Upload folder using huggingface_hub
Browse files- LaMa/big-lama/config.yaml +157 -0
- LaMa/big-lama/models/best.ckpt +3 -0
- LaMa/default.yaml +24 -0
- aesthetic-model.pth +3 -0
- face_extractor/models/antelopev2/1k3d68.onnx +3 -0
- face_extractor/models/antelopev2/2d106det.onnx +3 -0
- face_extractor/models/antelopev2/genderage.onnx +3 -0
- face_extractor/models/antelopev2/glintr100.onnx +3 -0
- face_extractor/models/antelopev2/scrfd_10g_bnkps.onnx +3 -0
- face_extractor/models/buffalo_l/1k3d68.onnx +3 -0
- face_extractor/models/buffalo_l/2d106det.onnx +3 -0
- face_extractor/models/buffalo_l/det_10g.onnx +3 -0
- face_extractor/models/buffalo_l/genderage.onnx +3 -0
- face_extractor/models/buffalo_l/w600k_r50.onnx +3 -0
- face_extractor/models/buffalo_m/1k3d68.onnx +3 -0
- face_extractor/models/buffalo_m/2d106det.onnx +3 -0
- face_extractor/models/buffalo_m/det_2.5g.onnx +3 -0
- face_extractor/models/buffalo_m/genderage.onnx +3 -0
- face_extractor/models/buffalo_m/w600k_r50.onnx +3 -0
- face_extractor/models/buffalo_s/1k3d68.onnx +3 -0
- face_extractor/models/buffalo_s/2d106det.onnx +3 -0
- face_extractor/models/buffalo_s/det_500m.onnx +3 -0
- face_extractor/models/buffalo_s/genderage.onnx +3 -0
- face_extractor/models/buffalo_s/w600k_mbf.onnx +3 -0
- glint360k_curricular_face_r101_backbone.bin +3 -0
- groundingdino_swint_ogc.pth +3 -0
- sam2.1_hiera_large.pt +3 -0
- yolo_world_v2_l_image_prompt_adapter-719a7afb.pth +3 -0
LaMa/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
|
LaMa/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
|
LaMa/default.yaml
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
indir: no # to be overriden in CLI
|
2 |
+
outdir: no # to be overriden in CLI
|
3 |
+
|
4 |
+
model:
|
5 |
+
path: no # to be overriden in CLI
|
6 |
+
checkpoint: best.ckpt
|
7 |
+
|
8 |
+
dataset:
|
9 |
+
kind: default
|
10 |
+
img_suffix: .png
|
11 |
+
pad_out_to_modulo: 8
|
12 |
+
|
13 |
+
device: cuda
|
14 |
+
out_key: inpainted
|
15 |
+
|
16 |
+
refine: False # refiner will only run if this is True
|
17 |
+
refiner:
|
18 |
+
gpu_ids: 0,1 # the GPU ids of the machine to use. If only single GPU, use: "0,"
|
19 |
+
modulo: ${dataset.pad_out_to_modulo}
|
20 |
+
n_iters: 15 # number of iterations of refinement for each scale
|
21 |
+
lr: 0.002 # learning rate
|
22 |
+
min_side: 512 # all sides of image on all scales should be >= min_side / sqrt(2)
|
23 |
+
max_scales: 3 # max number of downscaling scales for the image-mask pyramid
|
24 |
+
px_budget: 1800000 # pixels budget. Any image will be resized to satisfy height*width <= px_budget
|
aesthetic-model.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21dd590f3ccdc646f0d53120778b296013b096a035a2718c9cb0d511bff0f1e0
|
3 |
+
size 3714759
|
face_extractor/models/antelopev2/1k3d68.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df5c06b8a0c12e422b2ed8947b8869faa4105387f199c477af038aa01f9a45cc
|
3 |
+
size 143607619
|
face_extractor/models/antelopev2/2d106det.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f001b856447c413801ef5c42091ed0cd516fcd21f2d6b79635b1e733a7109dbf
|
3 |
+
size 5030888
|
face_extractor/models/antelopev2/genderage.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fde69b1c810857b88c64a335084f1c3fe8f01246c9a191b48c7bb756d6652fb
|
3 |
+
size 1322532
|
face_extractor/models/antelopev2/glintr100.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ab1d6435d639628a6f3e5008dd4f929edf4c4124b1a7169e1048f9fef534cdf
|
3 |
+
size 260665334
|
face_extractor/models/antelopev2/scrfd_10g_bnkps.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5838f7fe053675b1c7a08b633df49e7af5495cee0493c7dcf6697200b85b5b91
|
3 |
+
size 16923827
|
face_extractor/models/buffalo_l/1k3d68.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df5c06b8a0c12e422b2ed8947b8869faa4105387f199c477af038aa01f9a45cc
|
3 |
+
size 143607619
|
face_extractor/models/buffalo_l/2d106det.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f001b856447c413801ef5c42091ed0cd516fcd21f2d6b79635b1e733a7109dbf
|
3 |
+
size 5030888
|
face_extractor/models/buffalo_l/det_10g.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5838f7fe053675b1c7a08b633df49e7af5495cee0493c7dcf6697200b85b5b91
|
3 |
+
size 16923827
|
face_extractor/models/buffalo_l/genderage.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fde69b1c810857b88c64a335084f1c3fe8f01246c9a191b48c7bb756d6652fb
|
3 |
+
size 1322532
|
face_extractor/models/buffalo_l/w600k_r50.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c06341c33c2ca1f86781dab0e829f88ad5b64be9fba56e56bc9ebdefc619e43
|
3 |
+
size 174383860
|
face_extractor/models/buffalo_m/1k3d68.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df5c06b8a0c12e422b2ed8947b8869faa4105387f199c477af038aa01f9a45cc
|
3 |
+
size 143607619
|
face_extractor/models/buffalo_m/2d106det.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f001b856447c413801ef5c42091ed0cd516fcd21f2d6b79635b1e733a7109dbf
|
3 |
+
size 5030888
|
face_extractor/models/buffalo_m/det_2.5g.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:041f73f47371333d1d17a6fee6c8ab4e6aecabefe398ff32cca4e2d5eaee0af9
|
3 |
+
size 3292009
|
face_extractor/models/buffalo_m/genderage.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fde69b1c810857b88c64a335084f1c3fe8f01246c9a191b48c7bb756d6652fb
|
3 |
+
size 1322532
|
face_extractor/models/buffalo_m/w600k_r50.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c06341c33c2ca1f86781dab0e829f88ad5b64be9fba56e56bc9ebdefc619e43
|
3 |
+
size 174383860
|
face_extractor/models/buffalo_s/1k3d68.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df5c06b8a0c12e422b2ed8947b8869faa4105387f199c477af038aa01f9a45cc
|
3 |
+
size 143607619
|
face_extractor/models/buffalo_s/2d106det.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f001b856447c413801ef5c42091ed0cd516fcd21f2d6b79635b1e733a7109dbf
|
3 |
+
size 5030888
|
face_extractor/models/buffalo_s/det_500m.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e4447f50245bbd7966bd6c0fa52938c61474a04ec7def48753668a9d8b4ea3a
|
3 |
+
size 2524817
|
face_extractor/models/buffalo_s/genderage.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fde69b1c810857b88c64a335084f1c3fe8f01246c9a191b48c7bb756d6652fb
|
3 |
+
size 1322532
|
face_extractor/models/buffalo_s/w600k_mbf.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cc6e4a75f0e2bf0b1aed94578f144d15175f357bdc05e815e5c4a02b319eb4f
|
3 |
+
size 13616099
|
glint360k_curricular_face_r101_backbone.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa54ae6dc9f7ac6e262809f1a81d6108e221952bf836aee4cb677ef19246c6ec
|
3 |
+
size 261202954
|
groundingdino_swint_ogc.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b3ca2563c77c69f651d7bd133e97139c186df06231157a64c507099c52bc799
|
3 |
+
size 693997677
|
sam2.1_hiera_large.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2647878d5dfa5098f2f8649825738a9345572bae2d4350a2468587ece47dd318
|
3 |
+
size 898083611
|
yolo_world_v2_l_image_prompt_adapter-719a7afb.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:719a7afb9f084f9abfbada040ea7abdc7a22a3da5e858f6e5f158582010fd61a
|
3 |
+
size 797136834
|