firstorder_vox_mobile_256.yaml 2.6 KB
Newer Older
L
lzzyzlbb 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130
epochs: 100
output_dir: output_dir

dataset:
  train:
    name: FirstOrderDataset
    batch_size: 1
    num_workers: 1
    use_shared_memory: False
    phase: train
    dataroot: data/first_order/Voxceleb/
    frame_shape: [256, 256, 3]
    id_sampling: True
    pairs_list: None
    time_flip: True
    num_repeats: 75
    create_frames_folder: False
    transforms:
      - name: PairedRandomHorizontalFlip
        prob: 0.5
        keys: [image, image]
      - name: PairedColorJitter
        brightness: 0.1
        contrast: 0.1
        saturation: 0.1
        hue: 0.1
        keys: [image, image]
  test:
    name: FirstOrderDataset
    dataroot: data/first_order/Voxceleb/
    phase: test
    batch_size: 1
    num_workers: 1
    time_flip: False
    id_sampling: False
    create_frames_folder: False
    frame_shape: [ 256, 256, 3 ]


model:
  name: FirstOrderModel
  common_params:
    num_kp: 10
    num_channels: 3
    estimate_jacobian: True
  generator:
    name: FirstOrderGenerator
    kp_detector_cfg:
      temperature: 0.1
      block_expansion: 32
      max_features: 256
      scale_factor: 0.25
      num_blocks: 5
      mobile_net: True
    generator_cfg:
      block_expansion: 32
      max_features: 256
      num_down_blocks: 2
      num_bottleneck_blocks: 6
      estimate_occlusion_map: True
      dense_motion_params:
        block_expansion: 32
        max_features: 256
        num_blocks: 5
        scale_factor: 0.25
      mobile_net: True
  discriminator:
    name: FirstOrderDiscriminator
    discriminator_cfg:
      scales: [1]
      block_expansion: 32
      max_features: 512
      num_blocks: 4
      sn: True
  train_params:
    num_epochs: 100
    scales: [1, 0.5, 0.25, 0.125]
    checkpoint_freq: 50
    transform_params:
      sigma_affine: 0.05
      sigma_tps: 0.005
      points_tps: 5
    loss_weights:
      generator_gan: 1
      discriminator_gan: 1
      feature_matching: [10, 10, 10, 10]
      perceptual: [10, 10, 10, 10, 10]
      equivariance_value: 10
      equivariance_jacobian: 10

lr_scheduler:
  name: MultiStepDecay
  epoch_milestones: [237360, 356040]
  lr_generator: 2.0e-4
  lr_discriminator: 2.0e-4
  lr_kp_detector: 2.0e-4

reconstruction_params:
  num_videos: 1000
  format: '.mp4'

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

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

log_config:
  interval: 10
  visiual_interval: 10

validate:
  interval: 3000
  save_img: true

snapshot_config:
  interval: 1

optimizer:
  name: Adam

export_model:
  - {}