File size: 32,806 Bytes
cf449ad |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 7,
"id": "c656aead-5827-49aa-b231-0db4f22e0e63",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"import os\n",
"import zipfile\n",
"import numpy as np\n",
"import PIL.Image\n",
"import torch\n",
"from torch.utils.data import DataLoader\n",
"#import matplotlib.pyplot as plt\n",
"\n",
"\n",
"\n",
"# Assume MultiZipImageFolderDataset is already defined\n",
"\n",
"# Helper function to create random images and save them in zip files\n",
"def create_test_zip_files(num_zips=2, num_images_per_zip=10, img_size=(64, 64)):\n",
" os.makedirs('test_data', exist_ok=True)\n",
" for i in range(num_zips):\n",
" zip_path = os.path.join('test_data', f'images_{i}.zip')\n",
" with zipfile.ZipFile(zip_path, 'w') as zip_file:\n",
" for j in range(num_images_per_zip):\n",
" img_array = np.random.randint(0, 255, (img_size[0], img_size[1], 3), dtype=np.uint8)\n",
" img = PIL.Image.fromarray(img_array)\n",
" img_name = f'image_{i}_{j}.png'\n",
" img_bytes = img.tobytes()\n",
" img.save(img_name)\n",
" \n",
" with open(img_name, 'rb') as f:\n",
" zip_file.writestr(img_name, f.read())\n",
" os.remove(img_name)\n",
"\n",
"# Function to display a batch of images\n",
"def show_images(images):\n",
" fig, axes = plt.subplots(1, len(images), figsize=(15, 15))\n",
" for img, ax in zip(images, axes):\n",
" img = img.permute(1, 2, 0) # CHW to HWC for displaying\n",
" ax.imshow(img)\n",
" ax.axis('off')\n",
" plt.show()\n",
"\n",
"# Step 1: Create test zip files\n",
"create_test_zip_files(num_zips=3, num_images_per_zip=5, img_size=(64, 64))"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "4ff494a6-8b66-43dc-92c3-270ff38088d4",
"metadata": {
"tags": []
},
"outputs": [
{
"ename": "OSError",
"evalue": "Path must point to a directory or zip",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mOSError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[8], line 73\u001b[0m\n\u001b[1;32m 70\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m np\u001b[38;5;241m.\u001b[39mzeros([\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_raw_shape[\u001b[38;5;241m0\u001b[39m], \u001b[38;5;241m0\u001b[39m], dtype\u001b[38;5;241m=\u001b[39mnp\u001b[38;5;241m.\u001b[39mfloat32) \u001b[38;5;66;03m# No labels\u001b[39;00m\n\u001b[1;32m 72\u001b[0m \u001b[38;5;66;03m# Usage Example\u001b[39;00m\n\u001b[0;32m---> 73\u001b[0m dataset \u001b[38;5;241m=\u001b[39m \u001b[43mMultiZipImageFolderDataset\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43m/usr/local/google/home/mingyuanzhou/SiD_google3_multinode/test_data/\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mresolution\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m64\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43muse_labels\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m)\u001b[49m\n\u001b[1;32m 74\u001b[0m dataloader \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mutils\u001b[38;5;241m.\u001b[39mdata\u001b[38;5;241m.\u001b[39mDataLoader(dataset, batch_size\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m5\u001b[39m, shuffle\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m)\n",
"Cell \u001b[0;32mIn[8], line 27\u001b[0m, in \u001b[0;36mMultiZipImageFolderDataset.__init__\u001b[0;34m(self, path, resolution, use_labels, **super_kwargs)\u001b[0m\n\u001b[1;32m 25\u001b[0m zip_paths \u001b[38;5;241m=\u001b[39m [\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_path]\n\u001b[1;32m 26\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m---> 27\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mIOError\u001b[39;00m(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mPath must point to a directory or zip\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m 29\u001b[0m \u001b[38;5;66;03m# Make sure we have at least one zip file\u001b[39;00m\n\u001b[1;32m 30\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(zip_paths) \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m0\u001b[39m:\n",
"\u001b[0;31mOSError\u001b[0m: Path must point to a directory or zip"
]
}
],
"source": []
},
{
"cell_type": "code",
"execution_count": 9,
"id": "abc69c5b-ad3b-4149-a177-ddec21c75089",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Loading image: 00000/img00000000.npy from zip: /usr/local/google/home/mingyuanzhou/Downloads/img512_split/dataset_part_01.zip\n"
]
},
{
"ename": "UnidentifiedImageError",
"evalue": "cannot identify image file <zipfile.ZipExtFile name='00000/img00000000.npy' mode='r'>",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mUnidentifiedImageError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[9], line 86\u001b[0m\n\u001b[1;32m 84\u001b[0m \u001b[38;5;66;03m# Iterate through the DataLoader\u001b[39;00m\n\u001b[1;32m 85\u001b[0m data_iter \u001b[38;5;241m=\u001b[39m \u001b[38;5;28miter\u001b[39m(dataloader)\n\u001b[0;32m---> 86\u001b[0m batch \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mnext\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mdata_iter\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 87\u001b[0m images, labels \u001b[38;5;241m=\u001b[39m batch \u001b[38;5;66;03m# Unpack images and labels\u001b[39;00m\n\u001b[1;32m 89\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mBatch loaded. Image shapes:\u001b[39m\u001b[38;5;124m\"\u001b[39m, [img\u001b[38;5;241m.\u001b[39mshape \u001b[38;5;28;01mfor\u001b[39;00m img \u001b[38;5;129;01min\u001b[39;00m images])\n",
"File \u001b[0;32m~/miniconda3/lib/python3.12/site-packages/torch/utils/data/dataloader.py:630\u001b[0m, in \u001b[0;36m_BaseDataLoaderIter.__next__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 627\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_sampler_iter \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 628\u001b[0m \u001b[38;5;66;03m# TODO(https://github.com/pytorch/pytorch/issues/76750)\u001b[39;00m\n\u001b[1;32m 629\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_reset() \u001b[38;5;66;03m# type: ignore[call-arg]\u001b[39;00m\n\u001b[0;32m--> 630\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_next_data\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 631\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_num_yielded \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[1;32m 632\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_dataset_kind \u001b[38;5;241m==\u001b[39m _DatasetKind\u001b[38;5;241m.\u001b[39mIterable \u001b[38;5;129;01mand\u001b[39;00m \\\n\u001b[1;32m 633\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_IterableDataset_len_called \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m \\\n\u001b[1;32m 634\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_num_yielded \u001b[38;5;241m>\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_IterableDataset_len_called:\n",
"File \u001b[0;32m~/miniconda3/lib/python3.12/site-packages/torch/utils/data/dataloader.py:673\u001b[0m, in \u001b[0;36m_SingleProcessDataLoaderIter._next_data\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 671\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_next_data\u001b[39m(\u001b[38;5;28mself\u001b[39m):\n\u001b[1;32m 672\u001b[0m index \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_next_index() \u001b[38;5;66;03m# may raise StopIteration\u001b[39;00m\n\u001b[0;32m--> 673\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_dataset_fetcher\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfetch\u001b[49m\u001b[43m(\u001b[49m\u001b[43mindex\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;66;03m# may raise StopIteration\u001b[39;00m\n\u001b[1;32m 674\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_pin_memory:\n\u001b[1;32m 675\u001b[0m data \u001b[38;5;241m=\u001b[39m _utils\u001b[38;5;241m.\u001b[39mpin_memory\u001b[38;5;241m.\u001b[39mpin_memory(data, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_pin_memory_device)\n",
"File \u001b[0;32m~/miniconda3/lib/python3.12/site-packages/torch/utils/data/_utils/fetch.py:52\u001b[0m, in \u001b[0;36m_MapDatasetFetcher.fetch\u001b[0;34m(self, possibly_batched_index)\u001b[0m\n\u001b[1;32m 50\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdataset\u001b[38;5;241m.\u001b[39m__getitems__(possibly_batched_index)\n\u001b[1;32m 51\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m---> 52\u001b[0m data \u001b[38;5;241m=\u001b[39m [\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdataset\u001b[49m\u001b[43m[\u001b[49m\u001b[43midx\u001b[49m\u001b[43m]\u001b[49m \u001b[38;5;28;01mfor\u001b[39;00m idx \u001b[38;5;129;01min\u001b[39;00m possibly_batched_index]\n\u001b[1;32m 53\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 54\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdataset[possibly_batched_index]\n",
"Cell \u001b[0;32mIn[9], line 73\u001b[0m, in \u001b[0;36mMultiZipImageFolderDataset.__getitem__\u001b[0;34m(self, idx)\u001b[0m\n\u001b[1;32m 72\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__getitem__\u001b[39m(\u001b[38;5;28mself\u001b[39m, idx):\n\u001b[0;32m---> 73\u001b[0m image \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_load_raw_image\u001b[49m\u001b[43m(\u001b[49m\u001b[43midx\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 74\u001b[0m label \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39mzeros(\u001b[38;5;241m0\u001b[39m) \u001b[38;5;66;03m# No labels for now\u001b[39;00m\n\u001b[1;32m 75\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m image, label\n",
"Cell \u001b[0;32mIn[9], line 64\u001b[0m, in \u001b[0;36mMultiZipImageFolderDataset._load_raw_image\u001b[0;34m(self, raw_idx)\u001b[0m\n\u001b[1;32m 62\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mLoading image: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mfname\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m from zip: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mzip_file\u001b[38;5;241m.\u001b[39mfilename\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 63\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m zip_file\u001b[38;5;241m.\u001b[39mopen(fname) \u001b[38;5;28;01mas\u001b[39;00m f:\n\u001b[0;32m---> 64\u001b[0m image \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39marray(\u001b[43mPIL\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mImage\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mopen\u001b[49m\u001b[43m(\u001b[49m\u001b[43mf\u001b[49m\u001b[43m)\u001b[49m)\n\u001b[1;32m 65\u001b[0m image \u001b[38;5;241m=\u001b[39m image\u001b[38;5;241m.\u001b[39mtranspose(\u001b[38;5;241m2\u001b[39m, \u001b[38;5;241m0\u001b[39m, \u001b[38;5;241m1\u001b[39m) \u001b[38;5;66;03m# HWC to CHW\u001b[39;00m\n\u001b[1;32m 66\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m image\n",
"File \u001b[0;32m~/miniconda3/lib/python3.12/site-packages/PIL/Image.py:3498\u001b[0m, in \u001b[0;36mopen\u001b[0;34m(fp, mode, formats)\u001b[0m\n\u001b[1;32m 3496\u001b[0m warnings\u001b[38;5;241m.\u001b[39mwarn(message)\n\u001b[1;32m 3497\u001b[0m msg \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcannot identify image file \u001b[39m\u001b[38;5;132;01m%r\u001b[39;00m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m%\u001b[39m (filename \u001b[38;5;28;01mif\u001b[39;00m filename \u001b[38;5;28;01melse\u001b[39;00m fp)\n\u001b[0;32m-> 3498\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m UnidentifiedImageError(msg)\n",
"\u001b[0;31mUnidentifiedImageError\u001b[0m: cannot identify image file <zipfile.ZipExtFile name='00000/img00000000.npy' mode='r'>"
]
}
],
"source": [
"import os\n",
"import zipfile\n",
"import PIL.Image\n",
"import numpy as np\n",
"import torch\n",
"from torch.utils.data import Dataset\n",
"\n",
"class MultiZipImageFolderDataset(Dataset):\n",
" def __init__(self,\n",
" path_or_files, # Path to directory or list of zip files.\n",
" resolution = None, # Ensure specific resolution, None = anything goes.\n",
" use_labels = False, # Disable labels by default.\n",
" ):\n",
" self._zipfiles = [] # List to store zipfile objects\n",
" self._zips_data = [] # List to store tuples of (zipfile, image_filenames)\n",
"\n",
" # Check if input is a directory or a list of zip files\n",
" if isinstance(path_or_files, str) and os.path.isdir(path_or_files):\n",
" # If it's a directory, find all the zip files\n",
" zip_paths = sorted([os.path.join(path_or_files, f) for f in os.listdir(path_or_files) if f.endswith('.zip')])\n",
" if len(zip_paths) == 0:\n",
" raise IOError(f\"No zip files found in directory: {path_or_files}\")\n",
" elif isinstance(path_or_files, list):\n",
" # If it's a list of zip files, use it directly\n",
" zip_paths = path_or_files\n",
" else:\n",
" raise IOError('Input must be a directory or a list of zip files.')\n",
"\n",
" # Gather all image filenames from each zip file\n",
" for zip_path in zip_paths:\n",
" zip_file = zipfile.ZipFile(zip_path)\n",
" fnames = set(zip_file.namelist())\n",
" supported_ext = PIL.Image.EXTENSION.keys() | {'.npy'}\n",
" image_fnames = sorted(fname for fname in fnames if self._file_ext(fname) in supported_ext)\n",
" if len(image_fnames) == 0:\n",
" continue # Skip if no image files found\n",
" self._zipfiles.append(zip_file)\n",
" self._zips_data.append((zip_file, image_fnames))\n",
"\n",
" # Initialize dataset size and shape\n",
" total_images = sum(len(fnames) for _, fnames in self._zips_data)\n",
" if total_images == 0:\n",
" raise IOError(\"No image files found across the zip files.\")\n",
" \n",
" # Assume all images have the same resolution\n",
" self.name = os.path.basename(zip_paths[0]) if isinstance(zip_paths[0], str) else 'multi_zip_dataset'\n",
" self._raw_shape = [total_images, 3, resolution, resolution]\n",
" self._use_labels = use_labels\n",
"\n",
" @staticmethod\n",
" def _file_ext(fname):\n",
" return os.path.splitext(fname)[1].lower()\n",
"\n",
" def _open_file(self, zip_file, fname):\n",
" return zip_file.open(fname, 'r')\n",
"\n",
" def _load_raw_image(self, raw_idx):\n",
" cumulative_idx = 0\n",
" for zip_file, image_fnames in self._zips_data:\n",
" if raw_idx < cumulative_idx + len(image_fnames):\n",
" fname = image_fnames[raw_idx - cumulative_idx]\n",
" print(f\"Loading image: {fname} from zip: {zip_file.filename}\")\n",
" with zip_file.open(fname) as f:\n",
" image = np.array(PIL.Image.open(f))\n",
" image = image.transpose(2, 0, 1) # HWC to CHW\n",
" return image\n",
" cumulative_idx += len(image_fnames)\n",
"\n",
" def __len__(self):\n",
" return self._raw_shape[0] # Return total number of images\n",
"\n",
" def __getitem__(self, idx):\n",
" image = self._load_raw_image(idx)\n",
" label = np.zeros(0) # No labels for now\n",
" return image, label\n",
"\n",
"# Usage Example\n",
"zip_files_dir = '/usr/local/google/home/mingyuanzhou/Downloads/img512_split/'\n",
"dataset = MultiZipImageFolderDataset(zip_files_dir, resolution=64)\n",
"\n",
"# Create a DataLoader and fetch a batch\n",
"dataloader = torch.utils.data.DataLoader(dataset, batch_size=5, shuffle=False)\n",
"\n",
"# Iterate through the DataLoader\n",
"data_iter = iter(dataloader)\n",
"batch = next(data_iter)\n",
"images, labels = batch # Unpack images and labels\n",
"\n",
"print(\"Batch loaded. Image shapes:\", [img.shape for img in images])\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "cf85c9c2-2eb4-44e6-83b5-f21941516d01",
"metadata": {
"tags": []
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "3093b92e-4661-4b31-b494-05c846b836d1",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"len(dataset)"
]
},
{
"cell_type": "code",
"execution_count": 56,
"id": "651c125e-4fe9-458d-8b0c-5519dbb9da22",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Found 3 zip files.\n"
]
}
],
"source": [
"import os\n",
"\n",
"# Verify zip files in the directory\n",
"zip_dir = '/usr/local/google/home/mingyuanzhou/SiD_google3_multinode/test_data/'\n",
"zip_files = [f for f in os.listdir(zip_dir) if f.endswith('.zip')]\n",
"\n",
"if len(zip_files) == 0:\n",
" raise Exception(\"No zip files found in the directory.\")\n",
"else:\n",
" print(f\"Found {len(zip_files)} zip files.\")\n",
"\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "3b74da59-f2e4-4331-bb13-24b6bdc2e24f",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"<__main__.MultiZipImageFolderDataset at 0x7f372f2bd610>"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dataset\n"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "0ba70fc2-b518-456e-9f14-3602700efdbc",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"data_iter = iter(dataloader)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "a9222a9b-afb1-4636-b88a-1ff01a953f2f",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"<torch.utils.data.dataloader._SingleProcessDataLoaderIter at 0x7f37227a2510>"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data_iter"
]
},
{
"cell_type": "code",
"execution_count": 31,
"id": "9d13816b-fc9b-4b1f-a6be-bd973f667965",
"metadata": {
"tags": []
},
"outputs": [
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[31], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m dataset \u001b[38;5;241m=\u001b[39m MultiZipImageFolderDataset(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m/usr/local/google/home/mingyuanzhou/SiD_google3_multinode/test_data/\u001b[39m\u001b[38;5;124m'\u001b[39m, resolution\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m64\u001b[39m, use_labels\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m)\n\u001b[1;32m 3\u001b[0m \u001b[38;5;66;03m# Try loading one image\u001b[39;00m\n\u001b[1;32m 4\u001b[0m image \u001b[38;5;241m=\u001b[39m dataset\u001b[38;5;241m.\u001b[39m_load_raw_image(\u001b[38;5;241m0\u001b[39m)\n",
"Cell \u001b[0;32mIn[28], line 16\u001b[0m, in \u001b[0;36mMultiZipImageFolderDataset.__init__\u001b[0;34m(self, paths, resolution, **super_kwargs)\u001b[0m\n\u001b[1;32m 14\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39misdir(path):\n\u001b[1;32m 15\u001b[0m file_type \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdir\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[0;32m---> 16\u001b[0m fnames \u001b[38;5;241m=\u001b[39m {os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mrelpath(os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mjoin(root, fname), start\u001b[38;5;241m=\u001b[39mpath) \u001b[38;5;28;01mfor\u001b[39;00m root, _dirs, files \u001b[38;5;129;01min\u001b[39;00m os\u001b[38;5;241m.\u001b[39mwalk(path) \u001b[38;5;28;01mfor\u001b[39;00m fname \u001b[38;5;129;01min\u001b[39;00m files}\n\u001b[1;32m 17\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_file_ext(path) \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m.zip\u001b[39m\u001b[38;5;124m'\u001b[39m:\n\u001b[1;32m 18\u001b[0m file_type \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mzip\u001b[39m\u001b[38;5;124m'\u001b[39m\n",
"Cell \u001b[0;32mIn[28], line 16\u001b[0m, in \u001b[0;36m<setcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m 14\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39misdir(path):\n\u001b[1;32m 15\u001b[0m file_type \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdir\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[0;32m---> 16\u001b[0m fnames \u001b[38;5;241m=\u001b[39m {os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mrelpath(os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mjoin(root, fname), start\u001b[38;5;241m=\u001b[39mpath) \u001b[38;5;28;01mfor\u001b[39;00m root, _dirs, files \u001b[38;5;129;01min\u001b[39;00m os\u001b[38;5;241m.\u001b[39mwalk(path) \u001b[38;5;28;01mfor\u001b[39;00m fname \u001b[38;5;129;01min\u001b[39;00m files}\n\u001b[1;32m 17\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_file_ext(path) \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m.zip\u001b[39m\u001b[38;5;124m'\u001b[39m:\n\u001b[1;32m 18\u001b[0m file_type \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mzip\u001b[39m\u001b[38;5;124m'\u001b[39m\n",
"File \u001b[0;32m<frozen os>:419\u001b[0m, in \u001b[0;36m_walk\u001b[0;34m(top, topdown, onerror, followlinks)\u001b[0m\n",
"File \u001b[0;32m<frozen os>:419\u001b[0m, in \u001b[0;36m_walk\u001b[0;34m(top, topdown, onerror, followlinks)\u001b[0m\n",
" \u001b[0;31m[... skipping similar frames: _walk at line 419 (1 times)]\u001b[0m\n",
"File \u001b[0;32m<frozen os>:419\u001b[0m, in \u001b[0;36m_walk\u001b[0;34m(top, topdown, onerror, followlinks)\u001b[0m\n",
"File \u001b[0;32m<frozen os>:377\u001b[0m, in \u001b[0;36m_walk\u001b[0;34m(top, topdown, onerror, followlinks)\u001b[0m\n",
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
"dataset = MultiZipImageFolderDataset('/usr/local/google/home/mingyuanzhou/SiD_google3_multinode/test_data/', resolution=64, use_labels=False)\n",
"\n",
"# Try loading one image\n",
"image = dataset._load_raw_image(0)\n",
"print(\"Loaded image shape:\", image.shape)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "67bff7a1-285e-48c5-b283-05b8fa3b7005",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Downloading: \"https://github.com/facebookresearch/dinov2/zipball/main\" to /usr/local/google/home/mingyuanzhou/.cache/torch/hub/main.zip\n",
"/usr/local/google/home/mingyuanzhou/.cache/torch/hub/facebookresearch_dinov2_main/dinov2/layers/swiglu_ffn.py:51: UserWarning: xFormers is not available (SwiGLU)\n",
" warnings.warn(\"xFormers is not available (SwiGLU)\")\n",
"/usr/local/google/home/mingyuanzhou/.cache/torch/hub/facebookresearch_dinov2_main/dinov2/layers/attention.py:33: UserWarning: xFormers is not available (Attention)\n",
" warnings.warn(\"xFormers is not available (Attention)\")\n",
"/usr/local/google/home/mingyuanzhou/.cache/torch/hub/facebookresearch_dinov2_main/dinov2/layers/block.py:40: UserWarning: xFormers is not available (Block)\n",
" warnings.warn(\"xFormers is not available (Block)\")\n",
"Downloading: \"https://dl.fbaipublicfiles.com/dinov2/dinov2_vitl14/dinov2_vitl14_pretrain.pth\" to /usr/local/google/home/mingyuanzhou/.cache/torch/hub/checkpoints/dinov2_vitl14_pretrain.pth\n",
"100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1.13G/1.13G [00:08<00:00, 136MB/s]\n"
]
}
],
"source": [
"dinov2_vitl14 = torch.hub.load('facebookresearch/dinov2', 'dinov2_vitl14')"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "a1787954-299d-497f-9134-ec2d167896a3",
"metadata": {},
"outputs": [
{
"ename": "NameError",
"evalue": "name 'model' is not defined",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[11], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mmodel\u001b[49m\u001b[38;5;241m.\u001b[39mload_state_dict(torch\u001b[38;5;241m.\u001b[39mload(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m/usr/local/google/home/mingyuanzhou/.cache/torch/hub/checkpoints/dinov2_vitl14_pretrain.pth\u001b[39m\u001b[38;5;124m'\u001b[39m))\n",
"\u001b[0;31mNameError\u001b[0m: name 'model' is not defined"
]
}
],
"source": []
},
{
"cell_type": "code",
"execution_count": 12,
"id": "048e93f2-9556-4eed-a42f-0db1ef9fa2ec",
"metadata": {},
"outputs": [],
"source": [
"from dinov2.models.vision_transformer import vit_large \n",
"\n",
"model = vit_large(\n",
" patch_size=14,\n",
" img_size=526,\n",
" init_values=1.0,\n",
" block_chunks=0\n",
" )\n",
"model.load_state_dict(torch.load('/usr/local/google/home/mingyuanzhou/.cache/torch/hub/checkpoints/dinov2_vitl14_pretrain.pth'))"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "a05cea14-48fa-4e29-a2af-c47995e51f63",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/tmp/ipykernel_1579249/4014153075.py:1: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
" model.load_state_dict(torch.load('/usr/local/google/home/mingyuanzhou/.cache/torch/hub/checkpoints/dinov2_vitl14_pretrain.pth'))\n"
]
},
{
"data": {
"text/plain": [
"<All keys matched successfully>"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": []
},
{
"cell_type": "code",
"execution_count": 14,
"id": "f98e3de1-a926-44af-b4f8-7f274aff7489",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"DinoVisionTransformer(\n",
" (patch_embed): PatchEmbed(\n",
" (proj): Conv2d(3, 1024, kernel_size=(14, 14), stride=(14, 14))\n",
" (norm): Identity()\n",
" )\n",
" (blocks): ModuleList(\n",
" (0-23): 24 x NestedTensorBlock(\n",
" (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True)\n",
" (attn): MemEffAttention(\n",
" (qkv): Linear(in_features=1024, out_features=3072, bias=True)\n",
" (attn_drop): Dropout(p=0.0, inplace=False)\n",
" (proj): Linear(in_features=1024, out_features=1024, bias=True)\n",
" (proj_drop): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (ls1): LayerScale()\n",
" (drop_path1): Identity()\n",
" (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True)\n",
" (mlp): Mlp(\n",
" (fc1): Linear(in_features=1024, out_features=4096, bias=True)\n",
" (act): GELU(approximate='none')\n",
" (fc2): Linear(in_features=4096, out_features=1024, bias=True)\n",
" (drop): Dropout(p=0.0, inplace=False)\n",
" )\n",
" (ls2): LayerScale()\n",
" (drop_path2): Identity()\n",
" )\n",
" )\n",
" (norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True)\n",
" (head): Identity()\n",
")"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "4277869a-b0ab-4acc-8e96-820a51a6de2c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"/usr/local/google/home/mingyuanzhou/.cache/torch/hub\n"
]
}
],
"source": [
"print(torch.hub.get_dir())\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5d5fc2d3-a3fb-4958-86d2-604d3d56ed1d",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.4"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|