zamba.models.densepose.densepose_manager¶
DensePoseManager
¶
Source code in zamba/models/densepose/densepose_manager.py
75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 |
|
__init__(model=MODELS['chimps'], model_cache_dir=Path('.zamba_cache'), download_region=RegionEnum('us'))
¶
Create a DensePoseManager object.
Parameters¶
model : dict, optional (default MODELS['chimps']) A dictionary with the densepose model defintion like those defined in MODELS.
Source code in zamba/models/densepose/densepose_manager.py
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 |
|
anatomize_image(visualized_img_arr, outputs, output_path=None)
¶
Convert the pose information into the percent of pixels in the detection bounding box that correspond to each part of the anatomy in an image.
Parameters¶
visualized_img_arr : numpy array (unit8) BGR The numpy array the image after the texture has been visualized (by calling DensePoseManager.visualize_image). outputs : The outputs from running DensePoseManager.predict*
Returns¶
pandas.DataFrame DataFrame with percent of pixels of the bounding box that correspond to each anatomical part
Source code in zamba/models/densepose/densepose_manager.py
351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 |
|
anatomize_video(visualized_video_arr, outputs, output_path=None, fps=30)
¶
Convert the pose information into the percent of pixels in the detection bounding box that correspond to each part of the anatomy in a video.
Parameters¶
visualized_video_arr : numpy array (unit8) BGR The numpy array the video after the texture has been visualized (by calling DensePoseManager.visualize_video). outputs : The outputs from running DensePoseManager.predict*
Returns¶
numpy array (unit8) BGR DensePose outputs visualized on top of the image.
Source code in zamba/models/densepose/densepose_manager.py
488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 |
|
predict(image_arr)
¶
Main call to DensePose for inference. Runs inference on an image array.
Parameters¶
image_arr : numpy array BGR image array
Returns¶
Instances Detection instances with boxes, scores, and densepose estimates.
Source code in zamba/models/densepose/densepose_manager.py
183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 |
|
predict_image(image)
¶
Run inference to get the densepose results for an image.
Parameters¶
image : numpy array (unit8) of an image in BGR format or path to an image
Returns¶
tuple Returns the image array as passed or loaded and the the densepose Instances as results.
Source code in zamba/models/densepose/densepose_manager.py
139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 |
|
predict_video(video, video_loader_config=None, pbar=True)
¶
Run inference to get the densepose results for a video.
Parameters¶
video : numpy array (uint8) of a a video in BGR layout with time dimension first or path to a video video_loader_config : VideoLoaderConfig, optional A video loader config for loading videos (uses all defaults except pix_fmt="bgr24") pbar : bool, optional Whether to display a progress bar, by default True
Returns¶
tuple Tuple of (video_array, list of densepose results per frame)
Source code in zamba/models/densepose/densepose_manager.py
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 |
|
serialize_image_output(instances, filename=None, write_embeddings=False)
¶
Convert the densepose output into Python-native objects that can be written and read with json.
Parameters¶
instances : Instance The output from the densepose model filename : (str, Path), optional If not None, the filename to write the output to, by default None
Source code in zamba/models/densepose/densepose_manager.py
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 |
|
visualize_image(image_arr, outputs, output_path=None)
¶
Visualize the pose information.
Parameters¶
image_arr : numpy array (unit8) BGR The numpy array representing the image. outputs : The outputs from running DensePoseManager.predict* output_path : str or Path, optional If not None, write visualization to this path; by default None
Returns¶
numpy array (unit8) BGR DensePose outputs visualized on top of the image.
Source code in zamba/models/densepose/densepose_manager.py
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 |
|
visualize_video(video_arr, outputs, output_path=None, frame_size=None, fps=30, pbar=True)
¶
Visualize the pose information on a video
Parameters¶
video_arr : numpy array (unit8) BGR, time first The numpy array representing the video. outputs : The outputs from running DensePoseManager.predict* output_path : str or Path, optional If not None, write visualization to this path (should be .mp4); by default None frame_size : (innt, float), optional If frame_size is float, scale up or down by that float value; if frame_size is an integer, set width to that size and scale height appropriately. fps : int frames per second for output video if writing; defaults to 30 pbar : bool display a progress bar
Returns¶
numpy array (unit8) BGR DensePose outputs visualized on top of the image.
Source code in zamba/models/densepose/densepose_manager.py
407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 |
|