File size: 2,689 Bytes
13fd34d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
131
132
133
134
135
136
137
138
139
140
141
num_gpu: 1
manual_seed: 0
is_train: True
dist: False

# network structures
network_g:
  type: GFPGANv1
  out_size: 512
  num_style_feat: 512
  channel_multiplier: 1
  resample_kernel: [1, 3, 3, 1]
  decoder_load_path: ~
  fix_decoder: true
  num_mlp: 8
  lr_mlp: 0.01
  input_is_latent: true
  different_w: true
  narrow: 0.5
  sft_half: true

network_d:
  type: StyleGAN2Discriminator
  out_size: 512
  channel_multiplier: 1
  resample_kernel: [1, 3, 3, 1]

network_d_left_eye:
  type: FacialComponentDiscriminator

network_d_right_eye:
  type: FacialComponentDiscriminator

network_d_mouth:
  type: FacialComponentDiscriminator

network_identity:
  type: ResNetArcFace
  block: IRBlock
  layers: [2, 2, 2, 2]
  use_se: False

# path
path:
  pretrain_network_g: ~
  param_key_g: params_ema
  strict_load_g: ~
  pretrain_network_d: ~
  pretrain_network_d_left_eye: ~
  pretrain_network_d_right_eye: ~
  pretrain_network_d_mouth: ~
  pretrain_network_identity: ~
  # resume
  resume_state: ~
  ignore_resume_networks: ['network_identity']

# training settings
train:
  optim_g:
    type: Adam
    lr: !!float 2e-3
  optim_d:
    type: Adam
    lr: !!float 2e-3
  optim_component:
    type: Adam
    lr: !!float 2e-3

  scheduler:
    type: MultiStepLR
    milestones: [600000, 700000]
    gamma: 0.5

  total_iter: 800000
  warmup_iter: -1  # no warm up

  # losses
  # pixel loss
  pixel_opt:
    type: L1Loss
    loss_weight: !!float 1e-1
    reduction: mean
  # L1 loss used in pyramid loss, component style loss and identity loss
  L1_opt:
    type: L1Loss
    loss_weight: 1
    reduction: mean

  # image pyramid loss
  pyramid_loss_weight: 1
  remove_pyramid_loss: 50000
  # perceptual loss (content and style losses)
  perceptual_opt:
    type: PerceptualLoss
    layer_weights:
      # before relu
      'conv1_2': 0.1
      'conv2_2': 0.1
      'conv3_4': 1
      'conv4_4': 1
      'conv5_4': 1
    vgg_type: vgg19
    use_input_norm: true
    perceptual_weight: !!float 1
    style_weight: 50
    range_norm: true
    criterion: l1
  # gan loss
  gan_opt:
    type: GANLoss
    gan_type: wgan_softplus
    loss_weight: !!float 1e-1
  # r1 regularization for discriminator
  r1_reg_weight: 10
  # facial component loss
  gan_component_opt:
    type: GANLoss
    gan_type: vanilla
    real_label_val: 1.0
    fake_label_val: 0.0
    loss_weight: !!float 1
  comp_style_weight: 200
  # identity loss
  identity_weight: 10

  net_d_iters: 1
  net_d_init_iters: 0
  net_d_reg_every: 1

# validation settings
val:
  val_freq: !!float 5e3
  save_img: True
  use_pbar: True

  metrics:
    psnr: # metric name
      type: calculate_psnr
      crop_border: 0
      test_y_channel: false