	11.6+0.1s
+[6400/15600]	[L1: 0.5422]	10.0+0.1s
+[8000/15600]	[L1: 0.5445]	10.0+0.1s
+[9600/15600]	[L1: 0.5484]	10.1+0.1s
+[11200/15600]	[L1: 0.5508]	11.7+0.1s
+[12800/15600]	[L1: 0.5486]	10.0+0.1s
+[14400/15600]	[L1: 0.5508]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.597 (Best: 53.601 @epoch 100)
+Forward: 61.75s
+
+Saving...
+Total: 62.22s
+
+[Epoch 105]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5609]	11.5+0.7s
+[3200/15600]	[L1: 0.5495]	13.1+0.1s
+[4800/15600]	[L1: 0.5498]	11.1+0.1s
+[6400/15600]	[L1: 0.5491]	10.1+0.1s
+[8000/15600]	[L1: 0.5490]	12.8+0.1s
+[9600/15600]	[L1: 0.5510]	10.9+0.1s
+[11200/15600]	[L1: 0.5512]	11.1+0.1s
+[12800/15600]	[L1: 0.5492]	13.1+0.1s
+[14400/15600]	[L1: 0.5507]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.965 (Best: 53.965 @epoch 105)
+Forward: 64.28s
+
+Saving...
+Total: 64.84s
+
+[Epoch 106]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5463]	10.9+0.6s
+[3200/15600]	[L1: 0.5387]	10.8+0.1s
+[4800/15600]	[L1: 0.5404]	12.7+0.1s
+[6400/15600]	[L1: 0.5402]	10.9+0.1s
+[8000/15600]	[L1: 0.5434]	10.7+0.1s
+[9600/15600]	[L1: 0.5424]	12.6+0.1s
+[11200/15600]	[L1: 0.5438]	10.9+0.1s
+[12800/15600]	[L1: 0.5437]	11.1+0.1s
+[14400/15600]	[L1: 0.5445]	12.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.692 (Best: 53.965 @epoch 105)
+Forward: 60.49s
+
+Saving...
+Total: 60.95s
+
+[Epoch 107]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5426]	13.3+0.7s
+[3200/15600]	[L1: 0.5534]	11.2+0.1s
+[4800/15600]	[L1: 0.5508]	11.0+0.1s
+[6400/15600]	[L1: 0.5536]	13.0+0.1s
+[8000/15600]	[L1: 0.5545]	11.1+0.1s
+[9600/15600]	[L1: 0.5500]	11.1+0.1s
+[11200/15600]	[L1: 0.5501]	12.4+0.1s
+[12800/15600]	[L1: 0.5477]	10.2+0.1s
+[14400/15600]	[L1: 0.5472]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.428 (Best: 53.965 @epoch 105)
+Forward: 59.31s
+
+Saving...
+Total: 59.98s
+
+[Epoch 108]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5284]	11.8+0.6s
+[3200/15600]	[L1: 0.5400]	11.6+0.1s
+[4800/15600]	[L1: 0.5470]	11.0+0.1s
+[6400/15600]	[L1: 0.5551]	11.0+0.1s
+[8000/15600]	[L1: 0.5515]	12.9+0.1s
+[9600/15600]	[L1: 0.5537]	11.0+0.1s
+[11200/15600]	[L1: 0.5531]	11.7+0.1s
+[12800/15600]	[L1: 0.5517]	12.9+0.1s
+[14400/15600]	[L1: 0.5512]	10.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.256 (Best: 53.965 @epoch 105)
+Forward: 61.12s
+
+Saving...
+Total: 61.61s
+
+[Epoch 109]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5521]	10.5+0.6s
+[3200/15600]	[L1: 0.5579]	10.4+0.1s
+[4800/15600]	[L1: 0.5559]	11.3+0.1s
+[6400/15600]	[L1: 0.5556]	9.7+0.1s
+[8000/15600]	[L1: 0.5559]	10.1+0.1s
+[9600/15600]	[L1: 0.5538]	12.2+0.1s
+[11200/15600]	[L1: 0.5536]	10.8+0.1s
+[12800/15600]	[L1: 0.5516]	10.7+0.1s
+[14400/15600]	[L1: 0.5502]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.528 (Best: 53.965 @epoch 105)
+Forward: 61.35s
+
+Saving...
+Total: 61.84s
+
+[Epoch 110]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5426]	13.2+0.7s
+[3200/15600]	[L1: 0.5408]	11.3+0.1s
+[4800/15600]	[L1: 0.5424]	10.9+0.1s
+[6400/15600]	[L1: 0.5433]	13.0+0.1s
+[8000/15600]	[L1: 0.5416]	10.8+0.1s
+[9600/15600]	[L1: 0.5415]	11.0+0.1s
+[11200/15600]	[L1: 0.5401]	13.0+0.1s
+[12800/15600]	[L1: 0.5404]	10.5+0.1s
+[14400/15600]	[L1: 0.5405]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.914 (Best: 53.965 @epoch 105)
+Forward: 62.54s
+
+Saving...
+Total: 63.04s
+
+[Epoch 111]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5374]	10.1+0.6s
+[3200/15600]	[L1: 0.5345]	11.4+0.1s
+[4800/15600]	[L1: 0.5373]	9.9+0.1s
+[6400/15600]	[L1: 0.5411]	10.5+0.1s
+[8000/15600]	[L1: 0.5402]	9.8+0.1s
+[9600/15600]	[L1: 0.5410]	11.3+0.1s
+[11200/15600]	[L1: 0.5426]	9.6+0.1s
+[12800/15600]	[L1: 0.5416]	9.5+0.1s
+[14400/15600]	[L1: 0.5413]	11.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.025 (Best: 54.025 @epoch 111)
+Forward: 58.73s
+
+Saving...
+Total: 59.24s
+
+[Epoch 112]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5428]	11.6+0.6s
+[3200/15600]	[L1: 0.5370]	9.9+0.1s
+[4800/15600]	[L1: 0.5441]	9.5+0.1s
+[6400/15600]	[L1: 0.5411]	10.3+0.1s
+[8000/15600]	[L1: 0.5400]	11.8+0.1s
+[9600/15600]	[L1: 0.5378]	10.0+0.1s
+[11200/15600]	[L1: 0.5391]	10.6+0.1s
+[12800/15600]	[L1: 0.5384]	12.9+0.1s
+[14400/15600]	[L1: 0.5403]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.935 (Best: 54.025 @epoch 111)
+Forward: 63.08s
+
+Saving...
+Total: 63.61s
+
+[Epoch 113]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5291]	11.2+0.6s
+[3200/15600]	[L1: 0.5353]	12.1+0.1s
+[4800/15600]	[L1: 0.5449]	11.0+0.1s
+[6400/15600]	[L1: 0.5446]	11.0+0.1s
+[8000/15600]	[L1: 0.5420]	11.4+0.1s
+[9600/15600]	[L1: 0.5389]	11.3+0.1s
+[11200/15600]	[L1: 0.5381]	10.1+0.1s
+[12800/15600]	[L1: 0.5403]	11.1+0.1s
+[14400/15600]	[L1: 0.5408]	11.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.737 (Best: 54.025 @epoch 111)
+Forward: 63.53s
+
+Saving...
+Total: 64.04s
+
+[Epoch 114]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5343]	11.2+0.5s
+[3200/15600]	[L1: 0.5512]	11.0+0.1s
+[4800/15600]	[L1: 0.5489]	12.2+0.1s
+[6400/15600]	[L1: 0.5484]	10.7+0.1s
+[8000/15600]	[L1: 0.5454]	11.2+0.1s
+[9600/15600]	[L1: 0.5448]	12.0+0.1s
+[11200/15600]	[L1: 0.5436]	10.5+0.1s
+[12800/15600]	[L1: 0.5429]	10.9+0.1s
+[14400/15600]	[L1: 0.5418]	12.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.104 (Best: 54.025 @epoch 111)
+Forward: 63.42s
+
+Saving...
+Total: 63.93s
+
+[Epoch 115]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5292]	11.3+0.8s
+[3200/15600]	[L1: 0.5338]	10.8+0.1s
+[4800/15600]	[L1: 0.5353]	12.7+0.1s
+[6400/15600]	[L1: 0.5320]	10.8+0.1s
+[8000/15600]	[L1: 0.5348]	10.8+0.1s
+[9600/15600]	[L1: 0.5362]	11.8+0.1s
+[11200/15600]	[L1: 0.5365]	11.8+0.1s
+[12800/15600]	[L1: 0.5408]	11.1+0.1s
+[14400/15600]	[L1: 0.5390]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.329 (Best: 54.025 @epoch 111)
+Forward: 60.03s
+
+Saving...
+Total: 60.67s
+
+[Epoch 116]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5501]	12.8+0.6s
+[3200/15600]	[L1: 0.5489]	10.9+0.1s
+[4800/15600]	[L1: 0.5538]	11.0+0.1s
+[6400/15600]	[L1: 0.5484]	12.6+0.1s
+[8000/15600]	[L1: 0.5458]	9.9+0.1s
+[9600/15600]	[L1: 0.5440]	10.2+0.1s
+[11200/15600]	[L1: 0.5416]	10.2+0.1s
+[12800/15600]	[L1: 0.5417]	11.5+0.1s
+[14400/15600]	[L1: 0.5410]	9.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.918 (Best: 54.025 @epoch 111)
+Forward: 61.95s
+
+Saving...
+Total: 62.48s
+
+[Epoch 117]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5217]	11.3+0.6s
+[3200/15600]	[L1: 0.5385]	11.4+0.1s
+[4800/15600]	[L1: 0.5390]	12.8+0.1s
+[6400/15600]	[L1: 0.5397]	11.1+0.1s
+[8000/15600]	[L1: 0.5418]	11.0+0.1s
+[9600/15600]	[L1: 0.5388]	13.0+0.1s
+[11200/15600]	[L1: 0.5380]	11.0+0.1s
+[12800/15600]	[L1: 0.5387]	11.0+0.1s
+[14400/15600]	[L1: 0.5389]	12.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.182 (Best: 54.025 @epoch 111)
+Forward: 61.85s
+
+Saving...
+Total: 62.34s
+
+[Epoch 118]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5160]	11.5+0.6s
+[3200/15600]	[L1: 0.5305]	10.8+0.1s
+[4800/15600]	[L1: 0.5343]	11.2+0.1s
+[6400/15600]	[L1: 0.5399]	11.7+0.1s
+[8000/15600]	[L1: 0.5349]	11.1+0.1s
+[9600/15600]	[L1: 0.5374]	11.3+0.1s
+[11200/15600]	[L1: 0.5364]	11.5+0.1s
+[12800/15600]	[L1: 0.5360]	10.8+0.1s
+[14400/15600]	[L1: 0.5365]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.657 (Best: 54.025 @epoch 111)
+Forward: 59.42s
+
+Saving...
+Total: 59.95s
+
+[Epoch 119]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5256]	11.5+0.7s
+[3200/15600]	[L1: 0.5371]	10.2+0.1s
+[4800/15600]	[L1: 0.5352]	10.5+0.1s
+[6400/15600]	[L1: 0.5349]	12.4+0.1s
+[8000/15600]	[L1: 0.5344]	11.2+0.1s
+[9600/15600]	[L1: 0.5346]	11.0+0.1s
+[11200/15600]	[L1: 0.5349]	12.4+0.1s
+[12800/15600]	[L1: 0.5346]	11.5+0.1s
+[14400/15600]	[L1: 0.5353]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.779 (Best: 54.025 @epoch 111)
+Forward: 63.97s
+
+Saving...
+Total: 64.47s
+
+[Epoch 120]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5515]	11.2+0.6s
+[3200/15600]	[L1: 0.5477]	12.7+0.1s
+[4800/15600]	[L1: 0.5473]	11.2+0.1s
+[6400/15600]	[L1: 0.5455]	11.2+0.1s
+[8000/15600]	[L1: 0.5424]	12.9+0.1s
+[9600/15600]	[L1: 0.5418]	11.2+0.1s
+[11200/15600]	[L1: 0.5414]	11.1+0.1s
+[12800/15600]	[L1: 0.5388]	12.6+0.1s
+[14400/15600]	[L1: 0.5395]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.081 (Best: 54.081 @epoch 120)
+Forward: 62.42s
+
+Saving...
+Total: 62.95s
+
+[Epoch 121]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5226]	10.4+0.6s
+[3200/15600]	[L1: 0.5287]	9.9+0.1s
+[4800/15600]	[L1: 0.5301]	11.1+0.1s
+[6400/15600]	[L1: 0.5304]	10.5+0.1s
+[8000/15600]	[L1: 0.5286]	10.2+0.1s
+[9600/15600]	[L1: 0.5285]	11.1+0.1s
+[11200/15600]	[L1: 0.5279]	10.1+0.1s
+[12800/15600]	[L1: 0.5277]	10.5+0.1s
+[14400/15600]	[L1: 0.5283]	9.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.845 (Best: 54.081 @epoch 120)
+Forward: 63.37s
+
+Saving...
+Total: 63.85s
+
+[Epoch 122]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5315]	12.2+0.8s
+[3200/15600]	[L1: 0.5297]	9.8+0.1s
+[4800/15600]	[L1: 0.5436]	10.4+0.1s
+[6400/15600]	[L1: 0.5379]	11.0+0.1s
+[8000/15600]	[L1: 0.5395]	9.6+0.1s
+[9600/15600]	[L1: 0.5371]	9.4+0.1s
+[11200/15600]	[L1: 0.5363]	11.1+0.1s
+[12800/15600]	[L1: 0.5357]	10.3+0.1s
+[14400/15600]	[L1: 0.5338]	9.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.478 (Best: 54.081 @epoch 120)
+Forward: 62.08s
+
+Saving...
+Total: 62.58s
+
+[Epoch 123]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5380]	11.3+0.7s
+[3200/15600]	[L1: 0.5364]	12.7+0.1s
+[4800/15600]	[L1: 0.5333]	10.8+0.1s
+[6400/15600]	[L1: 0.5324]	10.2+0.1s
+[8000/15600]	[L1: 0.5313]	11.9+0.1s
+[9600/15600]	[L1: 0.5321]	11.0+0.1s
+[11200/15600]	[L1: 0.5330]	10.3+0.1s
+[12800/15600]	[L1: 0.5338]	10.0+0.1s
+[14400/15600]	[L1: 0.5332]	11.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.807 (Best: 54.081 @epoch 120)
+Forward: 61.98s
+
+Saving...
+Total: 62.48s
+
+[Epoch 124]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5289]	11.4+0.7s
+[3200/15600]	[L1: 0.5336]	10.7+0.1s
+[4800/15600]	[L1: 0.5302]	12.2+0.1s
+[6400/15600]	[L1: 0.5365]	11.8+0.1s
+[8000/15600]	[L1: 0.5359]	11.1+0.1s
+[9600/15600]	[L1: 0.5341]	10.9+0.1s
+[11200/15600]	[L1: 0.5356]	12.2+0.1s
+[12800/15600]	[L1: 0.5347]	10.0+0.1s
+[14400/15600]	[L1: 0.5342]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.702 (Best: 54.081 @epoch 120)
+Forward: 62.46s
+
+Saving...
+Total: 62.94s
+
+[Epoch 125]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5253]	12.3+0.6s
+[3200/15600]	[L1: 0.5274]	10.9+0.1s
+[4800/15600]	[L1: 0.5303]	9.9+0.1s
+[6400/15600]	[L1: 0.5293]	11.3+0.1s
+[8000/15600]	[L1: 0.5290]	10.3+0.1s
+[9600/15600]	[L1: 0.5280]	10.3+0.1s
+[11200/15600]	[L1: 0.5255]	10.7+0.1s
+[12800/15600]	[L1: 0.5247]	12.2+0.1s
+[14400/15600]	[L1: 0.5242]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.135 (Best: 54.081 @epoch 120)
+Forward: 62.03s
+
+Saving...
+Total: 62.58s
+
+[Epoch 126]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5290]	10.3+0.7s
+[3200/15600]	[L1: 0.5242]	10.9+0.1s
+[4800/15600]	[L1: 0.5222]	10.8+0.1s
+[6400/15600]	[L1: 0.5260]	10.7+0.1s
+[8000/15600]	[L1: 0.5260]	10.8+0.1s
+[9600/15600]	[L1: 0.5260]	12.8+0.1s
+[11200/15600]	[L1: 0.5264]	11.0+0.1s
+[12800/15600]	[L1: 0.5239]	10.9+0.1s
+[14400/15600]	[L1: 0.5243]	12.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.793 (Best: 54.081 @epoch 120)
+Forward: 60.90s
+
+Saving...
+Total: 61.83s
+
+[Epoch 127]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5345]	10.9+0.9s
+[3200/15600]	[L1: 0.5293]	10.4+0.1s
+[4800/15600]	[L1: 0.5281]	10.3+0.1s
+[6400/15600]	[L1: 0.5285]	12.3+0.1s
+[8000/15600]	[L1: 0.5276]	10.0+0.1s
+[9600/15600]	[L1: 0.5292]	9.7+0.1s
+[11200/15600]	[L1: 0.5310]	12.3+0.1s
+[12800/15600]	[L1: 0.5310]	10.8+0.1s
+[14400/15600]	[L1: 0.5326]	10.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.951 (Best: 54.081 @epoch 120)
+Forward: 61.34s
+
+Saving...
+Total: 61.88s
+
+[Epoch 128]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5438]	11.1+0.7s
+[3200/15600]	[L1: 0.5411]	13.0+0.1s
+[4800/15600]	[L1: 0.5394]	10.9+0.1s
+[6400/15600]	[L1: 0.5329]	11.0+0.1s
+[8000/15600]	[L1: 0.5364]	12.3+0.1s
+[9600/15600]	[L1: 0.5383]	10.9+0.1s
+[11200/15600]	[L1: 0.5366]	10.1+0.1s
+[12800/15600]	[L1: 0.5342]	11.9+0.1s
+[14400/15600]	[L1: 0.5327]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.611 (Best: 54.081 @epoch 120)
+Forward: 61.11s
+
+Saving...
+Total: 61.66s
+
+[Epoch 129]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5309]	10.4+0.6s
+[3200/15600]	[L1: 0.5397]	10.0+0.1s
+[4800/15600]	[L1: 0.5376]	11.4+0.1s
+[6400/15600]	[L1: 0.5339]	10.9+0.1s
+[8000/15600]	[L1: 0.5363]	9.8+0.1s
+[9600/15600]	[L1: 0.5383]	10.7+0.1s
+[11200/15600]	[L1: 0.5351]	12.3+0.1s
+[12800/15600]	[L1: 0.5328]	10.0+0.1s
+[14400/15600]	[L1: 0.5333]	10.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.367 (Best: 54.081 @epoch 120)
+Forward: 59.44s
+
+Saving...
+Total: 59.91s
+
+[Epoch 130]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5200]	11.2+0.6s
+[3200/15600]	[L1: 0.5267]	13.0+0.1s
+[4800/15600]	[L1: 0.5297]	11.0+0.1s
+[6400/15600]	[L1: 0.5240]	10.5+0.1s
+[8000/15600]	[L1: 0.5244]	12.3+0.1s
+[9600/15600]	[L1: 0.5278]	11.0+0.1s
+[11200/15600]	[L1: 0.5310]	10.5+0.1s
+[12800/15600]	[L1: 0.5280]	11.9+0.1s
+[14400/15600]	[L1: 0.5280]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.885 (Best: 54.081 @epoch 120)
+Forward: 61.80s
+
+Saving...
+Total: 62.30s
+
+[Epoch 131]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5242]	10.7+0.6s
+[3200/15600]	[L1: 0.5307]	10.0+0.1s
+[4800/15600]	[L1: 0.5309]	12.8+0.1s
+[6400/15600]	[L1: 0.5310]	10.7+0.1s
+[8000/15600]	[L1: 0.5323]	10.9+0.1s
+[9600/15600]	[L1: 0.5312]	12.7+0.1s
+[11200/15600]	[L1: 0.5310]	10.3+0.1s
+[12800/15600]	[L1: 0.5321]	11.1+0.1s
+[14400/15600]	[L1: 0.5314]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.858 (Best: 54.081 @epoch 120)
+Forward: 58.91s
+
+Saving...
+Total: 59.51s
+
+[Epoch 132]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5218]	12.7+0.7s
+[3200/15600]	[L1: 0.5163]	10.8+0.1s
+[4800/15600]	[L1: 0.5202]	11.0+0.1s
+[6400/15600]	[L1: 0.5274]	12.5+0.1s
+[8000/15600]	[L1: 0.5277]	11.0+0.1s
+[9600/15600]	[L1: 0.5253]	10.7+0.1s
+[11200/15600]	[L1: 0.5234]	10.5+0.1s
+[12800/15600]	[L1: 0.5223]	12.5+0.1s
+[14400/15600]	[L1: 0.5222]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.634 (Best: 54.081 @epoch 120)
+Forward: 60.89s
+
+Saving...
+Total: 61.41s
+
+[Epoch 133]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.4982]	11.2+0.7s
+[3200/15600]	[L1: 0.5024]	12.0+0.1s
+[4800/15600]	[L1: 0.5070]	9.8+0.1s
+[6400/15600]	[L1: 0.5079]	10.0+0.1s
+[8000/15600]	[L1: 0.5130]	11.2+0.1s
+[9600/15600]	[L1: 0.5144]	13.0+0.1s
+[11200/15600]	[L1: 0.5174]	10.7+0.1s
+[12800/15600]	[L1: 0.5196]	10.6+0.1s
+[14400/15600]	[L1: 0.5219]	12.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.863 (Best: 54.081 @epoch 120)
+Forward: 59.11s
+
+Saving...
+Total: 59.59s
+
+[Epoch 134]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5283]	11.7+0.6s
+[3200/15600]	[L1: 0.5206]	10.7+0.1s
+[4800/15600]	[L1: 0.5212]	9.8+0.1s
+[6400/15600]	[L1: 0.5218]	11.8+0.1s
+[8000/15600]	[L1: 0.5181]	11.1+0.1s
+[9600/15600]	[L1: 0.5191]	11.0+0.1s
+[11200/15600]	[L1: 0.5191]	12.5+0.1s
+[12800/15600]	[L1: 0.5203]	11.0+0.1s
+[14400/15600]	[L1: 0.5229]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.964 (Best: 54.081 @epoch 120)
+Forward: 63.37s
+
+Saving...
+Total: 63.86s
+
+[Epoch 135]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5245]	10.8+0.6s
+[3200/15600]	[L1: 0.5214]	12.3+0.1s
+[4800/15600]	[L1: 0.5234]	11.0+0.1s
+[6400/15600]	[L1: 0.5235]	10.7+0.1s
+[8000/15600]	[L1: 0.5253]	10.5+0.1s
+[9600/15600]	[L1: 0.5261]	12.8+0.1s
+[11200/15600]	[L1: 0.5269]	11.0+0.1s
+[12800/15600]	[L1: 0.5264]	11.1+0.1s
+[14400/15600]	[L1: 0.5268]	13.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.754 (Best: 54.081 @epoch 120)
+Forward: 64.33s
+
+Saving...
+Total: 64.85s
+
+[Epoch 136]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5159]	11.3+0.6s
+[3200/15600]	[L1: 0.5094]	11.0+0.1s
+[4800/15600]	[L1: 0.5116]	12.4+0.1s
+[6400/15600]	[L1: 0.5122]	10.3+0.1s
+[8000/15600]	[L1: 0.5198]	10.9+0.1s
+[9600/15600]	[L1: 0.5214]	12.1+0.1s
+[11200/15600]	[L1: 0.5232]	10.8+0.1s
+[12800/15600]	[L1: 0.5244]	10.2+0.1s
+[14400/15600]	[L1: 0.5255]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.798 (Best: 54.081 @epoch 120)
+Forward: 58.63s
+
+Saving...
+Total: 59.19s
+
+[Epoch 137]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5164]	12.8+0.7s
+[3200/15600]	[L1: 0.5125]	11.0+0.1s
+[4800/15600]	[L1: 0.5230]	10.9+0.1s
+[6400/15600]	[L1: 0.5245]	12.4+0.1s
+[8000/15600]	[L1: 0.5236]	11.3+0.1s
+[9600/15600]	[L1: 0.5253]	11.0+0.1s
+[11200/15600]	[L1: 0.5251]	11.1+0.1s
+[12800/15600]	[L1: 0.5251]	11.8+0.1s
+[14400/15600]	[L1: 0.5249]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.116 (Best: 54.116 @epoch 137)
+Forward: 59.37s
+
+Saving...
+Total: 59.97s
+
+[Epoch 138]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5336]	11.3+0.6s
+[3200/15600]	[L1: 0.5257]	12.2+0.1s
+[4800/15600]	[L1: 0.5306]	10.4+0.1s
+[6400/15600]	[L1: 0.5302]	10.2+0.1s
+[8000/15600]	[L1: 0.5301]	11.4+0.1s
+[9600/15600]	[L1: 0.5281]	10.1+0.1s
+[11200/15600]	[L1: 0.5292]	10.6+0.1s
+[12800/15600]	[L1: 0.5286]	11.0+0.1s
+[14400/15600]	[L1: 0.5296]	12.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.675 (Best: 54.116 @epoch 137)
+Forward: 60.45s
+
+Saving...
+Total: 60.98s
+
+[Epoch 139]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5096]	11.1+0.6s
+[3200/15600]	[L1: 0.5120]	11.0+0.1s
+[4800/15600]	[L1: 0.5184]	12.2+0.1s
+[6400/15600]	[L1: 0.5242]	10.7+0.1s
+[8000/15600]	[L1: 0.5237]	10.5+0.1s
+[9600/15600]	[L1: 0.5234]	11.3+0.1s
+[11200/15600]	[L1: 0.5242]	12.1+0.1s
+[12800/15600]	[L1: 0.5231]	10.3+0.1s
+[14400/15600]	[L1: 0.5215]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.400 (Best: 54.116 @epoch 137)
+Forward: 60.87s
+
+Saving...
+Total: 61.41s
+
+[Epoch 140]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5305]	13.1+0.6s
+[3200/15600]	[L1: 0.5186]	10.9+0.1s
+[4800/15600]	[L1: 0.5229]	10.6+0.1s
+[6400/15600]	[L1: 0.5217]	12.4+0.1s
+[8000/15600]	[L1: 0.5214]	11.1+0.1s
+[9600/15600]	[L1: 0.5234]	10.9+0.1s
+[11200/15600]	[L1: 0.5240]	12.4+0.1s
+[12800/15600]	[L1: 0.5225]	11.5+0.1s
+[14400/15600]	[L1: 0.5224]	11.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.013 (Best: 54.116 @epoch 137)
+Forward: 60.64s
+
+Saving...
+Total: 61.13s
+
+[Epoch 141]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5285]	11.1+0.7s
+[3200/15600]	[L1: 0.5196]	12.2+0.1s
+[4800/15600]	[L1: 0.5212]	11.0+0.1s
+[6400/15600]	[L1: 0.5233]	11.1+0.1s
+[8000/15600]	[L1: 0.5228]	12.4+0.1s
+[9600/15600]	[L1: 0.5218]	11.1+0.1s
+[11200/15600]	[L1: 0.5229]	11.0+0.1s
+[12800/15600]	[L1: 0.5238]	11.2+0.1s
+[14400/15600]	[L1: 0.5232]	12.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.971 (Best: 54.116 @epoch 137)
+Forward: 60.89s
+
+Saving...
+Total: 61.39s
+
+[Epoch 142]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5136]	11.1+0.7s
+[3200/15600]	[L1: 0.5306]	10.9+0.1s
+[4800/15600]	[L1: 0.5269]	12.4+0.1s
+[6400/15600]	[L1: 0.5288]	10.9+0.1s
+[8000/15600]	[L1: 0.5269]	10.8+0.1s
+[9600/15600]	[L1: 0.5265]	11.9+0.1s
+[11200/15600]	[L1: 0.5249]	11.7+0.1s
+[12800/15600]	[L1: 0.5256]	10.8+0.1s
+[14400/15600]	[L1: 0.5253]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 51.869 (Best: 54.116 @epoch 137)
+Forward: 58.96s
+
+Saving...
+Total: 59.46s
+
+[Epoch 143]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5283]	11.4+0.6s
+[3200/15600]	[L1: 0.5268]	10.6+0.1s
+[4800/15600]	[L1: 0.5165]	10.8+0.1s
+[6400/15600]	[L1: 0.5145]	9.7+0.1s
+[8000/15600]	[L1: 0.5168]	12.2+0.1s
+[9600/15600]	[L1: 0.5179]	10.8+0.1s
+[11200/15600]	[L1: 0.5183]	10.9+0.1s
+[12800/15600]	[L1: 0.5175]	12.5+0.1s
+[14400/15600]	[L1: 0.5182]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.294 (Best: 54.294 @epoch 143)
+Forward: 62.26s
+
+Saving...
+Total: 62.79s
+
+[Epoch 144]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5143]	10.4+0.6s
+[3200/15600]	[L1: 0.5121]	10.4+0.1s
+[4800/15600]	[L1: 0.5145]	12.3+0.1s
+[6400/15600]	[L1: 0.5147]	9.7+0.1s
+[8000/15600]	[L1: 0.5178]	9.7+0.1s
+[9600/15600]	[L1: 0.5251]	11.9+0.1s
+[11200/15600]	[L1: 0.5256]	11.1+0.1s
+[12800/15600]	[L1: 0.5239]	11.0+0.1s
+[14400/15600]	[L1: 0.5226]	12.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.169 (Best: 54.294 @epoch 143)
+Forward: 58.99s
+
+Saving...
+Total: 59.49s
+
+[Epoch 145]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5166]	12.8+0.7s
+[3200/15600]	[L1: 0.5169]	11.2+0.1s
+[4800/15600]	[L1: 0.5108]	11.3+0.1s
+[6400/15600]	[L1: 0.5094]	12.7+0.1s
+[8000/15600]	[L1: 0.5095]	11.1+0.1s
+[9600/15600]	[L1: 0.5126]	11.0+0.1s
+[11200/15600]	[L1: 0.5147]	12.5+0.1s
+[12800/15600]	[L1: 0.5160]	10.9+0.1s
+[14400/15600]	[L1: 0.5172]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.112 (Best: 54.294 @epoch 143)
+Forward: 59.81s
+
+Saving...
+Total: 60.31s
+
+[Epoch 146]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5209]	11.0+0.6s
+[3200/15600]	[L1: 0.5143]	12.5+0.1s
+[4800/15600]	[L1: 0.5146]	9.5+0.1s
+[6400/15600]	[L1: 0.5154]	9.6+0.1s
+[8000/15600]	[L1: 0.5186]	12.1+0.1s
+[9600/15600]	[L1: 0.5169]	9.8+0.1s
+[11200/15600]	[L1: 0.5171]	10.0+0.1s
+[12800/15600]	[L1: 0.5193]	11.2+0.1s
+[14400/15600]	[L1: 0.5210]	11.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.023 (Best: 54.294 @epoch 143)
+Forward: 61.17s
+
+Saving...
+Total: 61.70s
+
+[Epoch 147]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.4996]	10.3+0.6s
+[3200/15600]	[L1: 0.5010]	10.8+0.1s
+[4800/15600]	[L1: 0.5044]	12.9+0.1s
+[6400/15600]	[L1: 0.5059]	11.3+0.1s
+[8000/15600]	[L1: 0.5085]	11.0+0.1s
+[9600/15600]	[L1: 0.5074]	12.9+0.1s
+[11200/15600]	[L1: 0.5104]	11.1+0.1s
+[12800/15600]	[L1: 0.5113]	11.0+0.1s
+[14400/15600]	[L1: 0.5139]	11.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.836 (Best: 54.294 @epoch 143)
+Forward: 62.00s
+
+Saving...
+Total: 62.51s
+
+[Epoch 148]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5138]	12.3+0.6s
+[3200/15600]	[L1: 0.5214]	10.4+0.1s
+[4800/15600]	[L1: 0.5212]	10.4+0.1s
+[6400/15600]	[L1: 0.5278]	10.5+0.1s
+[8000/15600]	[L1: 0.5269]	9.3+0.1s
+[9600/15600]	[L1: 0.5234]	9.1+0.1s
+[11200/15600]	[L1: 0.5214]	9.1+0.1s
+[12800/15600]	[L1: 0.5222]	10.7+0.1s
+[14400/15600]	[L1: 0.5209]	9.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.796 (Best: 54.294 @epoch 143)
+Forward: 61.39s
+
+Saving...
+Total: 61.91s
+
+[Epoch 149]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5162]	10.8+0.8s
+[3200/15600]	[L1: 0.5126]	11.0+0.1s
+[4800/15600]	[L1: 0.5138]	11.8+0.1s
+[6400/15600]	[L1: 0.5159]	10.4+0.1s
+[8000/15600]	[L1: 0.5136]	11.0+0.1s
+[9600/15600]	[L1: 0.5168]	12.7+0.1s
+[11200/15600]	[L1: 0.5157]	11.0+0.1s
+[12800/15600]	[L1: 0.5185]	11.1+0.1s
+[14400/15600]	[L1: 0.5196]	12.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.817 (Best: 54.294 @epoch 143)
+Forward: 61.13s
+
+Saving...
+Total: 61.62s
+
+[Epoch 150]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5267]	13.3+0.6s
+[3200/15600]	[L1: 0.5301]	11.0+0.1s
+[4800/15600]	[L1: 0.5254]	11.0+0.1s
+[6400/15600]	[L1: 0.5245]	12.9+0.1s
+[8000/15600]	[L1: 0.5233]	11.3+0.1s
+[9600/15600]	[L1: 0.5252]	11.1+0.1s
+[11200/15600]	[L1: 0.5262]	12.7+0.1s
+[12800/15600]	[L1: 0.5269]	11.1+0.1s
+[14400/15600]	[L1: 0.5249]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.697 (Best: 54.294 @epoch 143)
+Forward: 65.75s
+
+Saving...
+Total: 66.25s
+
+[Epoch 151]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5229]	13.2+0.6s
+[3200/15600]	[L1: 0.5282]	11.0+0.1s
+[4800/15600]	[L1: 0.5195]	11.0+0.1s
+[6400/15600]	[L1: 0.5169]	12.7+0.1s
+[8000/15600]	[L1: 0.5153]	11.1+0.1s
+[9600/15600]	[L1: 0.5171]	11.0+0.1s
+[11200/15600]	[L1: 0.5160]	12.7+0.1s
+[12800/15600]	[L1: 0.5177]	11.0+0.1s
+[14400/15600]	[L1: 0.5151]	11.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.283 (Best: 54.294 @epoch 143)
+Forward: 63.34s
+
+Saving...
+Total: 63.83s
+
+[Epoch 152]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5127]	11.7+0.6s
+[3200/15600]	[L1: 0.5056]	10.3+0.1s
+[4800/15600]	[L1: 0.5089]	10.6+0.1s
+[6400/15600]	[L1: 0.5179]	9.8+0.1s
+[8000/15600]	[L1: 0.5160]	10.8+0.1s
+[9600/15600]	[L1: 0.5154]	10.0+0.1s
+[11200/15600]	[L1: 0.5137]	9.7+0.1s
+[12800/15600]	[L1: 0.5172]	11.5+0.1s
+[14400/15600]	[L1: 0.5163]	9.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.719 (Best: 54.294 @epoch 143)
+Forward: 61.07s
+
+Saving...
+Total: 61.58s
+
+[Epoch 153]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5322]	11.0+0.7s
+[3200/15600]	[L1: 0.5296]	10.9+0.1s
+[4800/15600]	[L1: 0.5211]	12.7+0.1s
+[6400/15600]	[L1: 0.5193]	10.8+0.1s
+[8000/15600]	[L1: 0.5170]	10.0+0.1s
+[9600/15600]	[L1: 0.5170]	11.7+0.1s
+[11200/15600]	[L1: 0.5177]	11.7+0.1s
+[12800/15600]	[L1: 0.5169]	10.9+0.1s
+[14400/15600]	[L1: 0.5176]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.246 (Best: 54.294 @epoch 143)
+Forward: 62.40s
+
+Saving...
+Total: 62.91s
+
+[Epoch 154]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5152]	12.6+0.7s
+[3200/15600]	[L1: 0.5102]	10.9+0.1s
+[4800/15600]	[L1: 0.5161]	10.8+0.1s
+[6400/15600]	[L1: 0.5139]	12.4+0.1s
+[8000/15600]	[L1: 0.5133]	10.9+0.1s
+[9600/15600]	[L1: 0.5116]	10.8+0.1s
+[11200/15600]	[L1: 0.5117]	12.5+0.1s
+[12800/15600]	[L1: 0.5113]	10.8+0.1s
+[14400/15600]	[L1: 0.5132]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.692 (Best: 54.294 @epoch 143)
+Forward: 60.07s
+
+Saving...
+Total: 60.57s
+
+[Epoch 155]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5318]	11.2+0.6s
+[3200/15600]	[L1: 0.5153]	12.9+0.1s
+[4800/15600]	[L1: 0.5142]	11.0+0.1s
+[6400/15600]	[L1: 0.5121]	11.1+0.1s
+[8000/15600]	[L1: 0.5129]	12.6+0.1s
+[9600/15600]	[L1: 0.5143]	11.1+0.1s
+[11200/15600]	[L1: 0.5158]	11.1+0.1s
+[12800/15600]	[L1: 0.5177]	12.9+0.1s
+[14400/15600]	[L1: 0.5178]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.860 (Best: 54.294 @epoch 143)
+Forward: 60.67s
+
+Saving...
+Total: 61.18s
+
+[Epoch 156]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5247]	10.4+0.6s
+[3200/15600]	[L1: 0.5220]	10.0+0.1s
+[4800/15600]	[L1: 0.5260]	12.3+0.1s
+[6400/15600]	[L1: 0.5232]	11.0+0.1s
+[8000/15600]	[L1: 0.5229]	11.0+0.1s
+[9600/15600]	[L1: 0.5223]	10.6+0.1s
+[11200/15600]	[L1: 0.5227]	11.1+0.1s
+[12800/15600]	[L1: 0.5223]	10.3+0.1s
+[14400/15600]	[L1: 0.5214]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.426 (Best: 54.294 @epoch 143)
+Forward: 59.59s
+
+Saving...
+Total: 60.13s
+
+[Epoch 157]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5048]	13.0+0.7s
+[3200/15600]	[L1: 0.5090]	11.1+0.1s
+[4800/15600]	[L1: 0.5078]	11.1+0.1s
+[6400/15600]	[L1: 0.5133]	12.6+0.1s
+[8000/15600]	[L1: 0.5138]	11.1+0.1s
+[9600/15600]	[L1: 0.5165]	10.8+0.1s
+[11200/15600]	[L1: 0.5187]	10.1+0.1s
+[12800/15600]	[L1: 0.5168]	12.9+0.1s
+[14400/15600]	[L1: 0.5152]	11.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.021 (Best: 54.294 @epoch 143)
+Forward: 61.89s
+
+Saving...
+Total: 62.39s
+
+[Epoch 158]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5061]	11.5+0.6s
+[3200/15600]	[L1: 0.5094]	12.9+0.1s
+[4800/15600]	[L1: 0.5097]	11.1+0.1s
+[6400/15600]	[L1: 0.5082]	11.0+0.1s
+[8000/15600]	[L1: 0.5074]	12.8+0.1s
+[9600/15600]	[L1: 0.5089]	11.1+0.1s
+[11200/15600]	[L1: 0.5084]	11.0+0.1s
+[12800/15600]	[L1: 0.5096]	12.9+0.1s
+[14400/15600]	[L1: 0.5081]	10.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.027 (Best: 54.294 @epoch 143)
+Forward: 61.95s
+
+Saving...
+Total: 62.68s
+
+[Epoch 159]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5346]	11.1+0.6s
+[3200/15600]	[L1: 0.5191]	11.0+0.1s
+[4800/15600]	[L1: 0.5194]	12.9+0.1s
+[6400/15600]	[L1: 0.5189]	11.0+0.1s
+[8000/15600]	[L1: 0.5164]	11.1+0.1s
+[9600/15600]	[L1: 0.5151]	12.8+0.1s
+[11200/15600]	[L1: 0.5143]	11.0+0.1s
+[12800/15600]	[L1: 0.5138]	10.5+0.1s
+[14400/15600]	[L1: 0.5134]	12.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.062 (Best: 54.294 @epoch 143)
+Forward: 62.26s
+
+Saving...
+Total: 62.77s
+
+[Epoch 160]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5120]	12.3+0.6s
+[3200/15600]	[L1: 0.5177]	11.0+0.1s
+[4800/15600]	[L1: 0.5155]	10.9+0.1s
+[6400/15600]	[L1: 0.5146]	12.6+0.1s
+[8000/15600]	[L1: 0.5133]	11.1+0.1s
+[9600/15600]	[L1: 0.5119]	11.0+0.1s
+[11200/15600]	[L1: 0.5140]	12.6+0.1s
+[12800/15600]	[L1: 0.5125]	10.7+0.1s
+[14400/15600]	[L1: 0.5116]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.116 (Best: 54.294 @epoch 143)
+Forward: 60.01s
+
+Saving...
+Total: 60.56s
+
+[Epoch 161]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5018]	10.6+0.6s
+[3200/15600]	[L1: 0.4954]	11.9+0.1s
+[4800/15600]	[L1: 0.5025]	10.1+0.1s
+[6400/15600]	[L1: 0.5039]	10.2+0.1s
+[8000/15600]	[L1: 0.5061]	11.7+0.1s
+[9600/15600]	[L1: 0.5071]	10.3+0.1s
+[11200/15600]	[L1: 0.5087]	10.1+0.1s
+[12800/15600]	[L1: 0.5084]	10.5+0.1s
+[14400/15600]	[L1: 0.5086]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.651 (Best: 54.294 @epoch 143)
+Forward: 62.82s
+
+Saving...
+Total: 63.51s
+
+[Epoch 162]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5186]	11.1+0.7s
+[3200/15600]	[L1: 0.5145]	11.0+0.1s
+[4800/15600]	[L1: 0.5164]	11.9+0.1s
+[6400/15600]	[L1: 0.5132]	12.1+0.1s
+[8000/15600]	[L1: 0.5112]	10.4+0.1s
+[9600/15600]	[L1: 0.5141]	10.9+0.1s
+[11200/15600]	[L1: 0.5113]	12.7+0.1s
+[12800/15600]	[L1: 0.5117]	10.9+0.1s
+[14400/15600]	[L1: 0.5118]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.168 (Best: 54.294 @epoch 143)
+Forward: 60.78s
+
+Saving...
+Total: 61.30s
+
+[Epoch 163]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5070]	13.0+0.6s
+[3200/15600]	[L1: 0.5058]	10.8+0.1s
+[4800/15600]	[L1: 0.5151]	10.8+0.1s
+[6400/15600]	[L1: 0.5172]	11.8+0.1s
+[8000/15600]	[L1: 0.5178]	11.2+0.1s
+[9600/15600]	[L1: 0.5151]	10.8+0.1s
+[11200/15600]	[L1: 0.5149]	10.8+0.1s
+[12800/15600]	[L1: 0.5144]	12.2+0.1s
+[14400/15600]	[L1: 0.5131]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.008 (Best: 54.294 @epoch 143)
+Forward: 63.64s
+
+Saving...
+Total: 64.20s
+
+[Epoch 164]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5101]	11.8+0.7s
+[3200/15600]	[L1: 0.5077]	12.8+0.1s
+[4800/15600]	[L1: 0.5121]	10.3+0.1s
+[6400/15600]	[L1: 0.5134]	9.6+0.1s
+[8000/15600]	[L1: 0.5120]	11.2+0.1s
+[9600/15600]	[L1: 0.5140]	11.8+0.1s
+[11200/15600]	[L1: 0.5127]	10.7+0.1s
+[12800/15600]	[L1: 0.5114]	10.8+0.1s
+[14400/15600]	[L1: 0.5103]	12.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.302 (Best: 54.302 @epoch 164)
+Forward: 62.46s
+
+Saving...
+Total: 63.03s
+
+[Epoch 165]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.4965]	11.1+0.6s
+[3200/15600]	[L1: 0.5108]	10.6+0.1s
+[4800/15600]	[L1: 0.5110]	11.3+0.1s
+[6400/15600]	[L1: 0.5174]	11.5+0.1s
+[8000/15600]	[L1: 0.5169]	10.6+0.1s
+[9600/15600]	[L1: 0.5124]	10.9+0.1s
+[11200/15600]	[L1: 0.5140]	10.6+0.1s
+[12800/15600]	[L1: 0.5152]	10.6+0.1s
+[14400/15600]	[L1: 0.5138]	10.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.171 (Best: 54.302 @epoch 164)
+Forward: 63.02s
+
+Saving...
+Total: 63.55s
+
+[Epoch 166]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5008]	11.8+0.5s
+[3200/15600]	[L1: 0.5094]	11.1+0.1s
+[4800/15600]	[L1: 0.5060]	10.9+0.1s
+[6400/15600]	[L1: 0.5037]	11.7+0.1s
+[8000/15600]	[L1: 0.5019]	10.9+0.1s
+[9600/15600]	[L1: 0.5061]	11.0+0.1s
+[11200/15600]	[L1: 0.5071]	11.7+0.1s
+[12800/15600]	[L1: 0.5075]	11.0+0.1s
+[14400/15600]	[L1: 0.5068]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.235 (Best: 54.302 @epoch 164)
+Forward: 63.04s
+
+Saving...
+Total: 63.56s
+
+[Epoch 167]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5045]	11.8+0.5s
+[3200/15600]	[L1: 0.5105]	11.1+0.1s
+[4800/15600]	[L1: 0.5094]	10.9+0.1s
+[6400/15600]	[L1: 0.5110]	11.7+0.1s
+[8000/15600]	[L1: 0.5102]	11.1+0.1s
+[9600/15600]	[L1: 0.5139]	10.3+0.1s
+[11200/15600]	[L1: 0.5146]	11.3+0.1s
+[12800/15600]	[L1: 0.5134]	10.0+0.1s
+[14400/15600]	[L1: 0.5152]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.088 (Best: 54.302 @epoch 164)
+Forward: 63.25s
+
+Saving...
+Total: 63.79s
+
+[Epoch 168]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5118]	11.9+0.5s
+[3200/15600]	[L1: 0.5105]	10.9+0.1s
+[4800/15600]	[L1: 0.5108]	10.9+0.1s
+[6400/15600]	[L1: 0.5086]	11.4+0.1s
+[8000/15600]	[L1: 0.5055]	10.7+0.1s
+[9600/15600]	[L1: 0.5097]	11.1+0.1s
+[11200/15600]	[L1: 0.5099]	12.0+0.1s
+[12800/15600]	[L1: 0.5101]	11.0+0.1s
+[14400/15600]	[L1: 0.5103]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 52.753 (Best: 54.302 @epoch 164)
+Forward: 62.30s
+
+Saving...
+Total: 62.80s
+
+[Epoch 169]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5083]	13.1+0.8s
+[3200/15600]	[L1: 0.5058]	10.7+0.1s
+[4800/15600]	[L1: 0.5097]	10.7+0.1s
+[6400/15600]	[L1: 0.5118]	12.3+0.1s
+[8000/15600]	[L1: 0.5075]	11.5+0.1s
+[9600/15600]	[L1: 0.5069]	11.1+0.1s
+[11200/15600]	[L1: 0.5058]	12.9+0.1s
+[12800/15600]	[L1: 0.5047]	9.9+0.1s
+[14400/15600]	[L1: 0.5057]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.935 (Best: 54.302 @epoch 164)
+Forward: 61.25s
+
+Saving...
+Total: 61.77s
+
+[Epoch 170]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5085]	10.1+0.7s
+[3200/15600]	[L1: 0.5046]	10.9+0.1s
+[4800/15600]	[L1: 0.5029]	9.8+0.1s
+[6400/15600]	[L1: 0.5010]	10.1+0.1s
+[8000/15600]	[L1: 0.5046]	10.8+0.1s
+[9600/15600]	[L1: 0.5034]	12.6+0.1s
+[11200/15600]	[L1: 0.5046]	10.8+0.1s
+[12800/15600]	[L1: 0.5050]	10.7+0.1s
+[14400/15600]	[L1: 0.5065]	12.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.771 (Best: 54.302 @epoch 164)
+Forward: 61.90s
+
+Saving...
+Total: 62.41s
+
+[Epoch 171]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5197]	10.5+0.6s
+[3200/15600]	[L1: 0.5193]	10.8+0.1s
+[4800/15600]	[L1: 0.5158]	9.7+0.1s
+[6400/15600]	[L1: 0.5099]	12.5+0.1s
+[8000/15600]	[L1: 0.5134]	10.8+0.1s
+[9600/15600]	[L1: 0.5145]	10.4+0.1s
+[11200/15600]	[L1: 0.5125]	12.5+0.1s
+[12800/15600]	[L1: 0.5136]	10.9+0.1s
+[14400/15600]	[L1: 0.5151]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.353 (Best: 54.353 @epoch 171)
+Forward: 61.16s
+
+Saving...
+Total: 61.71s
+
+[Epoch 172]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.4894]	12.6+0.6s
+[3200/15600]	[L1: 0.4997]	11.4+0.1s
+[4800/15600]	[L1: 0.4988]	11.0+0.1s
+[6400/15600]	[L1: 0.4997]	11.1+0.1s
+[8000/15600]	[L1: 0.5047]	12.7+0.1s
+[9600/15600]	[L1: 0.5059]	11.0+0.1s
+[11200/15600]	[L1: 0.5069]	10.2+0.1s
+[12800/15600]	[L1: 0.5058]	11.5+0.1s
+[14400/15600]	[L1: 0.5045]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.208 (Best: 54.353 @epoch 171)
+Forward: 62.46s
+
+Saving...
+Total: 63.01s
+
+[Epoch 173]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5056]	10.6+0.6s
+[3200/15600]	[L1: 0.5159]	9.7+0.1s
+[4800/15600]	[L1: 0.5126]	11.1+0.1s
+[6400/15600]	[L1: 0.5101]	9.4+0.1s
+[8000/15600]	[L1: 0.5103]	10.0+0.1s
+[9600/15600]	[L1: 0.5092]	12.0+0.1s
+[11200/15600]	[L1: 0.5082]	9.4+0.1s
+[12800/15600]	[L1: 0.5069]	9.5+0.1s
+[14400/15600]	[L1: 0.5066]	9.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.022 (Best: 54.353 @epoch 171)
+Forward: 61.22s
+
+Saving...
+Total: 61.71s
+
+[Epoch 174]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5067]	11.2+0.6s
+[3200/15600]	[L1: 0.5088]	11.4+0.1s
+[4800/15600]	[L1: 0.5054]	10.6+0.1s
+[6400/15600]	[L1: 0.5071]	11.0+0.1s
+[8000/15600]	[L1: 0.5096]	12.6+0.1s
+[9600/15600]	[L1: 0.5104]	10.9+0.1s
+[11200/15600]	[L1: 0.5108]	10.6+0.1s
+[12800/15600]	[L1: 0.5099]	12.0+0.1s
+[14400/15600]	[L1: 0.5091]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.744 (Best: 54.353 @epoch 171)
+Forward: 62.01s
+
+Saving...
+Total: 62.68s
+
+[Epoch 175]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5139]	10.9+0.6s
+[3200/15600]	[L1: 0.5021]	10.5+0.1s
+[4800/15600]	[L1: 0.5026]	11.7+0.1s
+[6400/15600]	[L1: 0.5039]	9.5+0.1s
+[8000/15600]	[L1: 0.5001]	9.7+0.1s
+[9600/15600]	[L1: 0.5019]	11.1+0.1s
+[11200/15600]	[L1: 0.5016]	9.6+0.1s
+[12800/15600]	[L1: 0.5052]	9.6+0.1s
+[14400/15600]	[L1: 0.5049]	9.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.426 (Best: 54.426 @epoch 175)
+Forward: 61.91s
+
+Saving...
+Total: 62.45s
+
+[Epoch 176]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.4991]	12.5+0.7s
+[3200/15600]	[L1: 0.4962]	10.9+0.1s
+[4800/15600]	[L1: 0.4957]	10.9+0.1s
+[6400/15600]	[L1: 0.4982]	12.5+0.1s
+[8000/15600]	[L1: 0.4980]	10.7+0.1s
+[9600/15600]	[L1: 0.4957]	10.9+0.1s
+[11200/15600]	[L1: 0.4987]	11.0+0.1s
+[12800/15600]	[L1: 0.4989]	12.0+0.1s
+[14400/15600]	[L1: 0.4987]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.055 (Best: 54.426 @epoch 175)
+Forward: 60.35s
+
+Saving...
+Total: 60.84s
+
+[Epoch 177]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.4922]	10.1+0.6s
+[3200/15600]	[L1: 0.5047]	10.1+0.1s
+[4800/15600]	[L1: 0.5074]	12.0+0.1s
+[6400/15600]	[L1: 0.5142]	11.1+0.1s
+[8000/15600]	[L1: 0.5112]	11.0+0.1s
+[9600/15600]	[L1: 0.5103]	12.5+0.1s
+[11200/15600]	[L1: 0.5071]	11.1+0.1s
+[12800/15600]	[L1: 0.5066]	10.9+0.1s
+[14400/15600]	[L1: 0.5072]	12.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.179 (Best: 54.426 @epoch 175)
+Forward: 61.05s
+
+Saving...
+Total: 61.87s
+
+[Epoch 178]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.4968]	12.8+0.7s
+[3200/15600]	[L1: 0.5016]	11.0+0.1s
+[4800/15600]	[L1: 0.4995]	11.0+0.1s
+[6400/15600]	[L1: 0.4960]	12.8+0.1s
+[8000/15600]	[L1: 0.4983]	11.0+0.1s
+[9600/15600]	[L1: 0.4992]	11.0+0.1s
+[11200/15600]	[L1: 0.4993]	12.6+0.1s
+[12800/15600]	[L1: 0.5000]	11.1+0.1s
+[14400/15600]	[L1: 0.4988]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.439 (Best: 54.439 @epoch 178)
+Forward: 59.22s
+
+Saving...
+Total: 59.76s
+
+[Epoch 179]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5030]	10.8+0.6s
+[3200/15600]	[L1: 0.5094]	11.9+0.1s
+[4800/15600]	[L1: 0.5058]	10.5+0.1s
+[6400/15600]	[L1: 0.5112]	10.4+0.1s
+[8000/15600]	[L1: 0.5080]	12.5+0.1s
+[9600/15600]	[L1: 0.5072]	11.0+0.1s
+[11200/15600]	[L1: 0.5061]	10.8+0.1s
+[12800/15600]	[L1: 0.5052]	12.7+0.1s
+[14400/15600]	[L1: 0.5071]	10.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.605 (Best: 54.439 @epoch 178)
+Forward: 61.76s
+
+Saving...
+Total: 62.25s
+
+[Epoch 180]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.4983]	11.2+0.6s
+[3200/15600]	[L1: 0.4965]	10.5+0.1s
+[4800/15600]	[L1: 0.4946]	11.2+0.1s
+[6400/15600]	[L1: 0.4967]	10.4+0.1s
+[8000/15600]	[L1: 0.4993]	10.8+0.1s
+[9600/15600]	[L1: 0.5002]	10.8+0.1s
+[11200/15600]	[L1: 0.5011]	10.1+0.1s
+[12800/15600]	[L1: 0.5009]	10.1+0.1s
+[14400/15600]	[L1: 0.5005]	9.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.496 (Best: 54.496 @epoch 180)
+Forward: 63.05s
+
+Saving...
+Total: 63.58s
+
+[Epoch 181]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.4967]	11.2+0.5s
+[3200/15600]	[L1: 0.5057]	10.5+0.1s
+[4800/15600]	[L1: 0.5067]	10.9+0.1s
+[6400/15600]	[L1: 0.5073]	11.8+0.1s
+[8000/15600]	[L1: 0.5062]	10.9+0.1s
+[9600/15600]	[L1: 0.5083]	9.9+0.1s
+[11200/15600]	[L1: 0.5045]	11.2+0.1s
+[12800/15600]	[L1: 0.5049]	10.9+0.1s
+[14400/15600]	[L1: 0.5030]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.223 (Best: 54.496 @epoch 180)
+Forward: 65.07s
+
+Saving...
+Total: 65.59s
+
+[Epoch 182]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.4932]	11.8+0.7s
+[3200/15600]	[L1: 0.5010]	10.4+0.1s
+[4800/15600]	[L1: 0.5053]	10.2+0.1s
+[6400/15600]	[L1: 0.5032]	11.3+0.1s
+[8000/15600]	[L1: 0.5004]	10.2+0.1s
+[9600/15600]	[L1: 0.5005]	10.3+0.1s
+[11200/15600]	[L1: 0.4992]	10.2+0.1s
+[12800/15600]	[L1: 0.4984]	11.2+0.1s
+[14400/15600]	[L1: 0.5001]	10.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.034 (Best: 54.496 @epoch 180)
+Forward: 63.55s
+
+Saving...
+Total: 64.11s
+
+[Epoch 183]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5352]	11.3+0.6s
+[3200/15600]	[L1: 0.5168]	11.2+0.1s
+[4800/15600]	[L1: 0.5098]	10.4+0.1s
+[6400/15600]	[L1: 0.5074]	11.1+0.1s
+[8000/15600]	[L1: 0.5116]	11.9+0.1s
+[9600/15600]	[L1: 0.5107]	10.8+0.1s
+[11200/15600]	[L1: 0.5109]	10.8+0.1s
+[12800/15600]	[L1: 0.5086]	11.7+0.1s
+[14400/15600]	[L1: 0.5096]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.115 (Best: 54.496 @epoch 180)
+Forward: 63.63s
+
+Saving...
+Total: 64.15s
+
+[Epoch 184]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5119]	11.0+0.5s
+[3200/15600]	[L1: 0.5027]	11.9+0.1s
+[4800/15600]	[L1: 0.5047]	10.9+0.1s
+[6400/15600]	[L1: 0.5011]	11.0+0.1s
+[8000/15600]	[L1: 0.5008]	11.6+0.1s
+[9600/15600]	[L1: 0.5005]	10.9+0.1s
+[11200/15600]	[L1: 0.5012]	10.7+0.1s
+[12800/15600]	[L1: 0.5022]	10.7+0.1s
+[14400/15600]	[L1: 0.5013]	10.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.751 (Best: 54.496 @epoch 180)
+Forward: 64.43s
+
+Saving...
+Total: 64.93s
+
+[Epoch 185]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5005]	10.6+0.5s
+[3200/15600]	[L1: 0.4970]	11.8+0.1s
+[4800/15600]	[L1: 0.5020]	10.5+0.1s
+[6400/15600]	[L1: 0.5028]	10.3+0.1s
+[8000/15600]	[L1: 0.5013]	11.7+0.1s
+[9600/15600]	[L1: 0.4998]	10.8+0.1s
+[11200/15600]	[L1: 0.5009]	10.9+0.1s
+[12800/15600]	[L1: 0.5012]	11.9+0.1s
+[14400/15600]	[L1: 0.5013]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.703 (Best: 54.496 @epoch 180)
+Forward: 64.34s
+
+Saving...
+Total: 64.87s
+
+[Epoch 186]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.4992]	10.5+0.5s
+[3200/15600]	[L1: 0.4949]	11.9+0.1s
+[4800/15600]	[L1: 0.4936]	11.1+0.1s
+[6400/15600]	[L1: 0.4957]	10.9+0.1s
+[8000/15600]	[L1: 0.4949]	11.9+0.1s
+[9600/15600]	[L1: 0.4968]	10.8+0.1s
+[11200/15600]	[L1: 0.4996]	10.3+0.1s
+[12800/15600]	[L1: 0.5001]	11.3+0.1s
+[14400/15600]	[L1: 0.5007]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.245 (Best: 54.496 @epoch 180)
+Forward: 64.06s
+
+Saving...
+Total: 64.59s
+
+[Epoch 187]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.4890]	10.7+0.5s
+[3200/15600]	[L1: 0.4882]	11.8+0.1s
+[4800/15600]	[L1: 0.4916]	10.9+0.1s
+[6400/15600]	[L1: 0.4929]	10.9+0.1s
+[8000/15600]	[L1: 0.4952]	11.8+0.1s
+[9600/15600]	[L1: 0.4982]	10.6+0.1s
+[11200/15600]	[L1: 0.4991]	10.7+0.1s
+[12800/15600]	[L1: 0.4974]	11.2+0.1s
+[14400/15600]	[L1: 0.4994]	10.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.122 (Best: 54.496 @epoch 180)
+Forward: 64.30s
+
+Saving...
+Total: 64.80s
+
+[Epoch 188]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5163]	11.2+0.5s
+[3200/15600]	[L1: 0.5097]	10.8+0.1s
+[4800/15600]	[L1: 0.5060]	11.5+0.1s
+[6400/15600]	[L1: 0.5028]	11.0+0.1s
+[8000/15600]	[L1: 0.5063]	11.1+0.1s
+[9600/15600]	[L1: 0.5048]	11.8+0.1s
+[11200/15600]	[L1: 0.5043]	11.0+0.1s
+[12800/15600]	[L1: 0.5043]	11.0+0.1s
+[14400/15600]	[L1: 0.5043]	12.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.161 (Best: 54.496 @epoch 180)
+Forward: 62.08s
+
+Saving...
+Total: 62.61s
+
+[Epoch 189]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.4976]	10.7+0.7s
+[3200/15600]	[L1: 0.4931]	10.4+0.1s
+[4800/15600]	[L1: 0.4895]	12.7+0.1s
+[6400/15600]	[L1: 0.4948]	10.3+0.1s
+[8000/15600]	[L1: 0.4977]	10.3+0.1s
+[9600/15600]	[L1: 0.4968]	11.8+0.1s
+[11200/15600]	[L1: 0.4990]	10.2+0.1s
+[12800/15600]	[L1: 0.4983]	10.1+0.1s
+[14400/15600]	[L1: 0.4973]	10.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.040 (Best: 54.496 @epoch 180)
+Forward: 60.62s
+
+Saving...
+Total: 61.13s
+
+[Epoch 190]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5102]	11.7+0.6s
+[3200/15600]	[L1: 0.5033]	11.9+0.1s
+[4800/15600]	[L1: 0.5006]	11.0+0.1s
+[6400/15600]	[L1: 0.4945]	10.8+0.1s
+[8000/15600]	[L1: 0.4929]	12.4+0.1s
+[9600/15600]	[L1: 0.4956]	11.1+0.1s
+[11200/15600]	[L1: 0.4955]	10.8+0.1s
+[12800/15600]	[L1: 0.4959]	12.5+0.1s
+[14400/15600]	[L1: 0.4963]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.431 (Best: 54.496 @epoch 180)
+Forward: 59.96s
+
+Saving...
+Total: 60.49s
+
+[Epoch 191]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.4816]	11.2+0.6s
+[3200/15600]	[L1: 0.4872]	11.0+0.1s
+[4800/15600]	[L1: 0.4927]	12.7+0.1s
+[6400/15600]	[L1: 0.4975]	11.0+0.1s
+[8000/15600]	[L1: 0.4967]	11.1+0.1s
+[9600/15600]	[L1: 0.4940]	12.4+0.1s
+[11200/15600]	[L1: 0.4942]	10.4+0.1s
+[12800/15600]	[L1: 0.4941]	10.6+0.1s
+[14400/15600]	[L1: 0.4964]	11.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.322 (Best: 54.496 @epoch 180)
+Forward: 59.18s
+
+Saving...
+Total: 59.69s
+
+[Epoch 192]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5073]	12.8+0.7s
+[3200/15600]	[L1: 0.4914]	10.7+0.1s
+[4800/15600]	[L1: 0.4907]	10.9+0.1s
+[6400/15600]	[L1: 0.4899]	12.4+0.1s
+[8000/15600]	[L1: 0.4897]	11.0+0.1s
+[9600/15600]	[L1: 0.4892]	11.0+0.1s
+[11200/15600]	[L1: 0.4905]	12.6+0.1s
+[12800/15600]	[L1: 0.4930]	11.0+0.1s
+[14400/15600]	[L1: 0.4927]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.101 (Best: 54.496 @epoch 180)
+Forward: 61.08s
+
+Saving...
+Total: 61.59s
+
+[Epoch 193]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5195]	11.1+0.6s
+[3200/15600]	[L1: 0.5145]	12.7+0.1s
+[4800/15600]	[L1: 0.5110]	11.0+0.1s
+[6400/15600]	[L1: 0.5107]	11.3+0.1s
+[8000/15600]	[L1: 0.5079]	12.9+0.1s
+[9600/15600]	[L1: 0.5055]	11.4+0.1s
+[11200/15600]	[L1: 0.5035]	11.3+0.1s
+[12800/15600]	[L1: 0.5024]	12.8+0.1s
+[14400/15600]	[L1: 0.5011]	11.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.178 (Best: 54.496 @epoch 180)
+Forward: 62.82s
+
+Saving...
+Total: 63.33s
+
+[Epoch 194]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.4927]	11.3+0.6s
+[3200/15600]	[L1: 0.4898]	12.3+0.1s
+[4800/15600]	[L1: 0.4971]	11.4+0.1s
+[6400/15600]	[L1: 0.4964]	11.0+0.1s
+[8000/15600]	[L1: 0.4950]	11.2+0.1s
+[9600/15600]	[L1: 0.4990]	12.9+0.1s
+[11200/15600]	[L1: 0.4998]	11.0+0.1s
+[12800/15600]	[L1: 0.4994]	11.1+0.1s
+[14400/15600]	[L1: 0.4996]	12.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.316 (Best: 54.496 @epoch 180)
+Forward: 61.41s
+
+Saving...
+Total: 61.91s
+
+[Epoch 195]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.4795]	11.2+0.7s
+[3200/15600]	[L1: 0.4884]	10.9+0.1s
+[4800/15600]	[L1: 0.4911]	11.9+0.1s
+[6400/15600]	[L1: 0.4941]	11.9+0.1s
+[8000/15600]	[L1: 0.4959]	10.8+0.1s
+[9600/15600]	[L1: 0.5011]	10.9+0.1s
+[11200/15600]	[L1: 0.5005]	12.6+0.1s
+[12800/15600]	[L1: 0.5011]	10.8+0.1s
+[14400/15600]	[L1: 0.4996]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.969 (Best: 54.496 @epoch 180)
+Forward: 59.30s
+
+Saving...
+Total: 59.81s
+
+[Epoch 196]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5241]	12.4+0.6s
+[3200/15600]	[L1: 0.5125]	10.9+0.1s
+[4800/15600]	[L1: 0.5020]	10.7+0.1s
+[6400/15600]	[L1: 0.5002]	11.5+0.1s
+[8000/15600]	[L1: 0.4994]	12.9+0.1s
+[9600/15600]	[L1: 0.4998]	11.1+0.1s
+[11200/15600]	[L1: 0.4987]	10.9+0.1s
+[12800/15600]	[L1: 0.4973]	12.5+0.1s
+[14400/15600]	[L1: 0.4996]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.057 (Best: 54.496 @epoch 180)
+Forward: 61.75s
+
+Saving...
+Total: 62.26s
+
+[Epoch 197]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.4883]	10.3+0.6s
+[3200/15600]	[L1: 0.4966]	10.5+0.1s
+[4800/15600]	[L1: 0.4984]	11.0+0.1s
+[6400/15600]	[L1: 0.4985]	10.8+0.1s
+[8000/15600]	[L1: 0.4987]	10.1+0.1s
+[9600/15600]	[L1: 0.5000]	11.6+0.1s
+[11200/15600]	[L1: 0.4999]	11.1+0.1s
+[12800/15600]	[L1: 0.4988]	11.0+0.1s
+[14400/15600]	[L1: 0.4988]	11.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.596 (Best: 54.596 @epoch 197)
+Forward: 60.29s
+
+Saving...
+Total: 61.09s
+
+[Epoch 198]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5023]	11.6+1.0s
+[3200/15600]	[L1: 0.5043]	10.0+0.1s
+[4800/15600]	[L1: 0.4986]	10.7+0.1s
+[6400/15600]	[L1: 0.4959]	11.6+0.1s
+[8000/15600]	[L1: 0.4966]	9.7+0.1s
+[9600/15600]	[L1: 0.4991]	9.9+0.1s
+[11200/15600]	[L1: 0.4990]	12.0+0.1s
+[12800/15600]	[L1: 0.4979]	10.9+0.1s
+[14400/15600]	[L1: 0.4991]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.184 (Best: 54.596 @epoch 197)
+Forward: 60.53s
+
+Saving...
+Total: 61.07s
+
+[Epoch 199]	Learning rate: 5.00e-5
+[1600/15600]	[L1: 0.5070]	11.3+0.6s
+[3200/15600]	[L1: 0.4995]	12.6+0.1s
+[4800/15600]	[L1: 0.5014]	11.1+0.1s
+[6400/15600]	[L1: 0.4997]	10.8+0.1s
+[8000/15600]	[L1: 0.4971]	12.7+0.1s
+[9600/15600]	[L1: 0.4946]	10.9+0.1s
+[11200/15600]	[L1: 0.4959]	11.1+0.1s
+[12800/15600]	[L1: 0.4936]	11.2+0.1s
+[14400/15600]	[L1: 0.4951]	12.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.286 (Best: 54.596 @epoch 197)
+Forward: 61.75s
+
+Saving...
+Total: 62.25s
+
+[Epoch 200]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4725]	11.3+0.6s
+[3200/15600]	[L1: 0.4710]	11.4+0.1s
+[4800/15600]	[L1: 0.4699]	12.8+0.1s
+[6400/15600]	[L1: 0.4671]	10.1+0.1s
+[8000/15600]	[L1: 0.4668]	11.0+0.1s
+[9600/15600]	[L1: 0.4670]	12.8+0.1s
+[11200/15600]	[L1: 0.4659]	11.1+0.1s
+[12800/15600]	[L1: 0.4661]	11.0+0.1s
+[14400/15600]	[L1: 0.4641]	12.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.211 (Best: 54.596 @epoch 197)
+Forward: 60.97s
+
+Saving...
+Total: 61.50s
+
+[Epoch 201]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4534]	11.9+0.6s
+[3200/15600]	[L1: 0.4663]	10.8+0.1s
+[4800/15600]	[L1: 0.4677]	10.7+0.1s
+[6400/15600]	[L1: 0.4696]	13.0+0.1s
+[8000/15600]	[L1: 0.4680]	11.1+0.1s
+[9600/15600]	[L1: 0.4697]	11.2+0.1s
+[11200/15600]	[L1: 0.4685]	13.0+0.1s
+[12800/15600]	[L1: 0.4674]	11.0+0.1s
+[14400/15600]	[L1: 0.4678]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.368 (Best: 54.596 @epoch 197)
+Forward: 62.41s
+
+Saving...
+Total: 62.92s
+
+[Epoch 202]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4839]	11.2+0.6s
+[3200/15600]	[L1: 0.4732]	12.8+0.1s
+[4800/15600]	[L1: 0.4687]	11.0+0.1s
+[6400/15600]	[L1: 0.4662]	11.2+0.1s
+[8000/15600]	[L1: 0.4712]	12.6+0.1s
+[9600/15600]	[L1: 0.4704]	11.1+0.1s
+[11200/15600]	[L1: 0.4678]	11.0+0.1s
+[12800/15600]	[L1: 0.4671]	11.3+0.1s
+[14400/15600]	[L1: 0.4681]	12.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.563 (Best: 54.596 @epoch 197)
+Forward: 60.61s
+
+Saving...
+Total: 61.16s
+
+[Epoch 203]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4638]	11.7+0.6s
+[3200/15600]	[L1: 0.4661]	11.2+0.1s
+[4800/15600]	[L1: 0.4638]	12.9+0.1s
+[6400/15600]	[L1: 0.4662]	11.1+0.1s
+[8000/15600]	[L1: 0.4653]	11.0+0.1s
+[9600/15600]	[L1: 0.4654]	12.9+0.1s
+[11200/15600]	[L1: 0.4675]	11.1+0.1s
+[12800/15600]	[L1: 0.4668]	11.0+0.1s
+[14400/15600]	[L1: 0.4659]	12.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.594 (Best: 54.596 @epoch 197)
+Forward: 60.68s
+
+Saving...
+Total: 61.18s
+
+[Epoch 204]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4712]	12.3+0.6s
+[3200/15600]	[L1: 0.4576]	11.1+0.1s
+[4800/15600]	[L1: 0.4636]	10.9+0.1s
+[6400/15600]	[L1: 0.4641]	11.8+0.1s
+[8000/15600]	[L1: 0.4620]	11.1+0.1s
+[9600/15600]	[L1: 0.4628]	10.8+0.1s
+[11200/15600]	[L1: 0.4643]	11.9+0.1s
+[12800/15600]	[L1: 0.4648]	11.1+0.1s
+[14400/15600]	[L1: 0.4663]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.559 (Best: 54.596 @epoch 197)
+Forward: 64.30s
+
+Saving...
+Total: 64.80s
+
+[Epoch 205]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4763]	11.1+0.8s
+[3200/15600]	[L1: 0.4726]	10.0+0.1s
+[4800/15600]	[L1: 0.4734]	10.9+0.1s
+[6400/15600]	[L1: 0.4699]	10.6+0.1s
+[8000/15600]	[L1: 0.4664]	10.3+0.1s
+[9600/15600]	[L1: 0.4655]	10.1+0.1s
+[11200/15600]	[L1: 0.4666]	11.4+0.1s
+[12800/15600]	[L1: 0.4658]	9.9+0.1s
+[14400/15600]	[L1: 0.4665]	9.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.573 (Best: 54.596 @epoch 197)
+Forward: 63.59s
+
+Saving...
+Total: 64.09s
+
+[Epoch 206]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4633]	12.0+0.6s
+[3200/15600]	[L1: 0.4666]	11.0+0.1s
+[4800/15600]	[L1: 0.4701]	10.7+0.1s
+[6400/15600]	[L1: 0.4706]	10.8+0.1s
+[8000/15600]	[L1: 0.4688]	10.9+0.1s
+[9600/15600]	[L1: 0.4704]	11.1+0.1s
+[11200/15600]	[L1: 0.4703]	11.2+0.1s
+[12800/15600]	[L1: 0.4675]	11.1+0.1s
+[14400/15600]	[L1: 0.4671]	9.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.717 (Best: 54.717 @epoch 206)
+Forward: 63.45s
+
+Saving...
+Total: 63.96s
+
+[Epoch 207]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4542]	10.8+0.5s
+[3200/15600]	[L1: 0.4590]	11.6+0.1s
+[4800/15600]	[L1: 0.4613]	10.5+0.1s
+[6400/15600]	[L1: 0.4642]	10.8+0.1s
+[8000/15600]	[L1: 0.4648]	11.8+0.1s
+[9600/15600]	[L1: 0.4655]	10.3+0.1s
+[11200/15600]	[L1: 0.4651]	11.0+0.1s
+[12800/15600]	[L1: 0.4644]	11.8+0.1s
+[14400/15600]	[L1: 0.4628]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.719 (Best: 54.719 @epoch 207)
+Forward: 63.58s
+
+Saving...
+Total: 64.09s
+
+[Epoch 208]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4583]	10.8+0.5s
+[3200/15600]	[L1: 0.4627]	10.5+0.1s
+[4800/15600]	[L1: 0.4581]	10.8+0.1s
+[6400/15600]	[L1: 0.4595]	11.1+0.1s
+[8000/15600]	[L1: 0.4594]	10.9+0.1s
+[9600/15600]	[L1: 0.4606]	11.6+0.1s
+[11200/15600]	[L1: 0.4611]	10.9+0.1s
+[12800/15600]	[L1: 0.4613]	11.0+0.1s
+[14400/15600]	[L1: 0.4619]	11.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.733 (Best: 54.733 @epoch 208)
+Forward: 62.41s
+
+Saving...
+Total: 62.96s
+
+[Epoch 209]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4498]	11.2+0.5s
+[3200/15600]	[L1: 0.4574]	10.9+0.1s
+[4800/15600]	[L1: 0.4603]	10.6+0.1s
+[6400/15600]	[L1: 0.4605]	9.7+0.1s
+[8000/15600]	[L1: 0.4610]	9.5+0.1s
+[9600/15600]	[L1: 0.4631]	10.5+0.1s
+[11200/15600]	[L1: 0.4641]	9.8+0.1s
+[12800/15600]	[L1: 0.4625]	11.0+0.1s
+[14400/15600]	[L1: 0.4624]	11.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.609 (Best: 54.733 @epoch 208)
+Forward: 61.48s
+
+Saving...
+Total: 61.99s
+
+[Epoch 210]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4668]	11.4+0.8s
+[3200/15600]	[L1: 0.4626]	10.3+0.1s
+[4800/15600]	[L1: 0.4620]	11.3+0.1s
+[6400/15600]	[L1: 0.4604]	11.0+0.1s
+[8000/15600]	[L1: 0.4579]	11.0+0.1s
+[9600/15600]	[L1: 0.4593]	11.0+0.1s
+[11200/15600]	[L1: 0.4586]	12.5+0.1s
+[12800/15600]	[L1: 0.4585]	11.0+0.1s
+[14400/15600]	[L1: 0.4596]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.569 (Best: 54.733 @epoch 208)
+Forward: 60.49s
+
+Saving...
+Total: 60.98s
+
+[Epoch 211]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4588]	12.9+0.6s
+[3200/15600]	[L1: 0.4652]	11.2+0.1s
+[4800/15600]	[L1: 0.4575]	11.0+0.1s
+[6400/15600]	[L1: 0.4571]	12.9+0.1s
+[8000/15600]	[L1: 0.4582]	11.0+0.1s
+[9600/15600]	[L1: 0.4589]	11.1+0.1s
+[11200/15600]	[L1: 0.4607]	11.4+0.1s
+[12800/15600]	[L1: 0.4625]	12.3+0.1s
+[14400/15600]	[L1: 0.4632]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.203 (Best: 54.733 @epoch 208)
+Forward: 62.20s
+
+Saving...
+Total: 62.68s
+
+[Epoch 212]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4633]	10.3+0.6s
+[3200/15600]	[L1: 0.4570]	10.1+0.1s
+[4800/15600]	[L1: 0.4608]	12.2+0.1s
+[6400/15600]	[L1: 0.4625]	10.8+0.1s
+[8000/15600]	[L1: 0.4613]	10.9+0.1s
+[9600/15600]	[L1: 0.4601]	12.1+0.1s
+[11200/15600]	[L1: 0.4597]	10.7+0.1s
+[12800/15600]	[L1: 0.4594]	10.8+0.1s
+[14400/15600]	[L1: 0.4604]	12.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.072 (Best: 54.733 @epoch 208)
+Forward: 61.07s
+
+Saving...
+Total: 61.65s
+
+[Epoch 213]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4552]	11.9+0.7s
+[3200/15600]	[L1: 0.4637]	10.1+0.1s
+[4800/15600]	[L1: 0.4610]	10.7+0.1s
+[6400/15600]	[L1: 0.4653]	12.7+0.1s
+[8000/15600]	[L1: 0.4643]	10.4+0.1s
+[9600/15600]	[L1: 0.4651]	9.6+0.1s
+[11200/15600]	[L1: 0.4659]	11.3+0.1s
+[12800/15600]	[L1: 0.4671]	10.5+0.1s
+[14400/15600]	[L1: 0.4679]	9.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.759 (Best: 54.759 @epoch 213)
+Forward: 62.52s
+
+Saving...
+Total: 63.06s
+
+[Epoch 214]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4603]	11.1+0.6s
+[3200/15600]	[L1: 0.4543]	12.7+0.1s
+[4800/15600]	[L1: 0.4574]	11.0+0.1s
+[6400/15600]	[L1: 0.4562]	11.1+0.1s
+[8000/15600]	[L1: 0.4579]	12.6+0.1s
+[9600/15600]	[L1: 0.4598]	11.2+0.1s
+[11200/15600]	[L1: 0.4589]	10.8+0.1s
+[12800/15600]	[L1: 0.4604]	11.0+0.1s
+[14400/15600]	[L1: 0.4588]	12.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.665 (Best: 54.759 @epoch 213)
+Forward: 61.19s
+
+Saving...
+Total: 61.66s
+
+[Epoch 215]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4626]	11.3+0.6s
+[3200/15600]	[L1: 0.4579]	10.9+0.1s
+[4800/15600]	[L1: 0.4628]	12.7+0.1s
+[6400/15600]	[L1: 0.4619]	11.1+0.1s
+[8000/15600]	[L1: 0.4622]	10.9+0.1s
+[9600/15600]	[L1: 0.4615]	12.7+0.1s
+[11200/15600]	[L1: 0.4621]	10.6+0.1s
+[12800/15600]	[L1: 0.4614]	10.8+0.1s
+[14400/15600]	[L1: 0.4614]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.637 (Best: 54.759 @epoch 213)
+Forward: 62.96s
+
+Saving...
+Total: 63.45s
+
+[Epoch 216]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4541]	12.1+0.6s
+[3200/15600]	[L1: 0.4582]	11.0+0.1s
+[4800/15600]	[L1: 0.4599]	11.1+0.1s
+[6400/15600]	[L1: 0.4608]	11.7+0.1s
+[8000/15600]	[L1: 0.4612]	11.0+0.1s
+[9600/15600]	[L1: 0.4643]	11.0+0.1s
+[11200/15600]	[L1: 0.4650]	11.8+0.1s
+[12800/15600]	[L1: 0.4635]	11.1+0.1s
+[14400/15600]	[L1: 0.4625]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.576 (Best: 54.759 @epoch 213)
+Forward: 63.69s
+
+Saving...
+Total: 64.15s
+
+[Epoch 217]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4428]	12.9+0.8s
+[3200/15600]	[L1: 0.4481]	11.0+0.1s
+[4800/15600]	[L1: 0.4483]	11.2+0.1s
+[6400/15600]	[L1: 0.4529]	12.5+0.1s
+[8000/15600]	[L1: 0.4560]	11.0+0.1s
+[9600/15600]	[L1: 0.4564]	10.9+0.1s
+[11200/15600]	[L1: 0.4586]	12.7+0.1s
+[12800/15600]	[L1: 0.4583]	10.9+0.1s
+[14400/15600]	[L1: 0.4592]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.280 (Best: 54.759 @epoch 213)
+Forward: 61.37s
+
+Saving...
+Total: 61.87s
+
+[Epoch 218]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4569]	11.4+0.6s
+[3200/15600]	[L1: 0.4564]	13.1+0.1s
+[4800/15600]	[L1: 0.4555]	11.0+0.1s
+[6400/15600]	[L1: 0.4570]	11.1+0.1s
+[8000/15600]	[L1: 0.4561]	12.9+0.1s
+[9600/15600]	[L1: 0.4566]	10.9+0.1s
+[11200/15600]	[L1: 0.4581]	9.7+0.1s
+[12800/15600]	[L1: 0.4602]	12.7+0.1s
+[14400/15600]	[L1: 0.4608]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.732 (Best: 54.759 @epoch 213)
+Forward: 62.25s
+
+Saving...
+Total: 62.74s
+
+[Epoch 219]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4679]	11.3+0.6s
+[3200/15600]	[L1: 0.4679]	11.1+0.1s
+[4800/15600]	[L1: 0.4707]	12.0+0.1s
+[6400/15600]	[L1: 0.4711]	11.0+0.1s
+[8000/15600]	[L1: 0.4701]	11.2+0.1s
+[9600/15600]	[L1: 0.4705]	11.9+0.1s
+[11200/15600]	[L1: 0.4722]	11.2+0.1s
+[12800/15600]	[L1: 0.4716]	10.9+0.1s
+[14400/15600]	[L1: 0.4703]	11.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.696 (Best: 54.759 @epoch 213)
+Forward: 62.42s
+
+Saving...
+Total: 62.92s
+
+[Epoch 220]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4696]	11.3+0.8s
+[3200/15600]	[L1: 0.4618]	10.9+0.1s
+[4800/15600]	[L1: 0.4657]	12.4+0.1s
+[6400/15600]	[L1: 0.4628]	11.1+0.1s
+[8000/15600]	[L1: 0.4588]	11.0+0.1s
+[9600/15600]	[L1: 0.4589]	12.6+0.1s
+[11200/15600]	[L1: 0.4572]	10.5+0.1s
+[12800/15600]	[L1: 0.4579]	10.5+0.1s
+[14400/15600]	[L1: 0.4594]	11.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.375 (Best: 54.759 @epoch 213)
+Forward: 59.19s
+
+Saving...
+Total: 59.70s
+
+[Epoch 221]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4597]	12.1+0.6s
+[3200/15600]	[L1: 0.4622]	10.0+0.1s
+[4800/15600]	[L1: 0.4623]	11.0+0.1s
+[6400/15600]	[L1: 0.4619]	12.4+0.1s
+[8000/15600]	[L1: 0.4611]	10.1+0.1s
+[9600/15600]	[L1: 0.4602]	10.9+0.1s
+[11200/15600]	[L1: 0.4606]	11.5+0.1s
+[12800/15600]	[L1: 0.4616]	12.3+0.1s
+[14400/15600]	[L1: 0.4624]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.662 (Best: 54.759 @epoch 213)
+Forward: 61.85s
+
+Saving...
+Total: 62.36s
+
+[Epoch 222]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4558]	11.1+0.6s
+[3200/15600]	[L1: 0.4602]	13.0+0.1s
+[4800/15600]	[L1: 0.4595]	11.1+0.1s
+[6400/15600]	[L1: 0.4652]	11.0+0.1s
+[8000/15600]	[L1: 0.4646]	13.0+0.1s
+[9600/15600]	[L1: 0.4658]	11.1+0.1s
+[11200/15600]	[L1: 0.4663]	10.9+0.1s
+[12800/15600]	[L1: 0.4648]	12.4+0.1s
+[14400/15600]	[L1: 0.4640]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.420 (Best: 54.759 @epoch 213)
+Forward: 60.81s
+
+Saving...
+Total: 61.33s
+
+[Epoch 223]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4531]	11.3+0.6s
+[3200/15600]	[L1: 0.4554]	11.0+0.1s
+[4800/15600]	[L1: 0.4558]	11.9+0.1s
+[6400/15600]	[L1: 0.4557]	11.0+0.1s
+[8000/15600]	[L1: 0.4561]	11.0+0.1s
+[9600/15600]	[L1: 0.4557]	12.0+0.1s
+[11200/15600]	[L1: 0.4565]	11.1+0.1s
+[12800/15600]	[L1: 0.4571]	11.2+0.1s
+[14400/15600]	[L1: 0.4588]	11.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.640 (Best: 54.759 @epoch 213)
+Forward: 62.50s
+
+Saving...
+Total: 63.19s
+
+[Epoch 224]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4519]	10.7+0.8s
+[3200/15600]	[L1: 0.4573]	10.9+0.1s
+[4800/15600]	[L1: 0.4569]	12.7+0.1s
+[6400/15600]	[L1: 0.4541]	11.0+0.1s
+[8000/15600]	[L1: 0.4556]	11.4+0.1s
+[9600/15600]	[L1: 0.4578]	12.6+0.1s
+[11200/15600]	[L1: 0.4577]	10.5+0.1s
+[12800/15600]	[L1: 0.4576]	10.7+0.1s
+[14400/15600]	[L1: 0.4578]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.252 (Best: 54.759 @epoch 213)
+Forward: 59.77s
+
+Saving...
+Total: 60.27s
+
+[Epoch 225]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4627]	12.9+0.6s
+[3200/15600]	[L1: 0.4640]	10.9+0.1s
+[4800/15600]	[L1: 0.4582]	11.2+0.1s
+[6400/15600]	[L1: 0.4550]	12.7+0.1s
+[8000/15600]	[L1: 0.4542]	11.2+0.1s
+[9600/15600]	[L1: 0.4616]	11.4+0.1s
+[11200/15600]	[L1: 0.4614]	13.0+0.1s
+[12800/15600]	[L1: 0.4613]	11.5+0.1s
+[14400/15600]	[L1: 0.4608]	11.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.126 (Best: 54.759 @epoch 213)
+Forward: 61.49s
+
+Saving...
+Total: 61.99s
+
+[Epoch 226]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4530]	11.4+0.6s
+[3200/15600]	[L1: 0.4506]	12.4+0.1s
+[4800/15600]	[L1: 0.4486]	11.3+0.1s
+[6400/15600]	[L1: 0.4479]	11.4+0.1s
+[8000/15600]	[L1: 0.4490]	12.3+0.1s
+[9600/15600]	[L1: 0.4508]	11.1+0.1s
+[11200/15600]	[L1: 0.4530]	10.7+0.1s
+[12800/15600]	[L1: 0.4523]	12.8+0.1s
+[14400/15600]	[L1: 0.4517]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.326 (Best: 54.759 @epoch 213)
+Forward: 61.75s
+
+Saving...
+Total: 62.39s
+
+[Epoch 227]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4612]	11.2+0.6s
+[3200/15600]	[L1: 0.4600]	11.2+0.1s
+[4800/15600]	[L1: 0.4587]	12.8+0.1s
+[6400/15600]	[L1: 0.4587]	11.2+0.1s
+[8000/15600]	[L1: 0.4594]	11.2+0.1s
+[9600/15600]	[L1: 0.4614]	12.6+0.1s
+[11200/15600]	[L1: 0.4618]	11.1+0.1s
+[12800/15600]	[L1: 0.4605]	11.1+0.1s
+[14400/15600]	[L1: 0.4595]	12.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.542 (Best: 54.759 @epoch 213)
+Forward: 59.80s
+
+Saving...
+Total: 60.26s
+
+[Epoch 228]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4618]	12.1+0.7s
+[3200/15600]	[L1: 0.4667]	10.8+0.1s
+[4800/15600]	[L1: 0.4653]	11.0+0.1s
+[6400/15600]	[L1: 0.4666]	12.8+0.1s
+[8000/15600]	[L1: 0.4667]	10.5+0.1s
+[9600/15600]	[L1: 0.4655]	11.0+0.1s
+[11200/15600]	[L1: 0.4654]	12.9+0.1s
+[12800/15600]	[L1: 0.4651]	11.0+0.1s
+[14400/15600]	[L1: 0.4655]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.743 (Best: 54.759 @epoch 213)
+Forward: 60.05s
+
+Saving...
+Total: 60.54s
+
+[Epoch 229]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4529]	11.5+0.6s
+[3200/15600]	[L1: 0.4531]	11.9+0.1s
+[4800/15600]	[L1: 0.4530]	10.4+0.1s
+[6400/15600]	[L1: 0.4565]	11.0+0.1s
+[8000/15600]	[L1: 0.4554]	12.5+0.1s
+[9600/15600]	[L1: 0.4545]	11.1+0.1s
+[11200/15600]	[L1: 0.4546]	11.1+0.1s
+[12800/15600]	[L1: 0.4559]	12.3+0.1s
+[14400/15600]	[L1: 0.4576]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.333 (Best: 54.759 @epoch 213)
+Forward: 60.75s
+
+Saving...
+Total: 61.38s
+
+[Epoch 230]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4557]	11.2+0.6s
+[3200/15600]	[L1: 0.4553]	11.2+0.1s
+[4800/15600]	[L1: 0.4559]	12.6+0.1s
+[6400/15600]	[L1: 0.4524]	11.1+0.1s
+[8000/15600]	[L1: 0.4559]	11.1+0.1s
+[9600/15600]	[L1: 0.4561]	12.4+0.1s
+[11200/15600]	[L1: 0.4566]	10.7+0.1s
+[12800/15600]	[L1: 0.4571]	10.8+0.1s
+[14400/15600]	[L1: 0.4568]	11.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.476 (Best: 54.759 @epoch 213)
+Forward: 59.90s
+
+Saving...
+Total: 60.43s
+
+[Epoch 231]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4502]	12.7+0.7s
+[3200/15600]	[L1: 0.4415]	10.9+0.1s
+[4800/15600]	[L1: 0.4465]	10.6+0.1s
+[6400/15600]	[L1: 0.4442]	12.6+0.1s
+[8000/15600]	[L1: 0.4528]	10.7+0.1s
+[9600/15600]	[L1: 0.4543]	11.1+0.1s
+[11200/15600]	[L1: 0.4562]	12.6+0.1s
+[12800/15600]	[L1: 0.4547]	10.8+0.1s
+[14400/15600]	[L1: 0.4546]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.594 (Best: 54.759 @epoch 213)
+Forward: 61.09s
+
+Saving...
+Total: 61.71s
+
+[Epoch 232]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4699]	11.0+0.8s
+[3200/15600]	[L1: 0.4579]	12.5+0.1s
+[4800/15600]	[L1: 0.4563]	10.9+0.1s
+[6400/15600]	[L1: 0.4584]	10.9+0.1s
+[8000/15600]	[L1: 0.4571]	12.4+0.1s
+[9600/15600]	[L1: 0.4556]	11.1+0.1s
+[11200/15600]	[L1: 0.4554]	11.0+0.1s
+[12800/15600]	[L1: 0.4581]	12.2+0.1s
+[14400/15600]	[L1: 0.4570]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.831 (Best: 54.831 @epoch 232)
+Forward: 61.57s
+
+Saving...
+Total: 62.11s
+
+[Epoch 233]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4520]	11.2+0.6s
+[3200/15600]	[L1: 0.4518]	10.1+0.1s
+[4800/15600]	[L1: 0.4575]	11.5+0.1s
+[6400/15600]	[L1: 0.4589]	11.0+0.1s
+[8000/15600]	[L1: 0.4588]	11.2+0.1s
+[9600/15600]	[L1: 0.4587]	12.7+0.1s
+[11200/15600]	[L1: 0.4572]	11.2+0.1s
+[12800/15600]	[L1: 0.4580]	11.0+0.1s
+[14400/15600]	[L1: 0.4593]	12.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.727 (Best: 54.831 @epoch 232)
+Forward: 59.71s
+
+Saving...
+Total: 60.50s
+
+[Epoch 234]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4606]	11.1+0.8s
+[3200/15600]	[L1: 0.4561]	11.2+0.1s
+[4800/15600]	[L1: 0.4553]	11.2+0.1s
+[6400/15600]	[L1: 0.4512]	10.7+0.1s
+[8000/15600]	[L1: 0.4516]	10.3+0.1s
+[9600/15600]	[L1: 0.4504]	10.7+0.1s
+[11200/15600]	[L1: 0.4517]	11.2+0.1s
+[12800/15600]	[L1: 0.4523]	10.2+0.1s
+[14400/15600]	[L1: 0.4532]	9.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.734 (Best: 54.831 @epoch 232)
+Forward: 63.35s
+
+Saving...
+Total: 63.86s
+
+[Epoch 235]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4557]	12.0+0.6s
+[3200/15600]	[L1: 0.4599]	11.0+0.1s
+[4800/15600]	[L1: 0.4570]	10.8+0.1s
+[6400/15600]	[L1: 0.4569]	12.0+0.1s
+[8000/15600]	[L1: 0.4584]	11.1+0.1s
+[9600/15600]	[L1: 0.4576]	10.6+0.1s
+[11200/15600]	[L1: 0.4557]	11.4+0.1s
+[12800/15600]	[L1: 0.4571]	9.8+0.1s
+[14400/15600]	[L1: 0.4570]	10.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.636 (Best: 54.831 @epoch 232)
+Forward: 64.20s
+
+Saving...
+Total: 64.67s
+
+[Epoch 236]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4635]	11.3+0.5s
+[3200/15600]	[L1: 0.4557]	11.5+0.1s
+[4800/15600]	[L1: 0.4536]	10.1+0.1s
+[6400/15600]	[L1: 0.4535]	9.6+0.1s
+[8000/15600]	[L1: 0.4552]	11.1+0.1s
+[9600/15600]	[L1: 0.4574]	9.9+0.1s
+[11200/15600]	[L1: 0.4566]	11.0+0.1s
+[12800/15600]	[L1: 0.4582]	11.2+0.1s
+[14400/15600]	[L1: 0.4575]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.807 (Best: 54.831 @epoch 232)
+Forward: 63.98s
+
+Saving...
+Total: 64.51s
+
+[Epoch 237]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4636]	10.2+0.5s
+[3200/15600]	[L1: 0.4654]	11.4+0.1s
+[4800/15600]	[L1: 0.4630]	10.7+0.1s
+[6400/15600]	[L1: 0.4634]	11.0+0.1s
+[8000/15600]	[L1: 0.4627]	11.7+0.1s
+[9600/15600]	[L1: 0.4617]	10.4+0.1s
+[11200/15600]	[L1: 0.4614]	9.8+0.1s
+[12800/15600]	[L1: 0.4608]	11.4+0.1s
+[14400/15600]	[L1: 0.4594]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.687 (Best: 54.831 @epoch 232)
+Forward: 61.79s
+
+Saving...
+Total: 62.30s
+
+[Epoch 238]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4660]	11.5+0.7s
+[3200/15600]	[L1: 0.4637]	11.9+0.1s
+[4800/15600]	[L1: 0.4660]	11.7+0.1s
+[6400/15600]	[L1: 0.4639]	11.0+0.1s
+[8000/15600]	[L1: 0.4630]	11.0+0.1s
+[9600/15600]	[L1: 0.4610]	12.6+0.1s
+[11200/15600]	[L1: 0.4623]	11.0+0.1s
+[12800/15600]	[L1: 0.4597]	11.0+0.1s
+[14400/15600]	[L1: 0.4597]	12.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.470 (Best: 54.831 @epoch 232)
+Forward: 60.09s
+
+Saving...
+Total: 61.01s
+
+[Epoch 239]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4492]	13.0+0.7s
+[3200/15600]	[L1: 0.4520]	11.0+0.1s
+[4800/15600]	[L1: 0.4484]	11.0+0.1s
+[6400/15600]	[L1: 0.4524]	12.9+0.1s
+[8000/15600]	[L1: 0.4524]	11.0+0.1s
+[9600/15600]	[L1: 0.4529]	10.4+0.1s
+[11200/15600]	[L1: 0.4533]	12.9+0.1s
+[12800/15600]	[L1: 0.4522]	11.2+0.1s
+[14400/15600]	[L1: 0.4521]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.650 (Best: 54.831 @epoch 232)
+Forward: 59.01s
+
+Saving...
+Total: 59.52s
+
+[Epoch 240]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4547]	10.6+0.6s
+[3200/15600]	[L1: 0.4575]	12.2+0.1s
+[4800/15600]	[L1: 0.4585]	11.1+0.1s
+[6400/15600]	[L1: 0.4584]	10.9+0.1s
+[8000/15600]	[L1: 0.4582]	12.5+0.1s
+[9600/15600]	[L1: 0.4593]	11.1+0.1s
+[11200/15600]	[L1: 0.4589]	11.2+0.1s
+[12800/15600]	[L1: 0.4588]	12.8+0.1s
+[14400/15600]	[L1: 0.4569]	11.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.239 (Best: 54.831 @epoch 232)
+Forward: 60.10s
+
+Saving...
+Total: 60.61s
+
+[Epoch 241]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4428]	11.2+0.7s
+[3200/15600]	[L1: 0.4485]	10.9+0.1s
+[4800/15600]	[L1: 0.4513]	12.8+0.1s
+[6400/15600]	[L1: 0.4521]	10.9+0.1s
+[8000/15600]	[L1: 0.4506]	10.9+0.1s
+[9600/15600]	[L1: 0.4501]	12.4+0.1s
+[11200/15600]	[L1: 0.4505]	11.1+0.1s
+[12800/15600]	[L1: 0.4523]	11.5+0.1s
+[14400/15600]	[L1: 0.4518]	12.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.422 (Best: 54.831 @epoch 232)
+Forward: 59.24s
+
+Saving...
+Total: 60.07s
+
+[Epoch 242]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4533]	12.6+0.8s
+[3200/15600]	[L1: 0.4568]	10.5+0.1s
+[4800/15600]	[L1: 0.4568]	10.0+0.1s
+[6400/15600]	[L1: 0.4555]	10.2+0.1s
+[8000/15600]	[L1: 0.4553]	9.2+0.1s
+[9600/15600]	[L1: 0.4543]	10.2+0.1s
+[11200/15600]	[L1: 0.4538]	10.8+0.1s
+[12800/15600]	[L1: 0.4559]	10.3+0.1s
+[14400/15600]	[L1: 0.4569]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.658 (Best: 54.831 @epoch 232)
+Forward: 63.48s
+
+Saving...
+Total: 64.05s
+
+[Epoch 243]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4443]	11.0+0.6s
+[3200/15600]	[L1: 0.4484]	11.9+0.1s
+[4800/15600]	[L1: 0.4499]	11.0+0.1s
+[6400/15600]	[L1: 0.4510]	11.0+0.1s
+[8000/15600]	[L1: 0.4506]	11.7+0.1s
+[9600/15600]	[L1: 0.4527]	11.1+0.1s
+[11200/15600]	[L1: 0.4528]	10.9+0.1s
+[12800/15600]	[L1: 0.4533]	11.6+0.1s
+[14400/15600]	[L1: 0.4538]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.165 (Best: 54.831 @epoch 232)
+Forward: 62.97s
+
+Saving...
+Total: 63.68s
+
+[Epoch 244]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4513]	11.1+0.8s
+[3200/15600]	[L1: 0.4648]	11.0+0.1s
+[4800/15600]	[L1: 0.4646]	9.3+0.1s
+[6400/15600]	[L1: 0.4629]	11.2+0.1s
+[8000/15600]	[L1: 0.4622]	12.6+0.1s
+[9600/15600]	[L1: 0.4616]	11.0+0.1s
+[11200/15600]	[L1: 0.4609]	11.0+0.1s
+[12800/15600]	[L1: 0.4599]	12.6+0.1s
+[14400/15600]	[L1: 0.4614]	10.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.579 (Best: 54.831 @epoch 232)
+Forward: 61.14s
+
+Saving...
+Total: 61.67s
+
+[Epoch 245]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4544]	11.2+0.7s
+[3200/15600]	[L1: 0.4538]	11.1+0.1s
+[4800/15600]	[L1: 0.4494]	12.5+0.1s
+[6400/15600]	[L1: 0.4529]	11.0+0.1s
+[8000/15600]	[L1: 0.4533]	11.0+0.1s
+[9600/15600]	[L1: 0.4533]	12.8+0.1s
+[11200/15600]	[L1: 0.4535]	11.1+0.1s
+[12800/15600]	[L1: 0.4534]	11.1+0.1s
+[14400/15600]	[L1: 0.4539]	13.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.413 (Best: 54.831 @epoch 232)
+Forward: 60.21s
+
+Saving...
+Total: 60.69s
+
+[Epoch 246]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4546]	13.0+0.7s
+[3200/15600]	[L1: 0.4499]	11.1+0.1s
+[4800/15600]	[L1: 0.4527]	10.9+0.1s
+[6400/15600]	[L1: 0.4568]	12.7+0.1s
+[8000/15600]	[L1: 0.4560]	11.1+0.1s
+[9600/15600]	[L1: 0.4557]	10.9+0.1s
+[11200/15600]	[L1: 0.4559]	12.6+0.1s
+[12800/15600]	[L1: 0.4568]	10.9+0.1s
+[14400/15600]	[L1: 0.4571]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.766 (Best: 54.831 @epoch 232)
+Forward: 59.75s
+
+Saving...
+Total: 60.27s
+
+[Epoch 247]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4369]	10.7+0.6s
+[3200/15600]	[L1: 0.4458]	12.8+0.1s
+[4800/15600]	[L1: 0.4516]	11.0+0.1s
+[6400/15600]	[L1: 0.4499]	11.2+0.1s
+[8000/15600]	[L1: 0.4511]	12.8+0.1s
+[9600/15600]	[L1: 0.4498]	11.0+0.1s
+[11200/15600]	[L1: 0.4503]	11.1+0.1s
+[12800/15600]	[L1: 0.4525]	12.5+0.1s
+[14400/15600]	[L1: 0.4527]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.718 (Best: 54.831 @epoch 232)
+Forward: 63.00s
+
+Saving...
+Total: 63.48s
+
+[Epoch 248]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4554]	10.9+0.6s
+[3200/15600]	[L1: 0.4550]	12.5+0.1s
+[4800/15600]	[L1: 0.4509]	10.2+0.1s
+[6400/15600]	[L1: 0.4530]	10.9+0.1s
+[8000/15600]	[L1: 0.4523]	10.0+0.1s
+[9600/15600]	[L1: 0.4519]	13.0+0.1s
+[11200/15600]	[L1: 0.4519]	11.1+0.1s
+[12800/15600]	[L1: 0.4510]	10.9+0.1s
+[14400/15600]	[L1: 0.4518]	12.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.699 (Best: 54.831 @epoch 232)
+Forward: 60.65s
+
+Saving...
+Total: 61.47s
+
+[Epoch 249]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4709]	12.8+0.7s
+[3200/15600]	[L1: 0.4621]	11.0+0.1s
+[4800/15600]	[L1: 0.4591]	11.0+0.1s
+[6400/15600]	[L1: 0.4573]	12.6+0.1s
+[8000/15600]	[L1: 0.4572]	11.1+0.1s
+[9600/15600]	[L1: 0.4531]	11.0+0.1s
+[11200/15600]	[L1: 0.4520]	12.7+0.1s
+[12800/15600]	[L1: 0.4541]	11.0+0.1s
+[14400/15600]	[L1: 0.4549]	11.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.611 (Best: 54.831 @epoch 232)
+Forward: 59.81s
+
+Saving...
+Total: 60.34s
+
+[Epoch 250]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4445]	11.2+0.7s
+[3200/15600]	[L1: 0.4501]	12.6+0.1s
+[4800/15600]	[L1: 0.4527]	11.0+0.1s
+[6400/15600]	[L1: 0.4511]	10.9+0.1s
+[8000/15600]	[L1: 0.4531]	12.6+0.1s
+[9600/15600]	[L1: 0.4517]	11.0+0.1s
+[11200/15600]	[L1: 0.4535]	10.8+0.1s
+[12800/15600]	[L1: 0.4534]	12.6+0.1s
+[14400/15600]	[L1: 0.4549]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.745 (Best: 54.831 @epoch 232)
+Forward: 60.42s
+
+Saving...
+Total: 60.94s
+
+[Epoch 251]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4522]	11.4+0.7s
+[3200/15600]	[L1: 0.4520]	10.9+0.1s
+[4800/15600]	[L1: 0.4484]	12.8+0.1s
+[6400/15600]	[L1: 0.4464]	10.9+0.1s
+[8000/15600]	[L1: 0.4482]	10.5+0.1s
+[9600/15600]	[L1: 0.4497]	12.5+0.1s
+[11200/15600]	[L1: 0.4502]	10.8+0.1s
+[12800/15600]	[L1: 0.4519]	10.7+0.1s
+[14400/15600]	[L1: 0.4517]	12.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.774 (Best: 54.831 @epoch 232)
+Forward: 60.45s
+
+Saving...
+Total: 61.41s
+
+[Epoch 252]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4666]	11.4+0.8s
+[3200/15600]	[L1: 0.4583]	11.1+0.1s
+[4800/15600]	[L1: 0.4610]	11.9+0.1s
+[6400/15600]	[L1: 0.4606]	12.1+0.1s
+[8000/15600]	[L1: 0.4591]	11.1+0.1s
+[9600/15600]	[L1: 0.4572]	10.9+0.1s
+[11200/15600]	[L1: 0.4580]	12.9+0.1s
+[12800/15600]	[L1: 0.4571]	11.1+0.1s
+[14400/15600]	[L1: 0.4568]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.707 (Best: 54.831 @epoch 232)
+Forward: 60.50s
+
+Saving...
+Total: 61.01s
+
+[Epoch 253]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4451]	12.4+0.6s
+[3200/15600]	[L1: 0.4583]	11.4+0.1s
+[4800/15600]	[L1: 0.4561]	11.3+0.1s
+[6400/15600]	[L1: 0.4549]	11.9+0.1s
+[8000/15600]	[L1: 0.4547]	11.1+0.1s
+[9600/15600]	[L1: 0.4530]	11.1+0.1s
+[11200/15600]	[L1: 0.4544]	11.8+0.1s
+[12800/15600]	[L1: 0.4546]	11.1+0.1s
+[14400/15600]	[L1: 0.4543]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.663 (Best: 54.831 @epoch 232)
+Forward: 63.92s
+
+Saving...
+Total: 64.47s
+
+[Epoch 254]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4482]	12.0+0.6s
+[3200/15600]	[L1: 0.4582]	11.4+0.1s
+[4800/15600]	[L1: 0.4571]	11.1+0.1s
+[6400/15600]	[L1: 0.4546]	11.8+0.1s
+[8000/15600]	[L1: 0.4545]	11.0+0.1s
+[9600/15600]	[L1: 0.4539]	11.2+0.1s
+[11200/15600]	[L1: 0.4527]	11.6+0.1s
+[12800/15600]	[L1: 0.4541]	10.6+0.1s
+[14400/15600]	[L1: 0.4546]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.797 (Best: 54.831 @epoch 232)
+Forward: 59.18s
+
+Saving...
+Total: 59.69s
+
+[Epoch 255]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4597]	12.4+0.8s
+[3200/15600]	[L1: 0.4526]	10.9+0.1s
+[4800/15600]	[L1: 0.4519]	10.5+0.1s
+[6400/15600]	[L1: 0.4504]	10.2+0.1s
+[8000/15600]	[L1: 0.4478]	11.3+0.1s
+[9600/15600]	[L1: 0.4484]	10.7+0.1s
+[11200/15600]	[L1: 0.4512]	10.4+0.1s
+[12800/15600]	[L1: 0.4507]	11.3+0.1s
+[14400/15600]	[L1: 0.4517]	10.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.831 (Best: 54.831 @epoch 232)
+Forward: 62.08s
+
+Saving...
+Total: 62.58s
+
+[Epoch 256]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4499]	10.8+0.6s
+[3200/15600]	[L1: 0.4592]	11.3+0.1s
+[4800/15600]	[L1: 0.4576]	10.8+0.1s
+[6400/15600]	[L1: 0.4558]	11.0+0.1s
+[8000/15600]	[L1: 0.4553]	11.6+0.1s
+[9600/15600]	[L1: 0.4549]	10.9+0.1s
+[11200/15600]	[L1: 0.4556]	10.6+0.1s
+[12800/15600]	[L1: 0.4536]	11.6+0.1s
+[14400/15600]	[L1: 0.4539]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.480 (Best: 54.831 @epoch 232)
+Forward: 63.27s
+
+Saving...
+Total: 63.93s
+
+[Epoch 257]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4463]	11.2+0.6s
+[3200/15600]	[L1: 0.4463]	11.8+0.1s
+[4800/15600]	[L1: 0.4537]	10.9+0.1s
+[6400/15600]	[L1: 0.4518]	9.6+0.1s
+[8000/15600]	[L1: 0.4516]	10.1+0.1s
+[9600/15600]	[L1: 0.4543]	10.8+0.1s
+[11200/15600]	[L1: 0.4559]	9.7+0.1s
+[12800/15600]	[L1: 0.4545]	9.9+0.1s
+[14400/15600]	[L1: 0.4548]	10.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.285 (Best: 54.831 @epoch 232)
+Forward: 64.42s
+
+Saving...
+Total: 65.04s
+
+[Epoch 258]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4540]	11.0+0.5s
+[3200/15600]	[L1: 0.4532]	11.1+0.1s
+[4800/15600]	[L1: 0.4549]	11.7+0.1s
+[6400/15600]	[L1: 0.4535]	10.1+0.1s
+[8000/15600]	[L1: 0.4551]	10.2+0.1s
+[9600/15600]	[L1: 0.4547]	11.3+0.1s
+[11200/15600]	[L1: 0.4541]	11.0+0.1s
+[12800/15600]	[L1: 0.4535]	11.0+0.1s
+[14400/15600]	[L1: 0.4539]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.816 (Best: 54.831 @epoch 232)
+Forward: 62.42s
+
+Saving...
+Total: 62.97s
+
+[Epoch 259]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4573]	11.6+0.6s
+[3200/15600]	[L1: 0.4540]	11.0+0.1s
+[4800/15600]	[L1: 0.4501]	10.8+0.1s
+[6400/15600]	[L1: 0.4497]	11.4+0.1s
+[8000/15600]	[L1: 0.4506]	10.9+0.1s
+[9600/15600]	[L1: 0.4499]	10.9+0.1s
+[11200/15600]	[L1: 0.4514]	11.6+0.1s
+[12800/15600]	[L1: 0.4504]	10.9+0.1s
+[14400/15600]	[L1: 0.4510]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.900 (Best: 54.900 @epoch 259)
+Forward: 61.39s
+
+Saving...
+Total: 61.94s
+
+[Epoch 260]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4612]	11.8+0.6s
+[3200/15600]	[L1: 0.4626]	11.0+0.1s
+[4800/15600]	[L1: 0.4596]	11.0+0.1s
+[6400/15600]	[L1: 0.4568]	11.8+0.1s
+[8000/15600]	[L1: 0.4551]	11.0+0.1s
+[9600/15600]	[L1: 0.4537]	11.2+0.1s
+[11200/15600]	[L1: 0.4541]	11.8+0.1s
+[12800/15600]	[L1: 0.4547]	11.1+0.1s
+[14400/15600]	[L1: 0.4525]	10.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.412 (Best: 54.900 @epoch 259)
+Forward: 60.74s
+
+Saving...
+Total: 61.26s
+
+[Epoch 261]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4591]	12.3+0.8s
+[3200/15600]	[L1: 0.4512]	10.8+0.1s
+[4800/15600]	[L1: 0.4537]	11.1+0.1s
+[6400/15600]	[L1: 0.4584]	11.5+0.1s
+[8000/15600]	[L1: 0.4587]	10.4+0.1s
+[9600/15600]	[L1: 0.4581]	10.8+0.1s
+[11200/15600]	[L1: 0.4584]	10.9+0.1s
+[12800/15600]	[L1: 0.4564]	12.4+0.1s
+[14400/15600]	[L1: 0.4558]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.517 (Best: 54.900 @epoch 259)
+Forward: 61.30s
+
+Saving...
+Total: 61.87s
+
+[Epoch 262]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4681]	11.2+0.7s
+[3200/15600]	[L1: 0.4614]	12.6+0.1s
+[4800/15600]	[L1: 0.4554]	10.9+0.1s
+[6400/15600]	[L1: 0.4530]	10.9+0.1s
+[8000/15600]	[L1: 0.4553]	12.3+0.1s
+[9600/15600]	[L1: 0.4544]	10.2+0.1s
+[11200/15600]	[L1: 0.4553]	11.4+0.1s
+[12800/15600]	[L1: 0.4537]	11.2+0.1s
+[14400/15600]	[L1: 0.4542]	11.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.767 (Best: 54.900 @epoch 259)
+Forward: 60.40s
+
+Saving...
+Total: 60.88s
+
+[Epoch 263]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4663]	11.4+0.6s
+[3200/15600]	[L1: 0.4690]	10.9+0.1s
+[4800/15600]	[L1: 0.4589]	12.6+0.1s
+[6400/15600]	[L1: 0.4581]	11.0+0.1s
+[8000/15600]	[L1: 0.4532]	11.1+0.1s
+[9600/15600]	[L1: 0.4542]	11.0+0.1s
+[11200/15600]	[L1: 0.4541]	12.3+0.1s
+[12800/15600]	[L1: 0.4531]	11.0+0.1s
+[14400/15600]	[L1: 0.4538]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.758 (Best: 54.900 @epoch 259)
+Forward: 60.64s
+
+Saving...
+Total: 61.15s
+
+[Epoch 264]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4502]	12.7+0.6s
+[3200/15600]	[L1: 0.4537]	10.2+0.1s
+[4800/15600]	[L1: 0.4535]	10.9+0.1s
+[6400/15600]	[L1: 0.4521]	12.6+0.1s
+[8000/15600]	[L1: 0.4550]	10.8+0.1s
+[9600/15600]	[L1: 0.4522]	11.0+0.1s
+[11200/15600]	[L1: 0.4519]	12.7+0.1s
+[12800/15600]	[L1: 0.4517]	11.1+0.1s
+[14400/15600]	[L1: 0.4514]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.714 (Best: 54.900 @epoch 259)
+Forward: 60.02s
+
+Saving...
+Total: 60.51s
+
+[Epoch 265]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4508]	11.3+0.6s
+[3200/15600]	[L1: 0.4462]	12.8+0.1s
+[4800/15600]	[L1: 0.4484]	11.0+0.1s
+[6400/15600]	[L1: 0.4491]	11.0+0.1s
+[8000/15600]	[L1: 0.4475]	12.6+0.1s
+[9600/15600]	[L1: 0.4469]	11.1+0.1s
+[11200/15600]	[L1: 0.4483]	10.8+0.1s
+[12800/15600]	[L1: 0.4499]	11.7+0.1s
+[14400/15600]	[L1: 0.4499]	11.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.604 (Best: 54.900 @epoch 259)
+Forward: 60.43s
+
+Saving...
+Total: 60.96s
+
+[Epoch 266]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4509]	11.4+0.7s
+[3200/15600]	[L1: 0.4530]	11.0+0.1s
+[4800/15600]	[L1: 0.4538]	12.4+0.1s
+[6400/15600]	[L1: 0.4511]	11.0+0.1s
+[8000/15600]	[L1: 0.4525]	11.2+0.1s
+[9600/15600]	[L1: 0.4529]	12.6+0.1s
+[11200/15600]	[L1: 0.4525]	10.8+0.1s
+[12800/15600]	[L1: 0.4514]	10.8+0.1s
+[14400/15600]	[L1: 0.4528]	11.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.701 (Best: 54.900 @epoch 259)
+Forward: 59.51s
+
+Saving...
+Total: 59.98s
+
+[Epoch 267]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4471]	13.1+0.6s
+[3200/15600]	[L1: 0.4515]	11.0+0.1s
+[4800/15600]	[L1: 0.4499]	11.2+0.1s
+[6400/15600]	[L1: 0.4517]	12.6+0.1s
+[8000/15600]	[L1: 0.4516]	11.1+0.1s
+[9600/15600]	[L1: 0.4534]	11.1+0.1s
+[11200/15600]	[L1: 0.4555]	12.7+0.1s
+[12800/15600]	[L1: 0.4545]	11.1+0.1s
+[14400/15600]	[L1: 0.4553]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.783 (Best: 54.900 @epoch 259)
+Forward: 58.56s
+
+Saving...
+Total: 59.04s
+
+[Epoch 268]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4538]	11.3+0.6s
+[3200/15600]	[L1: 0.4509]	12.5+0.1s
+[4800/15600]	[L1: 0.4535]	11.0+0.1s
+[6400/15600]	[L1: 0.4487]	10.9+0.1s
+[8000/15600]	[L1: 0.4477]	12.5+0.1s
+[9600/15600]	[L1: 0.4477]	10.9+0.1s
+[11200/15600]	[L1: 0.4486]	10.6+0.1s
+[12800/15600]	[L1: 0.4500]	11.3+0.1s
+[14400/15600]	[L1: 0.4503]	10.4+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.198 (Best: 54.900 @epoch 259)
+Forward: 60.23s
+
+Saving...
+Total: 60.76s
+
+[Epoch 269]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4567]	11.0+0.6s
+[3200/15600]	[L1: 0.4562]	10.3+0.1s
+[4800/15600]	[L1: 0.4563]	11.7+0.1s
+[6400/15600]	[L1: 0.4562]	10.5+0.1s
+[8000/15600]	[L1: 0.4540]	10.2+0.1s
+[9600/15600]	[L1: 0.4524]	11.0+0.1s
+[11200/15600]	[L1: 0.4523]	10.8+0.1s
+[12800/15600]	[L1: 0.4535]	10.4+0.1s
+[14400/15600]	[L1: 0.4524]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.670 (Best: 54.900 @epoch 259)
+Forward: 59.23s
+
+Saving...
+Total: 59.70s
+
+[Epoch 270]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4462]	11.9+0.8s
+[3200/15600]	[L1: 0.4480]	9.6+0.1s
+[4800/15600]	[L1: 0.4485]	10.6+0.1s
+[6400/15600]	[L1: 0.4474]	11.0+0.1s
+[8000/15600]	[L1: 0.4465]	12.7+0.1s
+[9600/15600]	[L1: 0.4463]	9.8+0.1s
+[11200/15600]	[L1: 0.4469]	10.1+0.1s
+[12800/15600]	[L1: 0.4462]	12.6+0.1s
+[14400/15600]	[L1: 0.4451]	11.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.698 (Best: 54.900 @epoch 259)
+Forward: 59.85s
+
+Saving...
+Total: 60.35s
+
+[Epoch 271]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4485]	11.3+0.6s
+[3200/15600]	[L1: 0.4525]	10.1+0.1s
+[4800/15600]	[L1: 0.4554]	11.7+0.1s
+[6400/15600]	[L1: 0.4530]	10.4+0.1s
+[8000/15600]	[L1: 0.4546]	11.1+0.1s
+[9600/15600]	[L1: 0.4547]	12.2+0.1s
+[11200/15600]	[L1: 0.4533]	10.9+0.1s
+[12800/15600]	[L1: 0.4524]	11.0+0.1s
+[14400/15600]	[L1: 0.4523]	12.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.198 (Best: 54.900 @epoch 259)
+Forward: 57.96s
+
+Saving...
+Total: 58.46s
+
+[Epoch 272]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4541]	13.1+0.7s
+[3200/15600]	[L1: 0.4528]	11.3+0.1s
+[4800/15600]	[L1: 0.4475]	11.2+0.1s
+[6400/15600]	[L1: 0.4458]	12.5+0.1s
+[8000/15600]	[L1: 0.4466]	11.2+0.1s
+[9600/15600]	[L1: 0.4476]	11.0+0.1s
+[11200/15600]	[L1: 0.4481]	12.5+0.1s
+[12800/15600]	[L1: 0.4499]	11.1+0.1s
+[14400/15600]	[L1: 0.4498]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.790 (Best: 54.900 @epoch 259)
+Forward: 58.71s
+
+Saving...
+Total: 59.21s
+
+[Epoch 273]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4480]	11.8+0.6s
+[3200/15600]	[L1: 0.4460]	10.9+0.1s
+[4800/15600]	[L1: 0.4470]	9.7+0.1s
+[6400/15600]	[L1: 0.4487]	9.9+0.1s
+[8000/15600]	[L1: 0.4508]	10.7+0.1s
+[9600/15600]	[L1: 0.4527]	10.1+0.1s
+[11200/15600]	[L1: 0.4510]	10.2+0.1s
+[12800/15600]	[L1: 0.4526]	10.2+0.1s
+[14400/15600]	[L1: 0.4531]	11.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.568 (Best: 54.900 @epoch 259)
+Forward: 59.45s
+
+Saving...
+Total: 59.98s
+
+[Epoch 274]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4532]	11.4+0.8s
+[3200/15600]	[L1: 0.4530]	11.0+0.1s
+[4800/15600]	[L1: 0.4542]	12.5+0.1s
+[6400/15600]	[L1: 0.4511]	11.0+0.1s
+[8000/15600]	[L1: 0.4529]	11.0+0.1s
+[9600/15600]	[L1: 0.4516]	11.3+0.1s
+[11200/15600]	[L1: 0.4523]	12.6+0.1s
+[12800/15600]	[L1: 0.4506]	11.4+0.1s
+[14400/15600]	[L1: 0.4506]	11.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.768 (Best: 54.900 @epoch 259)
+Forward: 59.89s
+
+Saving...
+Total: 60.36s
+
+[Epoch 275]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4580]	12.7+0.7s
+[3200/15600]	[L1: 0.4534]	11.2+0.1s
+[4800/15600]	[L1: 0.4525]	10.6+0.1s
+[6400/15600]	[L1: 0.4511]	12.4+0.1s
+[8000/15600]	[L1: 0.4503]	11.0+0.1s
+[9600/15600]	[L1: 0.4514]	11.2+0.1s
+[11200/15600]	[L1: 0.4514]	13.0+0.1s
+[12800/15600]	[L1: 0.4508]	10.9+0.1s
+[14400/15600]	[L1: 0.4524]	11.5+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.670 (Best: 54.900 @epoch 259)
+Forward: 57.24s
+
+Saving...
+Total: 57.72s
+
+[Epoch 276]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4462]	11.0+0.7s
+[3200/15600]	[L1: 0.4459]	12.5+0.1s
+[4800/15600]	[L1: 0.4478]	10.9+0.1s
+[6400/15600]	[L1: 0.4508]	11.0+0.1s
+[8000/15600]	[L1: 0.4517]	12.6+0.1s
+[9600/15600]	[L1: 0.4510]	11.1+0.1s
+[11200/15600]	[L1: 0.4502]	11.0+0.1s
+[12800/15600]	[L1: 0.4506]	12.5+0.1s
+[14400/15600]	[L1: 0.4507]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.689 (Best: 54.900 @epoch 259)
+Forward: 58.31s
+
+Saving...
+Total: 58.86s
+
+[Epoch 277]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4387]	11.0+0.6s
+[3200/15600]	[L1: 0.4433]	10.9+0.1s
+[4800/15600]	[L1: 0.4452]	12.4+0.1s
+[6400/15600]	[L1: 0.4441]	10.8+0.1s
+[8000/15600]	[L1: 0.4446]	11.0+0.1s
+[9600/15600]	[L1: 0.4454]	11.6+0.1s
+[11200/15600]	[L1: 0.4465]	11.5+0.1s
+[12800/15600]	[L1: 0.4457]	10.7+0.1s
+[14400/15600]	[L1: 0.4459]	10.8+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.707 (Best: 54.900 @epoch 259)
+Forward: 57.27s
+
+Saving...
+Total: 57.76s
+
+[Epoch 278]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4480]	12.6+0.7s
+[3200/15600]	[L1: 0.4478]	11.3+0.1s
+[4800/15600]	[L1: 0.4509]	11.0+0.1s
+[6400/15600]	[L1: 0.4534]	12.7+0.1s
+[8000/15600]	[L1: 0.4521]	10.9+0.1s
+[9600/15600]	[L1: 0.4502]	11.0+0.1s
+[11200/15600]	[L1: 0.4484]	10.9+0.1s
+[12800/15600]	[L1: 0.4500]	12.5+0.1s
+[14400/15600]	[L1: 0.4485]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.658 (Best: 54.900 @epoch 259)
+Forward: 59.08s
+
+Saving...
+Total: 59.57s
+
+[Epoch 279]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4523]	11.4+0.7s
+[3200/15600]	[L1: 0.4536]	12.5+0.1s
+[4800/15600]	[L1: 0.4528]	11.3+0.1s
+[6400/15600]	[L1: 0.4553]	11.0+0.1s
+[8000/15600]	[L1: 0.4555]	11.8+0.1s
+[9600/15600]	[L1: 0.4553]	11.8+0.1s
+[11200/15600]	[L1: 0.4546]	11.1+0.1s
+[12800/15600]	[L1: 0.4549]	11.3+0.1s
+[14400/15600]	[L1: 0.4545]	12.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.574 (Best: 54.900 @epoch 259)
+Forward: 59.13s
+
+Saving...
+Total: 59.61s
+
+[Epoch 280]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4644]	11.1+0.7s
+[3200/15600]	[L1: 0.4562]	10.7+0.1s
+[4800/15600]	[L1: 0.4564]	10.4+0.1s
+[6400/15600]	[L1: 0.4525]	11.0+0.1s
+[8000/15600]	[L1: 0.4517]	9.0+0.1s
+[9600/15600]	[L1: 0.4522]	10.1+0.1s
+[11200/15600]	[L1: 0.4522]	11.2+0.1s
+[12800/15600]	[L1: 0.4508]	10.4+0.1s
+[14400/15600]	[L1: 0.4505]	10.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.639 (Best: 54.900 @epoch 259)
+Forward: 61.09s
+
+Saving...
+Total: 61.60s
+
+[Epoch 281]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4427]	12.1+0.6s
+[3200/15600]	[L1: 0.4443]	10.9+0.1s
+[4800/15600]	[L1: 0.4477]	11.1+0.1s
+[6400/15600]	[L1: 0.4495]	11.9+0.1s
+[8000/15600]	[L1: 0.4525]	11.0+0.1s
+[9600/15600]	[L1: 0.4530]	11.1+0.1s
+[11200/15600]	[L1: 0.4527]	11.9+0.1s
+[12800/15600]	[L1: 0.4516]	11.1+0.1s
+[14400/15600]	[L1: 0.4508]	11.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.683 (Best: 54.900 @epoch 259)
+Forward: 59.98s
+
+Saving...
+Total: 60.46s
+
+[Epoch 282]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4413]	12.2+0.5s
+[3200/15600]	[L1: 0.4445]	11.4+0.1s
+[4800/15600]	[L1: 0.4434]	10.6+0.1s
+[6400/15600]	[L1: 0.4451]	12.0+0.1s
+[8000/15600]	[L1: 0.4458]	11.1+0.1s
+[9600/15600]	[L1: 0.4478]	11.1+0.1s
+[11200/15600]	[L1: 0.4474]	12.1+0.1s
+[12800/15600]	[L1: 0.4477]	11.2+0.1s
+[14400/15600]	[L1: 0.4491]	11.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.788 (Best: 54.900 @epoch 259)
+Forward: 63.52s
+
+Saving...
+Total: 64.04s
+
+[Epoch 283]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4528]	11.8+0.6s
+[3200/15600]	[L1: 0.4493]	11.0+0.1s
+[4800/15600]	[L1: 0.4480]	10.9+0.1s
+[6400/15600]	[L1: 0.4480]	11.7+0.1s
+[8000/15600]	[L1: 0.4469]	11.1+0.1s
+[9600/15600]	[L1: 0.4466]	10.9+0.1s
+[11200/15600]	[L1: 0.4469]	11.9+0.1s
+[12800/15600]	[L1: 0.4470]	11.1+0.1s
+[14400/15600]	[L1: 0.4466]	11.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.850 (Best: 54.900 @epoch 259)
+Forward: 61.09s
+
+Saving...
+Total: 61.58s
+
+[Epoch 284]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4423]	11.5+0.6s
+[3200/15600]	[L1: 0.4481]	11.5+0.1s
+[4800/15600]	[L1: 0.4467]	10.5+0.1s
+[6400/15600]	[L1: 0.4476]	10.8+0.1s
+[8000/15600]	[L1: 0.4480]	11.6+0.1s
+[9600/15600]	[L1: 0.4474]	11.0+0.1s
+[11200/15600]	[L1: 0.4464]	10.7+0.1s
+[12800/15600]	[L1: 0.4475]	11.7+0.1s
+[14400/15600]	[L1: 0.4470]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 53.603 (Best: 54.900 @epoch 259)
+Forward: 57.82s
+
+Saving...
+Total: 58.36s
+
+[Epoch 285]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4622]	12.0+0.7s
+[3200/15600]	[L1: 0.4502]	12.3+0.1s
+[4800/15600]	[L1: 0.4446]	11.8+0.1s
+[6400/15600]	[L1: 0.4465]	11.0+0.1s
+[8000/15600]	[L1: 0.4500]	11.1+0.1s
+[9600/15600]	[L1: 0.4490]	12.6+0.1s
+[11200/15600]	[L1: 0.4480]	11.0+0.1s
+[12800/15600]	[L1: 0.4473]	11.1+0.1s
+[14400/15600]	[L1: 0.4469]	12.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.559 (Best: 54.900 @epoch 259)
+Forward: 56.69s
+
+Saving...
+Total: 57.20s
+
+[Epoch 286]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4410]	12.6+0.6s
+[3200/15600]	[L1: 0.4463]	11.2+0.1s
+[4800/15600]	[L1: 0.4438]	11.3+0.1s
+[6400/15600]	[L1: 0.4445]	12.7+0.1s
+[8000/15600]	[L1: 0.4442]	10.9+0.1s
+[9600/15600]	[L1: 0.4444]	11.1+0.1s
+[11200/15600]	[L1: 0.4447]	12.4+0.1s
+[12800/15600]	[L1: 0.4448]	11.1+0.1s
+[14400/15600]	[L1: 0.4457]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.716 (Best: 54.900 @epoch 259)
+Forward: 57.49s
+
+Saving...
+Total: 58.01s
+
+[Epoch 287]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4542]	12.4+0.7s
+[3200/15600]	[L1: 0.4520]	11.4+0.1s
+[4800/15600]	[L1: 0.4501]	11.2+0.1s
+[6400/15600]	[L1: 0.4493]	11.1+0.1s
+[8000/15600]	[L1: 0.4483]	12.2+0.1s
+[9600/15600]	[L1: 0.4485]	11.2+0.1s
+[11200/15600]	[L1: 0.4488]	10.9+0.1s
+[12800/15600]	[L1: 0.4491]	12.6+0.1s
+[14400/15600]	[L1: 0.4499]	11.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.771 (Best: 54.900 @epoch 259)
+Forward: 59.04s
+
+Saving...
+Total: 59.59s
+
+[Epoch 288]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4603]	11.4+0.6s
+[3200/15600]	[L1: 0.4508]	12.6+0.1s
+[4800/15600]	[L1: 0.4515]	10.9+0.1s
+[6400/15600]	[L1: 0.4507]	11.0+0.1s
+[8000/15600]	[L1: 0.4470]	11.2+0.1s
+[9600/15600]	[L1: 0.4480]	12.2+0.1s
+[11200/15600]	[L1: 0.4485]	11.0+0.1s
+[12800/15600]	[L1: 0.4483]	11.0+0.1s
+[14400/15600]	[L1: 0.4470]	12.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.620 (Best: 54.900 @epoch 259)
+Forward: 59.14s
+
+Saving...
+Total: 59.83s
+
+[Epoch 289]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4355]	11.9+0.6s
+[3200/15600]	[L1: 0.4427]	11.1+0.1s
+[4800/15600]	[L1: 0.4476]	11.0+0.1s
+[6400/15600]	[L1: 0.4463]	12.0+0.1s
+[8000/15600]	[L1: 0.4457]	10.9+0.1s
+[9600/15600]	[L1: 0.4462]	10.4+0.1s
+[11200/15600]	[L1: 0.4467]	11.8+0.1s
+[12800/15600]	[L1: 0.4467]	11.0+0.1s
+[14400/15600]	[L1: 0.4463]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.717 (Best: 54.900 @epoch 259)
+Forward: 57.86s
+
+Saving...
+Total: 58.35s
+
+[Epoch 290]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4385]	12.2+0.5s
+[3200/15600]	[L1: 0.4442]	11.2+0.1s
+[4800/15600]	[L1: 0.4490]	10.3+0.1s
+[6400/15600]	[L1: 0.4470]	11.5+0.1s
+[8000/15600]	[L1: 0.4478]	10.6+0.1s
+[9600/15600]	[L1: 0.4457]	10.5+0.1s
+[11200/15600]	[L1: 0.4476]	11.0+0.1s
+[12800/15600]	[L1: 0.4470]	11.8+0.1s
+[14400/15600]	[L1: 0.4471]	11.0+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.599 (Best: 54.900 @epoch 259)
+Forward: 59.77s
+
+Saving...
+Total: 60.34s
+
+[Epoch 291]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4425]	11.4+0.8s
+[3200/15600]	[L1: 0.4448]	12.7+0.1s
+[4800/15600]	[L1: 0.4463]	11.1+0.1s
+[6400/15600]	[L1: 0.4438]	11.0+0.1s
+[8000/15600]	[L1: 0.4444]	12.6+0.1s
+[9600/15600]	[L1: 0.4437]	11.1+0.1s
+[11200/15600]	[L1: 0.4420]	11.1+0.1s
+[12800/15600]	[L1: 0.4414]	11.8+0.1s
+[14400/15600]	[L1: 0.4428]	11.2+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.799 (Best: 54.900 @epoch 259)
+Forward: 57.71s
+
+Saving...
+Total: 58.21s
+
+[Epoch 292]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4266]	11.2+0.6s
+[3200/15600]	[L1: 0.4351]	11.2+0.1s
+[4800/15600]	[L1: 0.4423]	12.6+0.1s
+[6400/15600]	[L1: 0.4416]	11.0+0.1s
+[8000/15600]	[L1: 0.4417]	11.0+0.1s
+[9600/15600]	[L1: 0.4435]	12.6+0.1s
+[11200/15600]	[L1: 0.4454]	11.3+0.1s
+[12800/15600]	[L1: 0.4458]	11.1+0.1s
+[14400/15600]	[L1: 0.4443]	12.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.164 (Best: 54.900 @epoch 259)
+Forward: 57.38s
+
+Saving...
+Total: 57.88s
+
+[Epoch 293]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4425]	13.0+0.6s
+[3200/15600]	[L1: 0.4494]	11.0+0.1s
+[4800/15600]	[L1: 0.4486]	11.0+0.1s
+[6400/15600]	[L1: 0.4464]	12.2+0.1s
+[8000/15600]	[L1: 0.4481]	11.1+0.1s
+[9600/15600]	[L1: 0.4494]	11.0+0.1s
+[11200/15600]	[L1: 0.4490]	12.6+0.1s
+[12800/15600]	[L1: 0.4492]	11.0+0.1s
+[14400/15600]	[L1: 0.4488]	11.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.165 (Best: 54.900 @epoch 259)
+Forward: 56.77s
+
+Saving...
+Total: 57.31s
+
+[Epoch 294]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4569]	10.9+0.6s
+[3200/15600]	[L1: 0.4565]	11.8+0.1s
+[4800/15600]	[L1: 0.4533]	10.6+0.1s
+[6400/15600]	[L1: 0.4515]	10.7+0.1s
+[8000/15600]	[L1: 0.4484]	11.9+0.1s
+[9600/15600]	[L1: 0.4465]	11.0+0.1s
+[11200/15600]	[L1: 0.4466]	11.1+0.1s
+[12800/15600]	[L1: 0.4476]	10.6+0.1s
+[14400/15600]	[L1: 0.4471]	12.3+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.868 (Best: 54.900 @epoch 259)
+Forward: 60.70s
+
+Saving...
+Total: 61.19s
+
+[Epoch 295]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4495]	11.3+0.6s
+[3200/15600]	[L1: 0.4462]	11.0+0.1s
+[4800/15600]	[L1: 0.4424]	12.6+0.1s
+[6400/15600]	[L1: 0.4407]	11.2+0.1s
+[8000/15600]	[L1: 0.4394]	11.0+0.1s
+[9600/15600]	[L1: 0.4399]	12.7+0.1s
+[11200/15600]	[L1: 0.4424]	11.1+0.1s
+[12800/15600]	[L1: 0.4427]	11.0+0.1s
+[14400/15600]	[L1: 0.4439]	12.6+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.529 (Best: 54.900 @epoch 259)
+Forward: 61.16s
+
+Saving...
+Total: 61.95s
+
+[Epoch 296]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4470]	12.1+0.9s
+[3200/15600]	[L1: 0.4541]	11.2+0.1s
+[4800/15600]	[L1: 0.4530]	10.7+0.1s
+[6400/15600]	[L1: 0.4511]	12.5+0.1s
+[8000/15600]	[L1: 0.4507]	11.0+0.1s
+[9600/15600]	[L1: 0.4493]	10.8+0.1s
+[11200/15600]	[L1: 0.4489]	12.5+0.1s
+[12800/15600]	[L1: 0.4497]	10.9+0.1s
+[14400/15600]	[L1: 0.4494]	10.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.515 (Best: 54.900 @epoch 259)
+Forward: 56.81s
+
+Saving...
+Total: 57.32s
+
+[Epoch 297]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4512]	11.3+0.7s
+[3200/15600]	[L1: 0.4489]	12.7+0.1s
+[4800/15600]	[L1: 0.4459]	11.5+0.1s
+[6400/15600]	[L1: 0.4453]	11.4+0.1s
+[8000/15600]	[L1: 0.4451]	12.7+0.1s
+[9600/15600]	[L1: 0.4453]	11.0+0.1s
+[11200/15600]	[L1: 0.4460]	11.0+0.1s
+[12800/15600]	[L1: 0.4459]	12.7+0.1s
+[14400/15600]	[L1: 0.4448]	10.9+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.779 (Best: 54.900 @epoch 259)
+Forward: 59.01s
+
+Saving...
+Total: 59.55s
+
+[Epoch 298]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4380]	11.1+0.6s
+[3200/15600]	[L1: 0.4483]	9.8+0.1s
+[4800/15600]	[L1: 0.4462]	11.1+0.1s
+[6400/15600]	[L1: 0.4494]	10.2+0.1s
+[8000/15600]	[L1: 0.4502]	11.0+0.1s
+[9600/15600]	[L1: 0.4508]	12.5+0.1s
+[11200/15600]	[L1: 0.4487]	11.0+0.1s
+[12800/15600]	[L1: 0.4494]	11.0+0.1s
+[14400/15600]	[L1: 0.4481]	12.7+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.562 (Best: 54.900 @epoch 259)
+Forward: 59.58s
+
+Saving...
+Total: 60.79s
+
+[Epoch 299]	Learning rate: 2.50e-5
+[1600/15600]	[L1: 0.4570]	11.7+0.7s
+[3200/15600]	[L1: 0.4473]	10.0+0.1s
+[4800/15600]	[L1: 0.4414]	10.0+0.1s
+[6400/15600]	[L1: 0.4422]	11.4+0.1s
+[8000/15600]	[L1: 0.4446]	10.0+0.1s
+[9600/15600]	[L1: 0.4437]	10.0+0.1s
+[11200/15600]	[L1: 0.4450]	11.3+0.1s
+[12800/15600]	[L1: 0.4456]	10.0+0.1s
+[14400/15600]	[L1: 0.4467]	10.1+0.1s
+
+Evaluation:
+[DIV2K x1]	PSNR: 54.801 (Best: 54.900 @epoch 259)
+Forward: 61.23s
+
+Saving...
+Total: 61.74s
+
diff --git a/experiment/smgarn_1/loss.pt b/experiment/smgarn_1/loss.pt
new file mode 100644
index 0000000000000000000000000000000000000000..59f6a29a9635b3267d0ac413274009a99633732d
--- /dev/null
+++ b/experiment/smgarn_1/loss.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8fe8e68621fb412dbae5e7473a290f0fd3da4bc4bdc9eca595a8f09a7358ae7
+size 980
diff --git a/experiment/smgarn_1/loss_L1.pdf b/experiment/smgarn_1/loss_L1.pdf
new file mode 100644
index 0000000000000000000000000000000000000000..dc8581f38fc5af4a984b297cc57482266bdfe335
Binary files /dev/null and b/experiment/smgarn_1/loss_L1.pdf differ
diff --git a/experiment/smgarn_1/loss_log.pt b/experiment/smgarn_1/loss_log.pt
new file mode 100644
index 0000000000000000000000000000000000000000..93fb1b87dd97a6f60e6ab7cc2ebf4770d005e284
--- /dev/null
+++ b/experiment/smgarn_1/loss_log.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68b9dc2999046568c7acd59edbaf0827dbae8e2662c92bb5b9a887dfcf4a928b
+size 2337
diff --git a/experiment/smgarn_1/model/model_best.pt b/experiment/smgarn_1/model/model_best.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6905f387992a2fcc3b4e4249394daec558e24460
--- /dev/null
+++ b/experiment/smgarn_1/model/model_best.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6b28cf4ac205f7a50baf6137ad6009a4860d4cabbafb2a58c2b0a04b11f3bb3
+size 8580304
diff --git a/experiment/smgarn_1/model/model_latest.pt b/experiment/smgarn_1/model/model_latest.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5c54c0cd2142721a316a456fb3ea11aabd540333
--- /dev/null
+++ b/experiment/smgarn_1/model/model_latest.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d67cde91db08776f6c611cb50e8a304773224c754dfa830e538e9259e83075
+size 8580604
diff --git a/experiment/smgarn_1/optimizer.pt b/experiment/smgarn_1/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c2bf8ce5adb659475e9227147659551fc60ec245
--- /dev/null
+++ b/experiment/smgarn_1/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c501eddcb51c1446e7c3c17bc255e04b733bf15e9b83aa4bf0d46878a5c794b5
+size 14534714
diff --git a/experiment/smgarn_1/psnr_log.pt b/experiment/smgarn_1/psnr_log.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b0e601ffc67334e732139320d8d2f842fe18bf50
--- /dev/null
+++ b/experiment/smgarn_1/psnr_log.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:183aadf1af5f5d8fd0bfdb4b5aee4fd1ff2b0fc7a2238ae1c17c3fab9c093c92
+size 2337
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0059.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0059.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..3818a67a1e93fa1e3590a1003bb637002b519b22
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0059.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0060.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0060.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..814462903a3f73bb21012ba9cf9f45d1afea75b6
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0060.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0061.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0061.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..229a9111f4cb5fe84ee18a2ed06129c53955c350
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0061.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0062.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0062.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..499e2f744570a1c2dd35fe975210af73648c8387
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0062.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0063.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0063.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..9b448823d55c17dbf80ba1616e83db92d2921f50
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0063.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0064.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0064.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..917d6d9b20a537aaba2ecebe52981e44c25363bd
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0064.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0065.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0065.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..9fc9dbb192a11e9f5c7c8c4e11cc756ab071750b
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0065.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0066.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0066.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..27d774e438d5a937eb33015cc82760646be2dea6
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0066.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0067.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0067.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..a206150cef244b7c275af364c06bdd5122021aae
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0067.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0068.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0068.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..fc21ba26f78646867f14197e2f5675363353efa7
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0068.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0069.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0069.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..8a091904749a17a90be4b1c081a2015fb32d7e44
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0069.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0070.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0070.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..8d2723b1ab570684c70cbeb7199bf297e77cdd4e
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0070.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0071.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0071.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..9dccf06503b06a64a7d4dae5e3856baab559dc5e
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0071.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0072.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0072.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..3b7617f465d640fde5ee14ca20782a63e809a90e
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0072.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0073.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0073.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..37879d127e9cd61bfe791f85a481bdd5100a4648
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0073.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0074.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0074.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..ef39e2b713b72f5b4bd4497bd1d7d71864d1c947
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0074.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0075.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0075.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..d4e753e21c7a8b778f6464e7df6ddbfe3b7dcdb4
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0075.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0076.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0076.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..333b57a87c65fcaf74b2d1ffc9908b3e5fcad9e2
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0076.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0077.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0077.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..a83c0bcdde2d6dee81e424502b91ea02b21d7482
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0077.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0078.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0078.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..74c8acddc69dd665bc908ccc409c8ae51c42845e
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0078.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0079.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0079.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..f7ec29663da7603a87cf4276b7fb60c8ec37af37
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0079.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0080.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0080.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..3146c9bea53e248538aa76d0e3799699f8926447
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0080.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0081.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0081.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..1ba26b4cbbb3c0a6fb225006b2695d15980fbc14
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0081.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0082.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0082.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..01acf75c3890c03ab23c88e6c2edb4061916e353
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0082.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0083.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0083.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..39e0fc7515a6c3795298a67d696feaff9794cd66
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0083.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0084.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0084.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..63c9228a39f00663c4081031ce1dd3fe9cc0fb48
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0084.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0085.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0085.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..1624490a07e87b74fe4dea46aac679e97c4cef9c
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0085.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0086.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0086.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..a03f839b4f776c13dc4583de46062191962b4c10
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0086.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0087.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0087.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..3b21048d7e124520472d928b667ffa5669851eba
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0087.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0088.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0088.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..f620725a9f4cd3a3fcecd07bd85e18e3fe2c75a6
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0088.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0089.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0089.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..0025af75654a9295a0d6e6d85da5a012156fd25d
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0089.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0090.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0090.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..1874bc6204f64f43f6fe6afe949b907de3acfa7f
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0090.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0091.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0091.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..bf56ab92be6e52765ceb160e9b857aaf697e1339
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0091.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0092.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0092.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..1ac08aec0fad972168ece79939830bf01e067932
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0092.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0093.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0093.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..f8dddfee8776f2ddfef2f360aae03f632a85dcfc
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0093.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0094.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0094.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..924d34e27ccb0a63c7b6c1b8ce96d37f2825c11d
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0094.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0095.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0095.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..33b1ae9fb9dc925d44e9ea0494ec525d902b11af
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0095.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0096.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0096.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..e56f1c98dff3d877073d40424f69a004b3f32825
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0096.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0097.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0097.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..eea06527bef401b3a9bf91925604f8b25b03afb8
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0097.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0098.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0098.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..7f7cbb6573232278de5f3a305d8c2827299c40ae
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0098.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0099.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0099.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..08428362894250cf4ce1ddb4960739fe2104e24e
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0099.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0100.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0100.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..71e1b8eb5002ae960a2b7922c13f528d19429343
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0100.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0101.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0101.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..fba2bd4c57de6bd372a663c6f0200f2376c18f06
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0101.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0102.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0102.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..b5506465b00db33a8389d930c81d4bb5158e2bb1
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0102.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0103.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0103.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..a7e085c1ad28f4b6f9da15cc4ac290e0fda2caa6
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0103.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0104.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0104.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..15e6334f4ac19dbe45e2072827b73dd30ae56975
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0104.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0105.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0105.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..8abc423c4eab7e6dd53bc14240f964e1cb013b90
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0105.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0106.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0106.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..02078ff57b0680805bd6e4ada5b3d35dac4bffff
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0106.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0107.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0107.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..390f2269524e380f08ff3188e7c6ad8f85f76c9c
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0107.jpg differ
diff --git a/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0108.jpg b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0108.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..e107aff0f2605ffd26c1efa90e9052c46b37d9ee
Binary files /dev/null and b/experiment/smgarn_1/results-DIV2K/4k_camry_3_frame_0108.jpg differ
diff --git a/experiment/smgarn_1/test_DIV2K.pdf b/experiment/smgarn_1/test_DIV2K.pdf
new file mode 100644
index 0000000000000000000000000000000000000000..8f433158525a624e3a78ad15cf627cddac7073b1
Binary files /dev/null and b/experiment/smgarn_1/test_DIV2K.pdf differ
diff --git a/src/.DS_Store b/src/.DS_Store
new file mode 100644
index 0000000000000000000000000000000000000000..fc5f657a8165f6a57ba491e5006329fae8c892db
Binary files /dev/null and b/src/.DS_Store differ
diff --git a/src/__init__.py b/src/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/src/__pycache__/option.cpython-37.pyc b/src/__pycache__/option.cpython-37.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..1ecbf73262e71f107b4fe38e89c44c3dbafe8455
Binary files /dev/null and b/src/__pycache__/option.cpython-37.pyc differ
diff --git a/src/__pycache__/option.cpython-38.pyc b/src/__pycache__/option.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..c40d5c1f800d7ff7e75d5248a8d8318b41775ca7
Binary files /dev/null and b/src/__pycache__/option.cpython-38.pyc differ
diff --git a/src/__pycache__/template.cpython-37.pyc b/src/__pycache__/template.cpython-37.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..820cac7ac9c6c9677624e600c882dd2828bcb0bf
Binary files /dev/null and b/src/__pycache__/template.cpython-37.pyc differ
diff --git a/src/__pycache__/template.cpython-38.pyc b/src/__pycache__/template.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..59bc7dc61adf971ef317fcafdc5d84a6b5508ba8
Binary files /dev/null and b/src/__pycache__/template.cpython-38.pyc differ
diff --git a/src/__pycache__/trainer.cpython-37.pyc b/src/__pycache__/trainer.cpython-37.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..7924303e92159a6b66df9c8ca3e50bd262cefc52
Binary files /dev/null and b/src/__pycache__/trainer.cpython-37.pyc differ
diff --git a/src/__pycache__/trainer.cpython-38.pyc b/src/__pycache__/trainer.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..d482b9451aac8c884bd0ca466b03d0bd60204035
Binary files /dev/null and b/src/__pycache__/trainer.cpython-38.pyc differ
diff --git a/src/__pycache__/utility.cpython-37.pyc b/src/__pycache__/utility.cpython-37.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..070d6d4d732998b0fe119d0cbca3e23ae8b41f6d
Binary files /dev/null and b/src/__pycache__/utility.cpython-37.pyc differ
diff --git a/src/__pycache__/utility.cpython-38.pyc b/src/__pycache__/utility.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..b9bb7e0971aa3775c4be937b928dfdfb14892359
Binary files /dev/null and b/src/__pycache__/utility.cpython-38.pyc differ
diff --git a/src/data/__init__.py b/src/data/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..6dc2cdb4a1652976634a657c9d4106cb58a233be
--- /dev/null
+++ b/src/data/__init__.py
@@ -0,0 +1,52 @@
+from importlib import import_module
+#from dataloader import MSDataLoader
+from torch.utils.data import dataloader
+from torch.utils.data import ConcatDataset
+
+# This is a simple wrapper function for ConcatDataset
+class MyConcatDataset(ConcatDataset):
+    def __init__(self, datasets):
+        super(MyConcatDataset, self).__init__(datasets)
+        self.train = datasets[0].train
+
+    def set_scale(self, idx_scale):
+        for d in self.datasets:
+            if hasattr(d, 'set_scale'): d.set_scale(idx_scale)
+
+class Data:
+    def __init__(self, args):
+        self.loader_train = None
+        if not args.test_only:
+            datasets = []
+            for d in args.data_train:
+                module_name = d if d.find('DIV2K-Q') < 0 else 'DIV2KJPEG'
+                m = import_module('data.' + module_name.lower())
+                datasets.append(getattr(m, module_name)(args, name=d))
+
+            self.loader_train = dataloader.DataLoader(
+                MyConcatDataset(datasets),
+                batch_size=args.batch_size,
+                shuffle=True,
+                pin_memory=not args.cpu,
+                num_workers=args.n_threads,
+            )
+
+        self.loader_test = []
+        for d in args.data_test:
+            if d in ['Set5', 'Set14', 'B100', 'Urban100']:
+                m = import_module('data.benchmark')
+                testset = getattr(m, 'Benchmark')(args, train=False, name=d)
+            else:
+                module_name = d if d.find('DIV2K-Q') < 0 else 'DIV2KJPEG'
+                m = import_module('data.' + module_name.lower())
+                testset = getattr(m, module_name)(args, train=False, name=d)
+
+            self.loader_test.append(
+                dataloader.DataLoader(
+                    testset,
+                    batch_size=1,
+                    shuffle=False,
+                    pin_memory=not args.cpu,
+                    num_workers=args.n_threads,
+                )
+            )
diff --git a/src/data/__pycache__/__init__.cpython-37.pyc b/src/data/__pycache__/__init__.cpython-37.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..5c1af0b2a2572fc4452c6ea38e38425a4a0f8e55
Binary files /dev/null and b/src/data/__pycache__/__init__.cpython-37.pyc differ
diff --git a/src/data/__pycache__/__init__.cpython-38.pyc b/src/data/__pycache__/__init__.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..ff051c0f78a486e6f7eccd94f66440ac398977cb
Binary files /dev/null and b/src/data/__pycache__/__init__.cpython-38.pyc differ
diff --git a/src/data/__pycache__/common.cpython-37.pyc b/src/data/__pycache__/common.cpython-37.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..d0ca63c17a04e2ebe4fe98f2c28fa4f1b27380d9
Binary files /dev/null and b/src/data/__pycache__/common.cpython-37.pyc differ
diff --git a/src/data/__pycache__/common.cpython-38.pyc b/src/data/__pycache__/common.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..8da3970086736e40d28a9ac06d9957de0886726e
Binary files /dev/null and b/src/data/__pycache__/common.cpython-38.pyc differ
diff --git a/src/data/__pycache__/div2k.cpython-37.pyc b/src/data/__pycache__/div2k.cpython-37.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..7a391a81d5244b31eb1bd64531d34c101c224cb4
Binary files /dev/null and b/src/data/__pycache__/div2k.cpython-37.pyc differ
diff --git a/src/data/__pycache__/div2k.cpython-38.pyc b/src/data/__pycache__/div2k.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..99bd060fa0ab532bc710565f76b59b9bdd0ec9ad
Binary files /dev/null and b/src/data/__pycache__/div2k.cpython-38.pyc differ
diff --git a/src/data/__pycache__/srdata.cpython-37.pyc b/src/data/__pycache__/srdata.cpython-37.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..bdbadf39b059165ef155a35bd03fb172f9ff24bb
Binary files /dev/null and b/src/data/__pycache__/srdata.cpython-37.pyc differ
diff --git a/src/data/__pycache__/srdata.cpython-38.pyc b/src/data/__pycache__/srdata.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..7eebb2a2ac82c7b51d5d6ae6bda6e112e295a5fe
Binary files /dev/null and b/src/data/__pycache__/srdata.cpython-38.pyc differ
diff --git a/src/data/benchmark.py b/src/data/benchmark.py
new file mode 100644
index 0000000000000000000000000000000000000000..9d4fb0ec13c6043bc997f6ae778f78301d94bf30
--- /dev/null
+++ b/src/data/benchmark.py
@@ -0,0 +1,26 @@
+import os
+
+from data import common
+from data import srdata
+
+import numpy as np
+
+import torch
+import torch.utils.data as data
+
+class Benchmark(srdata.SRData):
+    def __init__(self, args, name='', train=True, benchmark=True):
+        super(Benchmark, self).__init__(
+            args, name=name, train=train, benchmark=True
+        )
+
+    def _set_filesystem(self, dir_data):
+        self.apath = os.path.join(dir_data, 'benchmark', self.name)
+        self.dir_hr = os.path.join(self.apath, 'HR')
+        if self.input_large:
+            self.dir_lr = os.path.join(self.apath, 'LR_bicubicL')
+        else:
+            self.dir_lr = os.path.join(self.apath, 'LR_bicubic')
+        # self.ext = ('', '.png')
+        self.ext = ('', '.tif')
+
diff --git a/src/data/common.py b/src/data/common.py
new file mode 100644
index 0000000000000000000000000000000000000000..25259c1ffb7a97e86403092a0b035f69de0de901
--- /dev/null
+++ b/src/data/common.py
@@ -0,0 +1,88 @@
+import random
+
+import numpy as np
+import skimage.color as sc
+
+import torch
+
+def get_patch(*args, patch_size=96, scale=2, multi=False, input_large=False):
+    ih, iw = args[0].shape[:2]
+
+    if not input_large:
+        p = scale if multi else 1
+        tp = p * patch_size
+        ip = tp // scale
+    else:
+        tp = patch_size
+        ip = patch_size
+
+    ix = random.randrange(0, iw - ip + 1)
+    iy = random.randrange(0, ih - ip + 1)
+
+    if not input_large:
+        tx, ty = scale * ix, scale * iy
+    else:
+        tx, ty = ix, iy
+
+    ret = [
+        args[0][iy:iy + ip, ix:ix + ip, :],
+        # args[0][iy:iy + ip, ix:ix + ip],
+        *[a[ty:ty + tp, tx:tx + tp, :] for a in args[1:]]
+        # *[a[ty:ty + tp, tx:tx + tp] for a in args[1:]]
+    ]
+
+    return ret
+
+def set_channel(*args, n_channels=3):
+    def _set_channel(img):
+        if img.ndim == 2:
+            img = np.expand_dims(img, axis=2)
+
+        c = img.shape[2]
+        if n_channels == 1 and c == 3:
+            img = np.expand_dims(sc.rgb2ycbcr(img)[:, :, 0], 2)
+        elif n_channels == 3 and c == 1:
+            img = np.concatenate([img] * n_channels, 2)
+
+        return img
+
+    return [_set_channel(a) for a in args]
+
+def np2Tensor(*args, rgb_range=255):
+    def _np2Tensor(img):
+        np_transpose = np.ascontiguousarray(img.transpose((2, 0, 1)))
+        tensor = torch.from_numpy(np_transpose).float()
+        tensor.mul_(rgb_range / 255)
+
+        return tensor
+
+    return [_np2Tensor(a) for a in args]
+
+def augment(*args, hflip=True, rot=True):
+    hflip = hflip and random.random() < 0.5
+    vflip = rot and random.random() < 0.5
+    rot90 = rot and random.random() < 0.5
+
+    def _augment(img):
+        if hflip: img = img[:, ::-1, :]
+        if vflip: img = img[::-1, :, :]
+        if rot90: img = img.transpose(1, 0, 2)
+
+        return img
+
+    return [_augment(a) for a in args]
+# def augment(*args, hflip=True, rot=True):
+#     hflip = hflip and random.random() < 0.5
+#     vflip = rot and random.random() < 0.5
+#
+#     rot90 = rot and random.random() < 0.5
+#
+#     def _augment(img):
+#         if hflip: img = img[:, ::-1]
+#         if vflip: img = img[::-1, :]
+#         if rot90: img = img.transpose(1, 0)
+#
+#         return img
+#
+#     return [_augment(a) for a in args]
+
diff --git a/src/data/demo.py b/src/data/demo.py
new file mode 100644
index 0000000000000000000000000000000000000000..ab3bbbd4a95d627b57abd9133675180bf666e218
--- /dev/null
+++ b/src/data/demo.py
@@ -0,0 +1,40 @@
+import os
+
+from data import common
+
+import numpy as np
+import imageio
+
+import torch
+import torch.utils.data as data
+
+class Demo(data.Dataset):
+    def __init__(self, args, name='Demo', train=False, benchmark=False):
+        self.args = args
+        self.name = name
+        self.scale = args.scale
+        self.idx_scale = 0
+        self.train = False
+        self.benchmark = benchmark
+
+        self.filelist = []
+        for f in os.listdir(args.dir_demo):
+            # if f.find('.png') >= 0 or f.find('.jp') >= 0:
+            if f.find('.tif') >= 0 or f.find('.jp') >= 0:
+                self.filelist.append(os.path.join(args.dir_demo, f))
+        self.filelist.sort()
+
+    def __getitem__(self, idx):
+        filename = os.path.splitext(os.path.basename(self.filelist[idx]))[0]
+        lr = imageio.imread(self.filelist[idx])
+        lr, = common.set_channel(lr, n_channels=self.args.n_colors)
+        lr_t, = common.np2Tensor(lr, rgb_range=self.args.rgb_range)
+
+        return lr_t, -1, filename
+
+    def __len__(self):
+        return len(self.filelist)
+
+    def set_scale(self, idx_scale):
+        self.idx_scale = idx_scale
+
diff --git a/src/data/div2k.py b/src/data/div2k.py
new file mode 100644
index 0000000000000000000000000000000000000000..9d29e0c8efca2def7474ebed047dfe7026c37811
--- /dev/null
+++ b/src/data/div2k.py
@@ -0,0 +1,34 @@
+import os
+from data import srdata
+
+class DIV2K(srdata.SRData):
+    def __init__(self, args, name='DIV2K', train=True, benchmark=False):
+        data_range = [r.split('-') for r in args.data_range.split('/')]
+        if train:
+            data_range = data_range[0]
+        else:
+            if args.test_only and len(data_range) == 1:
+                data_range = data_range[0]
+            else:
+                data_range = data_range[1]
+
+        self.begin, self.end = list(map(lambda x: int(x), data_range))
+        super(DIV2K, self).__init__(
+            args, name=name, train=train, benchmark=benchmark
+        )
+
+    def _scan(self):
+        names_hr, names_edge, names_lr = super(DIV2K, self)._scan()
+        names_hr = names_hr[self.begin - 1:self.end]
+        names_edge = names_edge[self.begin - 1:self.end]
+        names_lr = [n[self.begin - 1:self.end] for n in names_lr]
+
+        return names_hr, names_edge, names_lr
+
+    def _set_filesystem(self, dir_data):
+        super(DIV2K, self)._set_filesystem(dir_data)
+        self.dir_hr = os.path.join(self.apath, 'DIV2K_train_HR')
+        self.dir_edge = os.path.join(self.apath, 'DIV2K_train_EDGE_disturbed') # 
+        self.dir_lr = os.path.join(self.apath, 'DIV2K_train_LR_bicubic')
+        if self.input_large: self.dir_lr += 'L'
+
diff --git a/src/data/div2kjpeg.py b/src/data/div2kjpeg.py
new file mode 100644
index 0000000000000000000000000000000000000000..9a4359e54cea2678c4ae164744a84b236bdc35c6
--- /dev/null
+++ b/src/data/div2kjpeg.py
@@ -0,0 +1,21 @@
+import os
+from data import srdata
+from data import div2k
+
+class DIV2KJPEG(div2k.DIV2K):
+    def __init__(self, args, name='', train=True, benchmark=False):
+        self.q_factor = int(name.replace('DIV2K-Q', ''))
+        super(DIV2KJPEG, self).__init__(
+            args, name=name, train=train, benchmark=benchmark
+        )
+
+    def _set_filesystem(self, dir_data):
+        self.apath = os.path.join(dir_data, 'DIV2K')
+        self.dir_hr = os.path.join(self.apath, 'DIV2K_train_HR')
+        self.dir_lr = os.path.join(
+            self.apath, 'DIV2K_Q{}'.format(self.q_factor)
+        )
+        if self.input_large: self.dir_lr += 'L'
+        # self.ext = ('.png', '.jpg')
+        self.ext = ('.tif', '.jpg')
+
diff --git a/src/data/sr291.py b/src/data/sr291.py
new file mode 100644
index 0000000000000000000000000000000000000000..5e843178612d64ae75975853085eb01191bc0c21
--- /dev/null
+++ b/src/data/sr291.py
@@ -0,0 +1,6 @@
+from data import srdata
+
+class SR291(srdata.SRData):
+    def __init__(self, args, name='SR291', train=True, benchmark=False):
+        super(SR291, self).__init__(args, name=name)
+
diff --git a/src/data/srdata.py b/src/data/srdata.py
new file mode 100644
index 0000000000000000000000000000000000000000..3658bbf35604971e8bf72316ffab28dadd3a7cb3
--- /dev/null
+++ b/src/data/srdata.py
@@ -0,0 +1,180 @@
+import os
+import glob
+import random
+import pickle
+
+from data import common
+
+import numpy as np
+import imageio
+import torch
+import torch.utils.data as data
+
+class SRData(data.Dataset):
+    def __init__(self, args, name='', train=True, benchmark=False):
+        self.args = args
+        self.name = name
+        self.train = train
+        self.split = 'train' if train else 'test'
+        self.do_eval = True
+        self.benchmark = benchmark
+        self.input_large = (args.model == 'VDSR')
+        self.scale = args.scale
+        self.idx_scale = 0
+        
+        self._set_filesystem(args.dir_data)
+        if args.ext.find('img') < 0:
+            path_bin = os.path.join(self.apath, 'bin')
+            os.makedirs(path_bin, exist_ok=True)
+
+        list_hr, list_edge, list_lr = self._scan()
+        if args.ext.find('img') >= 0 or benchmark:
+            self.images_hr, self.images_edge, self.images_lr = list_hr, list_edge, list_lr
+        elif args.ext.find('sep') >= 0:
+            os.makedirs(
+                self.dir_hr.replace(self.apath, path_bin),
+                exist_ok=True
+            )
+            os.makedirs(
+                self.dir_edge.replace(self.apath, path_bin),
+                exist_ok=True
+            )
+            for s in self.scale:
+                os.makedirs(
+                    os.path.join(
+                        self.dir_lr.replace(self.apath, path_bin),
+                        'X{}'.format(s)
+                    ),
+                    exist_ok=True
+                )
+            
+            self.images_hr, self.images_edge, self.images_lr = [], [], [[] for _ in self.scale]
+            for h in list_hr:
+                b = h.replace(self.apath, path_bin)
+                b = b.replace(self.ext[0], '.pt')
+                self.images_hr.append(b)
+                self._check_and_load(args.ext, h, b, verbose=True)
+
+            for e in list_edge:
+                g = e.replace(self.apath, path_bin)
+                g = g.replace(self.ext[0], '.pt')
+                self.images_edge.append(g)
+                self._check_and_load(
+                    args.ext, e, g, verbose=True)
+
+            for i, ll in enumerate(list_lr):
+                for l in ll:
+                    b = l.replace(self.apath, path_bin)
+                    b = b.replace(self.ext[1], '.pt')
+                    self.images_lr[i].append(b)
+                    self._check_and_load(args.ext, l, b, verbose=True) 
+        if train:
+            n_patches = args.batch_size * args.test_every
+            n_images = len(args.data_train) * len(self.images_hr)
+            if n_images == 0:
+                self.repeat = 0
+            else:
+                self.repeat = max(n_patches // n_images, 1)
+
+    # Below functions as used to prepare images
+    def _scan(self):
+        names_hr = sorted(
+            glob.glob(os.path.join(self.dir_hr, '*' + self.ext[0]))
+        )
+        names_edge = sorted(
+            glob.glob(os.path.join(self.dir_edge, '*' + self.ext[0]))
+        )
+        names_lr = [[] for _ in self.scale]
+        for f in names_hr:
+            filename, _ = os.path.splitext(os.path.basename(f))
+            for si, s in enumerate(self.scale):
+                names_lr[si].append(os.path.join(
+                    self.dir_lr, 'X{}/{}{}'.format(
+                        s, filename, self.ext[1]
+                    )
+                ))
+
+        return names_hr, names_edge, names_lr
+
+    def _set_filesystem(self, dir_data):
+        self.apath = os.path.join(dir_data, self.name)
+        self.dir_hr = os.path.join(self.apath, 'HR')
+        self.dir_edge = os.path.join(self.apath, 'EDGE')
+        self.dir_lr = os.path.join(self.apath, 'LR_bicubic')
+        if self.input_large: self.dir_lr += 'L'
+        self.ext = ('.jpg', '.jpg')
+        # self.ext = ('.tif', '.tif')
+
+    def _check_and_load(self, ext, img, f, verbose=True):
+        if not os.path.isfile(f) or ext.find('reset') >= 0:
+            if verbose:
+                print('Making a binary: {}'.format(f))
+            with open(f, 'wb') as _f:
+                pickle.dump(imageio.imread(img), _f)
+
+    def __getitem__(self, idx):
+        lr, edge, hr, filename = self._load_file(idx)
+        lr, edge, hr = self.get_patch(lr, edge, hr)
+        lr, edge, hr = common.set_channel(lr, edge, hr, n_channels=self.args.n_colors)
+        lr_tensor, edge_tensor, hr_tensor = common.np2Tensor(lr, edge, hr, rgb_range=self.args.rgb_range)
+
+        return lr_tensor, edge_tensor, hr_tensor, filename
+
+    def __len__(self):
+        if self.train:
+            return len(self.images_hr) * self.repeat
+        else:
+            return len(self.images_hr)
+
+    def _get_index(self, idx):
+        if self.train:
+            return idx % len(self.images_hr)
+        else:
+            return idx
+
+    def _load_file(self, idx):
+        idx = self._get_index(idx)
+        f_hr = self.images_hr[idx]
+        f_edge = self.images_edge[idx]
+        f_lr = self.images_lr[self.idx_scale][idx]
+
+        filename, _ = os.path.splitext(os.path.basename(f_hr))
+        if self.args.ext == 'img' or self.benchmark:
+            hr = imageio.imread(f_hr)
+            edge = imageio.imread(f_edge)
+            lr = imageio.imread(f_lr)
+        elif self.args.ext.find('sep') >= 0:
+            with open(f_hr, 'rb') as _f:
+                hr = pickle.load(_f)
+            with open(f_edge, 'rb') as _f:
+                edge = pickle.load(_f)
+            with open(f_lr, 'rb') as _f:
+                lr = pickle.load(_f)
+
+        return lr, edge, hr, filename
+
+    def get_patch(self, lr, edge, hr):
+        scale = self.scale[self.idx_scale]
+        if self.train:
+            lr, edge, hr = common.get_patch(
+                lr, edge, hr,
+                patch_size=self.args.patch_size,
+                scale=scale,
+                multi=(len(self.scale) > 1),
+                input_large=self.input_large
+            )
+            if not self.args.no_augment:
+                lr, edge, hr = common.augment(lr, edge, hr)
+        else:
+            ih, iw = lr.shape[:2]
+            hr = hr[0:ih * scale, 0:iw * scale]
+            edge = edge[0:ih * scale, 0:iw * scale]
+
+        return lr, edge, hr
+
+    def set_scale(self, idx_scale):
+        if not self.input_large:
+            self.idx_scale = idx_scale
+        else:
+            self.idx_scale = random.randint(0, len(self.scale) - 1)
+
diff --git a/src/data/video.py b/src/data/video.py
new file mode 100644
index 0000000000000000000000000000000000000000..19588a78ae7c8e69bc283eea8cc9b5e06ff89df0
--- /dev/null
+++ b/src/data/video.py
@@ -0,0 +1,44 @@
+import os
+
+from data import common
+
+import cv2
+import numpy as np
+import imageio
+
+import torch
+import torch.utils.data as data
+
+class Video(data.Dataset):
+    def __init__(self, args, name='Video', train=False, benchmark=False):
+        self.args = args
+        self.name = name
+        self.scale = args.scale
+        self.idx_scale = 0
+        self.train = False
+        self.do_eval = False
+        self.benchmark = benchmark
+
+        self.filename, _ = os.path.splitext(os.path.basename(args.dir_demo))
+        self.vidcap = cv2.VideoCapture(args.dir_demo)
+        self.n_frames = 0
+        self.total_frames = int(self.vidcap.get(cv2.CAP_PROP_FRAME_COUNT))
+
+    def __getitem__(self, idx):
+        success, lr = self.vidcap.read()
+        if success:
+            self.n_frames += 1
+            lr, = common.set_channel(lr, n_channels=self.args.n_colors)
+            lr_t, = common.np2Tensor(lr, rgb_range=self.args.rgb_range)
+
+            return lr_t, -1, '{}_{:0>5}'.format(self.filename, self.n_frames)
+        else:
+            vidcap.release()
+            return None
+
+    def __len__(self):
+        return self.total_frames
+
+    def set_scale(self, idx_scale):
+        self.idx_scale = idx_scale
+
diff --git a/src/dataloader.py b/src/dataloader.py
new file mode 100644
index 0000000000000000000000000000000000000000..63257a3008530f66fa56a19383e9fe7265fd0a9d
--- /dev/null
+++ b/src/dataloader.py
@@ -0,0 +1,158 @@
+import threading
+import random
+
+import torch
+import torch.multiprocessing as multiprocessing
+from torch.utils.data import DataLoader
+from torch.utils.data import SequentialSampler
+from torch.utils.data import RandomSampler
+from torch.utils.data import BatchSampler
+from torch.utils.data import _utils
+from torch.utils.data.dataloader import _DataLoaderIter
+
+from torch.utils.data._utils import collate
+from torch.utils.data._utils import signal_handling
+from torch.utils.data._utils import MP_STATUS_CHECK_INTERVAL
+from torch.utils.data._utils import ExceptionWrapper
+from torch.utils.data._utils import IS_WINDOWS
+from torch.utils.data._utils.worker import ManagerWatchdog
+
+from torch._six import queue
+
+def _ms_loop(dataset, index_queue, data_queue, done_event, collate_fn, scale, seed, init_fn, worker_id):
+    try:
+        collate._use_shared_memory = True
+        signal_handling._set_worker_signal_handlers()
+
+        torch.set_num_threads(1)
+        random.seed(seed)
+        torch.manual_seed(seed)
+
+        data_queue.cancel_join_thread()
+
+        if init_fn is not None:
+            init_fn(worker_id)
+
+        watchdog = ManagerWatchdog()
+
+        while watchdog.is_alive():
+            try:
+                r = index_queue.get(timeout=MP_STATUS_CHECK_INTERVAL)
+            except queue.Empty:
+                continue
+
+            if r is None:
+                assert done_event.is_set()
+                return
+            elif done_event.is_set():
+                continue
+
+            idx, batch_indices = r
+            try:
+                idx_scale = 0
+                if len(scale) > 1 and dataset.train:
+                    idx_scale = random.randrange(0, len(scale))
+                    dataset.set_scale(idx_scale)
+
+                samples = collate_fn([dataset[i] for i in batch_indices])
+                samples.append(idx_scale)
+            except Exception:
+                data_queue.put((idx, ExceptionWrapper(sys.exc_info())))
+            else:
+                data_queue.put((idx, samples))
+                del samples
+
+    except KeyboardInterrupt:
+        pass
+
+class _MSDataLoaderIter(_DataLoaderIter):
+
+    def __init__(self, loader):
+        self.dataset = loader.dataset
+        self.scale = loader.scale
+        self.collate_fn = loader.collate_fn
+        self.batch_sampler = loader.batch_sampler
+        self.num_workers = loader.num_workers
+        self.pin_memory = loader.pin_memory and torch.cuda.is_available()
+        self.timeout = loader.timeout
+
+        self.sample_iter = iter(self.batch_sampler)
+
+        base_seed = torch.LongTensor(1).random_().item()
+
+        if self.num_workers > 0:
+            self.worker_init_fn = loader.worker_init_fn
+            self.worker_queue_idx = 0
+            self.worker_result_queue = multiprocessing.Queue()
+            self.batches_outstanding = 0
+            self.worker_pids_set = False
+            self.shutdown = False
+            self.send_idx = 0
+            self.rcvd_idx = 0
+            self.reorder_dict = {}
+            self.done_event = multiprocessing.Event()
+
+            base_seed = torch.LongTensor(1).random_()[0]
+
+            self.index_queues = []
+            self.workers = []
+            for i in range(self.num_workers):
+                index_queue = multiprocessing.Queue()
+                index_queue.cancel_join_thread()
+                w = multiprocessing.Process(
+                    target=_ms_loop,
+                    args=(
+                        self.dataset,
+                        index_queue,
+                        self.worker_result_queue,
+                        self.done_event,
+                        self.collate_fn,
+                        self.scale,
+                        base_seed + i,
+                        self.worker_init_fn,
+                        i
+                    )
+                )
+                w.daemon = True
+                w.start()
+                self.index_queues.append(index_queue)
+                self.workers.append(w)
+
+            if self.pin_memory:
+                self.data_queue = queue.Queue()
+                pin_memory_thread = threading.Thread(
+                    target=_utils.pin_memory._pin_memory_loop,
+                    args=(
+                        self.worker_result_queue,
+                        self.data_queue,
+                        torch.cuda.current_device(),
+                        self.done_event
+                    )
+                )
+                pin_memory_thread.daemon = True
+                pin_memory_thread.start()
+                self.pin_memory_thread = pin_memory_thread
+            else:
+                self.data_queue = self.worker_result_queue
+
+            _utils.signal_handling._set_worker_pids(
+                id(self), tuple(w.pid for w in self.workers)
+            )
+            _utils.signal_handling._set_SIGCHLD_handler()
+            self.worker_pids_set = True
+
+            for _ in range(2 * self.num_workers):
+                self._put_indices()
+
+
+class MSDataLoader(DataLoader):
+
+    def __init__(self, cfg, *args, **kwargs):
+        super(MSDataLoader, self).__init__(
+            *args, **kwargs, num_workers=cfg.n_threads
+        )
+        self.scale = cfg.scale
+
+    def __iter__(self):
+        return _MSDataLoaderIter(self)
+
diff --git a/src/demo.sh b/src/demo.sh
new file mode 100644
index 0000000000000000000000000000000000000000..918c792308c6e86eeb839c96dd088a89c5d64c40
--- /dev/null
+++ b/src/demo.sh
@@ -0,0 +1,5 @@
+# EDSR baseline model (x2) + JPEG augmentation
+
+python main.py --scale 1 --patch_size 128 --save test --reset --save_results
+python main.py --scale 1 --patch_size 64 --save smgarn --ext sep_reset --save_results
+
diff --git a/src/loss/L0Loss.py b/src/loss/L0Loss.py
new file mode 100644
index 0000000000000000000000000000000000000000..4653dd8c71e5d4da367ae0ea580b1f841bbb6359
--- /dev/null
+++ b/src/loss/L0Loss.py
@@ -0,0 +1,16 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class L1Loss(nn.modules.loss._Loss):
+    def __init__(self):
+        super(L1Loss, self).__init__()
+
+    def forward(self, sr, hr):
+        sr_ = (sr != 0).sum().float()
+        hr_ = (hr != 0).sum().float()
+
+        l = F.l1_loss(sr_, hr_)
+
+        return l
\ No newline at end of file
diff --git a/src/loss/__init__.py b/src/loss/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..d9c5fcb382ab27f567a79e208c88b0e30636fbe4
--- /dev/null
+++ b/src/loss/__init__.py
@@ -0,0 +1,144 @@
+import os
+from importlib import import_module
+from loss import L0Loss
+
+import matplotlib
+matplotlib.use('Agg')
+import matplotlib.pyplot as plt
+
+import numpy as np
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+class Loss(nn.modules.loss._Loss):
+    def __init__(self, args, ckp):
+        super(Loss, self).__init__()
+        print('Preparing loss function:')
+
+        self.n_GPUs = args.n_GPUs
+        self.loss = []
+        self.loss_module = nn.ModuleList()
+        for loss in args.loss.split('+'):
+            weight, loss_type = loss.split('*')
+            if loss_type == 'MSE':
+                loss_function = nn.MSELoss()
+            elif loss_type == 'L1':
+                loss_function = nn.L1Loss()
+            elif loss_type.find('VGG') >= 0:
+                module = import_module('loss.vgg')
+                loss_function = getattr(module, 'VGG')(
+                    loss_type[3:],
+                    rgb_range=args.rgb_range
+                )
+            elif loss_type.find('GAN') >= 0:
+                module = import_module('loss.adversarial')
+                loss_function = getattr(module, 'Adversarial')(
+                    args,
+                    loss_type
+                )
+
+            self.loss.append({
+                'type': loss_type,
+                'weight': float(weight),
+                'function': loss_function}
+            )
+            if loss_type.find('GAN') >= 0:
+                self.loss.append({'type': 'DIS', 'weight': 1, 'function': None})
+
+        if len(self.loss) > 1:
+            self.loss.append({'type': 'Total', 'weight': 0, 'function': None})
+
+        for l in self.loss:
+            if l['function'] is not None:
+                print('{:.3f} * {}'.format(l['weight'], l['type']))
+                self.loss_module.append(l['function'])
+
+        self.log = torch.Tensor()
+
+        device = torch.device('cpu' if args.cpu else 'cuda')
+        self.loss_module.to(device)
+        if args.precision == 'half': self.loss_module.half()
+        if not args.cpu and args.n_GPUs > 1:
+            self.loss_module = nn.DataParallel(
+                self.loss_module, range(args.n_GPUs)
+            )
+
+        if args.load != '': self.load(ckp.dir, cpu=args.cpu)
+
+    def forward(self, sr, hr):
+        losses = []
+        for i, l in enumerate(self.loss):
+            if l['function'] is not None:
+                loss = l['function'](sr, hr)
+                effective_loss = l['weight'] * loss
+                losses.append(effective_loss)
+                self.log[-1, i] += effective_loss.item()
+            elif l['type'] == 'DIS':
+                self.log[-1, i] += self.loss[i - 1]['function'].loss
+
+        loss_sum = sum(losses)
+        if len(self.loss) > 1:
+            self.log[-1, -1] += loss_sum.item()
+
+        return loss_sum
+
+    def step(self):
+        for l in self.get_loss_module():
+            if hasattr(l, 'scheduler'):
+                l.scheduler.step()
+
+    def start_log(self):
+        self.log = torch.cat((self.log, torch.zeros(1, len(self.loss))))
+
+    def end_log(self, n_batches):
+        self.log[-1].div_(n_batches)
+
+    def display_loss(self, batch):
+        n_samples = batch + 1
+        log = []
+        for l, c in zip(self.loss, self.log[-1]):
+            log.append('[{}: {:.4f}]'.format(l['type'], c / n_samples))
+
+        return ''.join(log)
+
+    def plot_loss(self, apath, epoch):
+        axis = np.linspace(1, epoch, epoch)
+        for i, l in enumerate(self.loss):
+            label = '{} Loss'.format(l['type'])
+            fig = plt.figure()
+            plt.title(label)
+            plt.plot(axis, self.log[:, i].numpy(), label=label)
+            plt.legend()
+            plt.xlabel('Epochs')
+            plt.ylabel('Loss')
+            plt.grid(True)
+            plt.savefig(os.path.join(apath, 'loss_{}.pdf'.format(l['type'])))
+            plt.close(fig)
+
+    def get_loss_module(self):
+        if self.n_GPUs == 1:
+            return self.loss_module
+        else:
+            return self.loss_module.module
+
+    def save(self, apath):
+        torch.save(self.state_dict(), os.path.join(apath, 'loss.pt'))
+        torch.save(self.log, os.path.join(apath, 'loss_log.pt'))
+
+    def load(self, apath, cpu=False):
+        if cpu:
+            kwargs = {'map_location': lambda storage, loc: storage}
+        else:
+            kwargs = {}
+
+        self.load_state_dict(torch.load(
+            os.path.join(apath, 'loss.pt'),
+            **kwargs
+        ))
+        self.log = torch.load(os.path.join(apath, 'loss_log.pt'))
+        for l in self.get_loss_module():
+            if hasattr(l, 'scheduler'):
+                for _ in range(len(self.log)): l.scheduler.step()
+
diff --git a/src/loss/__pycache__/L0Loss.cpython-37.pyc b/src/loss/__pycache__/L0Loss.cpython-37.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..5709cfa51226d7fc95da40a12c6de03b3201f047
Binary files /dev/null and b/src/loss/__pycache__/L0Loss.cpython-37.pyc differ
diff --git a/src/loss/__pycache__/L0Loss.cpython-38.pyc b/src/loss/__pycache__/L0Loss.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..b434d0210dab7e86a262dbe38114d5f5b2ce2559
Binary files /dev/null and b/src/loss/__pycache__/L0Loss.cpython-38.pyc differ
diff --git a/src/loss/__pycache__/__init__.cpython-37.pyc b/src/loss/__pycache__/__init__.cpython-37.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..d6823f07173328be9af75c03a7f07215cd31e92a
Binary files /dev/null and b/src/loss/__pycache__/__init__.cpython-37.pyc differ
diff --git a/src/loss/__pycache__/__init__.cpython-38.pyc b/src/loss/__pycache__/__init__.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..cfe4d34aba22d9cd161cfcabf6898d6249aadb82
Binary files /dev/null and b/src/loss/__pycache__/__init__.cpython-38.pyc differ
diff --git a/src/loss/adversarial.py b/src/loss/adversarial.py
new file mode 100644
index 0000000000000000000000000000000000000000..7517335e66c1b1a84065722c44ddb743abdf3055
--- /dev/null
+++ b/src/loss/adversarial.py
@@ -0,0 +1,112 @@
+import utility
+from types import SimpleNamespace
+
+from model import common
+from loss import discriminator
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+import torch.optim as optim
+
+class Adversarial(nn.Module):
+    def __init__(self, args, gan_type):
+        super(Adversarial, self).__init__()
+        self.gan_type = gan_type
+        self.gan_k = args.gan_k
+        self.dis = discriminator.Discriminator(args)
+        if gan_type == 'WGAN_GP':
+            # see https://arxiv.org/pdf/1704.00028.pdf pp.4
+            optim_dict = {
+                'optimizer': 'ADAM',
+                'betas': (0, 0.9),
+                'epsilon': 1e-8,
+                'lr': 1e-5,
+                'weight_decay': args.weight_decay,
+                'decay': args.decay,
+                'gamma': args.gamma
+            }
+            optim_args = SimpleNamespace(**optim_dict)
+        else:
+            optim_args = args
+
+        self.optimizer = utility.make_optimizer(optim_args, self.dis)
+
+    def forward(self, fake, real):
+        # updating discriminator...
+        self.loss = 0
+        fake_detach = fake.detach()     # do not backpropagate through G
+        for _ in range(self.gan_k):
+            self.optimizer.zero_grad()
+            # d: B x 1 tensor
+            d_fake = self.dis(fake_detach)
+            d_real = self.dis(real)
+            retain_graph = False
+            if self.gan_type == 'GAN':
+                loss_d = self.bce(d_real, d_fake)
+            elif self.gan_type.find('WGAN') >= 0:
+                loss_d = (d_fake - d_real).mean()
+                if self.gan_type.find('GP') >= 0:
+                    epsilon = torch.rand_like(fake).view(-1, 1, 1, 1)
+                    hat = fake_detach.mul(1 - epsilon) + real.mul(epsilon)
+                    hat.requires_grad = True
+                    d_hat = self.dis(hat)
+                    gradients = torch.autograd.grad(
+                        outputs=d_hat.sum(), inputs=hat,
+                        retain_graph=True, create_graph=True, only_inputs=True
+                    )[0]
+                    gradients = gradients.view(gradients.size(0), -1)
+                    gradient_norm = gradients.norm(2, dim=1)
+                    gradient_penalty = 10 * gradient_norm.sub(1).pow(2).mean()
+                    loss_d += gradient_penalty
+            # from ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
+            elif self.gan_type == 'RGAN':
+                better_real = d_real - d_fake.mean(dim=0, keepdim=True)
+                better_fake = d_fake - d_real.mean(dim=0, keepdim=True)
+                loss_d = self.bce(better_real, better_fake)
+                retain_graph = True
+
+            # Discriminator update
+            self.loss += loss_d.item()
+            loss_d.backward(retain_graph=retain_graph)
+            self.optimizer.step()
+
+            if self.gan_type == 'WGAN':
+                for p in self.dis.parameters():
+                    p.data.clamp_(-1, 1)
+
+        self.loss /= self.gan_k
+
+        # updating generator...
+        d_fake_bp = self.dis(fake)      # for backpropagation, use fake as it is
+        if self.gan_type == 'GAN':
+            label_real = torch.ones_like(d_fake_bp)
+            loss_g = F.binary_cross_entropy_with_logits(d_fake_bp, label_real)
+        elif self.gan_type.find('WGAN') >= 0:
+            loss_g = -d_fake_bp.mean()
+        elif self.gan_type == 'RGAN':
+            better_real = d_real - d_fake_bp.mean(dim=0, keepdim=True)
+            better_fake = d_fake_bp - d_real.mean(dim=0, keepdim=True)
+            loss_g = self.bce(better_fake, better_real)
+
+        # Generator loss
+        return loss_g
+    
+    def state_dict(self, *args, **kwargs):
+        state_discriminator = self.dis.state_dict(*args, **kwargs)
+        state_optimizer = self.optimizer.state_dict()
+
+        return dict(**state_discriminator, **state_optimizer)
+
+    def bce(self, real, fake):
+        label_real = torch.ones_like(real)
+        label_fake = torch.zeros_like(fake)
+        bce_real = F.binary_cross_entropy_with_logits(real, label_real)
+        bce_fake = F.binary_cross_entropy_with_logits(fake, label_fake)
+        bce_loss = bce_real + bce_fake
+        return bce_loss
+               
+# Some references
+# https://github.com/kuc2477/pytorch-wgan-gp/blob/master/model.py
+# OR
+# https://github.com/caogang/wgan-gp/blob/master/gan_cifar10.py
diff --git a/src/loss/discriminator.py b/src/loss/discriminator.py
new file mode 100644
index 0000000000000000000000000000000000000000..4581dfeb1a5539daddf03419cff527a20bebe7a0
--- /dev/null
+++ b/src/loss/discriminator.py
@@ -0,0 +1,55 @@
+from model import common
+
+import torch.nn as nn
+
+class Discriminator(nn.Module):
+    '''
+        output is not normalized
+    '''
+    def __init__(self, args):
+        super(Discriminator, self).__init__()
+
+        in_channels = args.n_colors
+        out_channels = 64
+        depth = 7
+
+        def _block(_in_channels, _out_channels, stride=1):
+            return nn.Sequential(
+                nn.Conv2d(
+                    _in_channels,
+                    _out_channels,
+                    3,
+                    padding=1,
+                    stride=stride,
+                    bias=False
+                ),
+                nn.BatchNorm2d(_out_channels),
+                nn.LeakyReLU(negative_slope=0.2, inplace=True)
+            )
+
+        m_features = [_block(in_channels, out_channels)]
+        for i in range(depth):
+            in_channels = out_channels
+            if i % 2 == 1:
+                stride = 1
+                out_channels *= 2
+            else:
+                stride = 2
+            m_features.append(_block(in_channels, out_channels, stride=stride))
+
+        patch_size = args.patch_size // (2**((depth + 1) // 2))
+        m_classifier = [
+            nn.Linear(out_channels * patch_size**2, 1024),
+            nn.LeakyReLU(negative_slope=0.2, inplace=True),
+            nn.Linear(1024, 1)
+        ]
+
+        self.features = nn.Sequential(*m_features)
+        self.classifier = nn.Sequential(*m_classifier)
+
+    def forward(self, x):
+        features = self.features(x)
+        output = self.classifier(features.view(features.size(0), -1))
+
+        return output
+
diff --git a/src/loss/vgg.py b/src/loss/vgg.py
new file mode 100644
index 0000000000000000000000000000000000000000..42ab9d0a9914076e32b6400db2feb03c84574cbc
--- /dev/null
+++ b/src/loss/vgg.py
@@ -0,0 +1,36 @@
+from model import common
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+import torchvision.models as models
+
+class VGG(nn.Module):
+    def __init__(self, conv_index, rgb_range=1):
+        super(VGG, self).__init__()
+        vgg_features = models.vgg19(pretrained=True).features
+        modules = [m for m in vgg_features]
+        if conv_index.find('22') >= 0:
+            self.vgg = nn.Sequential(*modules[:8])
+        elif conv_index.find('54') >= 0:
+            self.vgg = nn.Sequential(*modules[:35])
+
+        vgg_mean = (0.485, 0.456, 0.406)
+        vgg_std = (0.229 * rgb_range, 0.224 * rgb_range, 0.225 * rgb_range)
+        self.sub_mean = common.MeanShift(rgb_range, vgg_mean, vgg_std)
+        for p in self.parameters():
+            p.requires_grad = False
+
+    def forward(self, sr, hr):
+        def _forward(x):
+            x = self.sub_mean(x)
+            x = self.vgg(x)
+            return x
+            
+        vgg_sr = _forward(sr)
+        with torch.no_grad():
+            vgg_hr = _forward(hr.detach())
+
+        loss = F.mse_loss(vgg_sr, vgg_hr)
+
+        return loss
diff --git a/src/main.py b/src/main.py
new file mode 100644
index 0000000000000000000000000000000000000000..dbfac3e008d04cc72f438179fdce265aa1f079ad
--- /dev/null
+++ b/src/main.py
@@ -0,0 +1,33 @@
+import torch
+
+import utility
+import data
+import model
+import loss
+from option import args
+from trainer import Trainer
+
+torch.manual_seed(args.seed)
+checkpoint = utility.checkpoint(args)
+
+def main():
+    global model
+    if args.data_test == ['video']:
+        from videotester import VideoTester
+        model = model.Model(args, checkpoint)
+        t = VideoTester(args, model, checkpoint)
+        t.test()
+    else:
+        if checkpoint.ok:
+            loader = data.Data(args)
+            _model = model.Model(args, checkpoint)
+            _loss = loss.Loss(args, checkpoint) if not args.test_only else None
+            t = Trainer(args, loader, _model, _loss, checkpoint)
+            while not t.terminate():
+                t.train()
+                t.test()
+
+            checkpoint.done()
+
+if __name__ == '__main__':
+    main()
diff --git a/src/model/MFAM.py b/src/model/MFAM.py
new file mode 100644
index 0000000000000000000000000000000000000000..c0dd8ca2a968ef845d4add8c01a91211fdd89b4a
--- /dev/null
+++ b/src/model/MFAM.py
@@ -0,0 +1,610 @@
+import math
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+import torch.utils.checkpoint as checkpoint
+from timm.models.layers import DropPath, to_2tuple, trunc_normal_
+
+
+class Mlp(nn.Module):
+    def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
+        super().__init__()
+        out_features = out_features or in_features
+        hidden_features = hidden_features or in_features
+        self.fc1 = nn.Linear(in_features, hidden_features)
+        self.act = act_layer()
+        self.fc2 = nn.Linear(hidden_features, out_features)
+        self.drop = nn.Dropout(drop)
+
+    def forward(self, x):
+        x = self.fc1(x)
+        x = self.act(x)
+        x = self.drop(x)
+        x = self.fc2(x)
+        x = self.drop(x)
+        return x
+
+
+def window_partition(x, window_size):
+    """
+    Args:
+        x: (B, H, W, C)
+        window_size (int): window size
+
+    Returns:
+        windows: (num_windows*B, window_size, window_size, C)
+    """
+    B, H, W, C = x.shape
+    x = x.view(B, H // window_size, window_size, W // window_size, window_size, C)
+    windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C)
+    return windows
+
+
+def window_reverse(windows, window_size, H, W):
+    """
+    Args:
+        windows: (num_windows*B, window_size, window_size, C)
+        window_size (int): Window size
+        H (int): Height of image
+        W (int): Width of image
+
+    Returns:
+        x: (B, H, W, C)
+    """
+    B = int(windows.shape[0] / (H * W / window_size / window_size))
+    x = windows.view(B, H // window_size, W // window_size, window_size, window_size, -1)
+    x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H, W, -1)
+    return x
+
+
+class WindowAttention(nn.Module):
+
+    def __init__(self, dim, window_size, num_heads, qkv_bias=True, qk_scale=None, attn_drop=0., proj_drop=0.):
+
+        super().__init__()
+        self.dim = dim
+        self.window_size = window_size  # Wh, Ww
+        self.num_heads = num_heads
+        head_dim = dim // num_heads
+        self.scale = qk_scale or head_dim ** -0.5
+
+        # define a parameter table of relative position bias
+        self.relative_position_bias_table = nn.Parameter(
+            torch.zeros((2 * window_size[0] - 1) * (2 * window_size[1] - 1), num_heads))  # 2*Wh-1 * 2*Ww-1, nH
+
+        # get pair-wise relative position index for each token inside the window
+        coords_h = torch.arange(self.window_size[0])
+        coords_w = torch.arange(self.window_size[1])
+        coords = torch.stack(torch.meshgrid([coords_h, coords_w]))  # 2, Wh, Ww
+        coords_flatten = torch.flatten(coords, 1)  # 2, Wh*Ww
+        relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :]  # 2, Wh*Ww, Wh*Ww
+        relative_coords = relative_coords.permute(1, 2, 0).contiguous()  # Wh*Ww, Wh*Ww, 2
+        relative_coords[:, :, 0] += self.window_size[0] - 1  # shift to start from 0
+        relative_coords[:, :, 1] += self.window_size[1] - 1
+        relative_coords[:, :, 0] *= 2 * self.window_size[1] - 1
+        relative_position_index = relative_coords.sum(-1)  # Wh*Ww, Wh*Ww
+        self.register_buffer("relative_position_index", relative_position_index)
+
+        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
+        self.attn_drop = nn.Dropout(attn_drop)
+        self.proj = nn.Linear(dim, dim)
+
+        self.proj_drop = nn.Dropout(proj_drop)
+
+        trunc_normal_(self.relative_position_bias_table, std=.02)
+        self.softmax = nn.Softmax(dim=-1)
+
+    def forward(self, x, mask=None):
+        """
+        Args:
+            x: input features with shape of (num_windows*B, N, C)
+            mask: (0/-inf) mask with shape of (num_windows, Wh*Ww, Wh*Ww) or None
+        """
+        B_, N, C = x.shape
+        qkv = self.qkv(x).reshape(B_, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
+        q, k, v = qkv[0], qkv[1], qkv[2]  # make torchscript happy (cannot use tensor as tuple)
+
+        q = q * self.scale
+        attn = (q @ k.transpose(-2, -1))
+
+        relative_position_bias = self.relative_position_bias_table[self.relative_position_index.view(-1)].view(
+            self.window_size[0] * self.window_size[1], self.window_size[0] * self.window_size[1], -1)  # Wh*Ww,Wh*Ww,nH
+        relative_position_bias = relative_position_bias.permute(2, 0, 1).contiguous()  # nH, Wh*Ww, Wh*Ww
+        attn = attn + relative_position_bias.unsqueeze(0)
+
+        if mask is not None:
+            nW = mask.shape[0]
+            attn = attn.view(B_ // nW, nW, self.num_heads, N, N) + mask.unsqueeze(1).unsqueeze(0)
+            attn = attn.view(-1, self.num_heads, N, N)
+            attn = self.softmax(attn)
+        else:
+            attn = self.softmax(attn)
+
+        attn = self.attn_drop(attn)
+
+        x = (attn @ v).transpose(1, 2).reshape(B_, N, C)
+        x = self.proj(x)
+        x = self.proj_drop(x)
+        return x
+
+    def extra_repr(self) -> str:
+        return f'dim={self.dim}, window_size={self.window_size}, num_heads={self.num_heads}'
+
+    def flops(self, N):
+        # calculate flops for 1 window with token length of N
+        flops = 0
+        # qkv = self.qkv(x)
+        flops += N * self.dim * 3 * self.dim
+        # attn = (q @ k.transpose(-2, -1))
+        flops += self.num_heads * N * (self.dim // self.num_heads) * N
+        #  x = (attn @ v)
+        flops += self.num_heads * N * N * (self.dim // self.num_heads)
+        # x = self.proj(x)
+        flops += N * self.dim * self.dim
+        return flops
+
+
+class SwinTransformerBlock(nn.Module):
+
+    def __init__(self, dim, img_resolution, num_heads, window_size=7, shift_size=0,
+                 mlp_ratio=4., qkv_bias=True, qk_scale=None, drop=0., attn_drop=0., drop_path=0.,
+                 act_layer=nn.GELU, norm_layer=nn.LayerNorm):
+        super().__init__()
+        self.dim = dim
+        self.img_resolution = img_resolution
+        self.num_heads = num_heads
+        self.window_size = window_size
+        self.shift_size = shift_size
+        self.mlp_ratio = mlp_ratio
+        if min(self.img_resolution) <= self.window_size:
+            # if window size is larger than input resolution, we don't partition windows
+            self.shift_size = 0
+            self.window_size = min(self.img_resolution)
+        assert 0 <= self.shift_size < self.window_size, "shift_size must in 0-window_size"
+
+        self.norm1 = norm_layer(dim)
+        self.attn = WindowAttention(
+            dim, window_size=to_2tuple(self.window_size), num_heads=num_heads,
+            qkv_bias=qkv_bias, qk_scale=qk_scale, attn_drop=attn_drop, proj_drop=drop)
+
+        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
+        self.norm2 = norm_layer(dim)
+        mlp_hidden_dim = int(dim * mlp_ratio)
+        self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
+
+        if self.shift_size > 0:
+            attn_mask = self.calculate_mask(self.img_resolution)
+        else:
+            attn_mask = None
+
+        self.register_buffer("attn_mask", attn_mask)
+
+    def calculate_mask(self, x_size):
+        # calculate attention mask for SW-MSA
+        H, W = x_size
+        img_mask = torch.zeros((1, H, W, 1))  # 1 H W 1
+        h_slices = (slice(0, -self.window_size),
+                    slice(-self.window_size, -self.shift_size),
+                    slice(-self.shift_size, None))
+        w_slices = (slice(0, -self.window_size),
+                    slice(-self.window_size, -self.shift_size),
+                    slice(-self.shift_size, None))
+        cnt = 0
+        for h in h_slices:
+            for w in w_slices:
+                img_mask[:, h, w, :] = cnt
+                cnt += 1
+
+        mask_windows = window_partition(img_mask, self.window_size)  # nW, window_size, window_size, 1
+        mask_windows = mask_windows.view(-1, self.window_size * self.window_size)
+        attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2)
+        attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0))
+
+        return attn_mask
+
+    def forward(self, x, x_size):
+        H, W = x_size
+        B, L, C = x.shape
+        # assert L == H * W, "input feature has wrong size"
+
+        shortcut = x
+        x = self.norm1(x)
+        x = x.view(B, H, W, C)
+
+        # cyclic shift
+        if self.shift_size > 0:
+            shifted_x = torch.roll(x, shifts=(-self.shift_size, -self.shift_size), dims=(1, 2))
+        else:
+            shifted_x = x
+
+        # partition windows
+        x_windows = window_partition(shifted_x, self.window_size)  # nW*B, window_size, window_size, C
+        x_windows = x_windows.view(-1, self.window_size * self.window_size, C)  # nW*B, window_size*window_size, C
+
+        # W-MSA/SW-MSA (to be compatible for testing on images whose shapes are the multiple of window size
+        if self.img_resolution == x_size:
+            attn_windows = self.attn(x_windows, mask=self.attn_mask)  # nW*B, window_size*window_size, C
+        else:
+            attn_windows = self.attn(x_windows, mask=self.calculate_mask(x_size).to(x.device))
+
+        # merge windows
+        attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C)
+        shifted_x = window_reverse(attn_windows, self.window_size, H, W)  # B H' W' C
+
+        # reverse cyclic shift
+        if self.shift_size > 0:
+            x = torch.roll(shifted_x, shifts=(self.shift_size, self.shift_size), dims=(1, 2))
+        else:
+            x = shifted_x
+        x = x.view(B, H * W, C)
+
+        # FFN
+        x = shortcut + self.drop_path(x)
+        x = x + self.drop_path(self.mlp(self.norm2(x)))
+
+        return x
+
+    def flops(self):
+        flops = 0
+        H, W = self.img_resolution
+        # norm1
+        flops += self.dim * H * W
+        # W-MSA/SW-MSA
+        nW = H * W / self.window_size / self.window_size
+        flops += nW * self.attn.flops(self.window_size * self.window_size)
+        # mlp
+        flops += 2 * H * W * self.dim * self.dim * self.mlp_ratio
+        # norm2
+        flops += self.dim * H * W
+        return flops
+
+
+class ResBlock(nn.Module):
+    def __init__(
+        self, n_feats, kernel_size,
+        bias=True, bn=False, act=nn.ReLU(True), res_scale=0.1):
+
+        super(ResBlock, self).__init__()
+        m = []
+        for i in range(2):
+            m.append(nn.Conv2d(n_feats, n_feats, kernel_size, padding=1, bias=bias))
+            if bn:
+                m.append(nn.BatchNorm2d(n_feats))
+            if i == 0:
+                m.append(act)
+
+        self.body = nn.Sequential(*m)
+        self.res_scale = res_scale
+
+    def forward(self, x):
+        res = self.body(x).mul(self.res_scale)
+        res += x
+
+        return res
+
+
+class DoubleBranchBlock(nn.Module):
+
+    def __init__(self, dim, img_resolution, depth, num_heads, window_size,
+                 mlp_ratio=4., qkv_bias=True, qk_scale=None, drop=0., attn_drop=0.,
+                 drop_path=0., norm_layer=nn.LayerNorm, use_checkpoint=False):
+
+        super().__init__()
+        self.dim = dim
+        self.input_resolution = img_resolution
+        self.depth = depth
+        self.use_checkpoint = use_checkpoint
+
+        # build blocks
+        self.FIEB = nn.ModuleList([
+            SwinTransformerBlock(dim=dim, img_resolution=img_resolution,
+                                 num_heads=num_heads, window_size=window_size,
+                                 shift_size=0 if (i % 2 == 0) else window_size // 2,
+                                 mlp_ratio=mlp_ratio,
+                                 qkv_bias=qkv_bias, qk_scale=qk_scale,
+                                 drop=drop, attn_drop=attn_drop,
+                                 drop_path=drop_path[i] if isinstance(drop_path, list) else drop_path,
+                                 norm_layer=norm_layer)
+            for i in range(depth)])
+
+        SIEB = []
+        SIEB.append(ResBlock(dim, 3))
+
+        self.SIEB = nn.Sequential(*SIEB)
+
+
+    def forward(self, x, x_size):
+        H, W = x_size
+        B, _, C = x.shape
+        x_ = self.SIEB(x.transpose(1, 2).reshape(B, C, H, W))
+        for fbranch in self.FIEB:
+            x = fbranch(x, x_size)
+        return torch.cat((x, x_.flatten(2).transpose(1, 2)), dim=2)
+
+    # def extra_repr(self) -> str:
+    #     return f"dim={self.dim}, input_resolution={self.input_resolution}, depth={self.depth}"
+
+    def flops(self):
+        flops = 0
+        for blk in self.blocks:
+            flops += blk.flops()
+        # if self.downsample is not None:
+        #     flops += self.downsample.flops()
+        return flops
+
+
+class DoublebranchFeatureExtractionBlock(nn.Module):
+
+    def __init__(self, dim, img_resolution, depth, num_heads, window_size,
+                 mlp_ratio=4., qkv_bias=True, qk_scale=None, drop=0., attn_drop=0.,
+                 drop_path=0., norm_layer=nn.LayerNorm, downsample=None, use_checkpoint=False,
+                 img_size=224, patch_size=4, resi_connection='1conv'):
+        super(DoublebranchFeatureExtractionBlock, self).__init__()
+
+        self.dim = dim
+        self.input_resolution = img_resolution
+
+        self.DFEB = DoubleBranchBlock(dim=dim,
+                                         img_resolution=img_resolution,
+                                         depth=depth,
+                                         num_heads=num_heads,
+                                         window_size=window_size,
+                                         mlp_ratio=mlp_ratio,
+                                         qkv_bias=qkv_bias, qk_scale=qk_scale,
+                                         drop=drop, attn_drop=attn_drop,
+                                         drop_path=drop_path,
+                                         norm_layer=norm_layer,
+                                         # downsample=downsample,
+                                         use_checkpoint=use_checkpoint)
+
+        if resi_connection == '1conv':
+            self.conv = nn.Conv2d(dim*2, dim, 3, 1, 1)
+            # self.conv = nn.Sequential(nn.Conv2d(dim*2, dim, 3, 1, 1),
+            #                           nn.ReLU(True),
+            #                           nn.Conv2d(dim, dim, 3, 1, 1))
+
+        self.token_embed = PatchEmbed(
+            img_size=img_size, patch_size=patch_size, in_chans=0, embed_dim=dim,
+            norm_layer=None)
+
+        self.token_unembed = PatchUnEmbed(
+            img_size=img_size, patch_size=patch_size, in_chans=0, embed_dim=dim,
+            norm_layer=None)
+
+    def forward(self, x, x_size):
+        x_token = self.DFEB(x, x_size)
+        x = self.token_unembed(x_token, x_size)
+        x = self.conv(x)
+        x_token = self.token_embed(x)
+
+        return x_token
+
+    def flops(self):
+        flops = 0
+        flops += self.residual_group.flops()
+        H, W = self.input_resolution
+        flops += 2 * H * W * (self.dim * 9 + 1) * self.dim * 2
+        flops += 2 * H * W * (self.dim * 2 * 9 + 1) * self.dim
+        flops += self.patch_embed.flops()
+        flops += self.patch_unembed.flops()
+
+        return flops
+
+
+class PatchEmbed(nn.Module):
+
+    def __init__(self, img_size=224, patch_size=4, in_chans=3, embed_dim=96, norm_layer=None):
+        super().__init__()
+        img_size = to_2tuple(img_size)
+        self.img_size = img_size
+
+        self.in_chans = in_chans
+        self.embed_dim = embed_dim
+
+        if norm_layer is not None:
+            self.norm = norm_layer(embed_dim)
+        else:
+            self.norm = None
+
+    def forward(self, x):
+        x = x.flatten(2).transpose(1, 2)  # B Ph*Pw C
+        if self.norm is not None:
+            x = self.norm(x)
+        return x
+
+    def flops(self):
+        flops = 0
+        H, W = self.img_size
+        if self.norm is not None:
+            flops += H * W * self.embed_dim
+        return flops
+
+
+class PatchUnEmbed(nn.Module):
+
+    def __init__(self, img_size=224, patch_size=4, in_chans=3, embed_dim=96, norm_layer=None):
+        super().__init__()
+        img_size = to_2tuple(img_size)
+        self.img_size = img_size
+
+        self.in_chans = in_chans
+        self.embed_dim = embed_dim
+
+    def forward(self, x, x_size):
+        B, HW, C = x.shape
+        x = x.transpose(1, 2).view(B, -1, x_size[0], x_size[1])  # B Ph*Pw C
+        return x
+
+    def flops(self):
+        flops = 0
+        return flops
+
+
+class MFAM(nn.Module):
+
+    def __init__(self, img_size=64, patch_size=1, in_chans=1,
+                 embed_dim=96, depths=[6, 6, 6, 6], num_heads=[6, 6, 6, 6],
+                 window_size=7, mlp_ratio=4., qkv_bias=True, qk_scale=None,
+                 drop_rate=0., attn_drop_rate=0., drop_path_rate=0.1,
+                 norm_layer=nn.LayerNorm, ape=False, patch_norm=True,
+                 use_checkpoint=False, upscale=2, img_range=1., upsampler='', resi_connection='1conv',
+                 **kwargs):
+        super(MFAM, self).__init__()
+        # print("MFAM-dongba")
+        num_in_ch = in_chans
+        num_out_ch = in_chans
+        self.img_range = img_range
+
+        # if in_chans == 3:
+        #     rgb_mean = (0.4488, 0.4371, 0.4040)
+        #     self.mean = torch.Tensor(rgb_mean).view(1, 3, 1, 1)
+        # else:
+        #     self.mean = torch.zeros(1, 1, 1, 1)
+
+        self.upscale = upscale
+        self.upsampler = upsampler
+        self.window_size = window_size
+
+        self.conv_first = nn.Conv2d(num_in_ch, embed_dim, 3, 1, 1)
+
+        self.num_layers = len(depths)
+        self.embed_dim = embed_dim
+        self.patch_norm = patch_norm
+        self.num_features = embed_dim
+        self.mlp_ratio = mlp_ratio
+
+        # split image into non-overlapping patches
+        self.patch_embed = PatchEmbed(
+            img_size=img_size, patch_size=patch_size, in_chans=embed_dim, embed_dim=embed_dim,
+            norm_layer=norm_layer if self.patch_norm else None)
+        # num_patches = self.patch_embed.num_patches
+        self.img_resolution = self.patch_embed.img_size
+        img_resolution = self.patch_embed.img_size
+
+        # merge non-overlapping patches into image
+        self.patch_unembed = PatchUnEmbed(
+            img_size=img_size, patch_size=patch_size, in_chans=embed_dim, embed_dim=embed_dim,
+            norm_layer=norm_layer if self.patch_norm else None)
+
+        self.pos_drop = nn.Dropout(p=drop_rate)
+
+        # stochastic depth
+        dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))]  # stochastic depth decay rule
+
+        # build Residual Swin Transformer blocks (RSTB)
+        self.layers = nn.ModuleList()
+        for i_layer in range(self.num_layers):
+            layer = DoublebranchFeatureExtractionBlock(dim=embed_dim,
+                         img_resolution=(img_resolution[0],
+                                           img_resolution[1]),
+                         depth=depths[i_layer],
+                         num_heads=num_heads[i_layer],
+                         window_size=window_size,
+                         mlp_ratio=self.mlp_ratio,
+                         qkv_bias=qkv_bias, qk_scale=qk_scale,
+                         drop=drop_rate, attn_drop=attn_drop_rate,
+                         drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])],  # no impact on SR results
+                         norm_layer=norm_layer,
+                         downsample=None,
+                         use_checkpoint=use_checkpoint,
+                         img_size=img_size,
+                         patch_size=patch_size,
+                         resi_connection=resi_connection
+
+                         )
+            self.layers.append(layer)
+        self.norm = norm_layer(self.num_features)
+
+        # build the last conv layer in deep feature extraction
+        if resi_connection == '1conv':
+            self.conv_after_body = ResBlock(embed_dim, 3)
+
+        self.conv_last = nn.Conv2d(embed_dim, num_out_ch//2, 3, 1, 1)
+
+        self.apply(self._init_weights)
+
+    def _init_weights(self, m):
+        if isinstance(m, nn.Linear):
+            trunc_normal_(m.weight, std=.02)
+            if isinstance(m, nn.Linear) and m.bias is not None:
+                nn.init.constant_(m.bias, 0)
+        elif isinstance(m, nn.LayerNorm):
+            nn.init.constant_(m.bias, 0)
+            nn.init.constant_(m.weight, 1.0)
+
+    @torch.jit.ignore
+    def no_weight_decay(self):
+        return {'absolute_pos_embed'}
+
+    @torch.jit.ignore
+    def no_weight_decay_keywords(self):
+        return {'relative_position_bias_table'}
+
+    def check_image_size(self, x):
+        _, _, h, w = x.size()
+        mod_pad_h = (self.window_size - h % self.window_size) % self.window_size
+        mod_pad_w = (self.window_size - w % self.window_size) % self.window_size
+        x = F.pad(x, (0, mod_pad_w, 0, mod_pad_h), 'reflect')
+        return x
+
+    def forward_features(self, x):
+        x_size = (x.shape[2], x.shape[3])
+        x = self.patch_embed(x)
+        # if self.ape:
+        #     x = x + self.absolute_pos_embed
+        x = self.pos_drop(x)
+        res = 0.
+        for layer in self.layers:
+            x = layer(x, x_size)
+            res += x
+        x = self.norm(x+res)  # B L C
+        x = self.patch_unembed(x, x_size)
+
+        return x
+
+    def forward(self, x):
+        H, W = x.shape[2:]
+        x = self.check_image_size(x)
+
+        x_first = self.conv_first(x)
+        res = self.conv_after_body(self.forward_features(x_first)) + x_first
+        # x = x + self.conv_last(res)
+        x = self.conv_last(res)
+
+        return x[:, :, :H * self.upscale, :W * self.upscale]
+
+    def flops(self):
+        flops = 0
+        H, W = self.img_resolution
+        flops += 2 * H * W * (12 * 9 + 1) * self.embed_dim * 2
+        flops += self.patch_embed.flops()
+        for i, layer in enumerate(self.layers):
+            flops += layer.flops()
+        flops += 2 * H * W * (self.embed_dim * 9 + 1) * self.embed_dim * 2
+        flops += 2 * H * W * (self.embed_dim * 9 + 1) * 12
+        return flops
+
+
+# if __name__ == '__main__':
+#     upscale = 4
+#     window_size = 8
+#     height = (1024 // upscale // window_size + 1) * window_size
+#     width = (720 // upscale // window_size + 1) * window_size
+#     model = SwinIR(upscale=1, img_size=(height, width),
+#                    window_size=window_size, img_range=1., depths=[6, 6, 6, 6, 6, 6],
+#                    embed_dim=180, num_heads=[6, 6, 6, 6, 6, 6], mlp_ratio=2, upsampler='')
+#
+    # def get_parameter_number(model):
+    #     total_num = sum(p.numel() for p in model.parameters())
+    #     trainable_num = sum(p.numel() for p in model.parameters() if p.requires_grad)
+    #     return {'Total': total_num, 'Trainable': trainable_num}
+    #
+    # print(get_parameter_number(model))
+
+    # print(model)
+    # print(height, width, model.flops() / 1e9)
+
+    # x = torch.randn((1, 3, height, width))
+    # x = torch.FloatTensor(x).cuda(1)
+    # x = model(x)
+    # print(x.shape)
\ No newline at end of file
diff --git a/src/model/__init__.py b/src/model/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..f1a1e035f3625b3dc280a7e44f7d387eb9d8ccaa
--- /dev/null
+++ b/src/model/__init__.py
@@ -0,0 +1,209 @@
+import os
+from importlib import import_module
+
+import torch
+import torch.nn as nn
+import torch.nn.parallel as P
+import torch.utils.model_zoo
+
+class Model(nn.Module):
+    def __init__(self, args, ckp):
+        super(Model, self).__init__()
+        print('Making model...')
+
+        self.scale = args.scale
+        self.idx_scale = 0
+        self.input_large = (args.model == 'VDSR')
+        self.self_ensemble = args.self_ensemble
+        self.chop = args.chop
+        self.precision = args.precision
+        self.cpu = args.cpu
+        self.device = torch.device('cpu' if args.cpu else 'cuda')
+        self.n_GPUs = args.n_GPUs
+        self.save_models = args.save_models
+
+        module = import_module('model.' + args.model.lower())
+        self.model = module.make_model(args).to(self.device)
+        if args.precision == 'half':
+            self.model.half()
+
+        self.load(
+            ckp.get_path('model'),
+            pre_train=args.pre_train,
+            resume=args.resume,
+            cpu=args.cpu
+        )
+        print(self.model, file=ckp.log_file)
+
+    def forward(self, x, idx_scale):
+        self.idx_scale = idx_scale
+        if hasattr(self.model, 'set_scale'):
+            self.model.set_scale(idx_scale)
+
+        if self.training:
+            if self.n_GPUs > 1:
+                return P.data_parallel(self.model, x, range(self.n_GPUs))
+            else:
+                return self.model(x)
+        else:
+            if self.chop:
+                forward_function = self.forward_chop
+            else:
+                forward_function = self.model.forward
+
+            if self.self_ensemble:
+                return self.forward_x8(x, forward_function=forward_function)
+            else:
+                return forward_function(x)
+
+    def save(self, apath, epoch, is_best=False):
+        save_dirs = [os.path.join(apath, 'model_latest.pt')]
+
+        if is_best:
+            save_dirs.append(os.path.join(apath, 'model_best.pt'))
+        if self.save_models:
+            save_dirs.append(
+                os.path.join(apath, 'model_{}.pt'.format(epoch))
+            )
+
+        for s in save_dirs:
+            torch.save(self.model.state_dict(), s)
+
+    def load(self, apath, pre_train='', resume=-1, cpu=False):
+        load_from = None
+        kwargs = {}
+        if cpu:
+            kwargs = {'map_location': lambda storage, loc: storage}
+
+        if resume == -1:
+            load_from = torch.load(
+                os.path.join(apath, 'model_latest.pt'),
+                **kwargs
+            )
+        elif resume == 0:
+            if pre_train == 'download':
+                print('Download the model')
+                dir_model = os.path.join('..', 'models')
+                os.makedirs(dir_model, exist_ok=True)
+                load_from = torch.utils.model_zoo.load_url(
+                    self.model.url,
+                    model_dir=dir_model,
+                    **kwargs
+                )
+            elif pre_train:
+                print('Load the model from {}'.format(pre_train))
+                load_from = torch.load(pre_train, **kwargs)
+        else:
+            load_from = torch.load(
+                os.path.join(apath, 'model_{}.pt'.format(resume)),
+                **kwargs
+            )
+
+        if load_from:
+            self.model.load_state_dict(load_from, strict=False)
+
+    def forward_chop(self, *args, shave=10, min_size=160000):
+        scale = 1 if self.input_large else self.scale[self.idx_scale]
+        n_GPUs = min(self.n_GPUs, 4)
+        # height, width
+        h, w = args[0].size()[-2:]
+
+        top = slice(0, h//2 + shave)
+        bottom = slice(h - h//2 - shave, h)
+        left = slice(0, w//2 + shave)
+        right = slice(w - w//2 - shave, w)
+        x_chops = [torch.cat([
+            a[..., top, left],
+            a[..., top, right],
+            a[..., bottom, left],
+            a[..., bottom, right]
+        ]) for a in args]
+
+        y_chops = []
+        if h * w < 4 * min_size:
+            for i in range(0, 4, n_GPUs):
+                x = [x_chop[i:(i + n_GPUs)] for x_chop in x_chops]
+                y = P.data_parallel(self.model, *x, range(n_GPUs))
+                if not isinstance(y, list): y = [y]
+                if not y_chops:
+                    y_chops = [[c for c in _y.chunk(n_GPUs, dim=0)] for _y in y]
+                else:
+                    for y_chop, _y in zip(y_chops, y):
+                        y_chop.extend(_y.chunk(n_GPUs, dim=0))
+        else:
+            for p in zip(*x_chops):
+                y = self.forward_chop(*p, shave=shave, min_size=min_size)
+                if not isinstance(y, list): y = [y]
+                if not y_chops:
+                    y_chops = [[_y] for _y in y]
+                else:
+                    for y_chop, _y in zip(y_chops, y): y_chop.append(_y)
+
+        h *= scale
+        w *= scale
+        top = slice(0, h//2)
+        bottom = slice(h - h//2, h)
+        bottom_r = slice(h//2 - h, None)
+        left = slice(0, w//2)
+        right = slice(w - w//2, w)
+        right_r = slice(w//2 - w, None)
+
+        # batch size, number of color channels
+        b, c = y_chops[0][0].size()[:-2]
+        y = [y_chop[0].new(b, c, h, w) for y_chop in y_chops]
+        for y_chop, _y in zip(y_chops, y):
+            _y[..., top, left] = y_chop[0][..., top, left]
+            _y[..., top, right] = y_chop[1][..., top, right_r]
+            _y[..., bottom, left] = y_chop[2][..., bottom_r, left]
+            _y[..., bottom, right] = y_chop[3][..., bottom_r, right_r]
+
+        if len(y) == 1: y = y[0]
+
+        return y
+
+    def forward_x8(self, *args, forward_function=None):
+        def _transform(v, op):
+            if self.precision != 'single': v = v.float()
+
+            v2np = v.data.cpu().numpy()
+            if op == 'v':
+                tfnp = v2np[:, :, :, ::-1].copy()
+            elif op == 'h':
+                tfnp = v2np[:, :, ::-1, :].copy()
+            elif op == 't':
+                tfnp = v2np.transpose((0, 1, 3, 2)).copy()
+
+            ret = torch.Tensor(tfnp).to(self.device)
+            if self.precision == 'half': ret = ret.half()
+
+            return ret
+
+        list_x = []
+        for a in args:
+            x = [a]
+            for tf in 'v', 'h', 't': x.extend([_transform(_x, tf) for _x in x])
+
+            list_x.append(x)
+
+        list_y = []
+        for x in zip(*list_x):
+            y = forward_function(*x)
+            if not isinstance(y, list): y = [y]
+            if not list_y:
+                list_y = [[_y] for _y in y]
+            else:
+                for _list_y, _y in zip(list_y, y): _list_y.append(_y)
+
+        for _list_y in list_y:
+            for i in range(len(_list_y)):
+                if i > 3:
+                    _list_y[i] = _transform(_list_y[i], 't')
+                if i % 4 > 1:
+                    _list_y[i] = _transform(_list_y[i], 'h')
+                if (i % 4) % 2 == 1:
+                    _list_y[i] = _transform(_list_y[i], 'v')
+
+        y = [torch.cat(_y, dim=0).mean(dim=0, keepdim=True) for _y in list_y]
+        if len(y) == 1: y = y[0]
+
+        return y
diff --git a/src/model/__pycache__/MFAM.cpython-38.pyc b/src/model/__pycache__/MFAM.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..6a8f90ab1186153dcd2b4f63bade611d2ca8a404
Binary files /dev/null and b/src/model/__pycache__/MFAM.cpython-38.pyc differ
diff --git a/src/model/__pycache__/__init__.cpython-37.pyc b/src/model/__pycache__/__init__.cpython-37.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..a1a9fa5ab0d7041c481061d9430189da89dbc527
Binary files /dev/null and b/src/model/__pycache__/__init__.cpython-37.pyc differ
diff --git a/src/model/__pycache__/__init__.cpython-38.pyc b/src/model/__pycache__/__init__.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..b237211b525e82f12808353e361a57c87b5f71a9
Binary files /dev/null and b/src/model/__pycache__/__init__.cpython-38.pyc differ
diff --git a/src/model/__pycache__/common.cpython-37.pyc b/src/model/__pycache__/common.cpython-37.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..880814f03a3eff5e21182382d65405a86b768df1
Binary files /dev/null and b/src/model/__pycache__/common.cpython-37.pyc differ
diff --git a/src/model/__pycache__/common.cpython-38.pyc b/src/model/__pycache__/common.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..05c6838617734c6bf79b037522a62bdf2a2e3d17
Binary files /dev/null and b/src/model/__pycache__/common.cpython-38.pyc differ
diff --git a/src/model/__pycache__/ewt.cpython-38.pyc b/src/model/__pycache__/ewt.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..c769c8a621fbef35a73772d0a3db57e9b8c3ace1
Binary files /dev/null and b/src/model/__pycache__/ewt.cpython-38.pyc differ
diff --git a/src/model/__pycache__/smgarn.cpython-37.pyc b/src/model/__pycache__/smgarn.cpython-37.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..0c04377f944bb1e47dd99eb2c2a1c31f8cdb8a66
Binary files /dev/null and b/src/model/__pycache__/smgarn.cpython-37.pyc differ
diff --git a/src/model/__pycache__/smgarn.cpython-38.pyc b/src/model/__pycache__/smgarn.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..edd66f2d5fb3c4436fe71ea7a45577ce2cca2ac1
Binary files /dev/null and b/src/model/__pycache__/smgarn.cpython-38.pyc differ
diff --git a/src/model/common.py b/src/model/common.py
new file mode 100644
index 0000000000000000000000000000000000000000..a5c89cca47b4006087a6d4e870de0c4c085ee7c2
--- /dev/null
+++ b/src/model/common.py
@@ -0,0 +1,207 @@
+import math
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+from torch.autograd import Variable
+
+
+def default_conv(in_channels, out_channels, kernel_size, bias=True):
+    return nn.Conv2d(
+        in_channels, out_channels, kernel_size,
+        padding=(kernel_size//2), bias=bias)
+
+
+class ResUnit(nn.Module):
+    def __init__(self, dim):
+        super(ResUnit, self).__init__()
+
+        self.act = nn.ReLU(True)
+        self.conv1 = default_conv(dim, dim, 3)
+        self.conv2 = default_conv(dim, dim*2, 1)
+        self.conv3 = default_conv(dim*2, dim, 1)
+
+    def forward(self, x):
+        shortcut = x
+
+        x = self.conv1(x)
+        x = self.conv2(x)
+        x = self.act(x)
+        x = self.conv3(x)
+
+        return x + shortcut
+
+
+class FusionBlock(nn.Module):
+    def __init__(self, n_color, embed_dim):
+        super(FusionBlock, self).__init__()
+
+        self.act = nn.ReLU(True)
+
+        self.conv_1 = default_conv(n_color, embed_dim, 3)
+        self.conv_2 = default_conv(embed_dim, embed_dim, 3)
+
+        self.conv_1_2 = default_conv(embed_dim, embed_dim, 3)
+        self.conv_2_2 = default_conv(embed_dim, embed_dim, 3)
+
+        self.ru_1 = ResUnit(embed_dim)
+        self.ru_2 = ResUnit(embed_dim)
+
+        self.ru_1_1 = ResUnit(embed_dim)
+        self.ru_2_1 = ResUnit(embed_dim)
+
+        self.ru = ResUnit(embed_dim)
+        self.ru_ = ResUnit(embed_dim)
+
+        self.conv_tail_1 = default_conv(embed_dim*2, embed_dim, 3)
+        self.conv_tail_2 = default_conv(embed_dim, embed_dim, 3)
+
+    def forward(self, img_snow, mask):
+
+        img_snow = self.ru_1(self.conv_1(img_snow))
+        mask = self.ru_2(self.conv_2(mask))
+
+        img_1 = self.ru(self.conv_1_2((img_snow-mask)))
+
+        img_snow = self.ru_1_1(img_snow)
+        mask = self.ru_2_1(mask)
+
+        img_2 = self.ru_(self.conv_2_2((img_snow-mask)))
+
+
+        return self.conv_tail_2(self.act(self.conv_tail_1(torch.cat((img_1, img_2), dim=1))))
+
+
+class MARB(nn.Module):
+    def __init__(self, dim):
+        super(MARB, self).__init__()
+
+        self.act = nn.ReLU(True)
+
+        self.conv_dl2 = default_conv(dim, dim, 1)
+        self.conv_dl3 = default_conv(dim, dim, 3)
+        self.conv_dl5 = default_conv(dim, dim, 5)
+
+        self.conv1_1 = default_conv(dim, dim, 1)
+        self.conv1_2 = default_conv(dim, dim, 1)
+        self.conv1_3 = default_conv(dim, dim, 1)
+
+        self.conv2_1 = default_conv(dim*2, dim, 1)
+        self.conv2_2 = default_conv(dim*2, dim, 1)
+
+        self.conv_tail = default_conv(dim*2, dim, 1)
+
+    def forward(self, x):
+        x1 = self.conv1_1(self.conv_dl2(x))
+        x2 = self.conv1_2(self.conv_dl3(x))
+        x3 = self.conv1_3(self.conv_dl5(x))
+
+        x_cat_1 = self.conv2_1(torch.cat((x1, x2), dim=1))
+        x_cat_2 = self.conv2_2(torch.cat((x2, x3), dim=1))
+
+        return self.conv_tail(self.act(torch.cat((x_cat_1, x_cat_2), dim=1))) + x
+
+# class MARB(nn.Module):
+#     def __init__(self, dim):
+#         super(MARB, self).__init__()
+#
+#         self.act = nn.ReLU(True)
+#
+#         self.conv_dl2 = default_conv(dim, dim, 1)
+#         self.conv_dl3 = default_conv(dim, dim, 3)
+#         self.conv_dl5 = default_conv(dim, dim, 5)
+#
+#         self.conv1_1 = default_conv(dim, dim, 3)
+#         self.conv1_2 = default_conv(dim, dim, 3)
+#         self.conv1_3 = default_conv(dim, dim, 3)
+#
+#         # self.conv2_1 = default_conv(dim*2, dim, 3)
+#         # self.conv2_2 = default_conv(dim*2, dim, 3)
+#
+#         self.conv_tail = default_conv(dim*3, dim, 3)
+#
+#     def forward(self, x):
+#         x1 = self.conv1_1(self.conv_dl2(x))
+#         x2 = self.conv1_2(self.conv_dl3(x))
+#         x3 = self.conv1_3(self.conv_dl5(x))
+#
+#         # x_cat_1 = self.conv2_1(torch.cat((x1, x2), dim=1))
+#         # x_cat_2 = self.conv2_2(torch.cat((x2, x3), dim=1))
+#
+#         return self.conv_tail(self.act(torch.cat((x1, x2, x3), dim=1))) + x
+
+
+class MaskBlock(nn.Module):
+    def __init__(self, embed_dim):
+        super(MaskBlock, self).__init__()
+        self.act = nn.ReLU(True)
+        self.conv_head = default_conv(embed_dim, embed_dim, 3)
+
+        self.conv_self = default_conv(embed_dim, embed_dim, 1)
+
+        self.conv1 = default_conv(embed_dim, embed_dim, 3)
+        self.conv1_1 = default_conv(embed_dim, embed_dim, 1)
+        self.conv1_2 = default_conv(embed_dim, embed_dim, 1)
+        self.conv_tail = default_conv(embed_dim, embed_dim, 3)
+
+    def forward(self, x):
+        x = self.conv_head(x)
+        x = self.conv_self(x)
+        x = x.mul(x)
+        x = self.act(self.conv1(x))
+        x = self.conv1_1(x).mul(self.conv1_2(x))
+
+        return self.conv_tail(x)
+
+def dwt_init(x):
+    x01 = x[:, :, 0::2, :] / 2
+    x02 = x[:, :, 1::2, :] / 2
+    x1 = x01[:, :, :, 0::2]
+    x2 = x02[:, :, :, 0::2]
+    x3 = x01[:, :, :, 1::2]
+    x4 = x02[:, :, :, 1::2]
+    x_LL = x1 + x2 + x3 + x4
+    x_HL = -x1 - x2 + x3 + x4
+    x_LH = -x1 + x2 - x3 + x4
+    x_HH = x1 - x2 - x3 + x4
+
+    return torch.cat((x_LL, x_HL, x_LH, x_HH), 1)
+
+
+def iwt_init(x):
+    r = 2
+    in_batch, in_channel, in_height, in_width = x.size()
+    # print([in_batch, in_channel, in_height, in_width])
+    out_batch, out_channel, out_height, out_width = in_batch, int(
+        in_channel / (r ** 2)), r * in_height, r * in_width
+    x1 = x[:, 0:out_channel, :, :] / 2
+    x2 = x[:, out_channel:out_channel * 2, :, :] / 2
+    x3 = x[:, out_channel * 2:out_channel * 3, :, :] / 2
+    x4 = x[:, out_channel * 3:out_channel * 4, :, :] / 2
+
+    h = torch.zeros([out_batch, out_channel, out_height, out_width]).float().cuda()
+
+    h[:, :, 0::2, 0::2] = x1 - x2 - x3 + x4
+    h[:, :, 1::2, 0::2] = x1 - x2 + x3 - x4
+    h[:, :, 0::2, 1::2] = x1 + x2 - x3 - x4
+    h[:, :, 1::2, 1::2] = x1 + x2 + x3 + x4
+
+    return h
+
+class DWT(nn.Module):
+    def __init__(self):
+        super(DWT, self).__init__()
+        self.requires_grad = False
+
+    def forward(self, x):
+        return dwt_init(x)
+
+
+class IWT(nn.Module):
+    def __init__(self):
+        super(IWT, self).__init__()
+        self.requires_grad = False
+
+    def forward(self, x):
+        return iwt_init(x)
\ No newline at end of file
diff --git a/src/model/ewt.py b/src/model/ewt.py
new file mode 100644
index 0000000000000000000000000000000000000000..0a23850e3506b612671fae586b42927e2530943d
--- /dev/null
+++ b/src/model/ewt.py
@@ -0,0 +1,119 @@
+from model import common
+# import common
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+# import scipy.io as sio
+# from model.masknet import MaskBlock
+# from masknet import MaskBlock
+from model.MFAM import MFAM
+# from MFAM import MFAM
+# from model.newarch import NEWARCH
+# from newarch import NEWARCH
+# from MFAM import MFAM
+# from model.swinir import SwinIR
+# from swinir import SwinIR
+# from model.uformer import Uformer
+# from uformer import Uformer
+# from model.mwt import MWT
+# from mwt import MWT
+# from model.restormer import Restormer
+# from restormer import Restormer
+import os
+
+def make_model(args, parent=False):
+    return EWT(args)
+
+class EWT(nn.Module):
+    # def __init__(self, args, conv=common.default_conv):
+    def __init__(self, conv=common.default_conv):
+        super(EWT, self).__init__()
+        print("EWT")
+        self.scale_idx = 0
+
+        self.DWT = common.DWT()
+        self.IWT = common.IWT()
+        # gray-4
+        # self.trans = MFAM(upscale=1, img_size=(32, 32), in_chans=12,
+        #              window_size=8, img_range=1., depths=[2, 2, 4],
+        #              embed_dim=96, num_heads=[6, 6, 6], mlp_ratio=2, upsampler='')
+
+        # gray-1
+        # self.trans = MFAM(upscale=1, img_size=(32, 32), in_chans=12,
+        #                   window_size=8, img_range=1., depths=[2, 2, 4],
+        #                   embed_dim=48, num_heads=[6, 6, 6], mlp_ratio=2, upsampler='')
+
+        # gray-5
+        self.trans = MFAM(upscale=1, img_size=(32, 32), in_chans=24,
+                          window_size=8, img_range=1., depths=[2, 2, 4],
+                          embed_dim=96, num_heads=[6, 6, 6], mlp_ratio=2, upsampler='')
+
+        # self.trans = NEWARCH(upscale=1, img_size=(32, 32), in_chans=12,
+        #              window_size=8, img_range=1., depths=[4, 4, 4, 4, 4],
+        #              embed_dim=180, num_heads=[6, 6, 6, 6, 6], mlp_ratio=2, upsamplermpler='')
+        # self.trans = SwinIR(upscale=1, img_size=(8, 8),
+        #              window_size=8, img_range=1., depths=[6, 6, 6],
+        #              embed_dim=180, num_heads=[6, 6, 6], mlp_ratio=2, upsampler='')
+        # self.trans = Uformer(img_size=[64, 64], embed_dim=16, depths=[2, 2, 2, 2, 2, 2, 2, 2, 2],
+        #         win_size=8, mlp_ratio=4., token_projection='linear', token_mlp='leff', modulator=True,
+        #         shift_flag=False)
+        # self.trans = Restormer()
+        # self.trans = MWT()
+        # self.trans = MaskBlock()
+
+
+    def _padding(self, x, scale):
+        delta_H = 0
+        delta_W = 0
+        if x.shape[2] % scale != 0:
+            delta_H = scale - x.shape[2] % scale
+            x = F.pad(x, (0, 0, 0, delta_H), 'reflect')
+        if x.shape[3] % scale != 0:
+            delta_W = scale - x.shape[3] % scale
+            x = F.pad(x, (0, delta_W, 0, 0), 'reflect')
+        return x, delta_H, delta_W
+
+    def _padding_2(self, x):
+        _, _, H, W = x.shape
+        delta = abs(H-W)
+        if H < W:
+            x = F.pad(x, (0, 0, 0, delta), 'reflect')
+        elif H > W:
+            x = F.pad(x, (0, delta, 0, 0), 'reflect')
+        return x
+
+
+    def forward(self, x):
+        _, _, H, W = x.shape
+        # x = self._padding_2(x)
+        x, delta_H, delta_W = self._padding(x, 2)
+        # print(x.shape)
+        x = self.DWT(x)
+        # x = self.DWT(x)
+        x = self.trans(x)
+        # x = self.IWT(x)
+        # x = self.IWT(x)
+        x = self.IWT(x)
+
+        x = x[:, :, :H, :W]
+
+        return x
+
+if __name__ == "__main__":
+
+    os.environ["CUDA_VISIBLE_DEVICES"] = '0'
+    # input size: [batch_size, C, N], where C is number of dimension, N is the number of mesh.
+    x = torch.rand(2, 3, 64, 64)
+    x = x.cuda()
+    # x = x.cuda()
+    model = EWT()
+    # model = model.cuda()
+    # y = model(x)
+    # print(y.shape)
+
+    def get_parameter_number(model):
+        total_num = sum(p.numel() for p in model.parameters())
+        trainable_num = sum(p.numel() for p in model.parameters() if p.requires_grad)
+        return {'Total': total_num, 'Trainable': trainable_num}
+
+    print(get_parameter_number(model))
\ No newline at end of file
diff --git a/src/model/smgarn.py b/src/model/smgarn.py
new file mode 100644
index 0000000000000000000000000000000000000000..64c5b151ccf63a8f41b4aa1423aeb3d8f068b0ad
--- /dev/null
+++ b/src/model/smgarn.py
@@ -0,0 +1,84 @@
+from model import common
+# from Train.model import common
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+def make_model(args, parent=False):
+    return SMGARN(args)
+
+
+class SnowMaskBlock(nn.Module):
+    def __init__(self, embed_dim):
+        super(SnowMaskBlock, self).__init__()
+        self.smblock = common.MaskBlock(embed_dim)
+        self.conv3 = common.default_conv(embed_dim, embed_dim, 3)
+        self.norm = nn.LayerNorm(embed_dim)
+
+    def forward(self, x):
+        B, H, W = x.shape[0], x.shape[2], x.shape[3]
+        shortcut = x
+        x = self.smblock(x)
+        x = self.norm(x.flatten(2).transpose(-1, -2))
+        x = self.conv3(x.transpose(-1, -2).view(B, -1, H, W))
+        return x + shortcut
+
+
+class Mask_Net(nn.Module):
+    def __init__(self, n_colors, embed_dim, conv):
+        super(Mask_Net, self).__init__()
+        h = []
+        h.append(conv(n_colors, embed_dim, 3))
+        h.append(conv(embed_dim, embed_dim, 3))
+        self.head = nn.Sequential(*h)
+        self.g_mp1 = SnowMaskBlock(embed_dim)
+
+        self.conv_out1 = common.default_conv(embed_dim, embed_dim, 3)
+        self.conv_out2 = common.default_conv(embed_dim, 3, 3)
+
+    def forward(self, x):
+        x = self.head(x)
+        out_1 = self.g_mp1(x)
+        out_1 = self.conv_out1(out_1)
+
+        out = self.conv_out2(out_1)
+        return out, out_1
+
+class ReconstructNet(nn.Module):
+    def __init__(self, n_colors, dim, depth):
+        super(ReconstructNet, self).__init__()
+        self.fusion = common.FusionBlock(n_colors, dim)
+        block = []
+        for i in range(depth):
+            block.append(common.MARB(dim))
+        self.recon = nn.Sequential(*block)
+        t = []
+        t.append(common.default_conv(dim, dim, 3))
+        t.append(nn.ReLU(True))
+        t.append(common.default_conv(dim, n_colors, 3))
+        self.tail = nn.Sequential(*t)
+
+    def forward(self, x, mask):
+        x = self.fusion(x, mask)
+        out = self.recon(x) + x
+        out = self.tail(out)
+        return out
+
+
+
+class SMGARN(nn.Module):
+    def __init__(self, args, conv=common.default_conv):
+        super(SMGARN, self).__init__()
+        print("SMGARN")
+        n_colors = 3
+        dim = 112
+        ReconNet_num = 3
+
+        self.Stage_I = Mask_Net(n_colors=n_colors, embed_dim=dim, conv=conv)
+
+        self.Stage_II = ReconstructNet(n_colors, dim, ReconNet_num)
+
+    def forward(self, x):
+        mask, mask_feature = self.Stage_I(x)
+        x = self.Stage_II(x, mask_feature)
+        return x, mask
\ No newline at end of file
diff --git a/src/option.py b/src/option.py
new file mode 100644
index 0000000000000000000000000000000000000000..15bbd118e1d82f0405e377832f4fbd32c59a6d31
--- /dev/null
+++ b/src/option.py
@@ -0,0 +1,164 @@
+import argparse
+import template
+
+parser = argparse.ArgumentParser(description='SMGARN')
+
+parser.add_argument('--debug', action='store_true',
+                    help='Enables debug mode')
+parser.add_argument('--template', default='.',
+                    help='You can set various templates in option.py')
+
+# Hardware specifications
+parser.add_argument('--n_threads', type=int, default=6,
+                    help='number of threads for data loading')
+parser.add_argument('--cpu', action='store_true',
+                    help='use cpu only')
+parser.add_argument('--n_GPUs', type=int, default=2,
+                    help='number of GPUs')
+parser.add_argument('--seed', type=int, default=1,
+                    help='random seed')
+
+# Data specifications
+# parser.add_argument('--dir_data', type=str, default='/home/luo/DeSnow/Train/dataset',
+#                     help='dataset directory')
+parser.add_argument('--dir_data', type=str, default='../dataset',
+                    help='dataset directory')
+parser.add_argument('--dir_demo', type=str, default='../test',
+                    help='demo image directory')
+parser.add_argument('--data_train', type=str, default='DIV2K',
+                    help='train dataset name')
+parser.add_argument('--data_test', type=str, default='DIV2K',
+                    help='test dataset name')
+parser.add_argument('--data_range', type=str, default='1-520/521-570',
+                    help='train/test data range')
+# parser.add_argument('--data_range', type=str, default='1-8000/8001-8050',
+#                     help='train/test data range')
+parser.add_argument('--ext', type=str, default='sep',
+                    help='dataset file extension')
+parser.add_argument('--scale', type=str, default='4',
+                    help='super resolution scale')
+parser.add_argument('--patch_size', type=int, default=192,
+                    help='output patch size')
+parser.add_argument('--rgb_range', type=int, default=255,
+                    help='maximum value of RGB')
+parser.add_argument('--n_colors', type=int, default=3,
+                    help='number of color channels to use')
+parser.add_argument('--chop', action='store_true',
+                    help='enable memory-efficient forward')
+parser.add_argument('--no_augment', action='store_true',
+                    help='do not use data augmentation')
+
+# Model specifications
+parser.add_argument('--model', default='EWT',
+                    help='model name')
+
+parser.add_argument('--act', type=str, default='relu',
+                    help='activation function')
+parser.add_argument('--pre_train', type=str, default='',
+                    help='pre-trained model directory')
+parser.add_argument('--extend', type=str, default='.',
+                    help='pre-trained model directory')
+parser.add_argument('--n_resblocks', type=int, default=16,
+                    help='number of residual blocks')
+parser.add_argument('--n_feats', type=int, default=64,
+                    help='number of feature maps')
+parser.add_argument('--res_scale', type=float, default=1,
+                    help='residual scaling')
+parser.add_argument('--shift_mean', default=True,
+                    help='subtract pixel mean from the input')
+parser.add_argument('--dilation', action='store_true',
+                    help='use dilated convolution')
+parser.add_argument('--precision', type=str, default='single',
+                    choices=('single', 'half'),
+                    help='FP precision for test (single | half)')
+
+# Option for Residual dense network (RDN)
+parser.add_argument('--G0', type=int, default=64,
+                    help='default number of filters. (Use in RDN)')
+parser.add_argument('--RDNkSize', type=int, default=3,
+                    help='default kernel size. (Use in RDN)')
+parser.add_argument('--RDNconfig', type=str, default='B',
+                    help='parameters config of RDN. (Use in RDN)')
+
+# Option for Residual channel attention network (RCAN)
+parser.add_argument('--n_resgroups', type=int, default=10,
+                    help='number of residual groups')
+parser.add_argument('--reduction', type=int, default=16,
+                    help='number of feature maps reduction')
+
+# Training specifications
+parser.add_argument('--reset', action='store_true',
+                    help='reset the training')
+parser.add_argument('--test_every', type=int, default=1000,
+                    help='do test per every N batches')
+parser.add_argument('--epochs', type=int, default=300,
+                    help='number of epochs to train')
+parser.add_argument('--batch_size', type=int, default=16,
+                    help='input batch size for training')
+parser.add_argument('--split_batch', type=int, default=1,
+                    help='split the batch into smaller chunks')
+parser.add_argument('--self_ensemble', action='store_true',
+                    help='use self-ensemble method for test')
+parser.add_argument('--test_only', action='store_true',
+                    help='set this option to test the model')
+parser.add_argument('--gan_k', type=int, default=1,
+                    help='k value for adversarial loss')
+
+# Optimization specifications
+parser.add_argument('--lr', type=float, default=1e-4,
+                    help='learning rate')
+parser.add_argument('--decay', type=str, default='100',
+                    help='learning rate decay type')
+parser.add_argument('--gamma', type=float, default=0.5,
+                    help='learning rate decay factor for step decay')
+parser.add_argument('--optimizer', default='ADAM',
+                    choices=('SGD', 'ADAM', 'RMSprop'),
+                    help='optimizer to use (SGD | ADAM | RMSprop)')
+parser.add_argument('--momentum', type=float, default=0.9,
+                    help='SGD momentum')
+parser.add_argument('--betas', type=tuple, default=(0.9, 0.999),
+                    help='ADAM beta')
+parser.add_argument('--epsilon', type=float, default=1e-8,
+                    help='ADAM epsilon for numerical stability')
+parser.add_argument('--weight_decay', type=float, default=0,
+                    help='weight decay')
+parser.add_argument('--gclip', type=float, default=0,
+                    help='gradient clipping threshold (0 = no clipping)')
+
+# Loss specifications
+parser.add_argument('--loss', type=str, default='1*L1',
+                    help='loss function configuration')
+parser.add_argument('--skip_threshold', type=float, default='1e8',
+                    help='skipping batch that has large error')
+
+# Log specifications
+parser.add_argument('--save', type=str, default='test',
+                    help='file name to save')
+parser.add_argument('--load', type=str, default='',
+                    help='file name to load')
+parser.add_argument('--resume', type=int, default=0,
+                    help='resume from specific checkpoint')
+parser.add_argument('--save_models', action='store_true',
+                    help='save all intermediate models')
+parser.add_argument('--print_every', type=int, default=100,
+                    help='how many batches to wait before logging training status')
+parser.add_argument('--save_results', action='store_true',
+                    help='save output results')
+parser.add_argument('--save_gt', action='store_true',
+                    help='save low-resolution and high-resolution images together')
+
+args = parser.parse_args()
+template.set_template(args)
+
+args.scale = list(map(lambda x: int(x), args.scale.split('+')))
+args.data_train = args.data_train.split('+')
+args.data_test = args.data_test.split('+')
+
+if args.epochs == 0:
+    args.epochs = 1e8
+
+for arg in vars(args):
+    if vars(args)[arg] == 'True':
+        vars(args)[arg] = True
+    elif vars(args)[arg] == 'False':
+        vars(args)[arg] = False
\ No newline at end of file
diff --git a/src/template.py b/src/template.py
new file mode 100644
index 0000000000000000000000000000000000000000..6fdd020beae0e0ffd28e8fe6f7825cd533a3944b
--- /dev/null
+++ b/src/template.py
@@ -0,0 +1,52 @@
+def set_template(args):
+    # Set the templates here
+    if args.template.find('jpeg') >= 0:
+        args.data_train = 'DIV2K_jpeg'
+        args.data_test = 'DIV2K_jpeg'
+        args.epochs = 200
+        args.decay = '100'
+
+    if args.template.find('EDSR_paper') >= 0:
+        args.model = 'EDSR'
+        args.n_resblocks = 32
+        args.n_feats = 256
+        args.res_scale = 0.1
+
+    if args.template.find('MDSR') >= 0:
+        args.model = 'MDSR'
+        args.patch_size = 48
+        args.epochs = 650
+
+    if args.template.find('DDBPN') >= 0:
+        args.model = 'DDBPN'
+        args.patch_size = 128
+        args.scale = '4'
+
+        args.data_test = 'Set5'
+
+        args.batch_size = 20
+        args.epochs = 1000
+        args.decay = '500'
+        args.gamma = 0.1
+        args.weight_decay = 1e-4
+
+        args.loss = '1*MSE'
+
+    if args.template.find('GAN') >= 0:
+        args.epochs = 200
+        args.lr = 5e-5
+        args.decay = '150'
+
+    if args.template.find('RCAN') >= 0:
+        args.model = 'RCAN'
+        args.n_resgroups = 10
+        args.n_resblocks = 20
+        args.n_feats = 64
+        args.chop = True
+
+    if args.template.find('VDSR') >= 0:
+        args.model = 'VDSR'
+        args.n_resblocks = 20
+        args.n_feats = 64
+        args.patch_size = 41
+        args.lr = 1e-1
\ No newline at end of file
diff --git a/src/trainer.py b/src/trainer.py
new file mode 100644
index 0000000000000000000000000000000000000000..be35e47a1651917e44088271052e6215880dcd6c
--- /dev/null
+++ b/src/trainer.py
@@ -0,0 +1,167 @@
+import os
+import math
+from decimal import Decimal
+
+import utility
+import torch.nn as nn
+import torch
+import torch.nn.utils as utils
+from tqdm import tqdm
+
+
+os.environ["CUDA_VISIBLE_DEVICES"] = "0,1"
+
+class Trainer():
+    def __init__(self, args, loader, my_model, my_loss, ckp):
+        self.args = args
+        self.scale = args.scale
+        self.lr = args.lr
+
+        self.ckp = ckp
+        self.loader_train = loader.loader_train
+        self.loader_test = loader.loader_test
+        self.model = my_model
+        self.loss = my_loss
+        self.optimizer = utility.make_optimizer(args, self.model)
+
+        if self.args.load != '':
+            self.optimizer.load(ckp.dir, epoch=len(ckp.log))
+
+        self.error_last = 1e8
+
+    #     self.mp = nn.MaxPool2d(4, stride=4)
+    #     self.ap = nn.AvgPool2d(4, stride=4)
+    #     self.up = nn.Upsample(scale_factor=4, mode='bilinear', align_corners=False)
+    #
+    # def wave_detect(self, img):
+    #     img_ = self.mp(img) - self.ap(img)
+    #     return self.up(img_)
+
+    def train(self):
+        self.loss.step()
+        epoch = self.optimizer.get_last_epoch() + 1
+        #lr = self.optimizer.get_lr()
+
+        lr = self.lr * (0.5 ** (epoch // 100))
+
+        for param_group in self.optimizer.param_groups:
+            param_group["lr"] = lr
+
+
+        self.ckp.write_log(
+            '[Epoch {}]\tLearning rate: {:.2e}'.format(epoch, Decimal(lr))
+        )
+        self.loss.start_log()
+        self.model.train()
+
+        timer_data, timer_model = utility.timer(), utility.timer()
+        # TEMP
+        self.loader_train.dataset.set_scale(0)
+        for batch, (lr, edge, hr, _,) in enumerate(self.loader_train):
+            lr, edge, hr = self.prepare(lr, edge, hr)
+            timer_data.hold()
+            timer_model.tic()
+
+            self.optimizer.zero_grad()
+            sr =  self.model(torch.cat((lr, edge), dim=1), 0)
+
+            loss = self.loss(sr, hr)
+
+            loss.backward()
+            if self.args.gclip > 0:
+                utils.clip_grad_value_(
+                    self.model.parameters(),
+                    self.args.gclip
+                )
+            self.optimizer.step()
+
+            timer_model.hold()
+
+            if (batch + 1) % self.args.print_every == 0:
+                self.ckp.write_log('[{}/{}]\t{}\t{:.1f}+{:.1f}s'.format(
+                    (batch + 1) * self.args.batch_size,
+                    len(self.loader_train.dataset),
+                    self.loss.display_loss(batch),
+                    timer_model.release(),
+                    timer_data.release()))
+
+            timer_data.tic()
+
+        self.loss.end_log(len(self.loader_train))
+        self.error_last = self.loss.log[-1, -1]
+        self.optimizer.schedule()
+
+    def test(self):
+        torch.set_grad_enabled(False)
+
+        epoch = self.optimizer.get_last_epoch()
+        self.ckp.write_log('\nEvaluation:')
+        self.ckp.add_log(
+            torch.zeros(1, len(self.loader_test), len(self.scale))
+        )
+        self.model.eval()
+
+        timer_test = utility.timer()
+        if self.args.save_results: self.ckp.begin_background()
+        for idx_data, d in enumerate(self.loader_test):
+            for idx_scale, scale in enumerate(self.scale):
+                d.dataset.set_scale(idx_scale)
+                tqdm_test = tqdm(d, ncols=80)
+                for _, (lr, edge, hr, filename) in enumerate(tqdm_test):
+                    lr, edge, hr = self.prepare(lr, edge, hr)
+                    sr = self.model(torch.cat((lr, edge), dim=1), idx_scale)
+                    sr = utility.quantize(sr, self.args.rgb_range)
+
+                    save_list = [sr]
+                    self.ckp.log[-1, idx_data, idx_scale] += utility.calc_psnr(
+                        sr, hr, scale, self.args.rgb_range, dataset=d
+                    )
+
+                    if self.args.save_gt:
+                        save_list.extend([hr])
+
+                    if self.args.save_results:
+                        self.ckp.save_results(d, filename[0], save_list, scale)
+
+                self.ckp.log[-1, idx_data, idx_scale] /= len(d)
+                best = self.ckp.log.max(0)
+                self.ckp.write_log(
+                    '[{} x{}]\tPSNR: {:.3f} (Best: {:.3f} @epoch {})'.format(
+                        d.dataset.name,
+                        scale,
+                        self.ckp.log[-1, idx_data, idx_scale],
+                        best[0][idx_data, idx_scale],
+                        best[1][idx_data, idx_scale] + 1
+                    )
+                )
+
+        self.ckp.write_log('Forward: {:.2f}s\n'.format(timer_test.toc()))
+        self.ckp.write_log('Saving...')
+
+        if self.args.save_results:
+            self.ckp.end_background()
+
+        if not self.args.test_only:
+            self.ckp.save(self, epoch, is_best=(best[1][0, 0] + 1 == epoch))
+
+        self.ckp.write_log(
+            'Total: {:.2f}s\n'.format(timer_test.toc()), refresh=True
+        )
+
+        torch.set_grad_enabled(True)
+
+    def prepare(self, *args):
+        device = torch.device('cpu' if self.args.cpu else 'cuda')
+        def _prepare(tensor):
+            if self.args.precision == 'half': tensor = tensor.half()
+            return tensor.to(device)
+
+        return [_prepare(a) for a in args]
+
+    def terminate(self):
+        if self.args.test_only:
+            self.test()
+            return True
+        else:
+            epoch = self.optimizer.get_last_epoch() + 1
+            return epoch >= self.args.epochs
\ No newline at end of file
diff --git a/src/utility.py b/src/utility.py
new file mode 100644
index 0000000000000000000000000000000000000000..77b7c1597150fd0b5daf0f5ec0177f0b28bb9fc3
--- /dev/null
+++ b/src/utility.py
@@ -0,0 +1,247 @@
+import os
+import math
+import time
+import datetime
+from multiprocessing import Process
+from multiprocessing import Queue
+
+import matplotlib
+
+matplotlib.use('Agg')
+import matplotlib.pyplot as plt
+
+import numpy as np
+import imageio
+import cv2
+
+import torch
+import torch.optim as optim
+import torch.optim.lr_scheduler as lrs
+
+
+class timer():
+    def __init__(self):
+        self.acc = 0
+        self.tic()
+
+    def tic(self):
+        self.t0 = time.time()
+
+    def toc(self, restart=False):
+        diff = time.time() - self.t0
+        if restart: self.t0 = time.time()
+        return diff
+
+    def hold(self):
+        self.acc += self.toc()
+
+    def release(self):
+        ret = self.acc
+        self.acc = 0
+
+        return ret
+
+    def reset(self):
+        self.acc = 0
+
+
+class checkpoint():
+    def __init__(self, args):
+        self.args = args
+        self.ok = True
+        self.log = torch.Tensor()
+        now = datetime.datetime.now().strftime('%Y-%m-%d-%H:%M:%S')
+
+        if not args.load:
+            if not args.save:
+                args.save = now
+            self.dir = os.path.join('..', 'experiment', args.save)
+        else:
+            self.dir = os.path.join('..', 'experiment', args.load)
+            if os.path.exists(self.dir):
+                self.log = torch.load(self.get_path('psnr_log.pt'))
+                print('Continue from epoch {}...'.format(len(self.log)))
+            else:
+                args.load = ''
+
+        if args.reset:
+            os.system('rm -rf ' + self.dir)
+            args.load = ''
+
+        os.makedirs(self.dir, exist_ok=True)
+        os.makedirs(self.get_path('model'), exist_ok=True)
+        for d in args.data_test:
+            os.makedirs(self.get_path('results-{}'.format(d)), exist_ok=True)
+
+        open_type = 'a' if os.path.exists(self.get_path('log.txt')) else 'w'
+        self.log_file = open(self.get_path('log.txt'), open_type)
+        with open(self.get_path('config.txt'), open_type) as f:
+            f.write(now + '\n\n')
+            for arg in vars(args):
+                f.write('{}: {}\n'.format(arg, getattr(args, arg)))
+            f.write('\n')
+
+        self.n_processes = 8
+
+    def get_path(self, *subdir):
+        return os.path.join(self.dir, *subdir)
+
+    def save(self, trainer, epoch, is_best=False):
+        trainer.model.save(self.get_path('model'), epoch, is_best=is_best)
+        trainer.loss.save(self.dir)
+        trainer.loss.plot_loss(self.dir, epoch)
+
+        self.plot_psnr(epoch)
+        trainer.optimizer.save(self.dir)
+        torch.save(self.log, self.get_path('psnr_log.pt'))
+
+    def add_log(self, log):
+        self.log = torch.cat([self.log, log])
+
+    def write_log(self, log, refresh=False):
+        print(log)
+        self.log_file.write(log + '\n')
+        if refresh:
+            self.log_file.close()
+            self.log_file = open(self.get_path('log.txt'), 'a')
+
+    def done(self):
+        self.log_file.close()
+
+    def plot_psnr(self, epoch):
+        axis = np.linspace(1, epoch, epoch)
+        for idx_data, d in enumerate(self.args.data_test):
+            label = 'SR on {}'.format(d)
+            fig = plt.figure()
+            plt.title(label)
+            for idx_scale, scale in enumerate(self.args.scale):
+                plt.plot(
+                    axis,
+                    self.log[:, idx_data, idx_scale].numpy(),
+                    label='Scale {}'.format(scale)
+                )
+            plt.legend()
+            plt.xlabel('Epochs')
+            plt.ylabel('PSNR')
+            plt.grid(True)
+            plt.savefig(self.get_path('test_{}.pdf'.format(d)))
+            plt.close(fig)
+
+    def begin_background(self):
+        self.queue = Queue()
+
+        def bg_target(queue):
+            while True:
+                if not queue.empty():
+                    filename, tensor = queue.get()
+                    if filename is None: break
+                    cv2.imwrite(filename, cv2.cvtColor( (tensor.numpy()).astype(np.uint8), cv2.COLOR_RGB2BGR))
+
+        self.process = [
+            Process(target=bg_target, args=(self.queue,)) \
+            for _ in range(self.n_processes)
+        ]
+
+        for p in self.process: p.start()
+
+    def end_background(self):
+        for _ in range(self.n_processes): self.queue.put((None, None))
+        while not self.queue.empty(): time.sleep(1)
+        for p in self.process: p.join()
+
+    def save_results(self, dataset, filename, save_list, scale):
+        if self.args.save_results:
+            filename = self.get_path(
+                'results-{}'.format(dataset.dataset.name),
+                # '{}_DS_'.format(filename)
+                '{}'.format(filename)
+            )
+
+            postfix = ('SMGARN', 'GT')
+            for v, p in zip(save_list, postfix):
+                normalized_sr = v[0].mul(255 / self.args.rgb_range)
+                tensor_cpu_sr = normalized_sr.byte().permute(1, 2, 0).cpu()
+                # self.queue.put(('{}{}.tif'.format(filename, p), tensor_cpu_sr))
+                # self.queue.put(('{}{}.jpg'.format(filename, p), tensor_cpu_sr))
+                self.queue.put(('{}.jpg'.format(filename), tensor_cpu_sr))
+
+
+def quantize(img, rgb_range):
+    pixel_range = 255 / rgb_range
+    return img.mul(pixel_range).clamp(0, 255).round().div(pixel_range)
+
+
+def calc_psnr(sr, hr, scale, rgb_range, dataset=None):
+    if hr.nelement() == 1: return 0
+
+    diff = (sr - hr) / rgb_range
+    if dataset and dataset.dataset.benchmark:
+        shave = scale
+        if diff.size(1) > 1:
+            gray_coeffs = [65.738, 129.057, 25.064]
+            convert = diff.new_tensor(gray_coeffs).view(1, 3, 1, 1) / 256
+            diff = diff.mul(convert).sum(dim=1)
+    else:
+        shave = scale + 6
+
+    # valid = diff
+    valid = diff[..., shave:-shave, shave:-shave]
+    mse = valid.pow(2).mean()
+
+    return -10 * math.log10(mse)
+
+
+def make_optimizer(args, target):
+    '''
+        make optimizer and scheduler together
+    '''
+    # optimizer
+    trainable = filter(lambda x: x.requires_grad, target.parameters())
+    kwargs_optimizer = {'lr': args.lr, 'weight_decay': args.weight_decay}
+
+    if args.optimizer == 'SGD':
+        optimizer_class = optim.SGD
+        kwargs_optimizer['momentum'] = args.momentum
+    elif args.optimizer == 'ADAM':
+        optimizer_class = optim.Adam
+        kwargs_optimizer['betas'] = args.betas
+        kwargs_optimizer['eps'] = args.epsilon
+    elif args.optimizer == 'RMSprop':
+        optimizer_class = optim.RMSprop
+        kwargs_optimizer['eps'] = args.epsilon
+
+    # scheduler
+    milestones = list(map(lambda x: int(x), args.decay.split('-')))
+    kwargs_scheduler = {'milestones': milestones, 'gamma': args.gamma}
+    scheduler_class = lrs.MultiStepLR
+
+    class CustomOptimizer(optimizer_class):
+        def __init__(self, *args, **kwargs):
+            super(CustomOptimizer, self).__init__(*args, **kwargs)
+
+        def _register_scheduler(self, scheduler_class, **kwargs):
+            self.scheduler = scheduler_class(self, **kwargs)
+
+        def save(self, save_dir):
+            torch.save(self.state_dict(), self.get_dir(save_dir))
+
+        def load(self, load_dir, epoch=1):
+            self.load_state_dict(torch.load(self.get_dir(load_dir)))
+            if epoch > 1:
+                for _ in range(epoch): self.scheduler.step()
+
+        def get_dir(self, dir_path):
+            return os.path.join(dir_path, 'optimizer.pt')
+
+        def schedule(self):
+            self.scheduler.step()
+
+        def get_lr(self):
+            return self.scheduler.get_lr()[0]
+
+        def get_last_epoch(self):
+            return self.scheduler.last_epoch
+
+    optimizer = CustomOptimizer(trainable, **kwargs_optimizer)
+    optimizer._register_scheduler(scheduler_class, **kwargs_scheduler)
+    return optimizer
\ No newline at end of file
diff --git a/src/videotester.py b/src/videotester.py
new file mode 100644
index 0000000000000000000000000000000000000000..d94bd84dbea3626a2fec7818db238ca063a9f660
--- /dev/null
+++ b/src/videotester.py
@@ -0,0 +1,72 @@
+import os
+import math
+
+import utility
+from data import common
+
+import torch
+import cv2
+
+from tqdm import tqdm
+
+class VideoTester():
+    def __init__(self, args, my_model, ckp):
+        self.args = args
+        self.scale = args.scale
+
+        self.ckp = ckp
+        self.model = my_model
+
+        self.filename, _ = os.path.splitext(os.path.basename(args.dir_demo))
+
+    def test(self):
+        torch.set_grad_enabled(False)
+
+        self.ckp.write_log('\nEvaluation on video:')
+        self.model.eval()
+
+        timer_test = utility.timer()
+        for idx_scale, scale in enumerate(self.scale):
+            vidcap = cv2.VideoCapture(self.args.dir_demo)
+            total_frames = int(vidcap.get(cv2.CAP_PROP_FRAME_COUNT))
+            vidwri = cv2.VideoWriter(
+                self.ckp.get_path('{}_x{}.avi'.format(self.filename, scale)),
+                cv2.VideoWriter_fourcc(*'XVID'),
+                vidcap.get(cv2.CAP_PROP_FPS),
+                (
+                    int(scale * vidcap.get(cv2.CAP_PROP_FRAME_WIDTH)),
+                    int(scale * vidcap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+                )
+            )
+
+            tqdm_test = tqdm(range(total_frames), ncols=80)
+            for _ in tqdm_test:
+                success, lr = vidcap.read()
+                if not success: break
+
+                lr, = common.set_channel(lr, n_channels=self.args.n_colors)
+                lr, = common.np2Tensor(lr, rgb_range=self.args.rgb_range)
+                lr, = self.prepare(lr.unsqueeze(0))
+                sr = self.model(lr, idx_scale)
+                sr = utility.quantize(sr, self.args.rgb_range).squeeze(0)
+
+                normalized = sr * 255 / self.args.rgb_range
+                ndarr = normalized.byte().permute(1, 2, 0).cpu().numpy()
+                vidwri.write(ndarr)
+
+            vidcap.release()
+            vidwri.release()
+
+        self.ckp.write_log(
+            'Total: {:.2f}s\n'.format(timer_test.toc()), refresh=True
+        )
+        torch.set_grad_enabled(True)
+
+    def prepare(self, *args):
+        device = torch.device('cpu' if self.args.cpu else 'cuda')
+        def _prepare(tensor):
+            if self.args.precision == 'half': tensor = tensor.half()
+            return tensor.to(device)
+
+        return [_prepare(a) for a in args]
+