config/vox-256.yaml

dataset_params:
  root_dir: /data/lh/repo/datasets/face-video-preprocessing/vox-png
  frame_shape: [256, 256, 3]
  id_sampling: True
  pairs_list: data/vox256.csv
  augmentation_params:
    flip_param:
      horizontal_flip: True
      time_flip: True
    jitter_param:
      brightness: 0.1
      contrast: 0.1
      saturation: 0.1
      hue: 0.1


model_params:
  common_params:
    num_kp: 10
    num_channels: 3
    estimate_jacobian: True
  kp_detector_params:
     temperature: 0.1
     block_expansion: 32
     max_features: 1024
     scale_factor: 0.25
     num_blocks: 5
  generator_params:
    block_expansion: 64
    max_features: 512
    num_down_blocks: 2
    num_bottleneck_blocks: 6
    estimate_occlusion_map: True
    dense_motion_params:
      block_expansion: 64
      max_features: 1024
      num_blocks: 5
      scale_factor: 0.25
    render_params:
      simpled_channel_rgb: 128
      simpled_channel_sigma: 128
      floor_num: 8
      hidden_size: 128
  discriminator_params:
    scales: [1]
    block_expansion: 32
    max_features: 512
    num_blocks: 4
    sn: True

train_params:
  num_epochs: 100
  num_repeats: 75
  epoch_milestones: [60, 90]
  lr_generator: 2.0e-4
  lr_discriminator: 2.0e-4
  lr_kp_detector: 2.0e-4
  lr_face_editor: 2.0e-4
  # batch_size: 40
  batch_size: 20
  scales: [1, 0.5, 0.25, 0.125]
  # checkpoint_freq: 75
  checkpoint_freq: 10
  transform_params:
    sigma_affine: 0.05
    sigma_tps: 0.005
    points_tps: 5
  loss_weights:
    generator_gan: 1  # 0
    discriminator_gan: 1
    feature_matching: [10, 10, 10, 10]
    perceptual: [10, 10, 10, 10, 10]
    equivariance_value: 10
    equivariance_jacobian: 10
    perceptual_l1: 5
    pose_edit: 1

reconstruction_params:
  num_videos: 1000
  format: '.mp4'

animate_params:
  num_pairs: 50
  format: '.mp4'
  normalization_params:
    adapt_movement_scale: True
    use_relative_movement: True
    use_relative_jacobian: True

visualizer_params:
  kp_size: 5
  draw_border: True
  colormap: 'gist_rainbow'