UGATIT pipeline

configs/synthesizers/UGATIT-VoxCeleb2Anime.yml

@@ -0,0 +1,129 @@
+name: VoxCeleb2Anime
+engine: UGATIT
+result_dir: ./result
+max_pairs: 1000000
+
+distributed:
+  model:
+  # broadcast_buffers: False
+
+misc:
+  random_seed: 324
+
+checkpoint:
+  epoch_interval: 1 # one checkpoint every 1 epoch
+  n_saved: 2
+
+interval:
+  print_per_iteration: 10 # print once per 10 iteration
+  tensorboard:
+    scalar: 10
+    image: 500
+
+model:
+  generator:
+    _type: UGATIT-Generator
+    in_channels: 3
+    out_channels: 3
+    base_channels: 64
+    num_blocks: 4
+    img_size: 128
+    light: True
+  local_discriminator:
+    _type: UGATIT-Discriminator
+    in_channels: 3
+    base_channels: 64
+    num_blocks: 5
+  global_discriminator:
+    _type: UGATIT-Discriminator
+    in_channels: 3
+    base_channels: 64
+    num_blocks: 7
+
+loss:
+  gan:
+    loss_type: lsgan
+    weight: 1.0
+    real_label_val: 1.0
+    fake_label_val: 0.0
+  cycle:
+    level: 1
+    weight: 10.0
+  id:
+    level: 1
+    weight: 10.0
+  cam:
+    weight: 1000
+
+optimizers:
+  generator:
+    _type: Adam
+    lr: 0.0001
+    betas: [ 0.5, 0.999 ]
+    weight_decay: 0.0001
+  discriminator:
+    _type: Adam
+    lr: 1e-4
+    betas: [ 0.5, 0.999 ]
+    weight_decay: 0.0001
+
+data:
+  train:
+    scheduler:
+      start_proportion: 0.5
+      target_lr: 0
+    buffer_size: 50
+    dataloader:
+      batch_size: 20
+      shuffle: True
+      num_workers: 2
+      pin_memory: True
+      drop_last: True
+    dataset:
+      _type: GenerationUnpairedDataset
+      root_a: "/data/i2i/VoxCeleb2Anime/trainA"
+      root_b: "/data/i2i/VoxCeleb2Anime/trainB"
+      random_pair: True
+      pipeline:
+        - Load
+        - Resize:
+            size: [ 135, 135 ]
+        - RandomCrop:
+            size: [ 128, 128 ]
+        - RandomHorizontalFlip
+        - ToTensor
+        - Normalize:
+            mean: [ 0.5, 0.5, 0.5 ]
+            std: [ 0.5, 0.5, 0.5 ]
+  test:
+    dataloader:
+      batch_size: 8
+      shuffle: False
+      num_workers: 1
+      pin_memory: False
+      drop_last: False
+    dataset:
+      _type: GenerationUnpairedDataset
+      root_a: "/data/i2i/VoxCeleb2Anime/testA"
+      root_b: "/data/i2i/VoxCeleb2Anime/testB"
+      random_pair: False
+      pipeline:
+        - Load
+        - Resize:
+            size: [ 128, 128 ]
+        - ToTensor
+        - Normalize:
+            mean: [ 0.5, 0.5, 0.5 ]
+            std: [ 0.5, 0.5, 0.5 ]
+    video_dataset:
+      _type: SingleFolderDataset
+      root: "/data/i2i/VoxCeleb2Anime/test_video_frames/"
+      with_path: True
+      pipeline:
+        - Load
+        - Resize:
+            size: [ 128, 128 ]
+        - ToTensor
+        - Normalize:
+            mean: [ 0.5, 0.5, 0.5 ]
+            std: [ 0.5, 0.5, 0.5 ]

configs/synthesizers/UGATIT.yml

@@ -115,3 +115,15 @@ data:
         - Normalize:
             mean: [0.5, 0.5, 0.5]
             std: [0.5, 0.5, 0.5]
+    video_dataset:
+      _type: SingleFolderDataset
+      root: "/data/i2i/VoxCeleb2Anime/test_video_frames/"
+      with_path: True
+      pipeline:
+        - Load
+        - Resize:
+            size: [ 256, 256 ]
+        - ToTensor
+        - Normalize:
+            mean: [ 0.5, 0.5, 0.5 ]
+            std: [ 0.5, 0.5, 0.5 ]