Upload folder using huggingface_hub

2024-06-24-21-18/training.log

@@ -0,0 +1,247 @@
+trainer:
+  target: trainer.TrainerDifIR
+model:
+  target: models.unet.UNetModelSwin
+  ckpt_path: null
+  params:
+    image_size: 64
+    in_channels: 3
+    model_channels: 160
+    out_channels: 3
+    attention_resolutions:
+    - 64
+    - 32
+    - 16
+    - 8
+    dropout: 0
+    channel_mult:
+    - 1
+    - 2
+    - 2
+    - 4
+    num_res_blocks:
+    - 2
+    - 2
+    - 2
+    - 2
+    conv_resample: true
+    dims: 2
+    use_fp16: false
+    num_head_channels: 32
+    use_scale_shift_norm: true
+    resblock_updown: false
+    swin_depth: 2
+    swin_embed_dim: 192
+    window_size: 8
+    mlp_ratio: 4
+    cond_lq: true
+    lq_size: 64
+diffusion:
+  target: models.script_util.create_gaussian_diffusion
+  params:
+    sf: 4
+    schedule_name: exponential
+    schedule_kwargs:
+      power: 0.3
+    etas_end: 0.99
+    steps: 15
+    min_noise_level: 0.04
+    kappa: 2.0
+    weighted_mse: false
+    predict_type: xstart
+    timestep_respacing: null
+    scale_factor: 1.0
+    normalize_input: true
+    latent_flag: true
+autoencoder:
+  target: ldm.models.autoencoder.VQModelTorch
+  ckpt_path: weights/autoencoder_vq_f4.pth
+  use_fp16: true
+  params:
+    embed_dim: 3
+    n_embed: 8192
+    ddconfig:
+      double_z: false
+      z_channels: 3
+      resolution: 256
+      in_channels: 3
+      out_ch: 3
+      ch: 128
+      ch_mult:
+      - 1
+      - 2
+      - 4
+      num_res_blocks: 2
+      attn_resolutions: []
+      dropout: 0.0
+      padding_mode: zeros
+degradation:
+  sf: 4
+  resize_prob:
+  - 0.2
+  - 0.7
+  - 0.1
+  resize_range:
+  - 0.15
+  - 1.5
+  gaussian_noise_prob: 0.5
+  noise_range:
+  - 1
+  - 30
+  poisson_scale_range:
+  - 0.05
+  - 3.0
+  gray_noise_prob: 0.4
+  jpeg_range:
+  - 30
+  - 95
+  second_order_prob: 0.5
+  second_blur_prob: 0.8
+  resize_prob2:
+  - 0.3
+  - 0.4
+  - 0.3
+  resize_range2:
+  - 0.3
+  - 1.2
+  gaussian_noise_prob2: 0.5
+  noise_range2:
+  - 1
+  - 25
+  poisson_scale_range2:
+  - 0.05
+  - 2.5
+  gray_noise_prob2: 0.4
+  jpeg_range2:
+  - 30
+  - 95
+  gt_size: 256
+  resize_back: false
+  use_sharp: false
+data:
+  train:
+    type: realesrgan
+    params:
+      dir_paths: []
+      txt_file_path:
+      - /content/ResShift/high_res/train.txt
+      im_exts:
+      - JPEG
+      io_backend:
+        type: disk
+      blur_kernel_size: 21
+      kernel_list:
+      - iso
+      - aniso
+      - generalized_iso
+      - generalized_aniso
+      - plateau_iso
+      - plateau_aniso
+      kernel_prob:
+      - 0.45
+      - 0.25
+      - 0.12
+      - 0.03
+      - 0.12
+      - 0.03
+      sinc_prob: 0.1
+      blur_sigma:
+      - 0.2
+      - 3.0
+      betag_range:
+      - 0.5
+      - 4.0
+      betap_range:
+      - 1
+      - 2.0
+      blur_kernel_size2: 15
+      kernel_list2:
+      - iso
+      - aniso
+      - generalized_iso
+      - generalized_aniso
+      - plateau_iso
+      - plateau_aniso
+      kernel_prob2:
+      - 0.45
+      - 0.25
+      - 0.12
+      - 0.03
+      - 0.12
+      - 0.03
+      sinc_prob2: 0.1
+      blur_sigma2:
+      - 0.2
+      - 1.5
+      betag_range2:
+      - 0.5
+      - 4.0
+      betap_range2:
+      - 1
+      - 2.0
+      final_sinc_prob: 0.8
+      gt_size: 256
+      crop_pad_size: 300
+      use_hflip: true
+      use_rot: false
+      rescale_gt: true
+  val:
+    type: base
+    params:
+      dir_path: testdata/Val_SR/lq
+      im_exts: png
+      transform_type: default
+      transform_kwargs:
+        mean: 0.5
+        std: 0.5
+      extra_dir_path: testdata/Val_SR/gt
+      extra_transform_type: default
+      extra_transform_kwargs:
+        mean: 0.5
+        std: 0.5
+      recursive: false
+train:
+  lr: 5.0e-05
+  lr_min: 2.0e-05
+  lr_schedule: null
+  warmup_iterations: 100
+  batch:
+  - 8
+  - 1
+  microbatch: 1
+  num_workers: 4
+  prefetch_factor: 2
+  weight_decay: 0
+  ema_rate: 0.999
+  iterations: 1000
+  save_freq: 10000
+  log_freq:
+  - 200
+  - 2000
+  - 1
+  local_logging: true
+  tf_logging: false
+  use_ema_val: true
+  val_freq: ${train.save_freq}
+  val_y_channel: true
+  val_resolution: ${model.params.lq_size}
+  val_padding_mode: reflect
+  use_amp: true
+  seed: 123456
+  global_seeding: false
+  compile:
+    flag: false
+    mode: reduce-overhead
+save_dir: logging/
+resume: ''
+cfg_path: configs/realsr_swinunet_realesrgan256.yaml
+
+Number of parameters: 118.59M
+Restoring autoencoder from weights/autoencoder_vq_f4.pth
+Number of images in train data set: 1254
+Number of images in val data set: 32
+Train: 000200/001000, Loss/MSE: t(1):1.6e-01/1.6e-01, t(8):4.5e-01/4.5e-01, t(15):5.9e-01/5.9e-01, lr:5.00e-05
+Train: 000400/001000, Loss/MSE: t(1):2.8e-02/2.8e-02, t(8):3.9e-01/3.9e-01, t(15):5.0e-01/5.0e-01, lr:5.00e-05
+Train: 000600/001000, Loss/MSE: t(1):2.1e-02/2.1e-02, t(8):3.4e-01/3.4e-01, t(15):4.6e-01/4.6e-01, lr:5.00e-05
+Train: 000800/001000, Loss/MSE: t(1):1.4e-02/1.4e-02, t(8):3.5e-01/3.5e-01, t(15):5.1e-01/5.1e-01, lr:5.00e-05
+Train: 001000/001000, Loss/MSE: t(1):1.4e-02/1.4e-02, t(8):2.9e-01/2.9e-01, t(15):4.6e-01/4.6e-01, lr:5.00e-05