Update app.py

app.py

@@ -5,126 +5,107 @@ import torch
 from basicsr.archs.srvgg_arch import SRVGGNetCompact
 from gfpgan.utils import GFPGANer
 from realesrgan.utils import RealESRGANer
-import spaces
 
-# Ensure weights directory
-WEIGHTS_DIR = "weights"
-os.makedirs(WEIGHTS_DIR, exist_ok=True)
-
-# List of required model weights
-weights = {
-    'realesr-general-x4v3.pth': 'https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth',
-    'GFPGANv1.2.pth': 'https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.2.pth',
-    'GFPGANv1.3.pth': 'https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth',
-    'GFPGANv1.4.pth': 'https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth',
-    'RestoreFormer.pth': 'https://github.com/TencentARC/GFPGAN/releases/download/v1.3.4/RestoreFormer.pth',
-    'CodeFormer.pth': 'https://github.com/TencentARC/GFPGAN/releases/download/v1.3.4/CodeFormer.pth'
-}
-
-# Download missing weights
-for file_name, url in weights.items():
-    file_path = os.path.join(WEIGHTS_DIR, file_name)
-    if not os.path.exists(file_path):
-        os.system(f"wget -O {file_path} {url}")
-
-# Load Real-ESRGAN model
+os.system("pip freeze")
+# download weights
+if not os.path.exists('realesr-general-x4v3.pth'):
+    os.system("wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth -P .")
+if not os.path.exists('GFPGANv1.2.pth'):
+    os.system("wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.2.pth -P .")
+if not os.path.exists('GFPGANv1.3.pth'):
+    os.system("wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth -P .")
+if not os.path.exists('GFPGANv1.4.pth'):
+    os.system("wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth -P .")
+if not os.path.exists('RestoreFormer.pth'):
+    os.system("wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.4/RestoreFormer.pth -P .")
+if not os.path.exists('CodeFormer.pth'):
+    os.system("wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.4/CodeFormer.pth -P .")
+
+
+# background enhancer with RealESRGAN
 model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=32, upscale=4, act_type='prelu')
-model_path = os.path.join(WEIGHTS_DIR, 'realesr-general-x4v3.pth')
-half = torch.cuda.is_available()
-
-upsampler = RealESRGANer(
-    scale=4,
-    model_path=model_path,
-    model=model,
-    tile=0,
-    tile_pad=10,
-    pre_pad=0,
-    half=half
-)
+model_path = 'realesr-general-x4v3.pth'
+half = True if torch.cuda.is_available() else False
+upsampler = RealESRGANer(scale=4, model_path=model_path, model=model, tile=0, tile_pad=10, pre_pad=0, half=half)
 
 os.makedirs('output', exist_ok=True)
 
-@spaces.GPU(enable_queue=True)
+
+# def inference(img, version, scale, weight):
 def inference(img, version, scale):
     print(img, version, scale)
     if scale > 4:
         scale = 4
-
     try:
         extension = os.path.splitext(os.path.basename(str(img)))[1]
         img = cv2.imread(img, cv2.IMREAD_UNCHANGED)
-
         if len(img.shape) == 3 and img.shape[2] == 4:
             img_mode = 'RGBA'
         elif len(img.shape) == 2:
-            img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
             img_mode = None
+            img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
         else:
             img_mode = None
 
-        h, w = img.shape[:2]
+        h, w = img.shape[0:2]
         if h > 3500 or w > 3500:
             print('too large size')
             return None, None
-
+        
         if h < 300:
             img = cv2.resize(img, (w * 2, h * 2), interpolation=cv2.INTER_LANCZOS4)
 
-        model_path_map = {
-            'v1.2': os.path.join(WEIGHTS_DIR, 'GFPGANv1.2.pth'),
-            'v1.3': os.path.join(WEIGHTS_DIR, 'GFPGANv1.3.pth'),
-            'v1.4': os.path.join(WEIGHTS_DIR, 'GFPGANv1.4.pth'),
-            'RestoreFormer': os.path.join(WEIGHTS_DIR, 'RestoreFormer.pth')
-        }
-
-        arch_map = {
-            'v1.2': 'clean',
-            'v1.3': 'clean',
-            'v1.4': 'clean',
-            'RestoreFormer': 'RestoreFormer'
-        }
-
-        face_enhancer = GFPGANer(
-            model_path=model_path_map[version],
-            upscale=2,
-            arch=arch_map[version],
-            channel_multiplier=2,
-            bg_upsampler=upsampler
-        )
-
-        _, _, output = face_enhancer.enhance(img, has_aligned=False, only_center_face=False, paste_back=True)
-
-        if scale != 2:
-            interpolation = cv2.INTER_AREA if scale < 2 else cv2.INTER_LANCZOS4
-            h, w = img.shape[:2]
-            output = cv2.resize(output, (int(w * scale / 2), int(h * scale / 2)), interpolation=interpolation)
-
-        extension = 'png' if img_mode == 'RGBA' else 'jpg'
+        if version == 'v1.2':
+            face_enhancer = GFPGANer(
+            model_path='GFPGANv1.2.pth', upscale=2, arch='clean', channel_multiplier=2, bg_upsampler=upsampler)
+        elif version == 'v1.3':
+            face_enhancer = GFPGANer(
+            model_path='GFPGANv1.3.pth', upscale=2, arch='clean', channel_multiplier=2, bg_upsampler=upsampler)
+        elif version == 'v1.4':
+            face_enhancer = GFPGANer(
+            model_path='GFPGANv1.4.pth', upscale=2, arch='clean', channel_multiplier=2, bg_upsampler=upsampler)
+        elif version == 'RestoreFormer':
+            face_enhancer = GFPGANer(
+            model_path='RestoreFormer.pth', upscale=2, arch='RestoreFormer', channel_multiplier=2, bg_upsampler=upsampler)
+
+        try:
+            _, _, output = face_enhancer.enhance(img, has_aligned=False, only_center_face=False, paste_back=True)
+        except RuntimeError as error:
+            print('Error', error)
+
+        try:
+            if scale != 2:
+                interpolation = cv2.INTER_AREA if scale < 2 else cv2.INTER_LANCZOS4
+                h, w = img.shape[0:2]
+                output = cv2.resize(output, (int(w * scale / 2), int(h * scale / 2)), interpolation=interpolation)
+        except Exception as error:
+            print('wrong scale input.', error)
+        if img_mode == 'RGBA':
+            extension = 'png'
+        else:
+            extension = 'jpg'
         save_path = f'output/out.{extension}'
         cv2.imwrite(save_path, output)
 
         output = cv2.cvtColor(output, cv2.COLOR_BGR2RGB)
         return output, save_path
-
     except Exception as error:
         print('global exception', error)
         return None, None
 
-description = "⚠ Sorry for the inconvenience. The Space is currently running on the CPU, which might affect performance. We appreciate your understanding."
+
+description = r""" """
 
 demo = gr.Interface(
-    fn=inference,
-    inputs=[
+    inference, [
         gr.Image(type="filepath", label="Input"),
         gr.Radio(['v1.2', 'v1.3', 'v1.4', 'RestoreFormer'], type="value", value='v1.4', label='version'),
-        gr.Number(label="Rescaling factor", value=2)
-    ],
-    outputs=[
+        gr.Number(label="Rescaling factor", value=2),
+    ], [
         gr.Image(type="numpy", label="Output (The whole image)"),
         gr.File(label="Download the output image")
     ],
     description=description,
-    theme="Yntec/HaleyCH_Theme_Orange"
-)
 
-demo.queue(max_size=50).launch()
+)
+demo.queue().launch()