File size: 15,673 Bytes
da6acc7 | 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 | {
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "b8e236f1-385a-4d93-bb39-bea3ee384d76",
"metadata": {
"scrolled": true,
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"outdir /weka/proj-fmri/ckadirt/fMRI-foundation-model/src/checkpoints/HCPflat_large_gsrFalse_\n",
"Loaded config.yaml from ckpt folder /weka/proj-fmri/ckadirt/fMRI-foundation-model/src/checkpoints/HCPflat_large_gsrFalse_\n",
"\n",
"__CONFIG__\n",
"base_lr = 0.001\n",
"batch_size = 32\n",
"ckpt_interval = 5\n",
"ckpt_saving = True\n",
"cls_embed = True\n",
"contrastive_loss_weight = 1.0\n",
"datasets_to_include = HCP\n",
"decoder_embed_dim = 512\n",
"grad_accumulation_steps = 1\n",
"grad_clip = 1.0\n",
"gsr = False\n",
"hcp_flat_path = /weka/proj-medarc/shared/HCP-Flat\n",
"mask_ratio = 0.75\n",
"model_name = HCPflat_large_gsrFalse_\n",
"no_qkv_bias = False\n",
"norm_pix_loss = False\n",
"nsd_flat_path = /weka/proj-medarc/shared/NSD-Flat\n",
"num_epochs = 100\n",
"num_frames = 16\n",
"num_samples_per_epoch = 200000\n",
"num_workers = 10\n",
"patch_size = 16\n",
"pct_masks_to_decode = 1\n",
"plotting = True\n",
"pred_t_dim = 8\n",
"print_interval = 20\n",
"probe_base_lr = 0.0003\n",
"probe_batch_size = 8\n",
"probe_num_epochs = 30\n",
"probe_num_samples_per_epoch = 100000\n",
"resume_from_ckpt = True\n",
"seed = 42\n",
"sep_pos_embed = True\n",
"t_patch_size = 2\n",
"test_num_samples_per_epoch = 50000\n",
"test_set = False\n",
"trunc_init = False\n",
"use_contrastive_loss = False\n",
"wandb_log = True\n",
"\n",
"\n",
"PID of this process = 1830897\n"
]
}
],
"source": [
"# Import packages and setup gpu configuration.\n",
"# This code block shouldnt need to be adjusted other than the model_name (if interactive)!\n",
"import os\n",
"import sys\n",
"import json\n",
"import yaml\n",
"import numpy as np\n",
"import math\n",
"import time\n",
"import datetime\n",
"import random\n",
"from tqdm import tqdm\n",
"import webdataset as wds\n",
"import matplotlib.pyplot as plt\n",
"import pandas as pd\n",
"import torch\n",
"import torch.nn as nn\n",
"from torchvision import transforms\n",
"import utils\n",
"from mae_utils import flat_models\n",
"from elbow.sinks import BufferedParquetWriter\n",
"\n",
"## MODEL TO LOAD ##\n",
"if utils.is_interactive():\n",
" model_name = \"HCPflat_large_gsrFalse_\"\n",
"else:\n",
" model_name = sys.argv[1]\n",
"outdir = os.path.abspath(f'checkpoints/{model_name}')\n",
"print(\"outdir\", outdir)\n",
"\n",
"# Load previously saved config.yaml made during main training script\n",
"assert os.path.exists(f\"{outdir}/config.yaml\")\n",
"config = yaml.load(open(f\"{outdir}/config.yaml\", 'r'), Loader=yaml.FullLoader)\n",
"print(f\"Loaded config.yaml from ckpt folder {outdir}\")\n",
"# create global variables from the config\n",
"print(\"\\n__CONFIG__\")\n",
"for attribute_name in config.keys():\n",
" print(f\"{attribute_name} = {config[attribute_name]}\")\n",
" globals()[attribute_name] = config[f'{attribute_name}']\n",
"print(\"\\n\")\n",
"\n",
"if utils.is_interactive():\n",
" # Following allows you to change functions in other files and \n",
" # have this notebook automatically update with your revisions\n",
" %load_ext autoreload\n",
" %autoreload 2\n",
"\n",
"device = torch.device('cuda')\n",
"\n",
"print(\"PID of this process =\",os.getpid())\n",
"\n",
"# seed all random functions\n",
"utils.seed_everything(seed)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "d505c08d-bd96-4b99-b7d9-32af3c50579e",
"metadata": {},
"outputs": [],
"source": [
"os.environ['HCP_FLAT_ROOT'] = hcp_flat_path\n",
"# os.environ['global_pool'] = \"False\""
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "fb0a4f06-c75b-4255-ab94-ea6206330778",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"global_pool = False\n",
"gsr = False\n"
]
}
],
"source": [
"if os.getenv('global_pool') == \"False\":\n",
" global_pool = False\n",
"else:\n",
" global_pool = True\n",
"print(f\"global_pool = {global_pool}\")\n",
"\n",
"try:\n",
" gsr\n",
"except:\n",
" gsr = True\n",
" print(\"set gsr to True\")\n",
"print(f\"gsr = {gsr}\")"
]
},
{
"cell_type": "markdown",
"id": "ab15aca0-148e-435f-b8f2-7a708b61a6d9",
"metadata": {},
"source": [
"# hcp_flat"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "de1a5b87-fa69-44e1-bdb9-bd9e257485c6",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"img_size (144, 320) patch_size (16, 16) frames 16 t_patch_size 2\n",
"model initialized\n"
]
}
],
"source": [
"from mae_utils.flat import load_hcp_flat_mask\n",
"from mae_utils.flat import create_hcp_flat\n",
"from mae_utils.flat import batch_unmask\n",
"import mae_utils.visualize as vis\n",
"\n",
"flat_mask = load_hcp_flat_mask(hcp_flat_path)\n",
"\n",
"model = flat_models.mae_vit_large_fmri(\n",
" patch_size=patch_size,\n",
" decoder_embed_dim=decoder_embed_dim,\n",
" t_patch_size=t_patch_size,\n",
" pred_t_dim=pred_t_dim,\n",
" decoder_depth=4,\n",
" cls_embed=cls_embed,\n",
" norm_pix_loss=norm_pix_loss,\n",
" no_qkv_bias=no_qkv_bias,\n",
" sep_pos_embed=sep_pos_embed,\n",
" trunc_init=trunc_init,\n",
" pct_masks_to_decode=pct_masks_to_decode,\n",
" img_mask=flat_mask,\n",
")"
]
},
{
"cell_type": "markdown",
"id": "2b8e6baa-4b1c-4f38-b078-70b2b092d14d",
"metadata": {},
"source": [
"# Load checkpoint"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "4da73c08-ca61-48ef-9e63-b70db6f07a59",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"latest_checkpoint: epoch99.pth\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/tmp/ipykernel_1830897/1892075218.py:12: 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",
" state = torch.load(checkpoint_path)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Loaded checkpoint epoch99.pth from /weka/proj-fmri/ckadirt/fMRI-foundation-model/src/checkpoints/HCPflat_large_gsrFalse_\n",
"\n"
]
}
],
"source": [
"checkpoint_files = [f for f in os.listdir(outdir) if f.endswith('.pth')]\n",
"\n",
"if utils.is_interactive():\n",
" latest_checkpoint = \"epoch99.pth\"\n",
"else:\n",
" latest_checkpoint = sys.argv[2] \n",
"print(f\"latest_checkpoint: {latest_checkpoint}\")\n",
"\n",
"# Load the checkpoint\n",
"checkpoint_path = os.path.join(outdir, latest_checkpoint)\n",
"\n",
"state = torch.load(checkpoint_path)\n",
"model.load_state_dict(state[\"model_state_dict\"], strict=False)\n",
"model.to(device)\n",
"model.eval()\n",
"\n",
"print(f\"\\nLoaded checkpoint {latest_checkpoint} from {outdir}\\n\")"
]
},
{
"cell_type": "markdown",
"id": "3dd51ddf-fb71-48f4-bdbd-88753b44d2aa",
"metadata": {},
"source": [
"## Create dataset and data loaders"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "3e330cd2-8f4f-4ca7-ae68-16698e90060f",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"changed batch_size to 1\n"
]
}
],
"source": [
"from torch.utils.data import default_collate\n",
"batch_size = 1\n",
"print(f\"changed batch_size to {batch_size}\")\n",
"\n",
"## Test ##\n",
"datasets_to_include = \"HCP\"\n",
"assert \"HCP\" in datasets_to_include\n",
"test_dataset = create_hcp_flat(root=hcp_flat_path, \n",
" clip_mode=\"event\", frames=num_frames, shuffle=False, gsr=gsr, sub_list = 'test')\n",
"test_dl = wds.WebLoader(\n",
" test_dataset.batched(batch_size, partial=False, collation_fn=default_collate),\n",
" batch_size=None,\n",
" shuffle=False,\n",
" num_workers=num_workers,\n",
" pin_memory=True,\n",
")\n",
"\n",
"## Train ##\n",
"assert \"HCP\" in datasets_to_include\n",
"train_dataset = create_hcp_flat(root=hcp_flat_path, \n",
" clip_mode=\"event\", frames=num_frames, shuffle=False, gsr=gsr, sub_list = 'train')\n",
"train_dl = wds.WebLoader(\n",
" train_dataset.batched(batch_size, partial=False, collation_fn=default_collate),\n",
" batch_size=None,\n",
" shuffle=False,\n",
" num_workers=num_workers,\n",
" pin_memory=True,\n",
")"
]
},
{
"cell_type": "markdown",
"id": "c43a5055-8afd-468a-93bf-32f94bd1d042",
"metadata": {},
"source": [
"# Start extraction"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "d347bfb0-b1e3-4cac-a792-b56311e7923c",
"metadata": {},
"outputs": [],
"source": [
"cnt = 9999 # need to change this"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "6507067f-1ece-46ac-ad8c-24ef7a9b3a58",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"@torch.no_grad()\n",
"def extract_features(dl, global_pool=True):\n",
" for samples in tqdm(dl,total=cnt): \n",
" samples_meta = samples['meta']\n",
" features = model(samples['image'].to(device),global_pool=global_pool, forward_features = True)\n",
" features = features.flatten(1)\n",
" features = features.cpu().numpy()\n",
" meta_dict = {}\n",
" for key, value in samples_meta.items():\n",
" if type(value) == torch.Tensor:\n",
" value = value.cpu().numpy()\n",
" meta_dict[key] = value\n",
" for feat, meta in zip(features, samples_meta):\n",
" yield {\"feature\": feat, **meta_dict}"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "8b75050d-ea61-489c-a777-7725935a6a74",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"/weka/proj-fmri/ckadirt/fMRI-foundation-model/src/checkpoints/HCPflat_large_gsrFalse__gpFalse/epoch99/HCP\n"
]
}
],
"source": [
"out_folder = f'{outdir}_gp{global_pool}/{latest_checkpoint[:-4]}/HCP'\n",
"print(out_folder)\n",
"os.makedirs(out_folder,exist_ok=True)"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "03905231-1e22-4aca-865f-322be2bf426f",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Start extract\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"12082it [15:26, 13.04it/s] \n"
]
},
{
"ename": "NameError",
"evalue": "name 'gg_ratas' 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[24], line 13\u001b[0m\n\u001b[1;32m 11\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m sample \u001b[38;5;129;01min\u001b[39;00m extract_features(test_dl, global_pool):\n\u001b[1;32m 12\u001b[0m writer\u001b[38;5;241m.\u001b[39mwrite(sample)\n\u001b[0;32m---> 13\u001b[0m \u001b[43mgg_ratas\u001b[49m\n\u001b[1;32m 14\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m BufferedParquetWriter(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00moutdir_parquet\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m/train.parquet\u001b[39m\u001b[38;5;124m\"\u001b[39m, blocking\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m) \u001b[38;5;28;01mas\u001b[39;00m writer:\n\u001b[1;32m 15\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m sample \u001b[38;5;129;01min\u001b[39;00m extract_features(train_dl, global_pool):\n",
"\u001b[0;31mNameError\u001b[0m: name 'gg_ratas' is not defined"
]
}
],
"source": [
"\n",
"# Ensure the output Parquet directory exists\n",
"outdir_parquet = os.path.join(f'{outdir}_gp{global_pool}/{latest_checkpoint[:-4]}', 'HCP')\n",
"os.makedirs(outdir_parquet, exist_ok=True) # <-- Add this line\n",
"\n",
"utils.seed_everything(seed)\n",
"\n",
"print(\"Start extract\")\n",
"start_time = time.time()\n",
"\n",
"with BufferedParquetWriter(f\"{outdir_parquet}/test.parquet\", blocking=True) as writer:\n",
" for sample in extract_features(test_dl, global_pool):\n",
" writer.write(sample)\n",
"\n",
"with BufferedParquetWriter(f\"{outdir_parquet}/train.parquet\", blocking=True) as writer:\n",
" for sample in extract_features(train_dl, global_pool):\n",
" writer.write(sample)\n",
"\n",
"total_time = time.time() - start_time\n",
"total_time_str = str(datetime.timedelta(seconds=int(total_time)))\n",
"print(\"Extract time {}\".format(total_time_str))\n",
"print(torch.cuda.memory_allocated())"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a4a54990-0790-4ee9-bef0-f8f19a7cabd1",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "foundation_env",
"language": "python",
"name": "foundation_env"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.10"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|