File size: 30,895 Bytes
a53f410 dd20309 a53f410 dd20309 a53f410 dd20309 a53f410 dd20309 a53f410 dd20309 a53f410 dd20309 a53f410 dd20309 a53f410 |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"WARNING:tensorflow:From C:\\Users\\franz\\AppData\\Local\\Temp\\ipykernel_16992\\1198363771.py:6: is_gpu_available (from tensorflow.python.framework.test_util) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use `tf.config.list_physical_devices('GPU')` instead.\n",
"GPU is available\n"
]
}
],
"source": [
"\n",
"import gpt_2_simple as gpt2\n",
"import os\n",
"import tensorflow as tf\n",
"import pandas as pd\n",
"import re\n",
"print(\"GPU is\", \"available\" if tf.test.is_gpu_available() else \"NOT AVAILABLE\")"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"model_name = \"124M\"\n",
"if not os.path.isdir(os.path.join(\"models\", model_name)):\n",
"\tprint(f\"Downloading {model_name} model...\")\n",
"\tgpt2.download_gpt2(model_name=model_name) "
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"path = 'AbstractGenerator/'\n",
"checkpoint_dir =path+'weights/'\n",
"data_path = path+'TrainigData/'\n",
"\n",
"\n",
"\n",
"file_name_en = 'en'\n",
"file_path_en = data_path+file_name_en\n",
"\n",
"file_name_es = 'es'\n",
"file_path_es = data_path+file_name_es\n",
"\n",
"\n",
"prefix= '<|startoftext|>'\n",
"sufix ='<|endoftext|>'"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# create trainig data"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"en = pd.read_csv('CSV\\scientific_paper_en.csv')\n",
"es = pd.read_csv('CSV\\scientific_paper_es.csv')"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"import codecs\n",
"def createTrainingData(ds,fileName= 'resumen.txt' ,path ='TrainigData/'):\n",
" with codecs.open(path+fileName,'a','utf-8') as f:\n",
" for i in ds.index:\n",
" f.write(prefix+\"\\n\")\n",
" f.write(ds.iloc[i]['text_no_abstract'])\n",
" f.write(\"ABSTRACT\\n\")\n",
" f.write(ds.iloc[i]['abstract']+\"\\n\")\n",
" f.write(sufix)\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"createTrainingData(en,'en.txt',data_path)\n",
"createTrainingData(es,'es.txt',data_path)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# pretrained"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"sess = gpt2.start_tf_sess()\n",
"gpt2.load_gpt2(sess,checkpoint_dir=checkpoint_dir,run_name='run1')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# train "
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"tf.compat.v1.reset_default_graph()\n",
"sess = gpt2.start_tf_sess()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## en"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"gpt2.finetune(sess,\n",
" file_path_en+'.txt',\n",
" model_name=model_name,\n",
" checkpoint_dir=checkpoint_dir, \n",
" steps=1000\n",
" ) "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## es"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Loading checkpoint models\\124M\\model.ckpt\n",
"INFO:tensorflow:Restoring parameters from models\\124M\\model.ckpt\n",
"Loading dataset...\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 1/1 [00:51<00:00, 51.03s/it]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"dataset has 17511492 tokens\n",
"Training...\n"
]
},
{
"ename": "ResourceExhaustedError",
"evalue": "Graph execution error:\n\nfailed to allocate memory\n\t [[{{node model/h10/attn/ArithmeticOptimizer/ReorderCastLikeAndValuePreserving_float_Cast_1}}]]\nHint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mResourceExhaustedError\u001b[0m Traceback (most recent call last)",
"File \u001b[1;32m~\\.conda\\envs\\tf-gpu\\lib\\site-packages\\tensorflow\\python\\client\\session.py:1377\u001b[0m, in \u001b[0;36mBaseSession._do_call\u001b[1;34m(self, fn, *args)\u001b[0m\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1375'>1376</a>\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[1;32m-> <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1376'>1377</a>\u001b[0m \u001b[39mreturn\u001b[39;00m fn(\u001b[39m*\u001b[39;49margs)\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1377'>1378</a>\u001b[0m \u001b[39mexcept\u001b[39;00m errors\u001b[39m.\u001b[39mOpError \u001b[39mas\u001b[39;00m e:\n",
"File \u001b[1;32m~\\.conda\\envs\\tf-gpu\\lib\\site-packages\\tensorflow\\python\\client\\session.py:1360\u001b[0m, in \u001b[0;36mBaseSession._do_run.<locals>._run_fn\u001b[1;34m(feed_dict, fetch_list, target_list, options, run_metadata)\u001b[0m\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1358'>1359</a>\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_extend_graph()\n\u001b[1;32m-> <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1359'>1360</a>\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_call_tf_sessionrun(options, feed_dict, fetch_list,\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1360'>1361</a>\u001b[0m target_list, run_metadata)\n",
"File \u001b[1;32m~\\.conda\\envs\\tf-gpu\\lib\\site-packages\\tensorflow\\python\\client\\session.py:1453\u001b[0m, in \u001b[0;36mBaseSession._call_tf_sessionrun\u001b[1;34m(self, options, feed_dict, fetch_list, target_list, run_metadata)\u001b[0m\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1450'>1451</a>\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m_call_tf_sessionrun\u001b[39m(\u001b[39mself\u001b[39m, options, feed_dict, fetch_list, target_list,\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1451'>1452</a>\u001b[0m run_metadata):\n\u001b[1;32m-> <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1452'>1453</a>\u001b[0m \u001b[39mreturn\u001b[39;00m tf_session\u001b[39m.\u001b[39;49mTF_SessionRun_wrapper(\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_session, options, feed_dict,\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1453'>1454</a>\u001b[0m fetch_list, target_list,\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1454'>1455</a>\u001b[0m run_metadata)\n",
"\u001b[1;31mResourceExhaustedError\u001b[0m: failed to allocate memory\n\t [[{{node model/h10/attn/ArithmeticOptimizer/ReorderCastLikeAndValuePreserving_float_Cast_1}}]]\nHint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode.\n",
"\nDuring handling of the above exception, another exception occurred:\n",
"\u001b[1;31mResourceExhaustedError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32mc:\\Users\\franz\\OneDrive\\Documentos\\GitHub\\Generador-de-abstracts\\AbstractGenerator.ipynb Cell 15'\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> <a href='vscode-notebook-cell:/c%3A/Users/franz/OneDrive/Documentos/GitHub/Generador-de-abstracts/AbstractGenerator.ipynb#ch0000014?line=0'>1</a>\u001b[0m gpt2\u001b[39m.\u001b[39;49mfinetune(sess,\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Users/franz/OneDrive/Documentos/GitHub/Generador-de-abstracts/AbstractGenerator.ipynb#ch0000014?line=1'>2</a>\u001b[0m file_path_es\u001b[39m+\u001b[39;49m\u001b[39m'\u001b[39;49m\u001b[39m.txt\u001b[39;49m\u001b[39m'\u001b[39;49m,\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Users/franz/OneDrive/Documentos/GitHub/Generador-de-abstracts/AbstractGenerator.ipynb#ch0000014?line=2'>3</a>\u001b[0m model_name\u001b[39m=\u001b[39;49mmodel_name,\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Users/franz/OneDrive/Documentos/GitHub/Generador-de-abstracts/AbstractGenerator.ipynb#ch0000014?line=3'>4</a>\u001b[0m checkpoint_dir\u001b[39m=\u001b[39;49mcheckpoint_dir, \n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Users/franz/OneDrive/Documentos/GitHub/Generador-de-abstracts/AbstractGenerator.ipynb#ch0000014?line=4'>5</a>\u001b[0m steps\u001b[39m=\u001b[39;49m\u001b[39m1000\u001b[39;49m\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Users/franz/OneDrive/Documentos/GitHub/Generador-de-abstracts/AbstractGenerator.ipynb#ch0000014?line=5'>6</a>\u001b[0m )\n",
"File \u001b[1;32m~\\.conda\\envs\\tf-gpu\\lib\\site-packages\\gpt_2_simple\\gpt_2.py:339\u001b[0m, in \u001b[0;36mfinetune\u001b[1;34m(sess, dataset, steps, model_name, model_dir, combine, batch_size, learning_rate, accumulate_gradients, restore_from, run_name, checkpoint_dir, sample_every, sample_length, sample_num, multi_gpu, save_every, print_every, max_checkpoints, use_memory_saving_gradients, only_train_transformer_layers, optimizer, overwrite, reuse)\u001b[0m\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/gpt_2_simple/gpt_2.py?line=336'>337</a>\u001b[0m sess\u001b[39m.\u001b[39mrun(opt_reset)\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/gpt_2_simple/gpt_2.py?line=337'>338</a>\u001b[0m \u001b[39mfor\u001b[39;00m _ \u001b[39min\u001b[39;00m \u001b[39mrange\u001b[39m(accumulate_gradients):\n\u001b[1;32m--> <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/gpt_2_simple/gpt_2.py?line=338'>339</a>\u001b[0m sess\u001b[39m.\u001b[39;49mrun(\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/gpt_2_simple/gpt_2.py?line=339'>340</a>\u001b[0m opt_compute, feed_dict\u001b[39m=\u001b[39;49m{context: sample_batch()})\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/gpt_2_simple/gpt_2.py?line=340'>341</a>\u001b[0m (v_loss, v_summary) \u001b[39m=\u001b[39m sess\u001b[39m.\u001b[39mrun((opt_apply, summary_loss))\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/gpt_2_simple/gpt_2.py?line=341'>342</a>\u001b[0m \u001b[39melse\u001b[39;00m:\n",
"File \u001b[1;32m~\\.conda\\envs\\tf-gpu\\lib\\site-packages\\tensorflow\\python\\client\\session.py:967\u001b[0m, in \u001b[0;36mBaseSession.run\u001b[1;34m(self, fetches, feed_dict, options, run_metadata)\u001b[0m\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=963'>964</a>\u001b[0m run_metadata_ptr \u001b[39m=\u001b[39m tf_session\u001b[39m.\u001b[39mTF_NewBuffer() \u001b[39mif\u001b[39;00m run_metadata \u001b[39melse\u001b[39;00m \u001b[39mNone\u001b[39;00m\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=965'>966</a>\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[1;32m--> <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=966'>967</a>\u001b[0m result \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_run(\u001b[39mNone\u001b[39;49;00m, fetches, feed_dict, options_ptr,\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=967'>968</a>\u001b[0m run_metadata_ptr)\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=968'>969</a>\u001b[0m \u001b[39mif\u001b[39;00m run_metadata:\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=969'>970</a>\u001b[0m proto_data \u001b[39m=\u001b[39m tf_session\u001b[39m.\u001b[39mTF_GetBuffer(run_metadata_ptr)\n",
"File \u001b[1;32m~\\.conda\\envs\\tf-gpu\\lib\\site-packages\\tensorflow\\python\\client\\session.py:1190\u001b[0m, in \u001b[0;36mBaseSession._run\u001b[1;34m(self, handle, fetches, feed_dict, options, run_metadata)\u001b[0m\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1186'>1187</a>\u001b[0m \u001b[39m# We only want to really perform the run if fetches or targets are provided,\u001b[39;00m\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1187'>1188</a>\u001b[0m \u001b[39m# or if the call is a partial run that specifies feeds.\u001b[39;00m\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1188'>1189</a>\u001b[0m \u001b[39mif\u001b[39;00m final_fetches \u001b[39mor\u001b[39;00m final_targets \u001b[39mor\u001b[39;00m (handle \u001b[39mand\u001b[39;00m feed_dict_tensor):\n\u001b[1;32m-> <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1189'>1190</a>\u001b[0m results \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_do_run(handle, final_targets, final_fetches,\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1190'>1191</a>\u001b[0m feed_dict_tensor, options, run_metadata)\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1191'>1192</a>\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1192'>1193</a>\u001b[0m results \u001b[39m=\u001b[39m []\n",
"File \u001b[1;32m~\\.conda\\envs\\tf-gpu\\lib\\site-packages\\tensorflow\\python\\client\\session.py:1370\u001b[0m, in \u001b[0;36mBaseSession._do_run\u001b[1;34m(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)\u001b[0m\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1366'>1367</a>\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_call_tf_sessionprun(handle, feed_dict, fetch_list)\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1368'>1369</a>\u001b[0m \u001b[39mif\u001b[39;00m handle \u001b[39mis\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[1;32m-> <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1369'>1370</a>\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_do_call(_run_fn, feeds, fetches, targets, options,\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1370'>1371</a>\u001b[0m run_metadata)\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1371'>1372</a>\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1372'>1373</a>\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_do_call(_prun_fn, handle, feeds, fetches)\n",
"File \u001b[1;32m~\\.conda\\envs\\tf-gpu\\lib\\site-packages\\tensorflow\\python\\client\\session.py:1396\u001b[0m, in \u001b[0;36mBaseSession._do_call\u001b[1;34m(self, fn, *args)\u001b[0m\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1390'>1391</a>\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39m'\u001b[39m\u001b[39monly supports NHWC tensor format\u001b[39m\u001b[39m'\u001b[39m \u001b[39min\u001b[39;00m message:\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1391'>1392</a>\u001b[0m message \u001b[39m+\u001b[39m\u001b[39m=\u001b[39m (\u001b[39m'\u001b[39m\u001b[39m\\n\u001b[39;00m\u001b[39mA possible workaround: Try disabling Grappler optimizer\u001b[39m\u001b[39m'\u001b[39m\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1392'>1393</a>\u001b[0m \u001b[39m'\u001b[39m\u001b[39m\\n\u001b[39;00m\u001b[39mby modifying the config for creating the session eg.\u001b[39m\u001b[39m'\u001b[39m\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1393'>1394</a>\u001b[0m \u001b[39m'\u001b[39m\u001b[39m\\n\u001b[39;00m\u001b[39msession_config.graph_options.rewrite_options.\u001b[39m\u001b[39m'\u001b[39m\n\u001b[0;32m <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1394'>1395</a>\u001b[0m \u001b[39m'\u001b[39m\u001b[39mdisable_meta_optimizer = True\u001b[39m\u001b[39m'\u001b[39m)\n\u001b[1;32m-> <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/tensorflow/python/client/session.py?line=1395'>1396</a>\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mtype\u001b[39m(e)(node_def, op, message)\n",
"\u001b[1;31mResourceExhaustedError\u001b[0m: Graph execution error:\n\nfailed to allocate memory\n\t [[{{node model/h10/attn/ArithmeticOptimizer/ReorderCastLikeAndValuePreserving_float_Cast_1}}]]\nHint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info. This isn't available when running in Eager mode."
]
}
],
"source": [
"gpt2.finetune(sess,\n",
" file_path_es+'.txt',\n",
" model_name=model_name,\n",
" checkpoint_dir=checkpoint_dir, \n",
" steps=1000\n",
" ) "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# test"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## en "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"text = \"\"\"Introduction and preliminaries\n",
"The focus of this paper is decompositions of (k, `)-sparse graphs into edge-disjoint subgraphs\n",
"that certify sparsity. We use graph to mean a multigraph, possibly with loops. We say that a\n",
"graph is (k, `)-sparse if no subset of n′ vertices spans more than kn′− ` edges in the graph; a\n",
"(k, `)-sparse graph with kn′− ` edges is (k, `)-tight. We call the range k ≤ `≤ 2k−1 the upper\n",
"range of sparse graphs and 0≤ `≤ k the lower range.\n",
"In this paper, we present efficient algorithms for finding decompositions that certify sparsity\n",
"in the upper range of `. Our algorithms also apply in the lower range, which was already ad-\n",
"dressed by [3, 4, 5, 6, 19]. A decomposition certifies the sparsity of a graph if the sparse graphs\n",
"and graphs admitting the decomposition coincide.\n",
"Our algorithms are based on a new characterization of sparse graphs, which we call the\n",
"pebble game with colors. The pebble game with colors is a simple graph construction rule that\n",
"produces a sparse graph along with a sparsity-certifying decomposition.\n",
"We define and study a canonical class of pebble game constructions, which correspond to\n",
"previously studied decompositions of sparse graphs into edge disjoint trees. Our results provide\n",
"a unifying framework for all the previously known special cases, including Nash-Williams-\n",
"Tutte and [7, 24]. Indeed, in the lower range, canonical pebble game constructions capture the\n",
"properties of the augmenting paths used in matroid union and intersection algorithms[5, 6].\n",
"Since the sparse graphs in the upper range are not known to be unions or intersections of the\n",
"matroids for which there are efficient augmenting path algorithms, these do not easily apply in\n",
"∗ Research of both authors funded by the NSF under grants NSF CCF-0430990 and NSF-DARPA CARGO\n",
"CCR-0310661 to the first author.\n",
"2 Ileana Streinu, Louis Theran\n",
"Term Meaning\n",
"Sparse graph G Every non-empty subgraph on n′ vertices has ≤ kn′− ` edges\n",
"Tight graph G G = (V,E) is sparse and |V |= n, |E|= kn− `\n",
"Block H in G G is sparse, and H is a tight subgraph\n",
"Component H of G G is sparse and H is a maximal block\n",
"Map-graph Graph that admits an out-degree-exactly-one orientation\n",
"(k, `)-maps-and-trees Edge-disjoint union of ` trees and (k− `) map-grpahs\n",
"`Tk Union of ` trees, each vertex is in exactly k of them\n",
"Set of tree-pieces of an `Tk induced on V ′ ⊂V Pieces of trees in the `Tk spanned by E(V ′)\n",
"Proper `Tk Every V ′ ⊂V contains ≥ ` pieces of trees from the `Tk\n",
"Table 1. Sparse graph and decomposition terminology used in this paper.\n",
"the upper range. Pebble game with colors constructions may thus be considered a strengthening\n",
"of augmenting paths to the upper range of matroidal sparse graphs.\n",
"1.1. Sparse graphs\n",
"\n",
"ABSTRACT\n",
"\"\"\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"gpt2.generate(sess,prefix=text,truncate=sufix,checkpoint_dir=checkpoint_dir,nsamples=1)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## es"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"text = \"\"\"El foco de este documento son las descomposicións de (k, `)-sparse gráficos en bordes-disjunto subgraphs\n",
"que certifique la escasez. Usamos el gráfico para significar un múltiplo, posiblemente con bucles. Nosotros decimos que un\n",
"grafo es (k, `)-sparse si ningún subconjunto de n′ vértices abarca más de kn ` bordes en el gráfico; a\n",
"(k, `)-sparse gráfico con kn ` bordes es (k, `)-estrechado. Llamamos al rango k ≤ 2k−1 el superior\n",
"rango de gráficos escasos y 0≤ k el rango inferior.\n",
"En este artículo, presentamos algoritmos eficientes para encontrar descomposicións que certifiquen la escasez\n",
"en el rango superior de `. Nuestros algoritmos también se aplican en el rango inferior, que ya era ad-\n",
"vestido por [3, 4, 5, 6, 19]. Una descomposición certifica la escasez de un gráfico si los gráficos dispersos\n",
"y los gráficos que admiten la descomposición coinciden.\n",
"Nuestros algoritmos se basan en una nueva caracterización de gráficos escasos, que llamamos el\n",
"juego de guijarros con colores. El juego de guijarros con colores es una regla de construcción de gráficos simples que\n",
"produce un gráfico escaso junto con una descomposición certificadora de la escasez.\n",
"Definimos y estudiamos una clase canónica de construcciones de juego de guijarros, que corresponden a\n",
"previamente estudiado las descomposiciones de los gráficos escasos en los árboles disjuntos del borde. Nuestros resultados proporcionan\n",
"un marco unificador para todos los casos especiales conocidos anteriormente, incluidos Nash-Williams-\n",
"Tutte y [7, 24]. De hecho, en el rango inferior, las construcciones canónicas de juego de guijarros capturan la\n",
"propiedades de las rutas de aumento utilizadas en los algoritmos de unión de matroides y de intersección[5, 6].\n",
"Dado que los gráficos escasos en el rango superior no se sabe que son uniones o intersecciones de la\n",
"matroides para los que hay algoritmos de ruta de aumento eficiente, estos no se aplican fácilmente en\n",
"* Investigación de ambos autores financiada por la NSF bajo subvenciones NSF CCF-0430990 y NSF-DARPA CARGO\n",
"CCR-0310661 al primer autor.\n",
"2 Ileana Streinu, Louis Theran\n",
"Significado del término\n",
"Gráfico escaso G Cada subgrafo no vacío en n′ vértices tiene ≤ kn ` bordes\n",
"El gráfico ajustado G G = (V,E) es escaso y V = n, E= kn− `\n",
"El bloque H en G G es escaso, y H es un subgrafo apretado\n",
"El componente H de G G es escaso y H es un bloqueo máximo\n",
"Gráfico cartográfico que admite una orientación de grado-exactamente-uno\n",
"(k, `)-maps-and-trees Edge-disjunt union de ` árboles y (k- `) map-grpahs\n",
"`Tk Unión de ` árboles, cada vértice está exactamente en k de ellos\n",
"Conjunto de piezas arbóreas de un `Tk inducido en V ′ ́V Piezas de árboles en el `Tk extendido por E(V ′)\n",
"`Tk Apropiado Cada V ′ V contiene ≥ ` pedazos de árboles de la `Tk\n",
"Cuadro 1 Gráfico escaso y terminología de descomposición utilizada en este artículo.\n",
"el rango superior. Pebble juego con construcciones de colores por lo tanto puede ser considerado un fortalecimiento\n",
"de caminos de aumento a la gama superior de gráficos de la escasez matroidal.\n",
"1.1. Gráficos escasos\n",
"Un gráfico es (k, `)-sparse si para cualquier subgrafo no vacío con bordes m′ y n′ vértices, m′ ≤\n",
"kn `. Observamos que esta condición implica que 0 ≤ ` ≤ 2k− 1, y a partir de ahora en este\n",
"Haremos esta suposición. Un gráfico escaso que tiene n vértices y exactamente bordes kn\n",
"se llama apretado.\n",
"Para un gráfico G = (V,E), y V ′ V, utilizamos el intervalo de notación (V ′) para el número de bordes\n",
"en el subgráfico inducido por V ′. En un gráfico dirigido, out(V ′) es el número de bordes con la cola\n",
"en V ′ y la cabeza en V −V ′; para un subgráfico inducido por V ′, llamamos a tal borde un borde superior.\n",
"Hay dos tipos importantes de subgrafías de gráficos escasos. Un bloque es un subgrafo apretado de\n",
"un gráfico escaso. Un componente es un bloque máximo.\n",
"La Tabla 1 resume la escasa terminología gráfica utilizada en este artículo.\n",
"1.2. Descomposiciónes de certificación de la sparsidad\n",
"Un k-arborescencia es un gráfico que admite una descomposición en k borde-desjunto que abarca los árboles.\n",
"La Figura 1(a) muestra un ejemplo de una 3-arborescencia. Se describen los gráficos k-arborescentes\n",
"por los conocidos teoremas de Tutte [23] y Nash-Williams [17] como exactamente el (k,k) apretado\n",
"gráficos.\n",
"ABSTRACT\n",
"\"\"\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"gpt2.generate(sess,prefix=text,truncate=sufix,checkpoint_dir=checkpoint_dir,nsamples=1)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# gradio interface"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def generateAbstract(text):\n",
" # with tf.compat.v1.variable_scope(\"weight\", reuse = True):\n",
" #sess = tf.compat.v1.get_variable('sess',gpt2.start_tf_sess())\n",
" tf.compat.v1.reset_default_graph()\n",
" sess = gpt2.start_tf_sess()\n",
" gpt2.load_gpt2(sess,checkpoint_dir=checkpoint_dir,run_name='run1')\n",
" txt = gpt2.generate(sess,prefix=str(text)+\"\\nABSTRACT\", return_as_list=True,truncate=sufix,checkpoint_dir=checkpoint_dir,nsamples=1)[0]\n",
" return str(txt[txt.find('ABSTRACT'):])\n",
"\n",
"\n",
"\n",
"iface = gr.Interface(fn=generateAbstract, inputs=gr.inputs.Textbox(lines=10, placeholder=\"text\"), outputs=\"textbox\")\n",
"iface.launch(debug = True )"
]
}
],
"metadata": {
"interpreter": {
"hash": "53fbdc69e3e12c371950068c144423682c30d04ec68c2bd46937202e33e0058d"
},
"kernelspec": {
"display_name": "Python 3.7.11 ('receta')",
"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": "3.9.7"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}
|