Spaces:
Runtime error
Runtime error
File size: 9,530 Bytes
6bc5f9c |
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 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Base Configurations"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import torch\n",
"from transformers import SegformerForSemanticSegmentation\n",
"from dataclasses import dataclass\n",
"\n",
"\n",
"@dataclass\n",
"class Configs:\n",
" NUM_CLASSES = 4\n",
" MODEL_PATH: str = \"nvidia/segformer-b4-finetuned-ade-512-512\""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Load Model To Inspect Parameter Names"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"\n",
"\n",
"def get_model(*, model_path, num_classes):\n",
" model = SegformerForSemanticSegmentation.from_pretrained(\n",
" model_path,\n",
" num_labels=num_classes,\n",
" ignore_mismatched_sizes=True,\n",
" )\n",
" return model"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Some weights of SegformerForSemanticSegmentation were not initialized from the model checkpoint at nvidia/segformer-b4-finetuned-ade-512-512 and are newly initialized because the shapes did not match:\n",
"- decode_head.classifier.weight: found shape torch.Size([150, 768, 1, 1]) in the checkpoint and torch.Size([4, 768, 1, 1]) in the model instantiated\n",
"- decode_head.classifier.bias: found shape torch.Size([150]) in the checkpoint and torch.Size([4]) in the model instantiated\n",
"You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"segformer.encoder.patch_embeddings.0.proj.weight\n",
"segformer.encoder.patch_embeddings.0.proj.bias\n",
"segformer.encoder.patch_embeddings.0.layer_norm.weight\n",
"segformer.encoder.patch_embeddings.0.layer_norm.bias\n",
"segformer.encoder.patch_embeddings.1.proj.weight\n",
"segformer.encoder.patch_embeddings.1.proj.bias\n"
]
}
],
"source": [
"model = get_model(model_path=Configs.MODEL_PATH, num_classes=Configs.NUM_CLASSES)\n",
"model_state_dict = model.state_dict()\n",
"\n",
"print()\n",
"for i, (key, val) in enumerate(model_state_dict.items()):\n",
" print(key)\n",
" if i == 5:\n",
" break"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Download & load PyTorch-Lightning Checkpoint and Inspect Parameter Names"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Failed to detect the name of this notebook, you can set it manually with the WANDB_NOTEBOOK_NAME environment variable to enable code saving.\n",
"\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33mveb-101\u001b[0m. Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\n"
]
},
{
"data": {
"text/html": [
"Tracking run with wandb version 0.15.5"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"Run data is saved locally in <code>c:\\Users\\vaibh\\OneDrive\\Desktop\\Work\\BigVision\\BLOG_POSTS\\Medical_segmentation\\GRADIO_APP\\UWMGI_Medical_Image_Segmentation\\wandb\\run-20230719_204221-w5qu5rqw</code>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"Syncing run <strong><a href='https://wandb.ai/veb-101/UWMGI_Medical_Image_Segmentation/runs/w5qu5rqw' target=\"_blank\">ethereal-bush-2</a></strong> to <a href='https://wandb.ai/veb-101/UWMGI_Medical_Image_Segmentation' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/run' target=\"_blank\">docs</a>)<br/>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" View project at <a href='https://wandb.ai/veb-101/UWMGI_Medical_Image_Segmentation' target=\"_blank\">https://wandb.ai/veb-101/UWMGI_Medical_Image_Segmentation</a>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" View run at <a href='https://wandb.ai/veb-101/UWMGI_Medical_Image_Segmentation/runs/w5qu5rqw' target=\"_blank\">https://wandb.ai/veb-101/UWMGI_Medical_Image_Segmentation/runs/w5qu5rqw</a>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[34m\u001b[1mwandb\u001b[0m: Downloading large artifact model-fpgquxev:v0, 977.89MB. 1 files... \n",
"\u001b[34m\u001b[1mwandb\u001b[0m: 1 of 1 files downloaded. \n",
"Done. 0:1:5.3\n"
]
}
],
"source": [
"import wandb\n",
"\n",
"run = wandb.init()\n",
"artifact = run.use_artifact(\"veb-101/UM_medical_segmentation/model-fpgquxev:v0\", type=\"model\")\n",
"artifact_dir = artifact.download()"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"dict_keys(['epoch', 'global_step', 'pytorch-lightning_version', 'state_dict', 'loops', 'callbacks', 'optimizer_states', 'lr_schedulers', 'MixedPrecisionPlugin', 'hparams_name', 'hyper_parameters'])\n"
]
}
],
"source": [
"CKPT = torch.load(os.path.join(artifact_dir, \"model.ckpt\"), map_location=\"cpu\")\n",
"print(CKPT.keys())"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"model.segformer.encoder.patch_embeddings.0.proj.weight\n",
"model.segformer.encoder.patch_embeddings.0.proj.bias\n",
"model.segformer.encoder.patch_embeddings.0.layer_norm.weight\n",
"model.segformer.encoder.patch_embeddings.0.layer_norm.bias\n",
"model.segformer.encoder.patch_embeddings.1.proj.weight\n",
"model.segformer.encoder.patch_embeddings.1.proj.bias\n"
]
}
],
"source": [
"TRAINED_CKPT_state_dict = CKPT[\"state_dict\"]\n",
"\n",
"for i, (key, val) in enumerate(TRAINED_CKPT_state_dict.items()):\n",
" print(key)\n",
" if i == 5:\n",
" break"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**The pytorch-lightning `state_dict()` has an extra `model.` string at the front that refers to the object/variable name that was holding the model in the `LightningModule` class.**\n",
"\n",
"We can simply iterate over the parameters and change the parameter key name. We'll create a new `OrderedDict` for it."
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"from collections import OrderedDict\n",
"\n",
"new_state_dict = OrderedDict()\n",
"\n",
"for key_name, value in CKPT[\"state_dict\"].items():\n",
" new_state_dict[key_name.replace(\"model.\", \"\")] = value"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<All keys matched successfully>"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model.load_state_dict(new_state_dict)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"# torch.save(model.state_dict(), \"Segformer_best_state_dict.ckpt\")"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"model.save_pretrained(\"segformer_trained_weights\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"To load the saved model, we simply need to pass the path to the directory \"segformer_trained_weights\"."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# model = get_model(model_path=os.path.join(os.getcwd(), \"segformer_trained_weights\"), num_classes=Configs.NUM_CLASSES)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "pytorchx",
"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": "3.10.12"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}
|