Kidbea commited on
Commit
fbefd1a
·
1 Parent(s): 336fe2b

This is the first commit

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +2 -0
  2. .gitignore +2 -0
  3. =4.66.3 +10 -0
  4. Change-Clothes-AI +0 -1
  5. README.md +8 -8
  6. app.py +401 -0
  7. apply_net.py +359 -0
  8. ckpt/densepose/model_final_162be9.pkl +3 -0
  9. ckpt/humanparsing/parsing_atr.onnx +3 -0
  10. ckpt/humanparsing/parsing_lip.onnx +3 -0
  11. ckpt/openpose/.DS_Store +0 -0
  12. ckpt/openpose/ckpts/body_pose_model.pth +3 -0
  13. configs/Base-DensePose-RCNN-FPN.yaml +48 -0
  14. configs/HRNet/densepose_rcnn_HRFPN_HRNet_w32_s1x.yaml +16 -0
  15. configs/HRNet/densepose_rcnn_HRFPN_HRNet_w40_s1x.yaml +23 -0
  16. configs/HRNet/densepose_rcnn_HRFPN_HRNet_w48_s1x.yaml +23 -0
  17. configs/cse/Base-DensePose-RCNN-FPN-Human.yaml +20 -0
  18. configs/cse/Base-DensePose-RCNN-FPN.yaml +60 -0
  19. configs/cse/densepose_rcnn_R_101_FPN_DL_s1x.yaml +12 -0
  20. configs/cse/densepose_rcnn_R_101_FPN_DL_soft_s1x.yaml +12 -0
  21. configs/cse/densepose_rcnn_R_101_FPN_s1x.yaml +12 -0
  22. configs/cse/densepose_rcnn_R_101_FPN_soft_s1x.yaml +12 -0
  23. configs/cse/densepose_rcnn_R_50_FPN_DL_s1x.yaml +12 -0
  24. configs/cse/densepose_rcnn_R_50_FPN_DL_soft_s1x.yaml +12 -0
  25. configs/cse/densepose_rcnn_R_50_FPN_s1x.yaml +12 -0
  26. configs/cse/densepose_rcnn_R_50_FPN_soft_animals_CA_finetune_16k.yaml +133 -0
  27. configs/cse/densepose_rcnn_R_50_FPN_soft_animals_CA_finetune_4k.yaml +133 -0
  28. configs/cse/densepose_rcnn_R_50_FPN_soft_animals_I0_finetune_16k.yaml +119 -0
  29. configs/cse/densepose_rcnn_R_50_FPN_soft_animals_I0_finetune_i2m_16k.yaml +121 -0
  30. configs/cse/densepose_rcnn_R_50_FPN_soft_animals_I0_finetune_m2m_16k.yaml +138 -0
  31. configs/cse/densepose_rcnn_R_50_FPN_soft_animals_finetune_16k.yaml +119 -0
  32. configs/cse/densepose_rcnn_R_50_FPN_soft_animals_finetune_4k.yaml +119 -0
  33. configs/cse/densepose_rcnn_R_50_FPN_soft_animals_finetune_maskonly_24k.yaml +118 -0
  34. configs/cse/densepose_rcnn_R_50_FPN_soft_chimps_finetune_4k.yaml +29 -0
  35. configs/cse/densepose_rcnn_R_50_FPN_soft_s1x.yaml +12 -0
  36. configs/densepose_rcnn_R_101_FPN_DL_WC1M_s1x.yaml +18 -0
  37. configs/densepose_rcnn_R_101_FPN_DL_WC1_s1x.yaml +16 -0
  38. configs/densepose_rcnn_R_101_FPN_DL_WC2M_s1x.yaml +18 -0
  39. configs/densepose_rcnn_R_101_FPN_DL_WC2_s1x.yaml +16 -0
  40. configs/densepose_rcnn_R_101_FPN_DL_s1x.yaml +10 -0
  41. configs/densepose_rcnn_R_101_FPN_WC1M_s1x.yaml +18 -0
  42. configs/densepose_rcnn_R_101_FPN_WC1_s1x.yaml +16 -0
  43. configs/densepose_rcnn_R_101_FPN_WC2M_s1x.yaml +18 -0
  44. configs/densepose_rcnn_R_101_FPN_WC2_s1x.yaml +16 -0
  45. configs/densepose_rcnn_R_101_FPN_s1x.yaml +8 -0
  46. configs/densepose_rcnn_R_101_FPN_s1x_legacy.yaml +17 -0
  47. configs/densepose_rcnn_R_50_FPN_DL_WC1M_s1x.yaml +18 -0
  48. configs/densepose_rcnn_R_50_FPN_DL_WC1_s1x.yaml +16 -0
  49. configs/densepose_rcnn_R_50_FPN_DL_WC2M_s1x.yaml +18 -0
  50. configs/densepose_rcnn_R_50_FPN_DL_WC2_s1x.yaml +16 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ /ckpt filter=lfs diff=lfs merge=lfs -text
37
+ detectron2/_C.cpython-39-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ *.pyc
2
+ .idea
=4.66.3 ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ Requirement already satisfied: tqdm in /usr/local/lib/python3.10/site-packages (4.64.1)
2
+ Collecting tqdm
3
+ Downloading tqdm-4.67.1-py3-none-any.whl.metadata (57 kB)
4
+ Downloading tqdm-4.67.1-py3-none-any.whl (78 kB)
5
+ Installing collected packages: tqdm
6
+ Attempting uninstall: tqdm
7
+ Found existing installation: tqdm 4.64.1
8
+ Uninstalling tqdm-4.64.1:
9
+ Successfully uninstalled tqdm-4.64.1
10
+ Successfully installed tqdm-4.67.1
Change-Clothes-AI DELETED
@@ -1 +0,0 @@
1
- Subproject commit 3030eea162285b7e9b6ce8907a3497ea35c96894
 
 
README.md CHANGED
@@ -1,12 +1,12 @@
1
  ---
2
- title: Kidbea-Virtual TryOn
3
- emoji: 🔥
4
- colorFrom: green
5
- colorTo: gray
6
  sdk: gradio
7
- sdk_version: 5.24.0
8
  app_file: app.py
9
  pinned: false
10
- ---
11
-
12
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
1
  ---
2
+ title: Change Clothes AI
3
+ emoji: 👚
4
+ colorFrom: yellow
5
+ colorTo: red
6
  sdk: gradio
7
+ sdk_version: 4.36.1
8
  app_file: app.py
9
  pinned: false
10
+ license: cc-by-nc-sa-4.0
11
+ short_description: AI Clothes Changer Online
12
+ ---
app.py ADDED
@@ -0,0 +1,401 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # app.py
2
+
3
+ # ====== PATCH GRADIO_CLIENT UTILS TO HANDLE BOOLEAN SCHEMAS ======
4
+ import gradio_client.utils as gc_utils
5
+
6
+ def patched_get_type(schema):
7
+ if not isinstance(schema, dict):
8
+ return "bool" if isinstance(schema, bool) else "unknown"
9
+ if "const" in schema:
10
+ return "const"
11
+ return schema.get("type", "object")
12
+ gc_utils.get_type = patched_get_type
13
+
14
+ _original_json_schema_to_python_type = gc_utils._json_schema_to_python_type
15
+ def patched_json_schema_to_python_type(schema, defs=None):
16
+ if isinstance(schema, bool):
17
+ return "bool"
18
+ if not isinstance(schema, dict):
19
+ return "unknown"
20
+ try:
21
+ return _original_json_schema_to_python_type(schema, defs)
22
+ except Exception as e:
23
+ return "unknown"
24
+ gc_utils._json_schema_to_python_type = patched_json_schema_to_python_type
25
+ # ====== END PATCHS ======
26
+
27
+ import spaces
28
+ import gradio as gr
29
+ from PIL import Image
30
+ import monkeypatch # This file should be present to patch
31
+ from src.tryon_pipeline import StableDiffusionXLInpaintPipeline as TryonPipeline
32
+ from src.unet_hacked_garmnet import UNet2DConditionModel as UNet2DConditionModel_ref
33
+ from src.unet_hacked_tryon import UNet2DConditionModel
34
+ from transformers import (
35
+ CLIPImageProcessor,
36
+ CLIPVisionModelWithProjection,
37
+ CLIPTextModel,
38
+ CLIPTextModelWithProjection,
39
+ )
40
+ from diffusers import DDPMScheduler, AutoencoderKL
41
+ from typing import List
42
+
43
+ import torch
44
+ import os
45
+ from transformers import AutoTokenizer
46
+
47
+ import numpy as np
48
+ from utils_mask import get_mask_location
49
+ from torchvision import transforms
50
+ import apply_net
51
+ from preprocess.humanparsing.run_parsing import Parsing
52
+ from preprocess.openpose.run_openpose import OpenPose
53
+ from detectron2.data.detection_utils import convert_PIL_to_numpy, _apply_exif_orientation
54
+ from torchvision.transforms.functional import to_pil_image
55
+
56
+ def pil_to_binary_mask(pil_image, threshold=0):
57
+ np_image = np.array(pil_image)
58
+ grayscale_image = Image.fromarray(np_image).convert("L")
59
+ binary_mask = np.array(grayscale_image) > threshold
60
+ mask = np.zeros(binary_mask.shape, dtype=np.uint8)
61
+ for i in range(binary_mask.shape[0]):
62
+ for j in range(binary_mask.shape[1]):
63
+ if binary_mask[i, j]:
64
+ mask[i, j] = 1
65
+ mask = (mask * 255).astype(np.uint8)
66
+ output_mask = Image.fromarray(mask)
67
+ return output_mask
68
+
69
+ base_path = 'yisol/IDM-VTON'
70
+ example_path = os.path.join(os.path.dirname(__file__), 'example')
71
+
72
+ unet = UNet2DConditionModel.from_pretrained(
73
+ base_path,
74
+ subfolder="unet",
75
+ torch_dtype=torch.float16,
76
+ )
77
+ unet.requires_grad_(False)
78
+
79
+ tokenizer_one = AutoTokenizer.from_pretrained(
80
+ base_path,
81
+ subfolder="tokenizer",
82
+ revision=None,
83
+ use_fast=False,
84
+ )
85
+ tokenizer_two = AutoTokenizer.from_pretrained(
86
+ base_path,
87
+ subfolder="tokenizer_2",
88
+ revision=None,
89
+ use_fast=False,
90
+ )
91
+ noise_scheduler = DDPMScheduler.from_pretrained(base_path, subfolder="scheduler")
92
+
93
+ text_encoder_one = CLIPTextModel.from_pretrained(
94
+ base_path,
95
+ subfolder="text_encoder",
96
+ torch_dtype=torch.float16,
97
+ )
98
+ text_encoder_two = CLIPTextModelWithProjection.from_pretrained(
99
+ base_path,
100
+ subfolder="text_encoder_2",
101
+ torch_dtype=torch.float16,
102
+ )
103
+ image_encoder = CLIPVisionModelWithProjection.from_pretrained(
104
+ base_path,
105
+ subfolder="image_encoder",
106
+ torch_dtype=torch.float16,
107
+ )
108
+ vae = AutoencoderKL.from_pretrained(
109
+ base_path,
110
+ subfolder="vae",
111
+ torch_dtype=torch.float16,
112
+ )
113
+
114
+ # "stabilityai/stable-diffusion-xl-base-1.0",
115
+ UNet_Encoder = UNet2DConditionModel_ref.from_pretrained(
116
+ base_path,
117
+ subfolder="unet_encoder",
118
+ torch_dtype=torch.float16,
119
+ )
120
+
121
+ parsing_model = Parsing(0)
122
+ openpose_model = OpenPose(0)
123
+
124
+ UNet_Encoder.requires_grad_(False)
125
+ image_encoder.requires_grad_(False)
126
+ vae.requires_grad_(False)
127
+ unet.requires_grad_(False)
128
+ text_encoder_one.requires_grad_(False)
129
+ text_encoder_two.requires_grad_(False)
130
+
131
+ tensor_transfrom = transforms.Compose([
132
+ transforms.ToTensor(),
133
+ transforms.Normalize([0.5], [0.5]),
134
+ ])
135
+
136
+ pipe = TryonPipeline.from_pretrained(
137
+ base_path,
138
+ unet=unet,
139
+ vae=vae,
140
+ feature_extractor=CLIPImageProcessor(),
141
+ text_encoder=text_encoder_one,
142
+ text_encoder_2=text_encoder_two,
143
+ tokenizer=tokenizer_one,
144
+ tokenizer_2=tokenizer_two,
145
+ scheduler=noise_scheduler,
146
+ image_encoder=image_encoder,
147
+ torch_dtype=torch.float16,
148
+ )
149
+ pipe.unet_encoder = UNet_Encoder
150
+
151
+ @spaces.GPU
152
+ def start_tryon(dict, garm_img, garment_des, is_checked, is_checked_crop, denoise_steps, seed, category):
153
+ """虚拟试衣主函数
154
+ Args:
155
+ dict: 输入图像字典,包含背景和图层信息
156
+ garm_img: 服装图片
157
+ garment_des: 服装描述文本
158
+ is_checked: 是否启用自动检测模式
159
+ is_checked_crop: 是否启用图像裁剪
160
+ denoise_steps: 去噪步数
161
+ seed: 随机种子
162
+ category: 服装类别
163
+ Returns:
164
+ 生成的试衣结果图��和灰度遮罩
165
+ """
166
+ device = "cuda"
167
+ openpose_model.preprocessor.body_estimation.model.to(device)
168
+ pipe.to(device)
169
+ pipe.unet_encoder.to(device)
170
+
171
+ # 2. 图像预处理 - 调整服装和人物图像大小
172
+ garm_img = garm_img.convert("RGB").resize((768, 1024))
173
+ human_img_orig = dict["background"].convert("RGB")
174
+ orig_size = human_img_orig.size # 保存原始尺寸
175
+
176
+ # 2.1 如果启用裁剪,按3:4比例裁剪人物图像
177
+ if is_checked_crop:
178
+ width, height = human_img_orig.size
179
+ target_width = int(min(width, height * (3 / 4)))
180
+ target_height = int(min(height, width * (4 / 3)))
181
+ left = (width - target_width) / 2
182
+ top = (height - target_height) / 2
183
+ right = (width + target_width) / 2
184
+ bottom = (height + target_height) / 2
185
+ cropped_img = human_img_orig.crop((left, top, right, bottom))
186
+ crop_size = cropped_img.size
187
+ human_img = cropped_img.resize((768, 1024))
188
+ else:
189
+ human_img = human_img_orig.resize((768, 1024))
190
+
191
+ # 3. 生成遮罩
192
+ if is_checked:
193
+ # 3.1 使用自动检测模式
194
+ keypoints = openpose_model(human_img.resize((384, 512)))
195
+ model_parse, _ = parsing_model(human_img.resize((384, 512)))
196
+ mask, mask_gray = get_mask_location('hd', category, model_parse, keypoints)
197
+ mask = mask.resize((768, 1024))
198
+ else:
199
+ # 3.2 使用手动提供的遮罩
200
+ mask = pil_to_binary_mask(dict['layers'][0].convert("RGB").resize((768, 1024)))
201
+
202
+ # 3.3 生成灰度遮罩
203
+ mask_gray = (1 - transforms.ToTensor()(mask)) * tensor_transfrom(human_img)
204
+ mask_gray = to_pil_image((mask_gray + 1.0) / 2.0)
205
+
206
+ # 4. 姿态处理
207
+ human_img_arg = _apply_exif_orientation(human_img.resize((384, 512)))
208
+ human_img_arg = convert_PIL_to_numpy(human_img_arg, format="BGR")
209
+ args = apply_net.create_argument_parser().parse_args((
210
+ 'show',
211
+ './configs/densepose_rcnn_R_50_FPN_s1x.yaml',
212
+ './ckpt/densepose/model_final_162be9.pkl',
213
+ 'dp_segm',
214
+ '-v',
215
+ '--opts',
216
+ 'MODEL.DEVICE',
217
+ 'cuda'
218
+ ))
219
+ pose_img = args.func(args, human_img_arg)
220
+ pose_img = pose_img[:, :, ::-1]
221
+ pose_img = Image.fromarray(pose_img).resize((768, 1024))
222
+
223
+ # 5. AI生成过程
224
+ with torch.no_grad():
225
+ with torch.cuda.amp.autocast():
226
+ # 5.1 生成正面提示词嵌入
227
+ prompt = "((best quality, masterpiece, ultra-detailed, high quality photography, photo realistic)), the model is wearing " + garment_des
228
+ negative_prompt = "monochrome, lowres, bad anatomy, worst quality, normal quality, low quality, blurry, jpeg artifacts, sketch"
229
+ with torch.inference_mode():
230
+ (
231
+ prompt_embeds,
232
+ negative_prompt_embeds,
233
+ pooled_prompt_embeds,
234
+ negative_pooled_prompt_embeds,
235
+ ) = pipe.encode_prompt(
236
+ prompt,
237
+ num_images_per_prompt=1,
238
+ do_classifier_free_guidance=True,
239
+ negative_prompt=negative_prompt,
240
+ )
241
+
242
+ # 5.2 生成服装相关的提示词嵌入
243
+ prompt = "((best quality, masterpiece, ultra-detailed, high quality photography, photo realistic)), a photo of " + garment_des
244
+ negative_prompt = "monochrome, lowres, bad anatomy, worst quality, normal quality, low quality, blurry, jpeg artifacts, sketch"
245
+ if not isinstance(prompt, List):
246
+ prompt = [prompt] * 1
247
+ if not isinstance(negative_prompt, List):
248
+ negative_prompt = [negative_prompt] * 1
249
+
250
+ (
251
+ prompt_embeds_c,
252
+ _,
253
+ _,
254
+ _,
255
+ ) = pipe.encode_prompt(
256
+ prompt,
257
+ num_images_per_prompt=1,
258
+ do_classifier_free_guidance=False,
259
+ negative_prompt=negative_prompt,
260
+ )
261
+
262
+ # 5.3 准备输入张量
263
+ pose_tensor = tensor_transfrom(pose_img).unsqueeze(0).to(device, torch.float16)
264
+ garm_tensor = tensor_transfrom(garm_img).unsqueeze(0).to(device, torch.float16)
265
+ generator = torch.Generator(device).manual_seed(seed) if seed is not None else None
266
+
267
+ # 6. 使用Stable Diffusion XL管道生成图像
268
+ images = pipe(
269
+ prompt_embeds=prompt_embeds.to(device, torch.float16),
270
+ negative_prompt_embeds=negative_prompt_embeds.to(device, torch.float16),
271
+ pooled_prompt_embeds=pooled_prompt_embeds.to(device, torch.float16),
272
+ negative_pooled_prompt_embeds=negative_pooled_prompt_embeds.to(device, torch.float16),
273
+ num_inference_steps=denoise_steps,
274
+ generator=generator,
275
+ strength=1.0,
276
+ pose_img=pose_tensor.to(device, torch.float16),
277
+ text_embeds_cloth=prompt_embeds_c.to(device, torch.float16),
278
+ cloth=garm_tensor.to(device, torch.float16),
279
+ mask_image=mask,
280
+ image=human_img,
281
+ height=1024,
282
+ width=768,
283
+ ip_adapter_image=garm_img.resize((768, 1024)),
284
+ guidance_scale=2.0,
285
+ )[0]
286
+
287
+ # 7. 后处理 - 处理裁剪情况并返回结果
288
+ if is_checked_crop:
289
+ return images[0].resize(crop_size), mask_gray.resize(crop_size)
290
+ else:
291
+ return images[0].resize(orig_size), mask_gray.resize(orig_size)
292
+
293
+ # Setup example paths and lists
294
+ garm_list = os.listdir(os.path.join(example_path, "cloth"))
295
+ garm_list_path = [os.path.join(example_path, "cloth", garm) for garm in garm_list]
296
+
297
+ human_list = os.listdir(os.path.join(example_path, "human"))
298
+ human_list_path = [os.path.join(example_path, "human", human) for human in human_list]
299
+
300
+ human_ex_list = []
301
+ for ex_human in human_list_path:
302
+ ex_dict = {}
303
+ ex_dict['background'] = ex_human
304
+ ex_dict['layers'] = None
305
+ ex_dict['composite'] = None
306
+ human_ex_list.append(ex_dict)
307
+
308
+ custom_css = """
309
+ :root {
310
+ --primary: #9D4BFF;
311
+ --secondary: #4A148C;
312
+ --accent: #E0AAFF;
313
+ }
314
+
315
+ body {
316
+ font-family: 'Helvetica Neue', sans-serif;
317
+ }
318
+
319
+ .purple-btn {
320
+ background: var(--primary) !important;
321
+ color: white !important;
322
+ border: none !important;
323
+ padding: 12px 24px !important;
324
+ border-radius: 8px !important;
325
+ }
326
+
327
+ .purple-btn:hover {
328
+ background: var(--secondary) !important;
329
+ }
330
+
331
+ .section-title {
332
+ color: var(--secondary) !important;
333
+ font-weight: 600 !important;
334
+ margin-bottom: 10px !important;
335
+ }
336
+ """
337
+
338
+ image_blocks = gr.Blocks(css=custom_css).queue()
339
+ with image_blocks as demo:
340
+ gr.Markdown("## 👶 Baby Virtual Try-On Studio", elem_classes=["section-title"])
341
+
342
+ # Coefficient Section (係數區塊)
343
+ with gr.Column():
344
+ try_button = gr.Button(
345
+ value="✨ Generate Virtual Try-On",
346
+ elem_classes=["purple-btn"],
347
+ scale=2
348
+ )
349
+ with gr.Accordion(label="Advanced Settings", open=False):
350
+ with gr.Row():
351
+ denoise_steps = gr.Number(label="Denoising Steps", minimum=20, maximum=40, value=30, step=1)
352
+ seed = gr.Number(label="Seed", minimum=-1, maximum=2147483647, step=1, value=50)
353
+
354
+ # Changing Section (更衣區塊)
355
+ with gr.Row():
356
+ with gr.Column():
357
+ gr.Markdown("### 👶 Upload Baby Photo", elem_classes=["section-title"])
358
+ imgs = gr.ImageEditor(sources='upload', type="pil", label='Human. Mask with pen or use auto-masking', interactive=True)
359
+ with gr.Row():
360
+ is_checked = gr.Checkbox(label="Yes", info="Use auto-generated mask (Takes 5 seconds)", value=True)
361
+ with gr.Row():
362
+ category = gr.Dropdown(
363
+ choices=["upper_body", "lower_body", "dresses"],
364
+ label="Category",
365
+ value="upper_body"
366
+ )
367
+ with gr.Row():
368
+ is_checked_crop = gr.Checkbox(label="Yes", info="Use auto-crop & resizing", value=False)
369
+ example = gr.Examples(
370
+ inputs=imgs,
371
+ examples_per_page=15,
372
+ examples=human_ex_list
373
+ )
374
+
375
+ with gr.Column():
376
+ gr.Markdown("### 👕 Upload Clothing", elem_classes=["section-title"])
377
+ garm_img = gr.Image(label="Garment", sources='upload', type="pil")
378
+ with gr.Row(elem_id="prompt-container"):
379
+ prompt = gr.Textbox(label="Description of garment", placeholder="Short Sleeve Round Neck T-shirts", show_label=True, elem_id="prompt")
380
+ example = gr.Examples(
381
+ inputs=garm_img,
382
+ examples_per_page=30,
383
+ examples=garm_list_path
384
+ )
385
+
386
+ with gr.Column():
387
+ image_out = gr.Image(label="Output", elem_id="output-img", show_share_button=False)
388
+ with gr.Column():
389
+ masked_img = gr.Image(label="Masked image output", elem_id="masked-img", show_share_button=False)
390
+
391
+ with gr.Row():
392
+ gr.Markdown("## Links")
393
+
394
+ try_button.click(
395
+ fn=start_tryon,
396
+ inputs=[imgs, garm_img, prompt, is_checked, is_checked_crop, denoise_steps, seed, category],
397
+ outputs=[image_out, masked_img],
398
+ api_name='tryon'
399
+ )
400
+
401
+ image_blocks.launch()
apply_net.py ADDED
@@ -0,0 +1,359 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python3
2
+ # Copyright (c) Facebook, Inc. and its affiliates.
3
+
4
+ import argparse
5
+ import glob
6
+ import logging
7
+ import os
8
+ import sys
9
+ from typing import Any, ClassVar, Dict, List
10
+ import torch
11
+
12
+ from detectron2.config import CfgNode, get_cfg
13
+ from detectron2.data.detection_utils import read_image
14
+ from detectron2.engine.defaults import DefaultPredictor
15
+ from detectron2.structures.instances import Instances
16
+ from detectron2.utils.logger import setup_logger
17
+
18
+ from densepose import add_densepose_config
19
+ from densepose.structures import DensePoseChartPredictorOutput, DensePoseEmbeddingPredictorOutput
20
+ from densepose.utils.logger import verbosity_to_level
21
+ from densepose.vis.base import CompoundVisualizer
22
+ from densepose.vis.bounding_box import ScoredBoundingBoxVisualizer
23
+ from densepose.vis.densepose_outputs_vertex import (
24
+ DensePoseOutputsTextureVisualizer,
25
+ DensePoseOutputsVertexVisualizer,
26
+ get_texture_atlases,
27
+ )
28
+ from densepose.vis.densepose_results import (
29
+ DensePoseResultsContourVisualizer,
30
+ DensePoseResultsFineSegmentationVisualizer,
31
+ DensePoseResultsUVisualizer,
32
+ DensePoseResultsVVisualizer,
33
+ )
34
+ from densepose.vis.densepose_results_textures import (
35
+ DensePoseResultsVisualizerWithTexture,
36
+ get_texture_atlas,
37
+ )
38
+ from densepose.vis.extractor import (
39
+ CompoundExtractor,
40
+ DensePoseOutputsExtractor,
41
+ DensePoseResultExtractor,
42
+ create_extractor,
43
+ )
44
+
45
+ DOC = """Apply Net - a tool to print / visualize DensePose results
46
+ """
47
+
48
+ LOGGER_NAME = "apply_net"
49
+ logger = logging.getLogger(LOGGER_NAME)
50
+
51
+ _ACTION_REGISTRY: Dict[str, "Action"] = {}
52
+
53
+
54
+ class Action:
55
+ @classmethod
56
+ def add_arguments(cls: type, parser: argparse.ArgumentParser):
57
+ parser.add_argument(
58
+ "-v",
59
+ "--verbosity",
60
+ action="count",
61
+ help="Verbose mode. Multiple -v options increase the verbosity.",
62
+ )
63
+
64
+
65
+ def register_action(cls: type):
66
+ """
67
+ Decorator for action classes to automate action registration
68
+ """
69
+ global _ACTION_REGISTRY
70
+ _ACTION_REGISTRY[cls.COMMAND] = cls
71
+ return cls
72
+
73
+
74
+ class InferenceAction(Action):
75
+ @classmethod
76
+ def add_arguments(cls: type, parser: argparse.ArgumentParser):
77
+ super(InferenceAction, cls).add_arguments(parser)
78
+ parser.add_argument("cfg", metavar="<config>", help="Config file")
79
+ parser.add_argument("model", metavar="<model>", help="Model file")
80
+ parser.add_argument(
81
+ "--opts",
82
+ help="Modify config options using the command-line 'KEY VALUE' pairs",
83
+ default=[],
84
+ nargs=argparse.REMAINDER,
85
+ )
86
+
87
+ @classmethod
88
+ def execute(cls: type, args: argparse.Namespace, human_img):
89
+ logger.info(f"Loading config from {args.cfg}")
90
+ opts = []
91
+ cfg = cls.setup_config(args.cfg, args.model, args, opts)
92
+ logger.info(f"Loading model from {args.model}")
93
+ predictor = DefaultPredictor(cfg)
94
+ # logger.info(f"Loading data from {args.input}")
95
+ # file_list = cls._get_input_file_list(args.input)
96
+ # if len(file_list) == 0:
97
+ # logger.warning(f"No input images for {args.input}")
98
+ # return
99
+ context = cls.create_context(args, cfg)
100
+ # for file_name in file_list:
101
+ # img = read_image(file_name, format="BGR") # predictor expects BGR image.
102
+ with torch.no_grad():
103
+ outputs = predictor(human_img)["instances"]
104
+ out_pose = cls.execute_on_outputs(context, {"image": human_img}, outputs)
105
+ cls.postexecute(context)
106
+ return out_pose
107
+
108
+ @classmethod
109
+ def setup_config(
110
+ cls: type, config_fpath: str, model_fpath: str, args: argparse.Namespace, opts: List[str]
111
+ ):
112
+ cfg = get_cfg()
113
+ add_densepose_config(cfg)
114
+ cfg.merge_from_file(config_fpath)
115
+ cfg.merge_from_list(args.opts)
116
+ if opts:
117
+ cfg.merge_from_list(opts)
118
+ cfg.MODEL.WEIGHTS = model_fpath
119
+ cfg.freeze()
120
+ return cfg
121
+
122
+ @classmethod
123
+ def _get_input_file_list(cls: type, input_spec: str):
124
+ if os.path.isdir(input_spec):
125
+ file_list = [
126
+ os.path.join(input_spec, fname)
127
+ for fname in os.listdir(input_spec)
128
+ if os.path.isfile(os.path.join(input_spec, fname))
129
+ ]
130
+ elif os.path.isfile(input_spec):
131
+ file_list = [input_spec]
132
+ else:
133
+ file_list = glob.glob(input_spec)
134
+ return file_list
135
+
136
+
137
+ @register_action
138
+ class DumpAction(InferenceAction):
139
+ """
140
+ Dump action that outputs results to a pickle file
141
+ """
142
+
143
+ COMMAND: ClassVar[str] = "dump"
144
+
145
+ @classmethod
146
+ def add_parser(cls: type, subparsers: argparse._SubParsersAction):
147
+ parser = subparsers.add_parser(cls.COMMAND, help="Dump model outputs to a file.")
148
+ cls.add_arguments(parser)
149
+ parser.set_defaults(func=cls.execute)
150
+
151
+ @classmethod
152
+ def add_arguments(cls: type, parser: argparse.ArgumentParser):
153
+ super(DumpAction, cls).add_arguments(parser)
154
+ parser.add_argument(
155
+ "--output",
156
+ metavar="<dump_file>",
157
+ default="results.pkl",
158
+ help="File name to save dump to",
159
+ )
160
+
161
+ @classmethod
162
+ def execute_on_outputs(
163
+ cls: type, context: Dict[str, Any], entry: Dict[str, Any], outputs: Instances
164
+ ):
165
+ image_fpath = entry["file_name"]
166
+ logger.info(f"Processing {image_fpath}")
167
+ result = {"file_name": image_fpath}
168
+ if outputs.has("scores"):
169
+ result["scores"] = outputs.get("scores").cpu()
170
+ if outputs.has("pred_boxes"):
171
+ result["pred_boxes_XYXY"] = outputs.get("pred_boxes").tensor.cpu()
172
+ if outputs.has("pred_densepose"):
173
+ if isinstance(outputs.pred_densepose, DensePoseChartPredictorOutput):
174
+ extractor = DensePoseResultExtractor()
175
+ elif isinstance(outputs.pred_densepose, DensePoseEmbeddingPredictorOutput):
176
+ extractor = DensePoseOutputsExtractor()
177
+ result["pred_densepose"] = extractor(outputs)[0]
178
+ context["results"].append(result)
179
+
180
+ @classmethod
181
+ def create_context(cls: type, args: argparse.Namespace, cfg: CfgNode):
182
+ context = {"results": [], "out_fname": args.output}
183
+ return context
184
+
185
+ @classmethod
186
+ def postexecute(cls: type, context: Dict[str, Any]):
187
+ out_fname = context["out_fname"]
188
+ out_dir = os.path.dirname(out_fname)
189
+ if len(out_dir) > 0 and not os.path.exists(out_dir):
190
+ os.makedirs(out_dir)
191
+ with open(out_fname, "wb") as hFile:
192
+ torch.save(context["results"], hFile)
193
+ logger.info(f"Output saved to {out_fname}")
194
+
195
+
196
+ @register_action
197
+ class ShowAction(InferenceAction):
198
+ """
199
+ Show action that visualizes selected entries on an image
200
+ """
201
+
202
+ COMMAND: ClassVar[str] = "show"
203
+ VISUALIZERS: ClassVar[Dict[str, object]] = {
204
+ "dp_contour": DensePoseResultsContourVisualizer,
205
+ "dp_segm": DensePoseResultsFineSegmentationVisualizer,
206
+ "dp_u": DensePoseResultsUVisualizer,
207
+ "dp_v": DensePoseResultsVVisualizer,
208
+ "dp_iuv_texture": DensePoseResultsVisualizerWithTexture,
209
+ "dp_cse_texture": DensePoseOutputsTextureVisualizer,
210
+ "dp_vertex": DensePoseOutputsVertexVisualizer,
211
+ "bbox": ScoredBoundingBoxVisualizer,
212
+ }
213
+
214
+ @classmethod
215
+ def add_parser(cls: type, subparsers: argparse._SubParsersAction):
216
+ parser = subparsers.add_parser(cls.COMMAND, help="Visualize selected entries")
217
+ cls.add_arguments(parser)
218
+ parser.set_defaults(func=cls.execute)
219
+
220
+ @classmethod
221
+ def add_arguments(cls: type, parser: argparse.ArgumentParser):
222
+ super(ShowAction, cls).add_arguments(parser)
223
+ parser.add_argument(
224
+ "visualizations",
225
+ metavar="<visualizations>",
226
+ help="Comma separated list of visualizations, possible values: "
227
+ "[{}]".format(",".join(sorted(cls.VISUALIZERS.keys()))),
228
+ )
229
+ parser.add_argument(
230
+ "--min_score",
231
+ metavar="<score>",
232
+ default=0.8,
233
+ type=float,
234
+ help="Minimum detection score to visualize",
235
+ )
236
+ parser.add_argument(
237
+ "--nms_thresh", metavar="<threshold>", default=None, type=float, help="NMS threshold"
238
+ )
239
+ parser.add_argument(
240
+ "--texture_atlas",
241
+ metavar="<texture_atlas>",
242
+ default=None,
243
+ help="Texture atlas file (for IUV texture transfer)",
244
+ )
245
+ parser.add_argument(
246
+ "--texture_atlases_map",
247
+ metavar="<texture_atlases_map>",
248
+ default=None,
249
+ help="JSON string of a dict containing texture atlas files for each mesh",
250
+ )
251
+ parser.add_argument(
252
+ "--output",
253
+ metavar="<image_file>",
254
+ default="outputres.png",
255
+ help="File name to save output to",
256
+ )
257
+
258
+ @classmethod
259
+ def setup_config(
260
+ cls: type, config_fpath: str, model_fpath: str, args: argparse.Namespace, opts: List[str]
261
+ ):
262
+ opts.append("MODEL.ROI_HEADS.SCORE_THRESH_TEST")
263
+ opts.append(str(args.min_score))
264
+ if args.nms_thresh is not None:
265
+ opts.append("MODEL.ROI_HEADS.NMS_THRESH_TEST")
266
+ opts.append(str(args.nms_thresh))
267
+ cfg = super(ShowAction, cls).setup_config(config_fpath, model_fpath, args, opts)
268
+ return cfg
269
+
270
+ @classmethod
271
+ def execute_on_outputs(
272
+ cls: type, context: Dict[str, Any], entry: Dict[str, Any], outputs: Instances
273
+ ):
274
+ import cv2
275
+ import numpy as np
276
+ visualizer = context["visualizer"]
277
+ extractor = context["extractor"]
278
+ # image_fpath = entry["file_name"]
279
+ # logger.info(f"Processing {image_fpath}")
280
+ image = cv2.cvtColor(entry["image"], cv2.COLOR_BGR2GRAY)
281
+ image = np.tile(image[:, :, np.newaxis], [1, 1, 3])
282
+ data = extractor(outputs)
283
+ image_vis = visualizer.visualize(image, data)
284
+
285
+ return image_vis
286
+ entry_idx = context["entry_idx"] + 1
287
+ out_fname = './image-densepose/' + image_fpath.split('/')[-1]
288
+ out_dir = './image-densepose'
289
+ out_dir = os.path.dirname(out_fname)
290
+ if len(out_dir) > 0 and not os.path.exists(out_dir):
291
+ os.makedirs(out_dir)
292
+ cv2.imwrite(out_fname, image_vis)
293
+ logger.info(f"Output saved to {out_fname}")
294
+ context["entry_idx"] += 1
295
+
296
+ @classmethod
297
+ def postexecute(cls: type, context: Dict[str, Any]):
298
+ pass
299
+ # python ./apply_net.py show ./configs/densepose_rcnn_R_50_FPN_s1x.yaml https://dl.fbaipublicfiles.com/densepose/densepose_rcnn_R_50_FPN_s1x/165712039/model_final_162be9.pkl /home/alin0222/DressCode/upper_body/images dp_segm -v --opts MODEL.DEVICE cpu
300
+
301
+ @classmethod
302
+ def _get_out_fname(cls: type, entry_idx: int, fname_base: str):
303
+ base, ext = os.path.splitext(fname_base)
304
+ return base + ".{0:04d}".format(entry_idx) + ext
305
+
306
+ @classmethod
307
+ def create_context(cls: type, args: argparse.Namespace, cfg: CfgNode) -> Dict[str, Any]:
308
+ vis_specs = args.visualizations.split(",")
309
+ visualizers = []
310
+ extractors = []
311
+ for vis_spec in vis_specs:
312
+ texture_atlas = get_texture_atlas(args.texture_atlas)
313
+ texture_atlases_dict = get_texture_atlases(args.texture_atlases_map)
314
+ vis = cls.VISUALIZERS[vis_spec](
315
+ cfg=cfg,
316
+ texture_atlas=texture_atlas,
317
+ texture_atlases_dict=texture_atlases_dict,
318
+ )
319
+ visualizers.append(vis)
320
+ extractor = create_extractor(vis)
321
+ extractors.append(extractor)
322
+ visualizer = CompoundVisualizer(visualizers)
323
+ extractor = CompoundExtractor(extractors)
324
+ context = {
325
+ "extractor": extractor,
326
+ "visualizer": visualizer,
327
+ "out_fname": args.output,
328
+ "entry_idx": 0,
329
+ }
330
+ return context
331
+
332
+
333
+ def create_argument_parser() -> argparse.ArgumentParser:
334
+ parser = argparse.ArgumentParser(
335
+ description=DOC,
336
+ formatter_class=lambda prog: argparse.HelpFormatter(prog, max_help_position=120),
337
+ )
338
+ parser.set_defaults(func=lambda _: parser.print_help(sys.stdout))
339
+ subparsers = parser.add_subparsers(title="Actions")
340
+ for _, action in _ACTION_REGISTRY.items():
341
+ action.add_parser(subparsers)
342
+ return parser
343
+
344
+
345
+ def main():
346
+ parser = create_argument_parser()
347
+ args = parser.parse_args()
348
+ verbosity = getattr(args, "verbosity", None)
349
+ global logger
350
+ logger = setup_logger(name=LOGGER_NAME)
351
+ logger.setLevel(verbosity_to_level(verbosity))
352
+ args.func(args)
353
+
354
+
355
+ if __name__ == "__main__":
356
+ main()
357
+
358
+
359
+ # python ./apply_net.py show ./configs/densepose_rcnn_R_50_FPN_s1x.yaml https://dl.fbaipublicfiles.com/densepose/densepose_rcnn_R_50_FPN_s1x/165712039/model_final_162be9.pkl /home/alin0222/Dresscode/dresses/humanonly dp_segm -v --opts MODEL.DEVICE cuda
ckpt/densepose/model_final_162be9.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8a7382001b16e453bad95ca9dbc68ae8f2b839b304cf90eaf5c27fbdb4dae91
3
+ size 255757821
ckpt/humanparsing/parsing_atr.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04c7d1d070d0e0ae943d86b18cb5aaaea9e278d97462e9cfb270cbbe4cd977f4
3
+ size 266859305
ckpt/humanparsing/parsing_lip.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8436e1dae96e2601c373d1ace29c8f0978b16357d9038c17a8ba756cca376dbc
3
+ size 266863411
ckpt/openpose/.DS_Store ADDED
Binary file (6.15 kB). View file
 
ckpt/openpose/ckpts/body_pose_model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25a948c16078b0f08e236bda51a385d855ef4c153598947c28c0d47ed94bb746
3
+ size 209267595
configs/Base-DensePose-RCNN-FPN.yaml ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ VERSION: 2
2
+ MODEL:
3
+ META_ARCHITECTURE: "GeneralizedRCNN"
4
+ BACKBONE:
5
+ NAME: "build_resnet_fpn_backbone"
6
+ RESNETS:
7
+ OUT_FEATURES: ["res2", "res3", "res4", "res5"]
8
+ FPN:
9
+ IN_FEATURES: ["res2", "res3", "res4", "res5"]
10
+ ANCHOR_GENERATOR:
11
+ SIZES: [[32], [64], [128], [256], [512]] # One size for each in feature map
12
+ ASPECT_RATIOS: [[0.5, 1.0, 2.0]] # Three aspect ratios (same for all in feature maps)
13
+ RPN:
14
+ IN_FEATURES: ["p2", "p3", "p4", "p5", "p6"]
15
+ PRE_NMS_TOPK_TRAIN: 2000 # Per FPN level
16
+ PRE_NMS_TOPK_TEST: 1000 # Per FPN level
17
+ # Detectron1 uses 2000 proposals per-batch,
18
+ # (See "modeling/rpn/rpn_outputs.py" for details of this legacy issue)
19
+ # which is approximately 1000 proposals per-image since the default batch size for FPN is 2.
20
+ POST_NMS_TOPK_TRAIN: 1000
21
+ POST_NMS_TOPK_TEST: 1000
22
+
23
+ DENSEPOSE_ON: True
24
+ ROI_HEADS:
25
+ NAME: "DensePoseROIHeads"
26
+ IN_FEATURES: ["p2", "p3", "p4", "p5"]
27
+ NUM_CLASSES: 1
28
+ ROI_BOX_HEAD:
29
+ NAME: "FastRCNNConvFCHead"
30
+ NUM_FC: 2
31
+ POOLER_RESOLUTION: 7
32
+ POOLER_SAMPLING_RATIO: 2
33
+ POOLER_TYPE: "ROIAlign"
34
+ ROI_DENSEPOSE_HEAD:
35
+ NAME: "DensePoseV1ConvXHead"
36
+ POOLER_TYPE: "ROIAlign"
37
+ NUM_COARSE_SEGM_CHANNELS: 2
38
+ DATASETS:
39
+ TRAIN: ("densepose_coco_2014_train", "densepose_coco_2014_valminusminival")
40
+ TEST: ("densepose_coco_2014_minival",)
41
+ SOLVER:
42
+ IMS_PER_BATCH: 16
43
+ BASE_LR: 0.01
44
+ STEPS: (60000, 80000)
45
+ MAX_ITER: 90000
46
+ WARMUP_FACTOR: 0.1
47
+ INPUT:
48
+ MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
configs/HRNet/densepose_rcnn_HRFPN_HRNet_w32_s1x.yaml ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "../Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "https://1drv.ms/u/s!Aus8VCZ_C_33dYBMemi9xOUFR0w"
4
+ BACKBONE:
5
+ NAME: "build_hrfpn_backbone"
6
+ RPN:
7
+ IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5']
8
+ ROI_HEADS:
9
+ IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5']
10
+ SOLVER:
11
+ MAX_ITER: 130000
12
+ STEPS: (100000, 120000)
13
+ CLIP_GRADIENTS:
14
+ ENABLED: True
15
+ CLIP_TYPE: "norm"
16
+ BASE_LR: 0.03
configs/HRNet/densepose_rcnn_HRFPN_HRNet_w40_s1x.yaml ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "../Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "https://1drv.ms/u/s!Aus8VCZ_C_33ck0gvo5jfoWBOPo"
4
+ BACKBONE:
5
+ NAME: "build_hrfpn_backbone"
6
+ RPN:
7
+ IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5']
8
+ ROI_HEADS:
9
+ IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5']
10
+ HRNET:
11
+ STAGE2:
12
+ NUM_CHANNELS: [40, 80]
13
+ STAGE3:
14
+ NUM_CHANNELS: [40, 80, 160]
15
+ STAGE4:
16
+ NUM_CHANNELS: [40, 80, 160, 320]
17
+ SOLVER:
18
+ MAX_ITER: 130000
19
+ STEPS: (100000, 120000)
20
+ CLIP_GRADIENTS:
21
+ ENABLED: True
22
+ CLIP_TYPE: "norm"
23
+ BASE_LR: 0.03
configs/HRNet/densepose_rcnn_HRFPN_HRNet_w48_s1x.yaml ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "../Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "https://1drv.ms/u/s!Aus8VCZ_C_33dKvqI6pBZlifgJk"
4
+ BACKBONE:
5
+ NAME: "build_hrfpn_backbone"
6
+ RPN:
7
+ IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5']
8
+ ROI_HEADS:
9
+ IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5']
10
+ HRNET:
11
+ STAGE2:
12
+ NUM_CHANNELS: [48, 96]
13
+ STAGE3:
14
+ NUM_CHANNELS: [48, 96, 192]
15
+ STAGE4:
16
+ NUM_CHANNELS: [48, 96, 192, 384]
17
+ SOLVER:
18
+ MAX_ITER: 130000
19
+ STEPS: (100000, 120000)
20
+ CLIP_GRADIENTS:
21
+ ENABLED: True
22
+ CLIP_TYPE: "norm"
23
+ BASE_LR: 0.03
configs/cse/Base-DensePose-RCNN-FPN-Human.yaml ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ ROI_DENSEPOSE_HEAD:
4
+ CSE:
5
+ EMBEDDERS:
6
+ "smpl_27554":
7
+ TYPE: vertex_feature
8
+ NUM_VERTICES: 27554
9
+ FEATURE_DIM: 256
10
+ FEATURES_TRAINABLE: False
11
+ IS_TRAINABLE: True
12
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_smpl_27554_256.pkl"
13
+ DATASETS:
14
+ TRAIN:
15
+ - "densepose_coco_2014_train_cse"
16
+ - "densepose_coco_2014_valminusminival_cse"
17
+ TEST:
18
+ - "densepose_coco_2014_minival_cse"
19
+ CLASS_TO_MESH_NAME_MAPPING:
20
+ "0": "smpl_27554"
configs/cse/Base-DensePose-RCNN-FPN.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ VERSION: 2
2
+ MODEL:
3
+ META_ARCHITECTURE: "GeneralizedRCNN"
4
+ BACKBONE:
5
+ NAME: "build_resnet_fpn_backbone"
6
+ RESNETS:
7
+ OUT_FEATURES: ["res2", "res3", "res4", "res5"]
8
+ FPN:
9
+ IN_FEATURES: ["res2", "res3", "res4", "res5"]
10
+ ANCHOR_GENERATOR:
11
+ SIZES: [[32], [64], [128], [256], [512]] # One size for each in feature map
12
+ ASPECT_RATIOS: [[0.5, 1.0, 2.0]] # Three aspect ratios (same for all in feature maps)
13
+ RPN:
14
+ IN_FEATURES: ["p2", "p3", "p4", "p5", "p6"]
15
+ PRE_NMS_TOPK_TRAIN: 2000 # Per FPN level
16
+ PRE_NMS_TOPK_TEST: 1000 # Per FPN level
17
+ # Detectron1 uses 2000 proposals per-batch,
18
+ # (See "modeling/rpn/rpn_outputs.py" for details of this legacy issue)
19
+ # which is approximately 1000 proposals per-image since the default batch size for FPN is 2.
20
+ POST_NMS_TOPK_TRAIN: 1000
21
+ POST_NMS_TOPK_TEST: 1000
22
+
23
+ DENSEPOSE_ON: True
24
+ ROI_HEADS:
25
+ NAME: "DensePoseROIHeads"
26
+ IN_FEATURES: ["p2", "p3", "p4", "p5"]
27
+ NUM_CLASSES: 1
28
+ ROI_BOX_HEAD:
29
+ NAME: "FastRCNNConvFCHead"
30
+ NUM_FC: 2
31
+ POOLER_RESOLUTION: 7
32
+ POOLER_SAMPLING_RATIO: 2
33
+ POOLER_TYPE: "ROIAlign"
34
+ ROI_DENSEPOSE_HEAD:
35
+ NAME: "DensePoseV1ConvXHead"
36
+ POOLER_TYPE: "ROIAlign"
37
+ NUM_COARSE_SEGM_CHANNELS: 2
38
+ PREDICTOR_NAME: "DensePoseEmbeddingPredictor"
39
+ LOSS_NAME: "DensePoseCseLoss"
40
+ CSE:
41
+ # embedding loss, possible values:
42
+ # - "EmbeddingLoss"
43
+ # - "SoftEmbeddingLoss"
44
+ EMBED_LOSS_NAME: "EmbeddingLoss"
45
+ SOLVER:
46
+ IMS_PER_BATCH: 16
47
+ BASE_LR: 0.01
48
+ STEPS: (60000, 80000)
49
+ MAX_ITER: 90000
50
+ WARMUP_FACTOR: 0.1
51
+ CLIP_GRADIENTS:
52
+ CLIP_TYPE: norm
53
+ CLIP_VALUE: 1.0
54
+ ENABLED: true
55
+ NORM_TYPE: 2.0
56
+ INPUT:
57
+ MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
58
+ DENSEPOSE_EVALUATION:
59
+ TYPE: cse
60
+ STORAGE: file
configs/cse/densepose_rcnn_R_101_FPN_DL_s1x.yaml ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
2
+ MODEL:
3
+ WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
4
+ RESNETS:
5
+ DEPTH: 101
6
+ ROI_DENSEPOSE_HEAD:
7
+ NAME: "DensePoseDeepLabHead"
8
+ CSE:
9
+ EMBED_LOSS_NAME: "EmbeddingLoss"
10
+ SOLVER:
11
+ MAX_ITER: 130000
12
+ STEPS: (100000, 120000)
configs/cse/densepose_rcnn_R_101_FPN_DL_soft_s1x.yaml ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
2
+ MODEL:
3
+ WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
4
+ RESNETS:
5
+ DEPTH: 101
6
+ ROI_DENSEPOSE_HEAD:
7
+ NAME: "DensePoseDeepLabHead"
8
+ CSE:
9
+ EMBED_LOSS_NAME: "SoftEmbeddingLoss"
10
+ SOLVER:
11
+ MAX_ITER: 130000
12
+ STEPS: (100000, 120000)
configs/cse/densepose_rcnn_R_101_FPN_s1x.yaml ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
2
+ MODEL:
3
+ WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
4
+ RESNETS:
5
+ DEPTH: 101
6
+ ROI_DENSEPOSE_HEAD:
7
+ NAME: "DensePoseV1ConvXHead"
8
+ CSE:
9
+ EMBED_LOSS_NAME: "EmbeddingLoss"
10
+ SOLVER:
11
+ MAX_ITER: 130000
12
+ STEPS: (100000, 120000)
configs/cse/densepose_rcnn_R_101_FPN_soft_s1x.yaml ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
2
+ MODEL:
3
+ WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
4
+ RESNETS:
5
+ DEPTH: 101
6
+ ROI_DENSEPOSE_HEAD:
7
+ NAME: "DensePoseV1ConvXHead"
8
+ CSE:
9
+ EMBED_LOSS_NAME: "SoftEmbeddingLoss"
10
+ SOLVER:
11
+ MAX_ITER: 130000
12
+ STEPS: (100000, 120000)
configs/cse/densepose_rcnn_R_50_FPN_DL_s1x.yaml ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
2
+ MODEL:
3
+ WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
4
+ RESNETS:
5
+ DEPTH: 50
6
+ ROI_DENSEPOSE_HEAD:
7
+ NAME: "DensePoseDeepLabHead"
8
+ CSE:
9
+ EMBED_LOSS_NAME: "EmbeddingLoss"
10
+ SOLVER:
11
+ MAX_ITER: 130000
12
+ STEPS: (100000, 120000)
configs/cse/densepose_rcnn_R_50_FPN_DL_soft_s1x.yaml ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
2
+ MODEL:
3
+ WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
4
+ RESNETS:
5
+ DEPTH: 50
6
+ ROI_DENSEPOSE_HEAD:
7
+ NAME: "DensePoseDeepLabHead"
8
+ CSE:
9
+ EMBED_LOSS_NAME: "SoftEmbeddingLoss"
10
+ SOLVER:
11
+ MAX_ITER: 130000
12
+ STEPS: (100000, 120000)
configs/cse/densepose_rcnn_R_50_FPN_s1x.yaml ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
2
+ MODEL:
3
+ WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
4
+ RESNETS:
5
+ DEPTH: 50
6
+ ROI_DENSEPOSE_HEAD:
7
+ NAME: "DensePoseV1ConvXHead"
8
+ CSE:
9
+ EMBED_LOSS_NAME: "EmbeddingLoss"
10
+ SOLVER:
11
+ MAX_ITER: 130000
12
+ STEPS: (100000, 120000)
configs/cse/densepose_rcnn_R_50_FPN_soft_animals_CA_finetune_16k.yaml ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_s1x/250533982/model_final_2c4512.pkl"
4
+ RESNETS:
5
+ DEPTH: 50
6
+ ROI_HEADS:
7
+ NUM_CLASSES: 1
8
+ ROI_DENSEPOSE_HEAD:
9
+ NAME: "DensePoseV1ConvXHead"
10
+ COARSE_SEGM_TRAINED_BY_MASKS: True
11
+ CSE:
12
+ EMBED_LOSS_NAME: "SoftEmbeddingLoss"
13
+ EMBEDDING_DIST_GAUSS_SIGMA: 0.1
14
+ GEODESIC_DIST_GAUSS_SIGMA: 0.1
15
+ EMBEDDERS:
16
+ "cat_7466":
17
+ TYPE: vertex_feature
18
+ NUM_VERTICES: 7466
19
+ FEATURE_DIM: 256
20
+ FEATURES_TRAINABLE: False
21
+ IS_TRAINABLE: True
22
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_7466_256.pkl"
23
+ "dog_7466":
24
+ TYPE: vertex_feature
25
+ NUM_VERTICES: 7466
26
+ FEATURE_DIM: 256
27
+ FEATURES_TRAINABLE: False
28
+ IS_TRAINABLE: True
29
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_7466_256.pkl"
30
+ "sheep_5004":
31
+ TYPE: vertex_feature
32
+ NUM_VERTICES: 5004
33
+ FEATURE_DIM: 256
34
+ FEATURES_TRAINABLE: False
35
+ IS_TRAINABLE: True
36
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
37
+ "horse_5004":
38
+ TYPE: vertex_feature
39
+ NUM_VERTICES: 5004
40
+ FEATURE_DIM: 256
41
+ FEATURES_TRAINABLE: False
42
+ IS_TRAINABLE: True
43
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
44
+ "zebra_5002":
45
+ TYPE: vertex_feature
46
+ NUM_VERTICES: 5002
47
+ FEATURE_DIM: 256
48
+ FEATURES_TRAINABLE: False
49
+ IS_TRAINABLE: True
50
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
51
+ "giraffe_5002":
52
+ TYPE: vertex_feature
53
+ NUM_VERTICES: 5002
54
+ FEATURE_DIM: 256
55
+ FEATURES_TRAINABLE: False
56
+ IS_TRAINABLE: True
57
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
58
+ "elephant_5002":
59
+ TYPE: vertex_feature
60
+ NUM_VERTICES: 5002
61
+ FEATURE_DIM: 256
62
+ FEATURES_TRAINABLE: False
63
+ IS_TRAINABLE: True
64
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
65
+ "cow_5002":
66
+ TYPE: vertex_feature
67
+ NUM_VERTICES: 5002
68
+ FEATURE_DIM: 256
69
+ FEATURES_TRAINABLE: False
70
+ IS_TRAINABLE: True
71
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
72
+ "bear_4936":
73
+ TYPE: vertex_feature
74
+ NUM_VERTICES: 4936
75
+ FEATURE_DIM: 256
76
+ FEATURES_TRAINABLE: False
77
+ IS_TRAINABLE: True
78
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
79
+ DATASETS:
80
+ TRAIN:
81
+ - "densepose_lvis_v1_ds2_train_v1"
82
+ TEST:
83
+ - "densepose_lvis_v1_ds2_val_v1"
84
+ WHITELISTED_CATEGORIES:
85
+ "densepose_lvis_v1_ds2_train_v1":
86
+ - 943 # sheep
87
+ - 1202 # zebra
88
+ - 569 # horse
89
+ - 496 # giraffe
90
+ - 422 # elephant
91
+ - 80 # cow
92
+ - 76 # bear
93
+ - 225 # cat
94
+ - 378 # dog
95
+ "densepose_lvis_v1_ds2_val_v1":
96
+ - 943 # sheep
97
+ - 1202 # zebra
98
+ - 569 # horse
99
+ - 496 # giraffe
100
+ - 422 # elephant
101
+ - 80 # cow
102
+ - 76 # bear
103
+ - 225 # cat
104
+ - 378 # dog
105
+ CATEGORY_MAPS:
106
+ "densepose_lvis_v1_ds2_train_v1":
107
+ "1202": 943 # zebra -> sheep
108
+ "569": 943 # horse -> sheep
109
+ "496": 943 # giraffe -> sheep
110
+ "422": 943 # elephant -> sheep
111
+ "80": 943 # cow -> sheep
112
+ "76": 943 # bear -> sheep
113
+ "225": 943 # cat -> sheep
114
+ "378": 943 # dog -> sheep
115
+ "densepose_lvis_v1_ds2_val_v1":
116
+ "1202": 943 # zebra -> sheep
117
+ "569": 943 # horse -> sheep
118
+ "496": 943 # giraffe -> sheep
119
+ "422": 943 # elephant -> sheep
120
+ "80": 943 # cow -> sheep
121
+ "76": 943 # bear -> sheep
122
+ "225": 943 # cat -> sheep
123
+ "378": 943 # dog -> sheep
124
+ CLASS_TO_MESH_NAME_MAPPING:
125
+ # Note: different classes are mapped to a single class
126
+ # mesh is chosen based on GT data, so this is just some
127
+ # value which has no particular meaning
128
+ "0": "sheep_5004"
129
+ SOLVER:
130
+ MAX_ITER: 16000
131
+ STEPS: (12000, 14000)
132
+ DENSEPOSE_EVALUATION:
133
+ EVALUATE_MESH_ALIGNMENT: True
configs/cse/densepose_rcnn_R_50_FPN_soft_animals_CA_finetune_4k.yaml ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_s1x/250533982/model_final_2c4512.pkl"
4
+ RESNETS:
5
+ DEPTH: 50
6
+ ROI_HEADS:
7
+ NUM_CLASSES: 1
8
+ ROI_DENSEPOSE_HEAD:
9
+ NAME: "DensePoseV1ConvXHead"
10
+ COARSE_SEGM_TRAINED_BY_MASKS: True
11
+ CSE:
12
+ EMBED_LOSS_NAME: "SoftEmbeddingLoss"
13
+ EMBEDDING_DIST_GAUSS_SIGMA: 0.1
14
+ GEODESIC_DIST_GAUSS_SIGMA: 0.1
15
+ EMBEDDERS:
16
+ "cat_5001":
17
+ TYPE: vertex_feature
18
+ NUM_VERTICES: 5001
19
+ FEATURE_DIM: 256
20
+ FEATURES_TRAINABLE: False
21
+ IS_TRAINABLE: True
22
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_5001_256.pkl"
23
+ "dog_5002":
24
+ TYPE: vertex_feature
25
+ NUM_VERTICES: 5002
26
+ FEATURE_DIM: 256
27
+ FEATURES_TRAINABLE: False
28
+ IS_TRAINABLE: True
29
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_5002_256.pkl"
30
+ "sheep_5004":
31
+ TYPE: vertex_feature
32
+ NUM_VERTICES: 5004
33
+ FEATURE_DIM: 256
34
+ FEATURES_TRAINABLE: False
35
+ IS_TRAINABLE: True
36
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
37
+ "horse_5004":
38
+ TYPE: vertex_feature
39
+ NUM_VERTICES: 5004
40
+ FEATURE_DIM: 256
41
+ FEATURES_TRAINABLE: False
42
+ IS_TRAINABLE: True
43
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
44
+ "zebra_5002":
45
+ TYPE: vertex_feature
46
+ NUM_VERTICES: 5002
47
+ FEATURE_DIM: 256
48
+ FEATURES_TRAINABLE: False
49
+ IS_TRAINABLE: True
50
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
51
+ "giraffe_5002":
52
+ TYPE: vertex_feature
53
+ NUM_VERTICES: 5002
54
+ FEATURE_DIM: 256
55
+ FEATURES_TRAINABLE: False
56
+ IS_TRAINABLE: True
57
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
58
+ "elephant_5002":
59
+ TYPE: vertex_feature
60
+ NUM_VERTICES: 5002
61
+ FEATURE_DIM: 256
62
+ FEATURES_TRAINABLE: False
63
+ IS_TRAINABLE: True
64
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
65
+ "cow_5002":
66
+ TYPE: vertex_feature
67
+ NUM_VERTICES: 5002
68
+ FEATURE_DIM: 256
69
+ FEATURES_TRAINABLE: False
70
+ IS_TRAINABLE: True
71
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
72
+ "bear_4936":
73
+ TYPE: vertex_feature
74
+ NUM_VERTICES: 4936
75
+ FEATURE_DIM: 256
76
+ FEATURES_TRAINABLE: False
77
+ IS_TRAINABLE: True
78
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
79
+ DATASETS:
80
+ TRAIN:
81
+ - "densepose_lvis_v1_ds1_train_v1"
82
+ TEST:
83
+ - "densepose_lvis_v1_ds1_val_v1"
84
+ WHITELISTED_CATEGORIES:
85
+ "densepose_lvis_v1_ds1_train_v1":
86
+ - 943 # sheep
87
+ - 1202 # zebra
88
+ - 569 # horse
89
+ - 496 # giraffe
90
+ - 422 # elephant
91
+ - 80 # cow
92
+ - 76 # bear
93
+ - 225 # cat
94
+ - 378 # dog
95
+ "densepose_lvis_v1_ds1_val_v1":
96
+ - 943 # sheep
97
+ - 1202 # zebra
98
+ - 569 # horse
99
+ - 496 # giraffe
100
+ - 422 # elephant
101
+ - 80 # cow
102
+ - 76 # bear
103
+ - 225 # cat
104
+ - 378 # dog
105
+ CATEGORY_MAPS:
106
+ "densepose_lvis_v1_ds1_train_v1":
107
+ "1202": 943 # zebra -> sheep
108
+ "569": 943 # horse -> sheep
109
+ "496": 943 # giraffe -> sheep
110
+ "422": 943 # elephant -> sheep
111
+ "80": 943 # cow -> sheep
112
+ "76": 943 # bear -> sheep
113
+ "225": 943 # cat -> sheep
114
+ "378": 943 # dog -> sheep
115
+ "densepose_lvis_v1_ds1_val_v1":
116
+ "1202": 943 # zebra -> sheep
117
+ "569": 943 # horse -> sheep
118
+ "496": 943 # giraffe -> sheep
119
+ "422": 943 # elephant -> sheep
120
+ "80": 943 # cow -> sheep
121
+ "76": 943 # bear -> sheep
122
+ "225": 943 # cat -> sheep
123
+ "378": 943 # dog -> sheep
124
+ CLASS_TO_MESH_NAME_MAPPING:
125
+ # Note: different classes are mapped to a single class
126
+ # mesh is chosen based on GT data, so this is just some
127
+ # value which has no particular meaning
128
+ "0": "sheep_5004"
129
+ SOLVER:
130
+ MAX_ITER: 4000
131
+ STEPS: (3000, 3500)
132
+ DENSEPOSE_EVALUATION:
133
+ EVALUATE_MESH_ALIGNMENT: True
configs/cse/densepose_rcnn_R_50_FPN_soft_animals_I0_finetune_16k.yaml ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_animals_finetune_maskonly_24k/270668502/model_final_21b1d2.pkl"
4
+ RESNETS:
5
+ DEPTH: 50
6
+ ROI_HEADS:
7
+ NUM_CLASSES: 9
8
+ ROI_DENSEPOSE_HEAD:
9
+ NAME: "DensePoseV1ConvXHead"
10
+ COARSE_SEGM_TRAINED_BY_MASKS: True
11
+ CSE:
12
+ EMBED_LOSS_NAME: "SoftEmbeddingLoss"
13
+ EMBEDDING_DIST_GAUSS_SIGMA: 0.1
14
+ GEODESIC_DIST_GAUSS_SIGMA: 0.1
15
+ EMBEDDERS:
16
+ "cat_7466":
17
+ TYPE: vertex_feature
18
+ NUM_VERTICES: 7466
19
+ FEATURE_DIM: 256
20
+ FEATURES_TRAINABLE: False
21
+ IS_TRAINABLE: True
22
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_7466_256.pkl"
23
+ "dog_7466":
24
+ TYPE: vertex_feature
25
+ NUM_VERTICES: 7466
26
+ FEATURE_DIM: 256
27
+ FEATURES_TRAINABLE: False
28
+ IS_TRAINABLE: True
29
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_7466_256.pkl"
30
+ "sheep_5004":
31
+ TYPE: vertex_feature
32
+ NUM_VERTICES: 5004
33
+ FEATURE_DIM: 256
34
+ FEATURES_TRAINABLE: False
35
+ IS_TRAINABLE: True
36
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
37
+ "horse_5004":
38
+ TYPE: vertex_feature
39
+ NUM_VERTICES: 5004
40
+ FEATURE_DIM: 256
41
+ FEATURES_TRAINABLE: False
42
+ IS_TRAINABLE: True
43
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
44
+ "zebra_5002":
45
+ TYPE: vertex_feature
46
+ NUM_VERTICES: 5002
47
+ FEATURE_DIM: 256
48
+ FEATURES_TRAINABLE: False
49
+ IS_TRAINABLE: True
50
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
51
+ "giraffe_5002":
52
+ TYPE: vertex_feature
53
+ NUM_VERTICES: 5002
54
+ FEATURE_DIM: 256
55
+ FEATURES_TRAINABLE: False
56
+ IS_TRAINABLE: True
57
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
58
+ "elephant_5002":
59
+ TYPE: vertex_feature
60
+ NUM_VERTICES: 5002
61
+ FEATURE_DIM: 256
62
+ FEATURES_TRAINABLE: False
63
+ IS_TRAINABLE: True
64
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
65
+ "cow_5002":
66
+ TYPE: vertex_feature
67
+ NUM_VERTICES: 5002
68
+ FEATURE_DIM: 256
69
+ FEATURES_TRAINABLE: False
70
+ IS_TRAINABLE: True
71
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
72
+ "bear_4936":
73
+ TYPE: vertex_feature
74
+ NUM_VERTICES: 4936
75
+ FEATURE_DIM: 256
76
+ FEATURES_TRAINABLE: False
77
+ IS_TRAINABLE: True
78
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
79
+ DATASETS:
80
+ TRAIN:
81
+ - "densepose_lvis_v1_ds2_train_v1"
82
+ TEST:
83
+ - "densepose_lvis_v1_ds2_val_v1"
84
+ WHITELISTED_CATEGORIES:
85
+ "densepose_lvis_v1_ds2_train_v1":
86
+ - 943 # sheep
87
+ - 1202 # zebra
88
+ - 569 # horse
89
+ - 496 # giraffe
90
+ - 422 # elephant
91
+ - 80 # cow
92
+ - 76 # bear
93
+ - 225 # cat
94
+ - 378 # dog
95
+ "densepose_lvis_v1_ds2_val_v1":
96
+ - 943 # sheep
97
+ - 1202 # zebra
98
+ - 569 # horse
99
+ - 496 # giraffe
100
+ - 422 # elephant
101
+ - 80 # cow
102
+ - 76 # bear
103
+ - 225 # cat
104
+ - 378 # dog
105
+ CLASS_TO_MESH_NAME_MAPPING:
106
+ "0": "bear_4936"
107
+ "1": "cow_5002"
108
+ "2": "cat_7466"
109
+ "3": "dog_7466"
110
+ "4": "elephant_5002"
111
+ "5": "giraffe_5002"
112
+ "6": "horse_5004"
113
+ "7": "sheep_5004"
114
+ "8": "zebra_5002"
115
+ SOLVER:
116
+ MAX_ITER: 16000
117
+ STEPS: (12000, 14000)
118
+ DENSEPOSE_EVALUATION:
119
+ EVALUATE_MESH_ALIGNMENT: True
configs/cse/densepose_rcnn_R_50_FPN_soft_animals_I0_finetune_i2m_16k.yaml ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_animals_finetune_maskonly_24k/270668502/model_final_21b1d2.pkl"
4
+ RESNETS:
5
+ DEPTH: 50
6
+ ROI_HEADS:
7
+ NUM_CLASSES: 9
8
+ ROI_DENSEPOSE_HEAD:
9
+ NAME: "DensePoseV1ConvXHead"
10
+ COARSE_SEGM_TRAINED_BY_MASKS: True
11
+ CSE:
12
+ EMBED_LOSS_NAME: "SoftEmbeddingLoss"
13
+ EMBEDDING_DIST_GAUSS_SIGMA: 0.1
14
+ GEODESIC_DIST_GAUSS_SIGMA: 0.1
15
+ PIX_TO_SHAPE_CYCLE_LOSS:
16
+ ENABLED: True
17
+ EMBEDDERS:
18
+ "cat_7466":
19
+ TYPE: vertex_feature
20
+ NUM_VERTICES: 7466
21
+ FEATURE_DIM: 256
22
+ FEATURES_TRAINABLE: False
23
+ IS_TRAINABLE: True
24
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_7466_256.pkl"
25
+ "dog_7466":
26
+ TYPE: vertex_feature
27
+ NUM_VERTICES: 7466
28
+ FEATURE_DIM: 256
29
+ FEATURES_TRAINABLE: False
30
+ IS_TRAINABLE: True
31
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_7466_256.pkl"
32
+ "sheep_5004":
33
+ TYPE: vertex_feature
34
+ NUM_VERTICES: 5004
35
+ FEATURE_DIM: 256
36
+ FEATURES_TRAINABLE: False
37
+ IS_TRAINABLE: True
38
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
39
+ "horse_5004":
40
+ TYPE: vertex_feature
41
+ NUM_VERTICES: 5004
42
+ FEATURE_DIM: 256
43
+ FEATURES_TRAINABLE: False
44
+ IS_TRAINABLE: True
45
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
46
+ "zebra_5002":
47
+ TYPE: vertex_feature
48
+ NUM_VERTICES: 5002
49
+ FEATURE_DIM: 256
50
+ FEATURES_TRAINABLE: False
51
+ IS_TRAINABLE: True
52
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
53
+ "giraffe_5002":
54
+ TYPE: vertex_feature
55
+ NUM_VERTICES: 5002
56
+ FEATURE_DIM: 256
57
+ FEATURES_TRAINABLE: False
58
+ IS_TRAINABLE: True
59
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
60
+ "elephant_5002":
61
+ TYPE: vertex_feature
62
+ NUM_VERTICES: 5002
63
+ FEATURE_DIM: 256
64
+ FEATURES_TRAINABLE: False
65
+ IS_TRAINABLE: True
66
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
67
+ "cow_5002":
68
+ TYPE: vertex_feature
69
+ NUM_VERTICES: 5002
70
+ FEATURE_DIM: 256
71
+ FEATURES_TRAINABLE: False
72
+ IS_TRAINABLE: True
73
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
74
+ "bear_4936":
75
+ TYPE: vertex_feature
76
+ NUM_VERTICES: 4936
77
+ FEATURE_DIM: 256
78
+ FEATURES_TRAINABLE: False
79
+ IS_TRAINABLE: True
80
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
81
+ DATASETS:
82
+ TRAIN:
83
+ - "densepose_lvis_v1_ds2_train_v1"
84
+ TEST:
85
+ - "densepose_lvis_v1_ds2_val_v1"
86
+ WHITELISTED_CATEGORIES:
87
+ "densepose_lvis_v1_ds2_train_v1":
88
+ - 943 # sheep
89
+ - 1202 # zebra
90
+ - 569 # horse
91
+ - 496 # giraffe
92
+ - 422 # elephant
93
+ - 80 # cow
94
+ - 76 # bear
95
+ - 225 # cat
96
+ - 378 # dog
97
+ "densepose_lvis_v1_ds2_val_v1":
98
+ - 943 # sheep
99
+ - 1202 # zebra
100
+ - 569 # horse
101
+ - 496 # giraffe
102
+ - 422 # elephant
103
+ - 80 # cow
104
+ - 76 # bear
105
+ - 225 # cat
106
+ - 378 # dog
107
+ CLASS_TO_MESH_NAME_MAPPING:
108
+ "0": "bear_4936"
109
+ "1": "cow_5002"
110
+ "2": "cat_7466"
111
+ "3": "dog_7466"
112
+ "4": "elephant_5002"
113
+ "5": "giraffe_5002"
114
+ "6": "horse_5004"
115
+ "7": "sheep_5004"
116
+ "8": "zebra_5002"
117
+ SOLVER:
118
+ MAX_ITER: 16000
119
+ STEPS: (12000, 14000)
120
+ DENSEPOSE_EVALUATION:
121
+ EVALUATE_MESH_ALIGNMENT: True
configs/cse/densepose_rcnn_R_50_FPN_soft_animals_I0_finetune_m2m_16k.yaml ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_animals_finetune_maskonly_24k/267687159/model_final_354e61.pkl"
4
+ RESNETS:
5
+ DEPTH: 50
6
+ ROI_HEADS:
7
+ NUM_CLASSES: 9
8
+ ROI_DENSEPOSE_HEAD:
9
+ NAME: "DensePoseV1ConvXHead"
10
+ COARSE_SEGM_TRAINED_BY_MASKS: True
11
+ CSE:
12
+ EMBED_LOSS_NAME: "SoftEmbeddingLoss"
13
+ EMBEDDING_DIST_GAUSS_SIGMA: 0.1
14
+ GEODESIC_DIST_GAUSS_SIGMA: 0.1
15
+ SHAPE_TO_SHAPE_CYCLE_LOSS:
16
+ ENABLED: True
17
+ EMBEDDERS:
18
+ "cat_7466":
19
+ TYPE: vertex_feature
20
+ NUM_VERTICES: 7466
21
+ FEATURE_DIM: 256
22
+ FEATURES_TRAINABLE: False
23
+ IS_TRAINABLE: True
24
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_7466_256.pkl"
25
+ "dog_7466":
26
+ TYPE: vertex_feature
27
+ NUM_VERTICES: 7466
28
+ FEATURE_DIM: 256
29
+ FEATURES_TRAINABLE: False
30
+ IS_TRAINABLE: True
31
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_7466_256.pkl"
32
+ "sheep_5004":
33
+ TYPE: vertex_feature
34
+ NUM_VERTICES: 5004
35
+ FEATURE_DIM: 256
36
+ FEATURES_TRAINABLE: False
37
+ IS_TRAINABLE: True
38
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
39
+ "horse_5004":
40
+ TYPE: vertex_feature
41
+ NUM_VERTICES: 5004
42
+ FEATURE_DIM: 256
43
+ FEATURES_TRAINABLE: False
44
+ IS_TRAINABLE: True
45
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
46
+ "zebra_5002":
47
+ TYPE: vertex_feature
48
+ NUM_VERTICES: 5002
49
+ FEATURE_DIM: 256
50
+ FEATURES_TRAINABLE: False
51
+ IS_TRAINABLE: True
52
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
53
+ "giraffe_5002":
54
+ TYPE: vertex_feature
55
+ NUM_VERTICES: 5002
56
+ FEATURE_DIM: 256
57
+ FEATURES_TRAINABLE: False
58
+ IS_TRAINABLE: True
59
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
60
+ "elephant_5002":
61
+ TYPE: vertex_feature
62
+ NUM_VERTICES: 5002
63
+ FEATURE_DIM: 256
64
+ FEATURES_TRAINABLE: False
65
+ IS_TRAINABLE: True
66
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
67
+ "cow_5002":
68
+ TYPE: vertex_feature
69
+ NUM_VERTICES: 5002
70
+ FEATURE_DIM: 256
71
+ FEATURES_TRAINABLE: False
72
+ IS_TRAINABLE: True
73
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
74
+ "bear_4936":
75
+ TYPE: vertex_feature
76
+ NUM_VERTICES: 4936
77
+ FEATURE_DIM: 256
78
+ FEATURES_TRAINABLE: False
79
+ IS_TRAINABLE: True
80
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
81
+ "smpl_27554":
82
+ TYPE: vertex_feature
83
+ NUM_VERTICES: 27554
84
+ FEATURE_DIM: 256
85
+ FEATURES_TRAINABLE: False
86
+ IS_TRAINABLE: True
87
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_smpl_27554_256.pkl"
88
+ DATASETS:
89
+ TRAIN:
90
+ - "densepose_lvis_v1_ds2_train_v1"
91
+ TEST:
92
+ - "densepose_lvis_v1_ds2_val_v1"
93
+ WHITELISTED_CATEGORIES:
94
+ "densepose_lvis_v1_ds2_train_v1":
95
+ - 943 # sheep
96
+ - 1202 # zebra
97
+ - 569 # horse
98
+ - 496 # giraffe
99
+ - 422 # elephant
100
+ - 80 # cow
101
+ - 76 # bear
102
+ - 225 # cat
103
+ - 378 # dog
104
+ "densepose_lvis_v1_ds2_val_v1":
105
+ - 943 # sheep
106
+ - 1202 # zebra
107
+ - 569 # horse
108
+ - 496 # giraffe
109
+ - 422 # elephant
110
+ - 80 # cow
111
+ - 76 # bear
112
+ - 225 # cat
113
+ - 378 # dog
114
+ CLASS_TO_MESH_NAME_MAPPING:
115
+ "0": "bear_4936"
116
+ "1": "cow_5002"
117
+ "2": "cat_7466"
118
+ "3": "dog_7466"
119
+ "4": "elephant_5002"
120
+ "5": "giraffe_5002"
121
+ "6": "horse_5004"
122
+ "7": "sheep_5004"
123
+ "8": "zebra_5002"
124
+ SOLVER:
125
+ MAX_ITER: 16000
126
+ STEPS: (12000, 14000)
127
+ DENSEPOSE_EVALUATION:
128
+ EVALUATE_MESH_ALIGNMENT: True
129
+ MESH_ALIGNMENT_MESH_NAMES:
130
+ - bear_4936
131
+ - cow_5002
132
+ - cat_7466
133
+ - dog_7466
134
+ - elephant_5002
135
+ - giraffe_5002
136
+ - horse_5004
137
+ - sheep_5004
138
+ - zebra_5002
configs/cse/densepose_rcnn_R_50_FPN_soft_animals_finetune_16k.yaml ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_s1x/250533982/model_final_2c4512.pkl"
4
+ RESNETS:
5
+ DEPTH: 50
6
+ ROI_HEADS:
7
+ NUM_CLASSES: 9
8
+ ROI_DENSEPOSE_HEAD:
9
+ NAME: "DensePoseV1ConvXHead"
10
+ COARSE_SEGM_TRAINED_BY_MASKS: True
11
+ CSE:
12
+ EMBED_LOSS_NAME: "SoftEmbeddingLoss"
13
+ EMBEDDING_DIST_GAUSS_SIGMA: 0.1
14
+ GEODESIC_DIST_GAUSS_SIGMA: 0.1
15
+ EMBEDDERS:
16
+ "cat_7466":
17
+ TYPE: vertex_feature
18
+ NUM_VERTICES: 7466
19
+ FEATURE_DIM: 256
20
+ FEATURES_TRAINABLE: False
21
+ IS_TRAINABLE: True
22
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_7466_256.pkl"
23
+ "dog_7466":
24
+ TYPE: vertex_feature
25
+ NUM_VERTICES: 7466
26
+ FEATURE_DIM: 256
27
+ FEATURES_TRAINABLE: False
28
+ IS_TRAINABLE: True
29
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_7466_256.pkl"
30
+ "sheep_5004":
31
+ TYPE: vertex_feature
32
+ NUM_VERTICES: 5004
33
+ FEATURE_DIM: 256
34
+ FEATURES_TRAINABLE: False
35
+ IS_TRAINABLE: True
36
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
37
+ "horse_5004":
38
+ TYPE: vertex_feature
39
+ NUM_VERTICES: 5004
40
+ FEATURE_DIM: 256
41
+ FEATURES_TRAINABLE: False
42
+ IS_TRAINABLE: True
43
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
44
+ "zebra_5002":
45
+ TYPE: vertex_feature
46
+ NUM_VERTICES: 5002
47
+ FEATURE_DIM: 256
48
+ FEATURES_TRAINABLE: False
49
+ IS_TRAINABLE: True
50
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
51
+ "giraffe_5002":
52
+ TYPE: vertex_feature
53
+ NUM_VERTICES: 5002
54
+ FEATURE_DIM: 256
55
+ FEATURES_TRAINABLE: False
56
+ IS_TRAINABLE: True
57
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
58
+ "elephant_5002":
59
+ TYPE: vertex_feature
60
+ NUM_VERTICES: 5002
61
+ FEATURE_DIM: 256
62
+ FEATURES_TRAINABLE: False
63
+ IS_TRAINABLE: True
64
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
65
+ "cow_5002":
66
+ TYPE: vertex_feature
67
+ NUM_VERTICES: 5002
68
+ FEATURE_DIM: 256
69
+ FEATURES_TRAINABLE: False
70
+ IS_TRAINABLE: True
71
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
72
+ "bear_4936":
73
+ TYPE: vertex_feature
74
+ NUM_VERTICES: 4936
75
+ FEATURE_DIM: 256
76
+ FEATURES_TRAINABLE: False
77
+ IS_TRAINABLE: True
78
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
79
+ DATASETS:
80
+ TRAIN:
81
+ - "densepose_lvis_v1_ds2_train_v1"
82
+ TEST:
83
+ - "densepose_lvis_v1_ds2_val_v1"
84
+ WHITELISTED_CATEGORIES:
85
+ "densepose_lvis_v1_ds2_train_v1":
86
+ - 943 # sheep
87
+ - 1202 # zebra
88
+ - 569 # horse
89
+ - 496 # giraffe
90
+ - 422 # elephant
91
+ - 80 # cow
92
+ - 76 # bear
93
+ - 225 # cat
94
+ - 378 # dog
95
+ "densepose_lvis_v1_ds2_val_v1":
96
+ - 943 # sheep
97
+ - 1202 # zebra
98
+ - 569 # horse
99
+ - 496 # giraffe
100
+ - 422 # elephant
101
+ - 80 # cow
102
+ - 76 # bear
103
+ - 225 # cat
104
+ - 378 # dog
105
+ CLASS_TO_MESH_NAME_MAPPING:
106
+ "0": "bear_4936"
107
+ "1": "cow_5002"
108
+ "2": "cat_7466"
109
+ "3": "dog_7466"
110
+ "4": "elephant_5002"
111
+ "5": "giraffe_5002"
112
+ "6": "horse_5004"
113
+ "7": "sheep_5004"
114
+ "8": "zebra_5002"
115
+ SOLVER:
116
+ MAX_ITER: 16000
117
+ STEPS: (12000, 14000)
118
+ DENSEPOSE_EVALUATION:
119
+ EVALUATE_MESH_ALIGNMENT: True
configs/cse/densepose_rcnn_R_50_FPN_soft_animals_finetune_4k.yaml ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_s1x/250533982/model_final_2c4512.pkl"
4
+ RESNETS:
5
+ DEPTH: 50
6
+ ROI_HEADS:
7
+ NUM_CLASSES: 9
8
+ ROI_DENSEPOSE_HEAD:
9
+ NAME: "DensePoseV1ConvXHead"
10
+ COARSE_SEGM_TRAINED_BY_MASKS: True
11
+ CSE:
12
+ EMBED_LOSS_NAME: "SoftEmbeddingLoss"
13
+ EMBEDDING_DIST_GAUSS_SIGMA: 0.1
14
+ GEODESIC_DIST_GAUSS_SIGMA: 0.1
15
+ EMBEDDERS:
16
+ "cat_5001":
17
+ TYPE: vertex_feature
18
+ NUM_VERTICES: 5001
19
+ FEATURE_DIM: 256
20
+ FEATURES_TRAINABLE: False
21
+ IS_TRAINABLE: True
22
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_5001_256.pkl"
23
+ "dog_5002":
24
+ TYPE: vertex_feature
25
+ NUM_VERTICES: 5002
26
+ FEATURE_DIM: 256
27
+ FEATURES_TRAINABLE: False
28
+ IS_TRAINABLE: True
29
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_5002_256.pkl"
30
+ "sheep_5004":
31
+ TYPE: vertex_feature
32
+ NUM_VERTICES: 5004
33
+ FEATURE_DIM: 256
34
+ FEATURES_TRAINABLE: False
35
+ IS_TRAINABLE: True
36
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
37
+ "horse_5004":
38
+ TYPE: vertex_feature
39
+ NUM_VERTICES: 5004
40
+ FEATURE_DIM: 256
41
+ FEATURES_TRAINABLE: False
42
+ IS_TRAINABLE: True
43
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
44
+ "zebra_5002":
45
+ TYPE: vertex_feature
46
+ NUM_VERTICES: 5002
47
+ FEATURE_DIM: 256
48
+ FEATURES_TRAINABLE: False
49
+ IS_TRAINABLE: True
50
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
51
+ "giraffe_5002":
52
+ TYPE: vertex_feature
53
+ NUM_VERTICES: 5002
54
+ FEATURE_DIM: 256
55
+ FEATURES_TRAINABLE: False
56
+ IS_TRAINABLE: True
57
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
58
+ "elephant_5002":
59
+ TYPE: vertex_feature
60
+ NUM_VERTICES: 5002
61
+ FEATURE_DIM: 256
62
+ FEATURES_TRAINABLE: False
63
+ IS_TRAINABLE: True
64
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
65
+ "cow_5002":
66
+ TYPE: vertex_feature
67
+ NUM_VERTICES: 5002
68
+ FEATURE_DIM: 256
69
+ FEATURES_TRAINABLE: False
70
+ IS_TRAINABLE: True
71
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
72
+ "bear_4936":
73
+ TYPE: vertex_feature
74
+ NUM_VERTICES: 4936
75
+ FEATURE_DIM: 256
76
+ FEATURES_TRAINABLE: False
77
+ IS_TRAINABLE: True
78
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
79
+ DATASETS:
80
+ TRAIN:
81
+ - "densepose_lvis_v1_ds1_train_v1"
82
+ TEST:
83
+ - "densepose_lvis_v1_ds1_val_v1"
84
+ WHITELISTED_CATEGORIES:
85
+ "densepose_lvis_v1_ds1_train_v1":
86
+ - 943 # sheep
87
+ - 1202 # zebra
88
+ - 569 # horse
89
+ - 496 # giraffe
90
+ - 422 # elephant
91
+ - 80 # cow
92
+ - 76 # bear
93
+ - 225 # cat
94
+ - 378 # dog
95
+ "densepose_lvis_v1_ds1_val_v1":
96
+ - 943 # sheep
97
+ - 1202 # zebra
98
+ - 569 # horse
99
+ - 496 # giraffe
100
+ - 422 # elephant
101
+ - 80 # cow
102
+ - 76 # bear
103
+ - 225 # cat
104
+ - 378 # dog
105
+ CLASS_TO_MESH_NAME_MAPPING:
106
+ "0": "bear_4936"
107
+ "1": "cow_5002"
108
+ "2": "cat_5001"
109
+ "3": "dog_5002"
110
+ "4": "elephant_5002"
111
+ "5": "giraffe_5002"
112
+ "6": "horse_5004"
113
+ "7": "sheep_5004"
114
+ "8": "zebra_5002"
115
+ SOLVER:
116
+ MAX_ITER: 4000
117
+ STEPS: (3000, 3500)
118
+ DENSEPOSE_EVALUATION:
119
+ EVALUATE_MESH_ALIGNMENT: True
configs/cse/densepose_rcnn_R_50_FPN_soft_animals_finetune_maskonly_24k.yaml ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_s1x/250533982/model_final_2c4512.pkl"
4
+ RESNETS:
5
+ DEPTH: 50
6
+ ROI_HEADS:
7
+ NUM_CLASSES: 9
8
+ ROI_DENSEPOSE_HEAD:
9
+ NAME: "DensePoseV1ConvXHead"
10
+ COARSE_SEGM_TRAINED_BY_MASKS: True
11
+ CSE:
12
+ EMBED_LOSS_NAME: "SoftEmbeddingLoss"
13
+ EMBED_LOSS_WEIGHT: 0.0
14
+ EMBEDDING_DIST_GAUSS_SIGMA: 0.1
15
+ GEODESIC_DIST_GAUSS_SIGMA: 0.1
16
+ EMBEDDERS:
17
+ "cat_7466":
18
+ TYPE: vertex_feature
19
+ NUM_VERTICES: 7466
20
+ FEATURE_DIM: 256
21
+ FEATURES_TRAINABLE: False
22
+ IS_TRAINABLE: True
23
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_7466_256.pkl"
24
+ "dog_7466":
25
+ TYPE: vertex_feature
26
+ NUM_VERTICES: 7466
27
+ FEATURE_DIM: 256
28
+ FEATURES_TRAINABLE: False
29
+ IS_TRAINABLE: True
30
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_7466_256.pkl"
31
+ "sheep_5004":
32
+ TYPE: vertex_feature
33
+ NUM_VERTICES: 5004
34
+ FEATURE_DIM: 256
35
+ FEATURES_TRAINABLE: False
36
+ IS_TRAINABLE: True
37
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
38
+ "horse_5004":
39
+ TYPE: vertex_feature
40
+ NUM_VERTICES: 5004
41
+ FEATURE_DIM: 256
42
+ FEATURES_TRAINABLE: False
43
+ IS_TRAINABLE: True
44
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
45
+ "zebra_5002":
46
+ TYPE: vertex_feature
47
+ NUM_VERTICES: 5002
48
+ FEATURE_DIM: 256
49
+ FEATURES_TRAINABLE: False
50
+ IS_TRAINABLE: True
51
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
52
+ "giraffe_5002":
53
+ TYPE: vertex_feature
54
+ NUM_VERTICES: 5002
55
+ FEATURE_DIM: 256
56
+ FEATURES_TRAINABLE: False
57
+ IS_TRAINABLE: True
58
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
59
+ "elephant_5002":
60
+ TYPE: vertex_feature
61
+ NUM_VERTICES: 5002
62
+ FEATURE_DIM: 256
63
+ FEATURES_TRAINABLE: False
64
+ IS_TRAINABLE: True
65
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
66
+ "cow_5002":
67
+ TYPE: vertex_feature
68
+ NUM_VERTICES: 5002
69
+ FEATURE_DIM: 256
70
+ FEATURES_TRAINABLE: False
71
+ IS_TRAINABLE: True
72
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
73
+ "bear_4936":
74
+ TYPE: vertex_feature
75
+ NUM_VERTICES: 4936
76
+ FEATURE_DIM: 256
77
+ FEATURES_TRAINABLE: False
78
+ IS_TRAINABLE: True
79
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
80
+ DATASETS:
81
+ TRAIN:
82
+ - "densepose_lvis_v1_ds2_train_v1"
83
+ TEST:
84
+ - "densepose_lvis_v1_ds2_val_v1"
85
+ WHITELISTED_CATEGORIES:
86
+ "densepose_lvis_v1_ds2_train_v1":
87
+ - 943 # sheep
88
+ - 1202 # zebra
89
+ - 569 # horse
90
+ - 496 # giraffe
91
+ - 422 # elephant
92
+ - 80 # cow
93
+ - 76 # bear
94
+ - 225 # cat
95
+ - 378 # dog
96
+ "densepose_lvis_v1_ds2_val_v1":
97
+ - 943 # sheep
98
+ - 1202 # zebra
99
+ - 569 # horse
100
+ - 496 # giraffe
101
+ - 422 # elephant
102
+ - 80 # cow
103
+ - 76 # bear
104
+ - 225 # cat
105
+ - 378 # dog
106
+ CLASS_TO_MESH_NAME_MAPPING:
107
+ "0": "bear_4936"
108
+ "1": "cow_5002"
109
+ "2": "cat_7466"
110
+ "3": "dog_7466"
111
+ "4": "elephant_5002"
112
+ "5": "giraffe_5002"
113
+ "6": "horse_5004"
114
+ "7": "sheep_5004"
115
+ "8": "zebra_5002"
116
+ SOLVER:
117
+ MAX_ITER: 24000
118
+ STEPS: (20000, 22000)
configs/cse/densepose_rcnn_R_50_FPN_soft_chimps_finetune_4k.yaml ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_s1x/250533982/model_final_2c4512.pkl"
4
+ RESNETS:
5
+ DEPTH: 50
6
+ ROI_DENSEPOSE_HEAD:
7
+ NAME: "DensePoseV1ConvXHead"
8
+ CSE:
9
+ EMBED_LOSS_NAME: "SoftEmbeddingLoss"
10
+ EMBEDDING_DIST_GAUSS_SIGMA: 0.1
11
+ GEODESIC_DIST_GAUSS_SIGMA: 0.1
12
+ EMBEDDERS:
13
+ "chimp_5029":
14
+ TYPE: vertex_feature
15
+ NUM_VERTICES: 5029
16
+ FEATURE_DIM: 256
17
+ FEATURES_TRAINABLE: False
18
+ IS_TRAINABLE: True
19
+ INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_chimp_5029_256.pkl"
20
+ DATASETS:
21
+ TRAIN:
22
+ - "densepose_chimps_cse_train"
23
+ TEST:
24
+ - "densepose_chimps_cse_val"
25
+ CLASS_TO_MESH_NAME_MAPPING:
26
+ "0": "chimp_5029"
27
+ SOLVER:
28
+ MAX_ITER: 4000
29
+ STEPS: (3000, 3500)
configs/cse/densepose_rcnn_R_50_FPN_soft_s1x.yaml ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
2
+ MODEL:
3
+ WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
4
+ RESNETS:
5
+ DEPTH: 50
6
+ ROI_DENSEPOSE_HEAD:
7
+ NAME: "DensePoseV1ConvXHead"
8
+ CSE:
9
+ EMBED_LOSS_NAME: "SoftEmbeddingLoss"
10
+ SOLVER:
11
+ MAX_ITER: 130000
12
+ STEPS: (100000, 120000)
configs/densepose_rcnn_R_101_FPN_DL_WC1M_s1x.yaml ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
4
+ RESNETS:
5
+ DEPTH: 101
6
+ ROI_DENSEPOSE_HEAD:
7
+ NAME: "DensePoseDeepLabHead"
8
+ UV_CONFIDENCE:
9
+ ENABLED: True
10
+ TYPE: "iid_iso"
11
+ SEGM_CONFIDENCE:
12
+ ENABLED: True
13
+ POINT_REGRESSION_WEIGHTS: 0.0005
14
+ SOLVER:
15
+ CLIP_GRADIENTS:
16
+ ENABLED: True
17
+ MAX_ITER: 130000
18
+ STEPS: (100000, 120000)
configs/densepose_rcnn_R_101_FPN_DL_WC1_s1x.yaml ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
4
+ RESNETS:
5
+ DEPTH: 101
6
+ ROI_DENSEPOSE_HEAD:
7
+ NAME: "DensePoseDeepLabHead"
8
+ UV_CONFIDENCE:
9
+ ENABLED: True
10
+ TYPE: "iid_iso"
11
+ POINT_REGRESSION_WEIGHTS: 0.0005
12
+ SOLVER:
13
+ CLIP_GRADIENTS:
14
+ ENABLED: True
15
+ MAX_ITER: 130000
16
+ STEPS: (100000, 120000)
configs/densepose_rcnn_R_101_FPN_DL_WC2M_s1x.yaml ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
4
+ RESNETS:
5
+ DEPTH: 101
6
+ ROI_DENSEPOSE_HEAD:
7
+ NAME: "DensePoseDeepLabHead"
8
+ UV_CONFIDENCE:
9
+ ENABLED: True
10
+ TYPE: "indep_aniso"
11
+ SEGM_CONFIDENCE:
12
+ ENABLED: True
13
+ POINT_REGRESSION_WEIGHTS: 0.0005
14
+ SOLVER:
15
+ CLIP_GRADIENTS:
16
+ ENABLED: True
17
+ MAX_ITER: 130000
18
+ STEPS: (100000, 120000)
configs/densepose_rcnn_R_101_FPN_DL_WC2_s1x.yaml ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
4
+ RESNETS:
5
+ DEPTH: 101
6
+ ROI_DENSEPOSE_HEAD:
7
+ NAME: "DensePoseDeepLabHead"
8
+ UV_CONFIDENCE:
9
+ ENABLED: True
10
+ TYPE: "indep_aniso"
11
+ POINT_REGRESSION_WEIGHTS: 0.0005
12
+ SOLVER:
13
+ CLIP_GRADIENTS:
14
+ ENABLED: True
15
+ MAX_ITER: 130000
16
+ STEPS: (100000, 120000)
configs/densepose_rcnn_R_101_FPN_DL_s1x.yaml ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
4
+ RESNETS:
5
+ DEPTH: 101
6
+ ROI_DENSEPOSE_HEAD:
7
+ NAME: "DensePoseDeepLabHead"
8
+ SOLVER:
9
+ MAX_ITER: 130000
10
+ STEPS: (100000, 120000)
configs/densepose_rcnn_R_101_FPN_WC1M_s1x.yaml ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
4
+ RESNETS:
5
+ DEPTH: 101
6
+ ROI_DENSEPOSE_HEAD:
7
+ UV_CONFIDENCE:
8
+ ENABLED: True
9
+ TYPE: "iid_iso"
10
+ SEGM_CONFIDENCE:
11
+ ENABLED: True
12
+ POINT_REGRESSION_WEIGHTS: 0.0005
13
+ SOLVER:
14
+ CLIP_GRADIENTS:
15
+ ENABLED: True
16
+ MAX_ITER: 130000
17
+ STEPS: (100000, 120000)
18
+ WARMUP_FACTOR: 0.025
configs/densepose_rcnn_R_101_FPN_WC1_s1x.yaml ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
4
+ RESNETS:
5
+ DEPTH: 101
6
+ ROI_DENSEPOSE_HEAD:
7
+ UV_CONFIDENCE:
8
+ ENABLED: True
9
+ TYPE: "iid_iso"
10
+ POINT_REGRESSION_WEIGHTS: 0.0005
11
+ SOLVER:
12
+ CLIP_GRADIENTS:
13
+ ENABLED: True
14
+ MAX_ITER: 130000
15
+ STEPS: (100000, 120000)
16
+ WARMUP_FACTOR: 0.025
configs/densepose_rcnn_R_101_FPN_WC2M_s1x.yaml ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
4
+ RESNETS:
5
+ DEPTH: 101
6
+ ROI_DENSEPOSE_HEAD:
7
+ UV_CONFIDENCE:
8
+ ENABLED: True
9
+ TYPE: "indep_aniso"
10
+ SEGM_CONFIDENCE:
11
+ ENABLED: True
12
+ POINT_REGRESSION_WEIGHTS: 0.0005
13
+ SOLVER:
14
+ CLIP_GRADIENTS:
15
+ ENABLED: True
16
+ MAX_ITER: 130000
17
+ STEPS: (100000, 120000)
18
+ WARMUP_FACTOR: 0.025
configs/densepose_rcnn_R_101_FPN_WC2_s1x.yaml ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
4
+ RESNETS:
5
+ DEPTH: 101
6
+ ROI_DENSEPOSE_HEAD:
7
+ UV_CONFIDENCE:
8
+ ENABLED: True
9
+ TYPE: "indep_aniso"
10
+ POINT_REGRESSION_WEIGHTS: 0.0005
11
+ SOLVER:
12
+ CLIP_GRADIENTS:
13
+ ENABLED: True
14
+ MAX_ITER: 130000
15
+ STEPS: (100000, 120000)
16
+ WARMUP_FACTOR: 0.025
configs/densepose_rcnn_R_101_FPN_s1x.yaml ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
4
+ RESNETS:
5
+ DEPTH: 101
6
+ SOLVER:
7
+ MAX_ITER: 130000
8
+ STEPS: (100000, 120000)
configs/densepose_rcnn_R_101_FPN_s1x_legacy.yaml ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
4
+ RESNETS:
5
+ DEPTH: 101
6
+ ROI_DENSEPOSE_HEAD:
7
+ NUM_COARSE_SEGM_CHANNELS: 15
8
+ POOLER_RESOLUTION: 14
9
+ HEATMAP_SIZE: 56
10
+ INDEX_WEIGHTS: 2.0
11
+ PART_WEIGHTS: 0.3
12
+ POINT_REGRESSION_WEIGHTS: 0.1
13
+ DECODER_ON: False
14
+ SOLVER:
15
+ BASE_LR: 0.002
16
+ MAX_ITER: 130000
17
+ STEPS: (100000, 120000)
configs/densepose_rcnn_R_50_FPN_DL_WC1M_s1x.yaml ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
4
+ RESNETS:
5
+ DEPTH: 50
6
+ ROI_DENSEPOSE_HEAD:
7
+ NAME: "DensePoseDeepLabHead"
8
+ UV_CONFIDENCE:
9
+ ENABLED: True
10
+ TYPE: "iid_iso"
11
+ SEGM_CONFIDENCE:
12
+ ENABLED: True
13
+ POINT_REGRESSION_WEIGHTS: 0.0005
14
+ SOLVER:
15
+ CLIP_GRADIENTS:
16
+ ENABLED: True
17
+ MAX_ITER: 130000
18
+ STEPS: (100000, 120000)
configs/densepose_rcnn_R_50_FPN_DL_WC1_s1x.yaml ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
4
+ RESNETS:
5
+ DEPTH: 50
6
+ ROI_DENSEPOSE_HEAD:
7
+ NAME: "DensePoseDeepLabHead"
8
+ UV_CONFIDENCE:
9
+ ENABLED: True
10
+ TYPE: "iid_iso"
11
+ POINT_REGRESSION_WEIGHTS: 0.0005
12
+ SOLVER:
13
+ CLIP_GRADIENTS:
14
+ ENABLED: True
15
+ MAX_ITER: 130000
16
+ STEPS: (100000, 120000)
configs/densepose_rcnn_R_50_FPN_DL_WC2M_s1x.yaml ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
4
+ RESNETS:
5
+ DEPTH: 50
6
+ ROI_DENSEPOSE_HEAD:
7
+ NAME: "DensePoseDeepLabHead"
8
+ UV_CONFIDENCE:
9
+ ENABLED: True
10
+ TYPE: "indep_aniso"
11
+ SEGM_CONFIDENCE:
12
+ ENABLED: True
13
+ POINT_REGRESSION_WEIGHTS: 0.0005
14
+ SOLVER:
15
+ CLIP_GRADIENTS:
16
+ ENABLED: True
17
+ MAX_ITER: 130000
18
+ STEPS: (100000, 120000)
configs/densepose_rcnn_R_50_FPN_DL_WC2_s1x.yaml ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _BASE_: "Base-DensePose-RCNN-FPN.yaml"
2
+ MODEL:
3
+ WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
4
+ RESNETS:
5
+ DEPTH: 50
6
+ ROI_DENSEPOSE_HEAD:
7
+ NAME: "DensePoseDeepLabHead"
8
+ UV_CONFIDENCE:
9
+ ENABLED: True
10
+ TYPE: "indep_aniso"
11
+ POINT_REGRESSION_WEIGHTS: 0.0005
12
+ SOLVER:
13
+ CLIP_GRADIENTS:
14
+ ENABLED: True
15
+ MAX_ITER: 130000
16
+ STEPS: (100000, 120000)