RysonFeng commited on
Commit
9a7372a
1 Parent(s): cdb26a4

Add pretrained weight

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
  third_party filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
  third_party filter=lfs diff=lfs merge=lfs -text
36
+ pretrained_models filter=lfs diff=lfs merge=lfs -text
pretrained_models/.gitkeep ADDED
@@ -0,0 +1 @@
 
 
1
+ # Put pretrained models into this directory
pretrained_models/big-lama/config.yaml ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ run_title: b18_ffc075_batch8x15
2
+ training_model:
3
+ kind: default
4
+ visualize_each_iters: 1000
5
+ concat_mask: true
6
+ store_discr_outputs_for_vis: true
7
+ losses:
8
+ l1:
9
+ weight_missing: 0
10
+ weight_known: 10
11
+ perceptual:
12
+ weight: 0
13
+ adversarial:
14
+ kind: r1
15
+ weight: 10
16
+ gp_coef: 0.001
17
+ mask_as_fake_target: true
18
+ allow_scale_mask: true
19
+ feature_matching:
20
+ weight: 100
21
+ resnet_pl:
22
+ weight: 30
23
+ weights_path: ${env:TORCH_HOME}
24
+
25
+ optimizers:
26
+ generator:
27
+ kind: adam
28
+ lr: 0.001
29
+ discriminator:
30
+ kind: adam
31
+ lr: 0.0001
32
+ visualizer:
33
+ key_order:
34
+ - image
35
+ - predicted_image
36
+ - discr_output_fake
37
+ - discr_output_real
38
+ - inpainted
39
+ rescale_keys:
40
+ - discr_output_fake
41
+ - discr_output_real
42
+ kind: directory
43
+ outdir: /group-volume/User-Driven-Content-Generation/r.suvorov/inpainting/experiments/r.suvorov_2021-04-30_14-41-12_train_simple_pix2pix2_gap_sdpl_novgg_large_b18_ffc075_batch8x15/samples
44
+ location:
45
+ data_root_dir: /group-volume/User-Driven-Content-Generation/datasets/inpainting_data_root_large
46
+ out_root_dir: /group-volume/User-Driven-Content-Generation/${env:USER}/inpainting/experiments
47
+ tb_dir: /group-volume/User-Driven-Content-Generation/${env:USER}/inpainting/tb_logs
48
+ data:
49
+ batch_size: 15
50
+ val_batch_size: 2
51
+ num_workers: 3
52
+ train:
53
+ indir: ${location.data_root_dir}/train
54
+ out_size: 256
55
+ mask_gen_kwargs:
56
+ irregular_proba: 1
57
+ irregular_kwargs:
58
+ max_angle: 4
59
+ max_len: 200
60
+ max_width: 100
61
+ max_times: 5
62
+ min_times: 1
63
+ box_proba: 1
64
+ box_kwargs:
65
+ margin: 10
66
+ bbox_min_size: 30
67
+ bbox_max_size: 150
68
+ max_times: 3
69
+ min_times: 1
70
+ segm_proba: 0
71
+ segm_kwargs:
72
+ confidence_threshold: 0.5
73
+ max_object_area: 0.5
74
+ min_mask_area: 0.07
75
+ downsample_levels: 6
76
+ num_variants_per_mask: 1
77
+ rigidness_mode: 1
78
+ max_foreground_coverage: 0.3
79
+ max_foreground_intersection: 0.7
80
+ max_mask_intersection: 0.1
81
+ max_hidden_area: 0.1
82
+ max_scale_change: 0.25
83
+ horizontal_flip: true
84
+ max_vertical_shift: 0.2
85
+ position_shuffle: true
86
+ transform_variant: distortions
87
+ dataloader_kwargs:
88
+ batch_size: ${data.batch_size}
89
+ shuffle: true
90
+ num_workers: ${data.num_workers}
91
+ val:
92
+ indir: ${location.data_root_dir}/val
93
+ img_suffix: .png
94
+ dataloader_kwargs:
95
+ batch_size: ${data.val_batch_size}
96
+ shuffle: false
97
+ num_workers: ${data.num_workers}
98
+ visual_test:
99
+ indir: ${location.data_root_dir}/korean_test
100
+ img_suffix: _input.png
101
+ pad_out_to_modulo: 32
102
+ dataloader_kwargs:
103
+ batch_size: 1
104
+ shuffle: false
105
+ num_workers: ${data.num_workers}
106
+ generator:
107
+ kind: ffc_resnet
108
+ input_nc: 4
109
+ output_nc: 3
110
+ ngf: 64
111
+ n_downsampling: 3
112
+ n_blocks: 18
113
+ add_out_act: sigmoid
114
+ init_conv_kwargs:
115
+ ratio_gin: 0
116
+ ratio_gout: 0
117
+ enable_lfu: false
118
+ downsample_conv_kwargs:
119
+ ratio_gin: ${generator.init_conv_kwargs.ratio_gout}
120
+ ratio_gout: ${generator.downsample_conv_kwargs.ratio_gin}
121
+ enable_lfu: false
122
+ resnet_conv_kwargs:
123
+ ratio_gin: 0.75
124
+ ratio_gout: ${generator.resnet_conv_kwargs.ratio_gin}
125
+ enable_lfu: false
126
+ discriminator:
127
+ kind: pix2pixhd_nlayer
128
+ input_nc: 3
129
+ ndf: 64
130
+ n_layers: 4
131
+ evaluator:
132
+ kind: default
133
+ inpainted_key: inpainted
134
+ integral_kind: ssim_fid100_f1
135
+ trainer:
136
+ kwargs:
137
+ gpus: -1
138
+ accelerator: ddp
139
+ max_epochs: 200
140
+ gradient_clip_val: 1
141
+ log_gpu_memory: None
142
+ limit_train_batches: 25000
143
+ val_check_interval: ${trainer.kwargs.limit_train_batches}
144
+ log_every_n_steps: 1000
145
+ precision: 32
146
+ terminate_on_nan: false
147
+ check_val_every_n_epoch: 1
148
+ num_sanity_val_steps: 8
149
+ limit_val_batches: 1000
150
+ replace_sampler_ddp: false
151
+ checkpoint_kwargs:
152
+ verbose: true
153
+ save_top_k: 5
154
+ save_last: true
155
+ period: 1
156
+ monitor: val_ssim_fid100_f1_total_mean
157
+ mode: max
pretrained_models/big-lama/models/best.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fccb7adffd53ec0974ee5503c3731c2c2f1e7e07856fd9228cdcc0b46fd5d423
3
+ size 410046389
pretrained_models/sam_vit_h_4b8939.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7bf3b02f3ebf1267aba913ff637d9a2d5c33d3173bb679e46d9f338c26f262e
3
+ size 2564550879