1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
|
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Clean Human Pose MPI Dataset\n",
"\n",
"Fix data\n",
"\n",
"Data structure:\n",
"- `data[2]` = 2 x 7 x 100 array\n",
"- `data[2][0]` = x locations\n",
"- `data[2][0]` = y locations\n",
"- ordering is `0 Head, 1 Right wrist, 2 Left wrist, 3 Right elbow, 4 Left elbow, 5 Right shoulder and 6 Left shoulder`"
]
},
{
"cell_type": "code",
"execution_count": 175,
"metadata": {},
"outputs": [],
"source": [
"%reload_ext autoreload\n",
"%autoreload 2\n",
"\n",
"import os\n",
"from os.path import join\n",
"import math\n",
"from glob import glob\n",
"from random import randint\n",
"\n",
"import cv2 as cv\n",
"import numpy as np\n",
"import pandas as pd\n",
"from PIL import Image, ImageDraw\n",
"%matplotlib inline\n",
"import matplotlib.pyplot as plt\n",
"import scipy.io\n",
"from pathlib import Path\n",
"from sklearn import preprocessing\n",
"\n",
"import sys\n",
"sys.path.append('/work/megapixels_dev/megapixels/')\n",
"from app.settings import app_cfg as cfg\n",
"from app.utils import file_utils"
]
},
{
"cell_type": "code",
"execution_count": 176,
"metadata": {},
"outputs": [],
"source": [
"DATA_STORE = '/data_store_nas/'\n",
"fp_dataset = join(DATA_STORE, 'datasets/people/youtube_poses')\n",
"dir_fp_frames = join(fp_dataset, 'YouTube_Pose_dataset_1.0/GT_frames')"
]
},
{
"cell_type": "code",
"execution_count": 177,
"metadata": {},
"outputs": [],
"source": [
"dirs_frames = glob(join(dir_fp_frames, '*'))\n",
"fps_frames = {}\n",
"for dir_frames in dirs_frames:\n",
" fps_frames[dir_frames] = join(dir_frames, '*')"
]
},
{
"cell_type": "code",
"execution_count": 178,
"metadata": {},
"outputs": [],
"source": [
"fp_pose_data = join(fp_dataset, 'YouTube_Pose_dataset_1.0/YouTube_Pose_dataset.mat')\n",
"fp_out = join(fp_dataset, 'poses.csv')\n",
"pose_data = scipy.io.loadmat(fp_pose_data)['data'][0]"
]
},
{
"cell_type": "code",
"execution_count": 182,
"metadata": {},
"outputs": [],
"source": [
"# convert data to pandas DF for sanity\n",
"poses = []\n",
"for i, pose in enumerate(pose_data):\n",
"\n",
" video_id = pose[1][0]\n",
" pose_pts = pose[2]\n",
" crop_x1 = int(pose[6][0][0])\n",
" crop_y1 = int(pose[6][0][1])\n",
" crop_x2 = int(pose[6][0][2])\n",
" crop_y2 = int(pose[6][0][3])\n",
" w = pose[7][0][0]\n",
" h = pose[7][0][1]\n",
" scale = pose[5][0][0]\n",
" \n",
" for j in range(pose_pts.shape[2]): # 100 frames\n",
" x = [pose_pts[0][i][j] for i in range(7)]\n",
" y = [pose_pts[1][i][j] for i in range(7)]\n",
" poses.append({\n",
" 'video_id': video_id, \n",
" 'scale': scale,\n",
" 'crop_x1': crop_x1,\n",
" 'crop_y1': crop_y1,\n",
" 'crop_x2': crop_x2,\n",
" 'crop_y2': crop_y2,\n",
" 'width': w, \n",
" 'height': h,\n",
" 'head_x': x[0],\n",
" 'head_y': y[0],\n",
" 'wrist_right_x': x[1],\n",
" 'wrist_right_y': y[1],\n",
" 'wrist_left_x': x[2], \n",
" 'wrist_left_y': y[2],\n",
" 'elbow_right_x': x[3],\n",
" 'elbow_right_y': y[3],\n",
" 'elbow_left_x': x[4], \n",
" 'elbow_left_y': y[4],\n",
" 'shoulder_right_x': x[5],\n",
" 'shoulder_right_y': y[5],\n",
" 'shoulder_left_x': x[6], \n",
" 'shoulder_left_y': y[6],\n",
" })\n",
"df_poses = pd.DataFrame.from_dict(poses)\n",
"df_poses.to_csv(fp_out)"
]
},
{
"cell_type": "code",
"execution_count": 183,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>crop_x1</th>\n",
" <th>crop_x2</th>\n",
" <th>crop_y1</th>\n",
" <th>crop_y2</th>\n",
" <th>elbow_left_x</th>\n",
" <th>elbow_left_y</th>\n",
" <th>elbow_right_x</th>\n",
" <th>elbow_right_y</th>\n",
" <th>head_x</th>\n",
" <th>head_y</th>\n",
" <th>...</th>\n",
" <th>shoulder_left_x</th>\n",
" <th>shoulder_left_y</th>\n",
" <th>shoulder_right_x</th>\n",
" <th>shoulder_right_y</th>\n",
" <th>video_id</th>\n",
" <th>width</th>\n",
" <th>wrist_left_x</th>\n",
" <th>wrist_left_y</th>\n",
" <th>wrist_right_x</th>\n",
" <th>wrist_right_y</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>1920</td>\n",
" <td>1</td>\n",
" <td>1080</td>\n",
" <td>277.721438</td>\n",
" <td>192.416331</td>\n",
" <td>147.628696</td>\n",
" <td>169.326277</td>\n",
" <td>195.498320</td>\n",
" <td>81.471438</td>\n",
" <td>...</td>\n",
" <td>254.631384</td>\n",
" <td>127.088374</td>\n",
" <td>178.603159</td>\n",
" <td>134.691196</td>\n",
" <td>-osma2n86oA</td>\n",
" <td>720</td>\n",
" <td>278.566196</td>\n",
" <td>235.498992</td>\n",
" <td>158.047379</td>\n",
" <td>122.301411</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>1920</td>\n",
" <td>1</td>\n",
" <td>1080</td>\n",
" <td>273.497648</td>\n",
" <td>187.629368</td>\n",
" <td>152.134073</td>\n",
" <td>129.341062</td>\n",
" <td>207.324933</td>\n",
" <td>72.742272</td>\n",
" <td>...</td>\n",
" <td>254.349798</td>\n",
" <td>131.593750</td>\n",
" <td>181.137433</td>\n",
" <td>123.990927</td>\n",
" <td>-osma2n86oA</td>\n",
" <td>720</td>\n",
" <td>274.342406</td>\n",
" <td>235.498992</td>\n",
" <td>135.238911</td>\n",
" <td>91.608535</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>1920</td>\n",
" <td>1</td>\n",
" <td>1080</td>\n",
" <td>258.010417</td>\n",
" <td>159.752352</td>\n",
" <td>160.581653</td>\n",
" <td>143.138777</td>\n",
" <td>229.007056</td>\n",
" <td>76.966062</td>\n",
" <td>...</td>\n",
" <td>250.407594</td>\n",
" <td>125.117272</td>\n",
" <td>190.992944</td>\n",
" <td>117.232863</td>\n",
" <td>-osma2n86oA</td>\n",
" <td>720</td>\n",
" <td>213.801411</td>\n",
" <td>108.785282</td>\n",
" <td>181.982191</td>\n",
" <td>89.074261</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>1920</td>\n",
" <td>1</td>\n",
" <td>1080</td>\n",
" <td>274.342406</td>\n",
" <td>188.192540</td>\n",
" <td>142.841734</td>\n",
" <td>110.193212</td>\n",
" <td>203.101142</td>\n",
" <td>76.402890</td>\n",
" <td>...</td>\n",
" <td>253.786626</td>\n",
" <td>128.777890</td>\n",
" <td>185.361223</td>\n",
" <td>120.611895</td>\n",
" <td>-osma2n86oA</td>\n",
" <td>720</td>\n",
" <td>276.595094</td>\n",
" <td>231.556788</td>\n",
" <td>156.921035</td>\n",
" <td>55.847110</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1</td>\n",
" <td>1920</td>\n",
" <td>1</td>\n",
" <td>1080</td>\n",
" <td>272.371304</td>\n",
" <td>194.387433</td>\n",
" <td>225.628024</td>\n",
" <td>164.820901</td>\n",
" <td>245.902218</td>\n",
" <td>93.016465</td>\n",
" <td>...</td>\n",
" <td>255.476142</td>\n",
" <td>139.478159</td>\n",
" <td>183.390121</td>\n",
" <td>126.806788</td>\n",
" <td>-osma2n86oA</td>\n",
" <td>720</td>\n",
" <td>305.316868</td>\n",
" <td>172.423723</td>\n",
" <td>278.284610</td>\n",
" <td>165.102487</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 22 columns</p>\n",
"</div>"
],
"text/plain": [
" crop_x1 crop_x2 crop_y1 crop_y2 elbow_left_x elbow_left_y \\\n",
"0 1 1920 1 1080 277.721438 192.416331 \n",
"1 1 1920 1 1080 273.497648 187.629368 \n",
"2 1 1920 1 1080 258.010417 159.752352 \n",
"3 1 1920 1 1080 274.342406 188.192540 \n",
"4 1 1920 1 1080 272.371304 194.387433 \n",
"\n",
" elbow_right_x elbow_right_y head_x head_y ... \\\n",
"0 147.628696 169.326277 195.498320 81.471438 ... \n",
"1 152.134073 129.341062 207.324933 72.742272 ... \n",
"2 160.581653 143.138777 229.007056 76.966062 ... \n",
"3 142.841734 110.193212 203.101142 76.402890 ... \n",
"4 225.628024 164.820901 245.902218 93.016465 ... \n",
"\n",
" shoulder_left_x shoulder_left_y shoulder_right_x shoulder_right_y \\\n",
"0 254.631384 127.088374 178.603159 134.691196 \n",
"1 254.349798 131.593750 181.137433 123.990927 \n",
"2 250.407594 125.117272 190.992944 117.232863 \n",
"3 253.786626 128.777890 185.361223 120.611895 \n",
"4 255.476142 139.478159 183.390121 126.806788 \n",
"\n",
" video_id width wrist_left_x wrist_left_y wrist_right_x wrist_right_y \n",
"0 -osma2n86oA 720 278.566196 235.498992 158.047379 122.301411 \n",
"1 -osma2n86oA 720 274.342406 235.498992 135.238911 91.608535 \n",
"2 -osma2n86oA 720 213.801411 108.785282 181.982191 89.074261 \n",
"3 -osma2n86oA 720 276.595094 231.556788 156.921035 55.847110 \n",
"4 -osma2n86oA 720 305.316868 172.423723 278.284610 165.102487 \n",
"\n",
"[5 rows x 22 columns]"
]
},
"execution_count": 183,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_poses.head()"
]
},
{
"cell_type": "code",
"execution_count": 172,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"22"
]
},
"execution_count": 172,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(df_poses.keys())"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "megapixels",
"language": "python",
"name": "megapixels"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.1"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|
