Hugging Face's logo

commanderx
/
Wav2Lip-HD

TensorBoard
Model card Files Metrics Community
1
Wav2Lip-HD
File size: 2,149 Bytes 
908a1ab
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
# general settings
name: 001_ESRGAN_x4_f64b23_custom16k_500k_B16G1_wandb
model_type: ESRGANModel
scale: 4
num_gpu: 1  # set num_gpu: 0 for cpu mode
manual_seed: 0

# dataset and data loader settings
datasets:
  train:
    name: face_dataset
    type: PairedImageDataset
    dataroot_gt: basicsr/data/hq
    dataroot_lq: basicsr/data/lq
    filename_tmpl: '{}'
    io_backend:
      type: disk

    gt_size: 384
    use_flip: true
    use_rot: true

    # data loader
    use_shuffle: true
    num_worker_per_gpu: 1
    batch_size_per_gpu: 4
    dataset_enlarge_ratio: 1
    prefetch_mode: ~

# network structures
network_g:
  type: RRDBNet
  num_in_ch: 3
  num_out_ch: 3
  num_feat: 64
  num_block: 23

network_d:
  type: VGGStyleDiscriminator128
  num_in_ch: 3
  num_feat: 64

# path
path:
  pretrain_network_g: ~
  strict_load_g: true
  resume_state: checkpoints/pretrained.state

# training settings
train:
  optim_g:
    type: Adam
    lr: !!float 1e-4
    weight_decay: 0
    betas: [0.9, 0.99]
  optim_d:
    type: Adam
    lr: !!float 1e-4
    weight_decay: 0
    betas: [0.9, 0.99]

  scheduler:
    type: MultiStepLR
    milestones: [50000, 100000, 200000, 300000]
    gamma: 0.5

  total_iter: 150000
  warmup_iter: -1  # no warm up

  # losses
  pixel_opt:
    type: L1Loss
    loss_weight: !!float 1e-2
    reduction: mean
  perceptual_opt:
    type: PerceptualLoss
    layer_weights:
      'conv5_4': 1  # before relu
    vgg_type: vgg19
    use_input_norm: true
    range_norm: false
    perceptual_weight: 1.0
    style_weight: 0
    criterion: l1
  gan_opt:
    type: GANLoss
    gan_type: vanilla
    real_label_val: 1.0
    fake_label_val: 0.0
    loss_weight: !!float 5e-3

  net_d_iters: 1
  net_d_init_iters: 0

# validation settings
val:
  val_freq: !!float 25e2
  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 25e2
  use_tb_logger: true
  wandb:
    project: ~
    resume_id: ~

# dist training settings
dist_params:
  backend: nccl
  port: 29500