Hugging Face's logo

Spaces:
Sumit7864
/
Image-Enhancer
Runtime error

App Files Community
1
Image-Enhancer
File size: 2,940 Bytes 
8875fed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
142
143
144
145
146
147
148
149
150
151
 
# general settings
name: finetune_RealESRGANx4plus_400k_pairdata
model_type: RealESRGANModel
scale: 4
num_gpu: auto
manual_seed: 0

# USM the ground-truth
l1_gt_usm: True
percep_gt_usm: True
gan_gt_usm: False

high_order_degradation: False # do not use the high-order degradation generation process

# dataset and data loader settings
datasets:
  train:
    name: DIV2K
    type: RealESRGANPairedDataset
    dataroot_gt: datasets/DF2K
    dataroot_lq: datasets/DF2K
    meta_info: datasets/DF2K/meta_info/meta_info_DIV2K_sub_pair.txt
    io_backend:
      type: disk

    gt_size: 256
    use_hflip: True
    use_rot: False

    # data loader
    use_shuffle: true
    num_worker_per_gpu: 5
    batch_size_per_gpu: 12
    dataset_enlarge_ratio: 1
    prefetch_mode: ~

  # Uncomment these for validation
  # val:
  #   name: validation
  #   type: PairedImageDataset
  #   dataroot_gt: path_to_gt
  #   dataroot_lq: path_to_lq
  #   io_backend:
  #     type: disk

# network structures
network_g:
  type: RRDBNet
  num_in_ch: 3
  num_out_ch: 3
  num_feat: 64
  num_block: 23
  num_grow_ch: 32

network_d:
  type: UNetDiscriminatorSN
  num_in_ch: 3
  num_feat: 64
  skip_connection: True

# path
path:
  # use the pre-trained Real-ESRNet model
  pretrain_network_g: experiments/pretrained_models/RealESRNet_x4plus.pth
  param_key_g: params_ema
  strict_load_g: true
  pretrain_network_d: experiments/pretrained_models/RealESRGAN_x4plus_netD.pth
  param_key_d: params
  strict_load_d: true
  resume_state: ~

# training settings
train:
  ema_decay: 0.999
  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: [400000]
    gamma: 0.5

  total_iter: 400000
  warmup_iter: -1  # no warm up

  # losses
  pixel_opt:
    type: L1Loss
    loss_weight: 1.0
    reduction: mean
  # 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 1.0
    style_weight: 0
    range_norm: false
    criterion: l1
  # gan loss
  gan_opt:
    type: GANLoss
    gan_type: vanilla
    real_label_val: 1.0
    fake_label_val: 0.0
    loss_weight: !!float 1e-1

  net_d_iters: 1
  net_d_init_iters: 0

# Uncomment these for validation
# validation settings
# val:
#   val_freq: !!float 5e3
#   save_img: True

#   metrics:
#     psnr: # metric name
#       type: calculate_psnr
#       crop_border: 4
#       test_y_channel: false

# logging settings
logger:
  print_freq: 100
  save_checkpoint_freq: !!float 5e3
  use_tb_logger: true
  wandb:
    project: ~
    resume_id: ~

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