options/CodeFormer_colorization.yml

# general settings
name: CodeFormer_colorization
model_type: CodeFormerIdxModel
num_gpu: 8
manual_seed: 0

# dataset and data loader settings
datasets:
  train:
    name: FFHQ
    type: FFHQBlindDataset
    dataroot_gt: datasets/ffhq/ffhq_512
    filename_tmpl: '{}'
    io_backend:
      type: disk

    in_size: 512
    gt_size: 512
    mean: [0.5, 0.5, 0.5]
    std: [0.5, 0.5, 0.5]
    use_hflip: true
    use_corrupt: true

    # large degradation in stageII
    blur_kernel_size: 41
    use_motion_kernel: false
    motion_kernel_prob: 0.001
    kernel_list: ['iso', 'aniso']
    kernel_prob: [0.5, 0.5]
    blur_sigma: [1, 15]
    downsample_range: [4, 30]
    noise_range: [0, 20]
    jpeg_range: [30, 80]

    # color jitter and gray
    color_jitter_prob: 0.3
    color_jitter_shift: 20
    color_jitter_pt_prob: 0.3
    gray_prob: 0.01

    latent_gt_path: ~ # without pre-calculated latent code
    # latent_gt_path: './experiments/pretrained_models/VQGAN/latent_gt_code1024.pth'

    # data loader
    num_worker_per_gpu: 2
    batch_size_per_gpu: 4
    dataset_enlarge_ratio: 100
    prefetch_mode: ~

  # val:
  #   name: CelebA-HQ-512
  #   type: PairedImageDataset
  #   dataroot_lq: datasets/faces/validation/lq
  #   dataroot_gt: datasets/faces/validation/gt
  #   io_backend:
  #     type: disk
  #   mean: [0.5, 0.5, 0.5]
  #   std: [0.5, 0.5, 0.5]
  #   scale: 1
    
# network structures
network_g:
  type: CodeFormer
  dim_embd: 512
  n_head: 8
  n_layers: 9
  codebook_size: 1024
  connect_list: ['32', '64', '128', '256']
  fix_modules: ['quantize','generator']
  vqgan_path: './experiments/pretrained_models/vqgan/vqgan_code1024.pth' # pretrained VQGAN 

network_vqgan: # this config is needed if no pre-calculated latent
  type: VQAutoEncoder
  img_size: 512
  nf: 64
  ch_mult: [1, 2, 2, 4, 4, 8]
  quantizer: 'nearest'
  codebook_size: 1024

# path
path:
  pretrain_network_g: ~
  param_key_g: params_ema
  strict_load_g: false
  pretrain_network_d: ~
  strict_load_d: true
  resume_state: ~

# base_lr(4.5e-6)*bach_size(4)
train:
  use_hq_feat_loss: true
  feat_loss_weight: 1.0
  cross_entropy_loss: true
  entropy_loss_weight: 0.5
  fidelity_weight: 0

  optim_g:
    type: Adam
    lr: !!float 1e-4
    weight_decay: 0
    betas: [0.9, 0.99]

  scheduler:
    type: MultiStepLR
    milestones: [400000, 450000]
    gamma: 0.5

  total_iter: 500000

  warmup_iter: -1  # no warm up
  ema_decay: 0.995

  use_adaptive_weight: true

  net_g_start_iter: 0
  net_d_iters: 1
  net_d_start_iter: 0
  manual_seed: 0

# validation settings
val:
  val_freq: !!float 5e10 # no validation
  save_img: true

  metrics:
    psnr: # metric name, can be arbitrary
      type: calculate_psnr
      crop_border: 4
      test_y_channel: false

# logging settings
logger:
  print_freq: 100
  save_checkpoint_freq: !!float 1e4
  use_tb_logger: true
  wandb:
    project: ~
    resume_id: ~

# dist training settings
dist_params:
  backend: nccl
  port: 29419

find_unused_parameters: true