Datasets
Models
Downloads: 1
Diff of
/notebooks/Training.ipynb
[000000]
..
[53d15f]
Switch to unified view
| a | b/notebooks/Training.ipynb | ||
|---|---|---|---|
| 1 | { |
||
| 2 | "cells": [ |
||
| 3 | { |
||
| 4 | "cell_type": "code", |
||
| 5 | "execution_count": 1, |
||
| 6 | "metadata": {}, |
||
| 7 | "outputs": [], |
||
| 8 | "source": [ |
||
| 9 | "VERSION = 33\n", |
||
| 10 | "\n", |
||
| 11 | "FOCAL_LOSS = 0\n", |
||
| 12 | "CLOUD_SINGLE = True\n", |
||
| 13 | "MIXUP = False\n", |
||
| 14 | "NO_BLACK_LOSS = True\n", |
||
| 15 | "DATA_SMALL = False\n", |
||
| 16 | "\n", |
||
| 17 | "# VERSION 31 old features, no stage2 training\n", |
||
| 18 | "# VERSION 32 old features, no stage2 training, fine-tuned weighted\n", |
||
| 19 | "# VERSION 33 old features, with stage2 training\n", |
||
| 20 | "# VERSION 34 old features, with stage2 training, fine-tuned weighted\n", |
||
| 21 | "# VERSION 35 new features, with stage2 training\n", |
||
| 22 | "# VERSION 35 new features, with stage2 training, fine-tuned weighted" |
||
| 23 | ] |
||
| 24 | }, |
||
| 25 | { |
||
| 26 | "cell_type": "code", |
||
| 27 | "execution_count": 2, |
||
| 28 | "metadata": {}, |
||
| 29 | "outputs": [], |
||
| 30 | "source": [ |
||
| 31 | "if VERSION in [31,32]:\n", |
||
| 32 | " TRAIN_ON_STAGE_1 = False\n", |
||
| 33 | "else:\n", |
||
| 34 | " TRAIN_ON_STAGE_1 = True\n", |
||
| 35 | "\n", |
||
| 36 | "if VERSION in [32,34,36]:\n", |
||
| 37 | " WEIGHTED = True\n", |
||
| 38 | "else:\n", |
||
| 39 | " WEIGHTED = False" |
||
| 40 | ] |
||
| 41 | }, |
||
| 42 | { |
||
| 43 | "cell_type": "code", |
||
| 44 | "execution_count": 6, |
||
| 45 | "metadata": {}, |
||
| 46 | "outputs": [], |
||
| 47 | "source": [ |
||
| 48 | "%run ./Code.ipynb" |
||
| 49 | ] |
||
| 50 | }, |
||
| 51 | { |
||
| 52 | "cell_type": "code", |
||
| 53 | "execution_count": 4, |
||
| 54 | "metadata": {}, |
||
| 55 | "outputs": [], |
||
| 56 | "source": [ |
||
| 57 | "if VERSION in [31,32]:\n", |
||
| 58 | " # old features, no stage2 training\n", |
||
| 59 | " train_md, test_md = loadMetadata()\n", |
||
| 60 | "elif VERSION in [33,34]:\n", |
||
| 61 | " # old features, with stage2 training\n", |
||
| 62 | " train_md, test_md = loadMetadata3()\n", |
||
| 63 | "elif VERSION in [35,36]:\n", |
||
| 64 | " # new features\n", |
||
| 65 | " train_md, test_md = loadMetadata2()" |
||
| 66 | ] |
||
| 67 | }, |
||
| 68 | { |
||
| 69 | "cell_type": "code", |
||
| 70 | "execution_count": 9, |
||
| 71 | "metadata": {}, |
||
| 72 | "outputs": [ |
||
| 73 | { |
||
| 74 | "data": { |
||
| 75 | "text/plain": [ |
||
| 76 | "1.111931 230422\n", |
||
| 77 | "0.864417 230399\n", |
||
| 78 | "1.200910 221421\n", |
||
| 79 | "0.446933 70301\n", |
||
| 80 | "0.737883 129\n", |
||
| 81 | "0.000000 124\n", |
||
| 82 | "0.796930 1\n", |
||
| 83 | "Name: weights, dtype: int64" |
||
| 84 | ] |
||
| 85 | }, |
||
| 86 | "execution_count": 9, |
||
| 87 | "metadata": {}, |
||
| 88 | "output_type": "execute_result" |
||
| 89 | } |
||
| 90 | ], |
||
| 91 | "source": [ |
||
| 92 | "train_md.weights.value_counts()" |
||
| 93 | ] |
||
| 94 | }, |
||
| 95 | { |
||
| 96 | "cell_type": "code", |
||
| 97 | "execution_count": 10, |
||
| 98 | "metadata": { |
||
| 99 | "scrolled": true |
||
| 100 | }, |
||
| 101 | "outputs": [ |
||
| 102 | { |
||
| 103 | "data": { |
||
| 104 | "text/plain": [ |
||
| 105 | "0" |
||
| 106 | ] |
||
| 107 | }, |
||
| 108 | "execution_count": 10, |
||
| 109 | "metadata": {}, |
||
| 110 | "output_type": "execute_result" |
||
| 111 | } |
||
| 112 | ], |
||
| 113 | "source": [ |
||
| 114 | "train_md.weights.isnull().sum()" |
||
| 115 | ] |
||
| 116 | }, |
||
| 117 | { |
||
| 118 | "cell_type": "code", |
||
| 119 | "execution_count": 11, |
||
| 120 | "metadata": {}, |
||
| 121 | "outputs": [ |
||
| 122 | { |
||
| 123 | "data": { |
||
| 124 | "text/plain": [ |
||
| 125 | "(752797, 103)" |
||
| 126 | ] |
||
| 127 | }, |
||
| 128 | "execution_count": 11, |
||
| 129 | "metadata": {}, |
||
| 130 | "output_type": "execute_result" |
||
| 131 | } |
||
| 132 | ], |
||
| 133 | "source": [ |
||
| 134 | "train_md.shape" |
||
| 135 | ] |
||
| 136 | }, |
||
| 137 | { |
||
| 138 | "cell_type": "markdown", |
||
| 139 | "metadata": {}, |
||
| 140 | "source": [ |
||
| 141 | "# Pre-processing features" |
||
| 142 | ] |
||
| 143 | }, |
||
| 144 | { |
||
| 145 | "cell_type": "code", |
||
| 146 | "execution_count": 29, |
||
| 147 | "metadata": {}, |
||
| 148 | "outputs": [], |
||
| 149 | "source": [ |
||
| 150 | "_,_ = loadMetadata(True)" |
||
| 151 | ] |
||
| 152 | }, |
||
| 153 | { |
||
| 154 | "cell_type": "code", |
||
| 155 | "execution_count": 9, |
||
| 156 | "metadata": {}, |
||
| 157 | "outputs": [], |
||
| 158 | "source": [ |
||
| 159 | "_,_ = loadMetadata3(True)" |
||
| 160 | ] |
||
| 161 | }, |
||
| 162 | { |
||
| 163 | "cell_type": "code", |
||
| 164 | "execution_count": 8, |
||
| 165 | "metadata": {}, |
||
| 166 | "outputs": [], |
||
| 167 | "source": [ |
||
| 168 | "_,_ = loadMetadata2(True)" |
||
| 169 | ] |
||
| 170 | }, |
||
| 171 | { |
||
| 172 | "cell_type": "code", |
||
| 173 | "execution_count": null, |
||
| 174 | "metadata": {}, |
||
| 175 | "outputs": [], |
||
| 176 | "source": [] |
||
| 177 | }, |
||
| 178 | { |
||
| 179 | "cell_type": "code", |
||
| 180 | "execution_count": 12, |
||
| 181 | "metadata": {}, |
||
| 182 | "outputs": [ |
||
| 183 | { |
||
| 184 | "data": { |
||
| 185 | "text/plain": [ |
||
| 186 | "[7, 9]" |
||
| 187 | ] |
||
| 188 | }, |
||
| 189 | "execution_count": 12, |
||
| 190 | "metadata": {}, |
||
| 191 | "output_type": "execute_result" |
||
| 192 | } |
||
| 193 | ], |
||
| 194 | "source": [ |
||
| 195 | "my_datasets3" |
||
| 196 | ] |
||
| 197 | }, |
||
| 198 | { |
||
| 199 | "cell_type": "code", |
||
| 200 | "execution_count": 18, |
||
| 201 | "metadata": {}, |
||
| 202 | "outputs": [ |
||
| 203 | { |
||
| 204 | "name": "stdout", |
||
| 205 | "output_type": "stream", |
||
| 206 | "text": [ |
||
| 207 | "dataset 7 fold 0 feats size torch.Size([2697008, 552])\n", |
||
| 208 | "dataset 7 fold 1 feats size torch.Size([2697008, 552])\n", |
||
| 209 | "dataset 7 fold 2 feats size torch.Size([2697008, 552])\n" |
||
| 210 | ] |
||
| 211 | } |
||
| 212 | ], |
||
| 213 | "source": [ |
||
| 214 | "preprocessedData(7,do_train=True,do_test=False)" |
||
| 215 | ] |
||
| 216 | }, |
||
| 217 | { |
||
| 218 | "cell_type": "code", |
||
| 219 | "execution_count": 19, |
||
| 220 | "metadata": {}, |
||
| 221 | "outputs": [ |
||
| 222 | { |
||
| 223 | "name": "stdout", |
||
| 224 | "output_type": "stream", |
||
| 225 | "text": [ |
||
| 226 | "dataset 9 fold 0 feats size torch.Size([2697008, 256])\n", |
||
| 227 | "dataset 9 fold 1 feats size torch.Size([2697008, 256])\n", |
||
| 228 | "dataset 9 fold 2 feats size torch.Size([2697008, 256])\n" |
||
| 229 | ] |
||
| 230 | } |
||
| 231 | ], |
||
| 232 | "source": [ |
||
| 233 | "preprocessedData(9,do_train=True,do_test=False)" |
||
| 234 | ] |
||
| 235 | }, |
||
| 236 | { |
||
| 237 | "cell_type": "code", |
||
| 238 | "execution_count": 20, |
||
| 239 | "metadata": {}, |
||
| 240 | "outputs": [ |
||
| 241 | { |
||
| 242 | "data": { |
||
| 243 | "text/plain": [ |
||
| 244 | "[11, 12, 13]" |
||
| 245 | ] |
||
| 246 | }, |
||
| 247 | "execution_count": 20, |
||
| 248 | "metadata": {}, |
||
| 249 | "output_type": "execute_result" |
||
| 250 | } |
||
| 251 | ], |
||
| 252 | "source": [ |
||
| 253 | "my_datasets5" |
||
| 254 | ] |
||
| 255 | }, |
||
| 256 | { |
||
| 257 | "cell_type": "code", |
||
| 258 | "execution_count": 23, |
||
| 259 | "metadata": { |
||
| 260 | "scrolled": false |
||
| 261 | }, |
||
| 262 | "outputs": [ |
||
| 263 | { |
||
| 264 | "name": "stdout", |
||
| 265 | "output_type": "stream", |
||
| 266 | "text": [ |
||
| 267 | "dataset 11 fold 0 feats size torch.Size([2697008, 256])\n", |
||
| 268 | "dataset 11 fold 1 feats size torch.Size([2697008, 256])\n", |
||
| 269 | "dataset 11 fold 2 feats size torch.Size([2697008, 256])\n", |
||
| 270 | "dataset 11 fold 3 feats size torch.Size([2697008, 256])\n", |
||
| 271 | "dataset 11 fold 4 feats size torch.Size([2697008, 256])\n" |
||
| 272 | ] |
||
| 273 | } |
||
| 274 | ], |
||
| 275 | "source": [ |
||
| 276 | "preprocessedData(11,do_train=True,do_test=False, folds=range(5))" |
||
| 277 | ] |
||
| 278 | }, |
||
| 279 | { |
||
| 280 | "cell_type": "code", |
||
| 281 | "execution_count": 24, |
||
| 282 | "metadata": { |
||
| 283 | "scrolled": false |
||
| 284 | }, |
||
| 285 | "outputs": [ |
||
| 286 | { |
||
| 287 | "name": "stdout", |
||
| 288 | "output_type": "stream", |
||
| 289 | "text": [ |
||
| 290 | "dataset 12 fold 0 feats size torch.Size([2697008, 256])\n", |
||
| 291 | "dataset 12 fold 1 feats size torch.Size([2697008, 256])\n", |
||
| 292 | "dataset 12 fold 2 feats size torch.Size([2697008, 256])\n", |
||
| 293 | "dataset 12 fold 3 feats size torch.Size([2697008, 256])\n", |
||
| 294 | "dataset 12 fold 4 feats size torch.Size([2697008, 256])\n" |
||
| 295 | ] |
||
| 296 | } |
||
| 297 | ], |
||
| 298 | "source": [ |
||
| 299 | "preprocessedData(12,do_train=True,do_test=False, folds=range(5))" |
||
| 300 | ] |
||
| 301 | }, |
||
| 302 | { |
||
| 303 | "cell_type": "code", |
||
| 304 | "execution_count": 26, |
||
| 305 | "metadata": { |
||
| 306 | "scrolled": true |
||
| 307 | }, |
||
| 308 | "outputs": [ |
||
| 309 | { |
||
| 310 | "name": "stdout", |
||
| 311 | "output_type": "stream", |
||
| 312 | "text": [ |
||
| 313 | "dataset 13 fold 0 feats size torch.Size([2697008, 256])\n", |
||
| 314 | "dataset 13 fold 1 feats size torch.Size([2697008, 256])\n", |
||
| 315 | "dataset 13 fold 2 feats size torch.Size([2697008, 256])\n", |
||
| 316 | "dataset 13 fold 3 feats size torch.Size([2697008, 256])\n", |
||
| 317 | "dataset 13 fold 4 feats size torch.Size([2697008, 256])\n" |
||
| 318 | ] |
||
| 319 | } |
||
| 320 | ], |
||
| 321 | "source": [ |
||
| 322 | "preprocessedData(13,do_train=True,do_test=False, folds=range(5))" |
||
| 323 | ] |
||
| 324 | }, |
||
| 325 | { |
||
| 326 | "cell_type": "code", |
||
| 327 | "execution_count": null, |
||
| 328 | "metadata": {}, |
||
| 329 | "outputs": [], |
||
| 330 | "source": [] |
||
| 331 | }, |
||
| 332 | { |
||
| 333 | "cell_type": "code", |
||
| 334 | "execution_count": 8, |
||
| 335 | "metadata": {}, |
||
| 336 | "outputs": [ |
||
| 337 | { |
||
| 338 | "name": "stdout", |
||
| 339 | "output_type": "stream", |
||
| 340 | "text": [ |
||
| 341 | "dataset 7 fold 0 feats size torch.Size([2697008, 552])\n", |
||
| 342 | "dataset 7 fold 1 feats size torch.Size([2697008, 552])\n", |
||
| 343 | "dataset 7 fold 2 feats size torch.Size([2697008, 552])\n", |
||
| 344 | "dataset 9 fold 0 feats size torch.Size([2697008, 256])\n", |
||
| 345 | "dataset 9 fold 1 feats size torch.Size([2697008, 256])\n", |
||
| 346 | "dataset 9 fold 2 feats size torch.Size([2697008, 256])\n", |
||
| 347 | "dataset 11 fold 0 feats size torch.Size([2697008, 256])\n", |
||
| 348 | "dataset 11 fold 1 feats size torch.Size([2697008, 256])\n", |
||
| 349 | "dataset 11 fold 2 feats size torch.Size([2697008, 256])\n", |
||
| 350 | "dataset 11 fold 3 feats size torch.Size([2697008, 256])\n", |
||
| 351 | "dataset 11 fold 4 feats size torch.Size([2697008, 256])\n", |
||
| 352 | "dataset 12 fold 0 feats size torch.Size([2697008, 256])\n", |
||
| 353 | "dataset 12 fold 1 feats size torch.Size([2697008, 256])\n", |
||
| 354 | "dataset 12 fold 2 feats size torch.Size([2697008, 256])\n", |
||
| 355 | "dataset 12 fold 3 feats size torch.Size([2697008, 256])\n", |
||
| 356 | "dataset 12 fold 4 feats size torch.Size([2697008, 256])\n", |
||
| 357 | "dataset 13 fold 0 feats size torch.Size([2697008, 256])\n", |
||
| 358 | "dataset 13 fold 1 feats size torch.Size([2697008, 256])\n", |
||
| 359 | "dataset 13 fold 2 feats size torch.Size([2697008, 256])\n", |
||
| 360 | "dataset 13 fold 3 feats size torch.Size([2697008, 256])\n", |
||
| 361 | "dataset 13 fold 4 feats size torch.Size([2697008, 256])\n" |
||
| 362 | ] |
||
| 363 | } |
||
| 364 | ], |
||
| 365 | "source": [ |
||
| 366 | "for ds in my_datasets3:\n", |
||
| 367 | " preprocessedData(ds)\n", |
||
| 368 | "\n", |
||
| 369 | "for ds in my_datasets5:\n", |
||
| 370 | " preprocessedData(ds, folds=range(5))" |
||
| 371 | ] |
||
| 372 | }, |
||
| 373 | { |
||
| 374 | "cell_type": "code", |
||
| 375 | "execution_count": 10, |
||
| 376 | "metadata": {}, |
||
| 377 | "outputs": [ |
||
| 378 | { |
||
| 379 | "name": "stdout", |
||
| 380 | "output_type": "stream", |
||
| 381 | "text": [ |
||
| 382 | "dataset 14 fold 0 feats size torch.Size([3011188, 256])\n" |
||
| 383 | ] |
||
| 384 | }, |
||
| 385 | { |
||
| 386 | "ename": "FileNotFoundError", |
||
| 387 | "evalue": "[Errno 2] No such file or directory: '/mnt/edisk/running/yuval/model_se_resnet101_version_new_splits_stage2_type_features_test_split_0.pkl'", |
||
| 388 | "output_type": "error", |
||
| 389 | "traceback": [ |
||
| 390 | "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", |
||
| 391 | "\u001b[0;31mFileNotFoundError\u001b[0m Traceback (most recent call last)", |
||
| 392 | "\u001b[0;32m<ipython-input-10-5a07cc4fa1a8>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mpreprocessedData\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m14\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mfold_col\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'fold5'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mdo_test\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mdo_train\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", |
||
| 393 | "\u001b[0;32m<ipython-input-6-51e1d35e10f9>\u001b[0m in \u001b[0;36mpreprocessedData\u001b[0;34m(dataset, folds, fold_col, do_test, do_test2, do_train)\u001b[0m\n\u001b[1;32m 62\u001b[0m .format(dataset_name.replace('_5n','').replace('_5f','').replace('_5',''),\n\u001b[1;32m 63\u001b[0m filename_add,dsft,focal,ds_num,test_fix,fold)\n\u001b[0;32m---> 64\u001b[0;31m \u001b[0mfeats\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpickle\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mload\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mopen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilename\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'rb'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 65\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 66\u001b[0m \u001b[0;32massert\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfeats\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;36m8\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtest_md\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", |
||
| 394 | "\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: '/mnt/edisk/running/yuval/model_se_resnet101_version_new_splits_stage2_type_features_test_split_0.pkl'" |
||
| 395 | ] |
||
| 396 | } |
||
| 397 | ], |
||
| 398 | "source": [ |
||
| 399 | "preprocessedData(14,fold_col='fold5',do_test=True,do_train=True)" |
||
| 400 | ] |
||
| 401 | }, |
||
| 402 | { |
||
| 403 | "cell_type": "code", |
||
| 404 | "execution_count": null, |
||
| 405 | "metadata": {}, |
||
| 406 | "outputs": [], |
||
| 407 | "source": [] |
||
| 408 | }, |
||
| 409 | { |
||
| 410 | "cell_type": "markdown", |
||
| 411 | "metadata": {}, |
||
| 412 | "source": [ |
||
| 413 | "# Running" |
||
| 414 | ] |
||
| 415 | }, |
||
| 416 | { |
||
| 417 | "cell_type": "code", |
||
| 418 | "execution_count": 28, |
||
| 419 | "metadata": { |
||
| 420 | "scrolled": true |
||
| 421 | }, |
||
| 422 | "outputs": [ |
||
| 423 | { |
||
| 424 | "name": "stdout", |
||
| 425 | "output_type": "stream", |
||
| 426 | "text": [ |
||
| 427 | "completed epochs: 0 starting now: 4\n", |
||
| 428 | "DataSet 14 train size 17355 fold 2\n", |
||
| 429 | "adding dummy serieses 27\n", |
||
| 430 | "DataSet 14 valid size 4416 fold 2\n", |
||
| 431 | "setFeats, augmentation 0\n", |
||
| 432 | "dataset train: 17355 valid: 4416 loader train: 542 valid: 138\n", |
||
| 433 | "starting from scratch\n", |
||
| 434 | "setFeats, augmentation -1\n", |
||
| 435 | "Batch 50 device: cuda time passed: 22.728 time per batch: 0.455\n", |
||
| 436 | "Batch 100 device: cuda time passed: 39.605 time per batch: 0.396\n", |
||
| 437 | "Batch 150 device: cuda time passed: 55.920 time per batch: 0.373\n", |
||
| 438 | "Batch 200 device: cuda time passed: 72.699 time per batch: 0.363\n", |
||
| 439 | "Batch 250 device: cuda time passed: 89.437 time per batch: 0.358\n", |
||
| 440 | "Batch 300 device: cuda time passed: 105.583 time per batch: 0.352\n", |
||
| 441 | "Batch 350 device: cuda time passed: 122.869 time per batch: 0.351\n", |
||
| 442 | "Batch 400 device: cuda time passed: 139.694 time per batch: 0.349\n", |
||
| 443 | "Batch 450 device: cuda time passed: 158.701 time per batch: 0.353\n", |
||
| 444 | "Batch 500 device: cuda time passed: 176.083 time per batch: 0.352\n", |
||
| 445 | "Batch 50 device: cuda time passed: 8.131 time per batch: 0.163\n", |
||
| 446 | "Batch 100 device: cuda time passed: 14.930 time per batch: 0.149\n", |
||
| 447 | "v35, d14, e1, f2, trn ll: 0.0580, val ll: 0.0650, ll_w: 0.0575, cor: 0.8338, auc: 0.9870, lr: 0.0002\n", |
||
| 448 | "setFeats, augmentation -1\n", |
||
| 449 | "Batch 50 device: cuda time passed: 22.873 time per batch: 0.457\n", |
||
| 450 | "Batch 100 device: cuda time passed: 39.907 time per batch: 0.399\n", |
||
| 451 | "Batch 150 device: cuda time passed: 57.763 time per batch: 0.385\n", |
||
| 452 | "Batch 200 device: cuda time passed: 75.045 time per batch: 0.375\n", |
||
| 453 | "Batch 250 device: cuda time passed: 92.730 time per batch: 0.371\n", |
||
| 454 | "Batch 300 device: cuda time passed: 109.667 time per batch: 0.366\n", |
||
| 455 | "Batch 350 device: cuda time passed: 126.574 time per batch: 0.362\n", |
||
| 456 | "Batch 400 device: cuda time passed: 143.725 time per batch: 0.359\n", |
||
| 457 | "Batch 450 device: cuda time passed: 161.952 time per batch: 0.360\n", |
||
| 458 | "Batch 500 device: cuda time passed: 178.315 time per batch: 0.357\n", |
||
| 459 | "Batch 50 device: cuda time passed: 8.428 time per batch: 0.169\n", |
||
| 460 | "Batch 100 device: cuda time passed: 15.068 time per batch: 0.151\n", |
||
| 461 | "v35, d14, e2, f2, trn ll: 0.0356, val ll: 0.0640, ll_w: 0.0562, cor: 0.8351, auc: 0.9872, lr: 0.0002\n", |
||
| 462 | "setFeats, augmentation -1\n", |
||
| 463 | "Batch 50 device: cuda time passed: 22.887 time per batch: 0.458\n", |
||
| 464 | "Batch 100 device: cuda time passed: 39.853 time per batch: 0.399\n", |
||
| 465 | "Batch 150 device: cuda time passed: 56.609 time per batch: 0.377\n", |
||
| 466 | "Batch 200 device: cuda time passed: 73.060 time per batch: 0.365\n", |
||
| 467 | "Batch 250 device: cuda time passed: 90.475 time per batch: 0.362\n", |
||
| 468 | "Batch 300 device: cuda time passed: 107.703 time per batch: 0.359\n", |
||
| 469 | "Batch 350 device: cuda time passed: 124.235 time per batch: 0.355\n", |
||
| 470 | "Batch 400 device: cuda time passed: 141.549 time per batch: 0.354\n", |
||
| 471 | "Batch 450 device: cuda time passed: 159.349 time per batch: 0.354\n", |
||
| 472 | "Batch 500 device: cuda time passed: 175.549 time per batch: 0.351\n", |
||
| 473 | "Batch 50 device: cuda time passed: 8.712 time per batch: 0.174\n", |
||
| 474 | "Batch 100 device: cuda time passed: 15.378 time per batch: 0.154\n", |
||
| 475 | "v35, d14, e3, f2, trn ll: 0.0341, val ll: 0.0622, ll_w: 0.0549, cor: 0.8409, auc: 0.9887, lr: 0.0002\n", |
||
| 476 | "setFeats, augmentation -1\n", |
||
| 477 | "Batch 50 device: cuda time passed: 23.339 time per batch: 0.467\n", |
||
| 478 | "Batch 100 device: cuda time passed: 40.154 time per batch: 0.402\n", |
||
| 479 | "Batch 150 device: cuda time passed: 56.698 time per batch: 0.378\n", |
||
| 480 | "Batch 200 device: cuda time passed: 74.060 time per batch: 0.370\n", |
||
| 481 | "Batch 250 device: cuda time passed: 91.302 time per batch: 0.365\n", |
||
| 482 | "Batch 300 device: cuda time passed: 108.675 time per batch: 0.362\n", |
||
| 483 | "Batch 350 device: cuda time passed: 126.067 time per batch: 0.360\n", |
||
| 484 | "Batch 400 device: cuda time passed: 143.346 time per batch: 0.358\n", |
||
| 485 | "Batch 450 device: cuda time passed: 162.692 time per batch: 0.362\n", |
||
| 486 | "Batch 500 device: cuda time passed: 179.814 time per batch: 0.360\n", |
||
| 487 | "Batch 50 device: cuda time passed: 7.879 time per batch: 0.158\n", |
||
| 488 | "Batch 100 device: cuda time passed: 14.703 time per batch: 0.147\n", |
||
| 489 | "v35, d14, e4, f2, trn ll: 0.0335, val ll: 0.0613, ll_w: 0.0539, cor: 0.8421, auc: 0.9887, lr: 0.0002\n", |
||
| 490 | "total running time 900.058856010437\n", |
||
| 491 | "completed epochs: 4 starting now: 4\n", |
||
| 492 | "DataSet 14 train size 17355 fold 2\n", |
||
| 493 | "adding dummy serieses 27\n", |
||
| 494 | "DataSet 14 valid size 4416 fold 2\n", |
||
| 495 | "setFeats, augmentation 0\n", |
||
| 496 | "dataset train: 17355 valid: 4416 loader train: 542 valid: 138\n", |
||
| 497 | "loading model model.b4.f2.d14.v35\n", |
||
| 498 | "setFeats, augmentation -1\n", |
||
| 499 | "Batch 50 device: cuda time passed: 22.315 time per batch: 0.446\n", |
||
| 500 | "Batch 100 device: cuda time passed: 38.974 time per batch: 0.390\n", |
||
| 501 | "Batch 150 device: cuda time passed: 56.082 time per batch: 0.374\n", |
||
| 502 | "Batch 200 device: cuda time passed: 73.546 time per batch: 0.368\n", |
||
| 503 | "Batch 250 device: cuda time passed: 90.717 time per batch: 0.363\n", |
||
| 504 | "Batch 300 device: cuda time passed: 107.371 time per batch: 0.358\n", |
||
| 505 | "Batch 350 device: cuda time passed: 124.145 time per batch: 0.355\n", |
||
| 506 | "Batch 400 device: cuda time passed: 140.102 time per batch: 0.350\n", |
||
| 507 | "Batch 450 device: cuda time passed: 158.547 time per batch: 0.352\n", |
||
| 508 | "Batch 500 device: cuda time passed: 176.664 time per batch: 0.353\n", |
||
| 509 | "Batch 50 device: cuda time passed: 8.467 time per batch: 0.169\n", |
||
| 510 | "Batch 100 device: cuda time passed: 15.208 time per batch: 0.152\n", |
||
| 511 | "v35, d14, e5, f2, trn ll: 0.0319, val ll: 0.0602, ll_w: 0.0530, cor: 0.8445, auc: 0.9892, lr: 2e-05\n", |
||
| 512 | "setFeats, augmentation -1\n", |
||
| 513 | "Batch 50 device: cuda time passed: 23.093 time per batch: 0.462\n", |
||
| 514 | "Batch 100 device: cuda time passed: 40.190 time per batch: 0.402\n", |
||
| 515 | "Batch 150 device: cuda time passed: 57.287 time per batch: 0.382\n", |
||
| 516 | "Batch 200 device: cuda time passed: 74.458 time per batch: 0.372\n", |
||
| 517 | "Batch 250 device: cuda time passed: 91.213 time per batch: 0.365\n", |
||
| 518 | "Batch 300 device: cuda time passed: 108.222 time per batch: 0.361\n", |
||
| 519 | "Batch 350 device: cuda time passed: 125.171 time per batch: 0.358\n", |
||
| 520 | "Batch 400 device: cuda time passed: 142.199 time per batch: 0.355\n", |
||
| 521 | "Batch 450 device: cuda time passed: 162.403 time per batch: 0.361\n", |
||
| 522 | "Batch 500 device: cuda time passed: 179.653 time per batch: 0.359\n", |
||
| 523 | "Batch 50 device: cuda time passed: 8.772 time per batch: 0.175\n", |
||
| 524 | "Batch 100 device: cuda time passed: 15.212 time per batch: 0.152\n", |
||
| 525 | "v35, d14, e6, f2, trn ll: 0.0316, val ll: 0.0603, ll_w: 0.0531, cor: 0.8444, auc: 0.9892, lr: 2e-05\n", |
||
| 526 | "setFeats, augmentation -1\n", |
||
| 527 | "Batch 50 device: cuda time passed: 21.633 time per batch: 0.433\n", |
||
| 528 | "Batch 100 device: cuda time passed: 38.635 time per batch: 0.386\n", |
||
| 529 | "Batch 150 device: cuda time passed: 55.617 time per batch: 0.371\n", |
||
| 530 | "Batch 200 device: cuda time passed: 72.396 time per batch: 0.362\n", |
||
| 531 | "Batch 250 device: cuda time passed: 89.274 time per batch: 0.357\n", |
||
| 532 | "Batch 300 device: cuda time passed: 106.187 time per batch: 0.354\n", |
||
| 533 | "Batch 350 device: cuda time passed: 122.741 time per batch: 0.351\n", |
||
| 534 | "Batch 400 device: cuda time passed: 139.218 time per batch: 0.348\n", |
||
| 535 | "Batch 450 device: cuda time passed: 158.183 time per batch: 0.352\n", |
||
| 536 | "Batch 500 device: cuda time passed: 175.811 time per batch: 0.352\n", |
||
| 537 | "Batch 50 device: cuda time passed: 8.583 time per batch: 0.172\n", |
||
| 538 | "Batch 100 device: cuda time passed: 15.243 time per batch: 0.152\n", |
||
| 539 | "v35, d14, e7, f2, trn ll: 0.0315, val ll: 0.0602, ll_w: 0.0530, cor: 0.8446, auc: 0.9892, lr: 2e-05\n", |
||
| 540 | "setFeats, augmentation -1\n", |
||
| 541 | "Batch 50 device: cuda time passed: 23.204 time per batch: 0.464\n", |
||
| 542 | "Batch 100 device: cuda time passed: 40.589 time per batch: 0.406\n", |
||
| 543 | "Batch 150 device: cuda time passed: 58.004 time per batch: 0.387\n", |
||
| 544 | "Batch 200 device: cuda time passed: 75.275 time per batch: 0.376\n", |
||
| 545 | "Batch 250 device: cuda time passed: 92.072 time per batch: 0.368\n", |
||
| 546 | "Batch 300 device: cuda time passed: 109.143 time per batch: 0.364\n", |
||
| 547 | "Batch 350 device: cuda time passed: 125.692 time per batch: 0.359\n", |
||
| 548 | "Batch 400 device: cuda time passed: 143.440 time per batch: 0.359\n", |
||
| 549 | "Batch 450 device: cuda time passed: 164.424 time per batch: 0.365\n", |
||
| 550 | "Batch 500 device: cuda time passed: 181.490 time per batch: 0.363\n", |
||
| 551 | "Batch 50 device: cuda time passed: 8.635 time per batch: 0.173\n", |
||
| 552 | "Batch 100 device: cuda time passed: 15.140 time per batch: 0.151\n", |
||
| 553 | "v35, d14, e8, f2, trn ll: 0.0314, val ll: 0.0601, ll_w: 0.0529, cor: 0.8448, auc: 0.9892, lr: 2e-05\n", |
||
| 554 | "total running time 871.9309167861938\n", |
||
| 555 | "completed epochs: 8 starting now: 3\n", |
||
| 556 | "DataSet 14 train size 17355 fold 2\n", |
||
| 557 | "adding dummy serieses 27\n", |
||
| 558 | "DataSet 14 valid size 4416 fold 2\n", |
||
| 559 | "setFeats, augmentation 0\n", |
||
| 560 | "dataset train: 17355 valid: 4416 loader train: 542 valid: 138\n", |
||
| 561 | "loading model model.b8.f2.d14.v35\n", |
||
| 562 | "setFeats, augmentation -1\n", |
||
| 563 | "Batch 50 device: cuda time passed: 22.052 time per batch: 0.441\n", |
||
| 564 | "Batch 100 device: cuda time passed: 38.728 time per batch: 0.387\n" |
||
| 565 | ] |
||
| 566 | }, |
||
| 567 | { |
||
| 568 | "name": "stdout", |
||
| 569 | "output_type": "stream", |
||
| 570 | "text": [ |
||
| 571 | "Batch 150 device: cuda time passed: 56.020 time per batch: 0.373\n", |
||
| 572 | "Batch 200 device: cuda time passed: 73.183 time per batch: 0.366\n", |
||
| 573 | "Batch 250 device: cuda time passed: 90.324 time per batch: 0.361\n", |
||
| 574 | "Batch 300 device: cuda time passed: 107.782 time per batch: 0.359\n", |
||
| 575 | "Batch 350 device: cuda time passed: 124.543 time per batch: 0.356\n", |
||
| 576 | "Batch 400 device: cuda time passed: 141.478 time per batch: 0.354\n", |
||
| 577 | "Batch 450 device: cuda time passed: 162.319 time per batch: 0.361\n", |
||
| 578 | "Batch 500 device: cuda time passed: 179.659 time per batch: 0.359\n", |
||
| 579 | "Batch 50 device: cuda time passed: 7.857 time per batch: 0.157\n", |
||
| 580 | "Batch 100 device: cuda time passed: 14.956 time per batch: 0.150\n", |
||
| 581 | "v35, d14, e9, f2, trn ll: 0.0313, val ll: 0.0599, ll_w: 0.0527, cor: 0.8454, auc: 0.9892, lr: 5e-06\n", |
||
| 582 | "setFeats, augmentation -1\n", |
||
| 583 | "Batch 50 device: cuda time passed: 23.852 time per batch: 0.477\n", |
||
| 584 | "Batch 100 device: cuda time passed: 41.405 time per batch: 0.414\n", |
||
| 585 | "Batch 150 device: cuda time passed: 59.015 time per batch: 0.393\n", |
||
| 586 | "Batch 200 device: cuda time passed: 76.762 time per batch: 0.384\n", |
||
| 587 | "Batch 250 device: cuda time passed: 94.142 time per batch: 0.377\n", |
||
| 588 | "Batch 300 device: cuda time passed: 111.812 time per batch: 0.373\n", |
||
| 589 | "Batch 350 device: cuda time passed: 129.992 time per batch: 0.371\n", |
||
| 590 | "Batch 400 device: cuda time passed: 147.178 time per batch: 0.368\n", |
||
| 591 | "Batch 450 device: cuda time passed: 168.899 time per batch: 0.375\n", |
||
| 592 | "Batch 500 device: cuda time passed: 184.992 time per batch: 0.370\n", |
||
| 593 | "Batch 50 device: cuda time passed: 8.119 time per batch: 0.162\n", |
||
| 594 | "Batch 100 device: cuda time passed: 14.013 time per batch: 0.140\n", |
||
| 595 | "v35, d14, e10, f2, trn ll: 0.0313, val ll: 0.0600, ll_w: 0.0528, cor: 0.8451, auc: 0.9893, lr: 5e-06\n", |
||
| 596 | "setFeats, augmentation -1\n", |
||
| 597 | "Batch 50 device: cuda time passed: 21.209 time per batch: 0.424\n", |
||
| 598 | "Batch 100 device: cuda time passed: 37.676 time per batch: 0.377\n", |
||
| 599 | "Batch 150 device: cuda time passed: 53.211 time per batch: 0.355\n", |
||
| 600 | "Batch 200 device: cuda time passed: 68.886 time per batch: 0.344\n", |
||
| 601 | "Batch 250 device: cuda time passed: 84.449 time per batch: 0.338\n", |
||
| 602 | "Batch 300 device: cuda time passed: 100.285 time per batch: 0.334\n", |
||
| 603 | "Batch 350 device: cuda time passed: 116.165 time per batch: 0.332\n", |
||
| 604 | "Batch 400 device: cuda time passed: 131.615 time per batch: 0.329\n", |
||
| 605 | "Batch 450 device: cuda time passed: 150.426 time per batch: 0.334\n", |
||
| 606 | "Batch 500 device: cuda time passed: 166.304 time per batch: 0.333\n", |
||
| 607 | "Batch 50 device: cuda time passed: 7.404 time per batch: 0.148\n", |
||
| 608 | "Batch 100 device: cuda time passed: 13.992 time per batch: 0.140\n", |
||
| 609 | "v35, d14, e11, f2, trn ll: 0.0312, val ll: 0.0600, ll_w: 0.0528, cor: 0.8450, auc: 0.9893, lr: 5e-06\n", |
||
| 610 | "total running time 644.8997066020966\n", |
||
| 611 | "completed epochs: 11 starting now: 2\n", |
||
| 612 | "DataSet 14 train size 17355 fold 2\n", |
||
| 613 | "adding dummy serieses 27\n", |
||
| 614 | "DataSet 14 valid size 4416 fold 2\n", |
||
| 615 | "setFeats, augmentation 0\n", |
||
| 616 | "dataset train: 17355 valid: 4416 loader train: 542 valid: 138\n", |
||
| 617 | "loading model model.b11.f2.d14.v35\n", |
||
| 618 | "setFeats, augmentation -1\n", |
||
| 619 | "Batch 50 device: cuda time passed: 21.014 time per batch: 0.420\n", |
||
| 620 | "Batch 100 device: cuda time passed: 36.560 time per batch: 0.366\n", |
||
| 621 | "Batch 150 device: cuda time passed: 53.272 time per batch: 0.355\n", |
||
| 622 | "Batch 200 device: cuda time passed: 68.574 time per batch: 0.343\n", |
||
| 623 | "Batch 250 device: cuda time passed: 83.938 time per batch: 0.336\n", |
||
| 624 | "Batch 300 device: cuda time passed: 100.283 time per batch: 0.334\n", |
||
| 625 | "Batch 350 device: cuda time passed: 116.620 time per batch: 0.333\n", |
||
| 626 | "Batch 400 device: cuda time passed: 132.783 time per batch: 0.332\n", |
||
| 627 | "Batch 450 device: cuda time passed: 152.425 time per batch: 0.339\n", |
||
| 628 | "Batch 500 device: cuda time passed: 168.627 time per batch: 0.337\n", |
||
| 629 | "Batch 50 device: cuda time passed: 8.257 time per batch: 0.165\n", |
||
| 630 | "Batch 100 device: cuda time passed: 14.836 time per batch: 0.148\n", |
||
| 631 | "v35, d14, e12, f2, trn ll: 0.0311, val ll: 0.0600, ll_w: 0.0528, cor: 0.8451, auc: 0.9893, lr: 2e-06\n", |
||
| 632 | "setFeats, augmentation -1\n", |
||
| 633 | "Batch 50 device: cuda time passed: 21.311 time per batch: 0.426\n", |
||
| 634 | "Batch 100 device: cuda time passed: 38.735 time per batch: 0.387\n", |
||
| 635 | "Batch 150 device: cuda time passed: 54.760 time per batch: 0.365\n", |
||
| 636 | "Batch 200 device: cuda time passed: 71.364 time per batch: 0.357\n", |
||
| 637 | "Batch 250 device: cuda time passed: 87.975 time per batch: 0.352\n", |
||
| 638 | "Batch 300 device: cuda time passed: 104.126 time per batch: 0.347\n", |
||
| 639 | "Batch 350 device: cuda time passed: 120.536 time per batch: 0.344\n", |
||
| 640 | "Batch 400 device: cuda time passed: 136.741 time per batch: 0.342\n", |
||
| 641 | "Batch 450 device: cuda time passed: 154.903 time per batch: 0.344\n", |
||
| 642 | "Batch 500 device: cuda time passed: 173.138 time per batch: 0.346\n", |
||
| 643 | "Batch 50 device: cuda time passed: 8.686 time per batch: 0.174\n", |
||
| 644 | "Batch 100 device: cuda time passed: 15.208 time per batch: 0.152\n", |
||
| 645 | "v35, d14, e13, f2, trn ll: 0.0311, val ll: 0.0599, ll_w: 0.0527, cor: 0.8454, auc: 0.9892, lr: 2e-06\n", |
||
| 646 | "total running time 421.16584634780884\n", |
||
| 647 | "total time 2838.7946536540985\n", |
||
| 648 | "completed epochs: 0 starting now: 4\n", |
||
| 649 | "DataSet 14 train size 17408 fold 3\n", |
||
| 650 | "adding dummy serieses 16\n", |
||
| 651 | "DataSet 14 valid size 4352 fold 3\n", |
||
| 652 | "setFeats, augmentation 0\n", |
||
| 653 | "dataset train: 17408 valid: 4352 loader train: 544 valid: 136\n", |
||
| 654 | "starting from scratch\n", |
||
| 655 | "setFeats, augmentation -1\n", |
||
| 656 | "Batch 50 device: cuda time passed: 21.909 time per batch: 0.438\n", |
||
| 657 | "Batch 100 device: cuda time passed: 38.295 time per batch: 0.383\n", |
||
| 658 | "Batch 150 device: cuda time passed: 54.459 time per batch: 0.363\n", |
||
| 659 | "Batch 200 device: cuda time passed: 71.059 time per batch: 0.355\n", |
||
| 660 | "Batch 250 device: cuda time passed: 87.285 time per batch: 0.349\n", |
||
| 661 | "Batch 300 device: cuda time passed: 103.278 time per batch: 0.344\n", |
||
| 662 | "Batch 350 device: cuda time passed: 119.758 time per batch: 0.342\n", |
||
| 663 | "Batch 400 device: cuda time passed: 136.023 time per batch: 0.340\n", |
||
| 664 | "Batch 450 device: cuda time passed: 156.381 time per batch: 0.348\n", |
||
| 665 | "Batch 500 device: cuda time passed: 172.724 time per batch: 0.345\n", |
||
| 666 | "Batch 50 device: cuda time passed: 8.381 time per batch: 0.168\n", |
||
| 667 | "Batch 100 device: cuda time passed: 15.352 time per batch: 0.154\n", |
||
| 668 | "v35, d14, e1, f3, trn ll: 0.0574, val ll: 0.0673, ll_w: 0.0595, cor: 0.8311, auc: 0.9867, lr: 0.0002\n", |
||
| 669 | "setFeats, augmentation -1\n", |
||
| 670 | "Batch 50 device: cuda time passed: 21.941 time per batch: 0.439\n", |
||
| 671 | "Batch 100 device: cuda time passed: 38.796 time per batch: 0.388\n", |
||
| 672 | "Batch 150 device: cuda time passed: 55.281 time per batch: 0.369\n", |
||
| 673 | "Batch 200 device: cuda time passed: 72.261 time per batch: 0.361\n", |
||
| 674 | "Batch 250 device: cuda time passed: 88.752 time per batch: 0.355\n", |
||
| 675 | "Batch 300 device: cuda time passed: 105.021 time per batch: 0.350\n", |
||
| 676 | "Batch 350 device: cuda time passed: 121.855 time per batch: 0.348\n", |
||
| 677 | "Batch 400 device: cuda time passed: 137.611 time per batch: 0.344\n", |
||
| 678 | "Batch 450 device: cuda time passed: 158.361 time per batch: 0.352\n", |
||
| 679 | "Batch 500 device: cuda time passed: 175.196 time per batch: 0.350\n", |
||
| 680 | "Batch 50 device: cuda time passed: 7.713 time per batch: 0.154\n", |
||
| 681 | "Batch 100 device: cuda time passed: 15.676 time per batch: 0.157\n", |
||
| 682 | "v35, d14, e2, f3, trn ll: 0.0356, val ll: 0.0659, ll_w: 0.0581, cor: 0.8330, auc: 0.9871, lr: 0.0002\n", |
||
| 683 | "setFeats, augmentation -1\n", |
||
| 684 | "Batch 50 device: cuda time passed: 22.308 time per batch: 0.446\n", |
||
| 685 | "Batch 100 device: cuda time passed: 38.613 time per batch: 0.386\n", |
||
| 686 | "Batch 150 device: cuda time passed: 55.122 time per batch: 0.367\n", |
||
| 687 | "Batch 200 device: cuda time passed: 71.951 time per batch: 0.360\n", |
||
| 688 | "Batch 250 device: cuda time passed: 88.792 time per batch: 0.355\n", |
||
| 689 | "Batch 300 device: cuda time passed: 105.939 time per batch: 0.353\n", |
||
| 690 | "Batch 350 device: cuda time passed: 121.911 time per batch: 0.348\n", |
||
| 691 | "Batch 400 device: cuda time passed: 138.362 time per batch: 0.346\n", |
||
| 692 | "Batch 450 device: cuda time passed: 158.974 time per batch: 0.353\n", |
||
| 693 | "Batch 500 device: cuda time passed: 175.745 time per batch: 0.351\n", |
||
| 694 | "Batch 50 device: cuda time passed: 8.061 time per batch: 0.161\n", |
||
| 695 | "Batch 100 device: cuda time passed: 14.448 time per batch: 0.144\n", |
||
| 696 | "v35, d14, e3, f3, trn ll: 0.0344, val ll: 0.0648, ll_w: 0.0572, cor: 0.8354, auc: 0.9880, lr: 0.0002\n", |
||
| 697 | "setFeats, augmentation -1\n", |
||
| 698 | "Batch 50 device: cuda time passed: 22.337 time per batch: 0.447\n", |
||
| 699 | "Batch 100 device: cuda time passed: 39.126 time per batch: 0.391\n", |
||
| 700 | "Batch 150 device: cuda time passed: 56.197 time per batch: 0.375\n", |
||
| 701 | "Batch 200 device: cuda time passed: 72.948 time per batch: 0.365\n", |
||
| 702 | "Batch 250 device: cuda time passed: 89.869 time per batch: 0.359\n", |
||
| 703 | "Batch 300 device: cuda time passed: 106.597 time per batch: 0.355\n", |
||
| 704 | "Batch 350 device: cuda time passed: 123.356 time per batch: 0.352\n" |
||
| 705 | ] |
||
| 706 | }, |
||
| 707 | { |
||
| 708 | "name": "stdout", |
||
| 709 | "output_type": "stream", |
||
| 710 | "text": [ |
||
| 711 | "Batch 400 device: cuda time passed: 140.828 time per batch: 0.352\n", |
||
| 712 | "Batch 450 device: cuda time passed: 161.360 time per batch: 0.359\n", |
||
| 713 | "Batch 500 device: cuda time passed: 178.210 time per batch: 0.356\n", |
||
| 714 | "Batch 50 device: cuda time passed: 8.594 time per batch: 0.172\n", |
||
| 715 | "Batch 100 device: cuda time passed: 15.062 time per batch: 0.151\n", |
||
| 716 | "v35, d14, e4, f3, trn ll: 0.0338, val ll: 0.0646, ll_w: 0.0566, cor: 0.8354, auc: 0.9876, lr: 0.0002\n", |
||
| 717 | "total running time 878.9186632633209\n", |
||
| 718 | "completed epochs: 4 starting now: 4\n", |
||
| 719 | "DataSet 14 train size 17408 fold 3\n", |
||
| 720 | "adding dummy serieses 16\n", |
||
| 721 | "DataSet 14 valid size 4352 fold 3\n", |
||
| 722 | "setFeats, augmentation 0\n", |
||
| 723 | "dataset train: 17408 valid: 4352 loader train: 544 valid: 136\n", |
||
| 724 | "loading model model.b4.f3.d14.v35\n", |
||
| 725 | "setFeats, augmentation -1\n", |
||
| 726 | "Batch 50 device: cuda time passed: 22.351 time per batch: 0.447\n", |
||
| 727 | "Batch 100 device: cuda time passed: 39.285 time per batch: 0.393\n", |
||
| 728 | "Batch 150 device: cuda time passed: 56.332 time per batch: 0.376\n", |
||
| 729 | "Batch 200 device: cuda time passed: 73.401 time per batch: 0.367\n", |
||
| 730 | "Batch 250 device: cuda time passed: 90.373 time per batch: 0.361\n", |
||
| 731 | "Batch 300 device: cuda time passed: 107.953 time per batch: 0.360\n", |
||
| 732 | "Batch 350 device: cuda time passed: 125.840 time per batch: 0.360\n", |
||
| 733 | "Batch 400 device: cuda time passed: 141.813 time per batch: 0.355\n", |
||
| 734 | "Batch 450 device: cuda time passed: 163.658 time per batch: 0.364\n", |
||
| 735 | "Batch 500 device: cuda time passed: 180.005 time per batch: 0.360\n", |
||
| 736 | "Batch 50 device: cuda time passed: 9.095 time per batch: 0.182\n", |
||
| 737 | "Batch 100 device: cuda time passed: 15.365 time per batch: 0.154\n", |
||
| 738 | "v35, d14, e5, f3, trn ll: 0.0323, val ll: 0.0630, ll_w: 0.0553, cor: 0.8398, auc: 0.9887, lr: 2e-05\n", |
||
| 739 | "setFeats, augmentation -1\n", |
||
| 740 | "Batch 50 device: cuda time passed: 22.265 time per batch: 0.445\n", |
||
| 741 | "Batch 100 device: cuda time passed: 38.806 time per batch: 0.388\n", |
||
| 742 | "Batch 150 device: cuda time passed: 55.889 time per batch: 0.373\n", |
||
| 743 | "Batch 200 device: cuda time passed: 72.973 time per batch: 0.365\n", |
||
| 744 | "Batch 250 device: cuda time passed: 89.595 time per batch: 0.358\n", |
||
| 745 | "Batch 300 device: cuda time passed: 106.073 time per batch: 0.354\n", |
||
| 746 | "Batch 350 device: cuda time passed: 123.445 time per batch: 0.353\n", |
||
| 747 | "Batch 400 device: cuda time passed: 139.717 time per batch: 0.349\n", |
||
| 748 | "Batch 450 device: cuda time passed: 159.922 time per batch: 0.355\n", |
||
| 749 | "Batch 500 device: cuda time passed: 177.361 time per batch: 0.355\n", |
||
| 750 | "Batch 50 device: cuda time passed: 8.455 time per batch: 0.169\n", |
||
| 751 | "Batch 100 device: cuda time passed: 15.167 time per batch: 0.152\n", |
||
| 752 | "v35, d14, e6, f3, trn ll: 0.0319, val ll: 0.0627, ll_w: 0.0550, cor: 0.8406, auc: 0.9888, lr: 2e-05\n", |
||
| 753 | "setFeats, augmentation -1\n", |
||
| 754 | "Batch 50 device: cuda time passed: 21.948 time per batch: 0.439\n", |
||
| 755 | "Batch 100 device: cuda time passed: 38.589 time per batch: 0.386\n", |
||
| 756 | "Batch 150 device: cuda time passed: 56.699 time per batch: 0.378\n", |
||
| 757 | "Batch 200 device: cuda time passed: 74.066 time per batch: 0.370\n", |
||
| 758 | "Batch 250 device: cuda time passed: 90.412 time per batch: 0.362\n", |
||
| 759 | "Batch 300 device: cuda time passed: 108.005 time per batch: 0.360\n", |
||
| 760 | "Batch 350 device: cuda time passed: 124.540 time per batch: 0.356\n", |
||
| 761 | "Batch 400 device: cuda time passed: 141.433 time per batch: 0.354\n", |
||
| 762 | "Batch 450 device: cuda time passed: 158.940 time per batch: 0.353\n", |
||
| 763 | "Batch 500 device: cuda time passed: 176.269 time per batch: 0.353\n", |
||
| 764 | "Batch 50 device: cuda time passed: 7.920 time per batch: 0.158\n", |
||
| 765 | "Batch 100 device: cuda time passed: 14.641 time per batch: 0.146\n", |
||
| 766 | "v35, d14, e7, f3, trn ll: 0.0317, val ll: 0.0628, ll_w: 0.0550, cor: 0.8408, auc: 0.9888, lr: 2e-05\n", |
||
| 767 | "setFeats, augmentation -1\n", |
||
| 768 | "Batch 50 device: cuda time passed: 21.956 time per batch: 0.439\n", |
||
| 769 | "Batch 100 device: cuda time passed: 38.717 time per batch: 0.387\n", |
||
| 770 | "Batch 150 device: cuda time passed: 54.847 time per batch: 0.366\n", |
||
| 771 | "Batch 200 device: cuda time passed: 73.123 time per batch: 0.366\n", |
||
| 772 | "Batch 250 device: cuda time passed: 89.668 time per batch: 0.359\n", |
||
| 773 | "Batch 300 device: cuda time passed: 105.873 time per batch: 0.353\n", |
||
| 774 | "Batch 350 device: cuda time passed: 122.045 time per batch: 0.349\n", |
||
| 775 | "Batch 400 device: cuda time passed: 138.273 time per batch: 0.346\n", |
||
| 776 | "Batch 450 device: cuda time passed: 157.145 time per batch: 0.349\n", |
||
| 777 | "Batch 500 device: cuda time passed: 173.020 time per batch: 0.346\n", |
||
| 778 | "Batch 50 device: cuda time passed: 8.091 time per batch: 0.162\n", |
||
| 779 | "Batch 100 device: cuda time passed: 14.363 time per batch: 0.144\n", |
||
| 780 | "v35, d14, e8, f3, trn ll: 0.0317, val ll: 0.0624, ll_w: 0.0548, cor: 0.8413, auc: 0.9889, lr: 2e-05\n", |
||
| 781 | "total running time 867.7460985183716\n", |
||
| 782 | "completed epochs: 8 starting now: 3\n", |
||
| 783 | "DataSet 14 train size 17408 fold 3\n", |
||
| 784 | "adding dummy serieses 16\n", |
||
| 785 | "DataSet 14 valid size 4352 fold 3\n", |
||
| 786 | "setFeats, augmentation 0\n", |
||
| 787 | "dataset train: 17408 valid: 4352 loader train: 544 valid: 136\n", |
||
| 788 | "loading model model.b8.f3.d14.v35\n", |
||
| 789 | "setFeats, augmentation -1\n", |
||
| 790 | "Batch 50 device: cuda time passed: 20.904 time per batch: 0.418\n", |
||
| 791 | "Batch 100 device: cuda time passed: 37.911 time per batch: 0.379\n", |
||
| 792 | "Batch 150 device: cuda time passed: 54.975 time per batch: 0.367\n", |
||
| 793 | "Batch 200 device: cuda time passed: 71.442 time per batch: 0.357\n", |
||
| 794 | "Batch 250 device: cuda time passed: 87.521 time per batch: 0.350\n", |
||
| 795 | "Batch 300 device: cuda time passed: 104.238 time per batch: 0.347\n", |
||
| 796 | "Batch 350 device: cuda time passed: 121.406 time per batch: 0.347\n", |
||
| 797 | "Batch 400 device: cuda time passed: 137.836 time per batch: 0.345\n", |
||
| 798 | "Batch 450 device: cuda time passed: 157.379 time per batch: 0.350\n", |
||
| 799 | "Batch 500 device: cuda time passed: 173.441 time per batch: 0.347\n", |
||
| 800 | "Batch 50 device: cuda time passed: 8.016 time per batch: 0.160\n", |
||
| 801 | "Batch 100 device: cuda time passed: 14.483 time per batch: 0.145\n", |
||
| 802 | "v35, d14, e9, f3, trn ll: 0.0313, val ll: 0.0623, ll_w: 0.0547, cor: 0.8414, auc: 0.9889, lr: 5e-06\n", |
||
| 803 | "setFeats, augmentation -1\n", |
||
| 804 | "Batch 50 device: cuda time passed: 22.463 time per batch: 0.449\n", |
||
| 805 | "Batch 100 device: cuda time passed: 39.561 time per batch: 0.396\n", |
||
| 806 | "Batch 150 device: cuda time passed: 56.056 time per batch: 0.374\n", |
||
| 807 | "Batch 200 device: cuda time passed: 72.486 time per batch: 0.362\n", |
||
| 808 | "Batch 250 device: cuda time passed: 88.576 time per batch: 0.354\n", |
||
| 809 | "Batch 300 device: cuda time passed: 105.400 time per batch: 0.351\n", |
||
| 810 | "Batch 350 device: cuda time passed: 122.470 time per batch: 0.350\n", |
||
| 811 | "Batch 400 device: cuda time passed: 138.730 time per batch: 0.347\n", |
||
| 812 | "Batch 450 device: cuda time passed: 158.273 time per batch: 0.352\n", |
||
| 813 | "Batch 500 device: cuda time passed: 174.807 time per batch: 0.350\n", |
||
| 814 | "Batch 50 device: cuda time passed: 8.288 time per batch: 0.166\n", |
||
| 815 | "Batch 100 device: cuda time passed: 14.541 time per batch: 0.145\n", |
||
| 816 | "v35, d14, e10, f3, trn ll: 0.0314, val ll: 0.0623, ll_w: 0.0547, cor: 0.8414, auc: 0.9889, lr: 5e-06\n", |
||
| 817 | "setFeats, augmentation -1\n", |
||
| 818 | "Batch 50 device: cuda time passed: 23.117 time per batch: 0.462\n", |
||
| 819 | "Batch 100 device: cuda time passed: 40.982 time per batch: 0.410\n", |
||
| 820 | "Batch 150 device: cuda time passed: 61.655 time per batch: 0.411\n", |
||
| 821 | "Batch 200 device: cuda time passed: 78.830 time per batch: 0.394\n", |
||
| 822 | "Batch 250 device: cuda time passed: 94.886 time per batch: 0.380\n", |
||
| 823 | "Batch 300 device: cuda time passed: 111.050 time per batch: 0.370\n", |
||
| 824 | "Batch 350 device: cuda time passed: 127.401 time per batch: 0.364\n", |
||
| 825 | "Batch 400 device: cuda time passed: 144.495 time per batch: 0.361\n", |
||
| 826 | "Batch 450 device: cuda time passed: 163.904 time per batch: 0.364\n", |
||
| 827 | "Batch 500 device: cuda time passed: 180.762 time per batch: 0.362\n", |
||
| 828 | "Batch 50 device: cuda time passed: 9.296 time per batch: 0.186\n", |
||
| 829 | "Batch 100 device: cuda time passed: 15.943 time per batch: 0.159\n", |
||
| 830 | "v35, d14, e11, f3, trn ll: 0.0314, val ll: 0.0623, ll_w: 0.0548, cor: 0.8414, auc: 0.9890, lr: 5e-06\n", |
||
| 831 | "total running time 650.1911387443542\n", |
||
| 832 | "completed epochs: 11 starting now: 2\n", |
||
| 833 | "DataSet 14 train size 17408 fold 3\n", |
||
| 834 | "adding dummy serieses 16\n", |
||
| 835 | "DataSet 14 valid size 4352 fold 3\n", |
||
| 836 | "setFeats, augmentation 0\n", |
||
| 837 | "dataset train: 17408 valid: 4352 loader train: 544 valid: 136\n", |
||
| 838 | "loading model model.b11.f3.d14.v35\n", |
||
| 839 | "setFeats, augmentation -1\n", |
||
| 840 | "Batch 50 device: cuda time passed: 22.074 time per batch: 0.441\n", |
||
| 841 | "Batch 100 device: cuda time passed: 38.499 time per batch: 0.385\n", |
||
| 842 | "Batch 150 device: cuda time passed: 55.562 time per batch: 0.370\n", |
||
| 843 | "Batch 200 device: cuda time passed: 71.852 time per batch: 0.359\n", |
||
| 844 | "Batch 250 device: cuda time passed: 88.012 time per batch: 0.352\n", |
||
| 845 | "Batch 300 device: cuda time passed: 105.386 time per batch: 0.351\n", |
||
| 846 | "Batch 350 device: cuda time passed: 123.305 time per batch: 0.352\n", |
||
| 847 | "Batch 400 device: cuda time passed: 140.065 time per batch: 0.350\n" |
||
| 848 | ] |
||
| 849 | }, |
||
| 850 | { |
||
| 851 | "name": "stdout", |
||
| 852 | "output_type": "stream", |
||
| 853 | "text": [ |
||
| 854 | "Batch 450 device: cuda time passed: 162.016 time per batch: 0.360\n", |
||
| 855 | "Batch 500 device: cuda time passed: 179.990 time per batch: 0.360\n", |
||
| 856 | "Batch 50 device: cuda time passed: 8.722 time per batch: 0.174\n", |
||
| 857 | "Batch 100 device: cuda time passed: 15.752 time per batch: 0.158\n", |
||
| 858 | "v35, d14, e12, f3, trn ll: 0.0313, val ll: 0.0622, ll_w: 0.0546, cor: 0.8417, auc: 0.9890, lr: 2e-06\n", |
||
| 859 | "setFeats, augmentation -1\n", |
||
| 860 | "Batch 50 device: cuda time passed: 24.253 time per batch: 0.485\n", |
||
| 861 | "Batch 100 device: cuda time passed: 41.866 time per batch: 0.419\n", |
||
| 862 | "Batch 150 device: cuda time passed: 60.387 time per batch: 0.403\n", |
||
| 863 | "Batch 200 device: cuda time passed: 77.524 time per batch: 0.388\n", |
||
| 864 | "Batch 250 device: cuda time passed: 95.133 time per batch: 0.381\n", |
||
| 865 | "Batch 300 device: cuda time passed: 113.060 time per batch: 0.377\n", |
||
| 866 | "Batch 350 device: cuda time passed: 130.037 time per batch: 0.372\n", |
||
| 867 | "Batch 400 device: cuda time passed: 146.372 time per batch: 0.366\n", |
||
| 868 | "Batch 450 device: cuda time passed: 166.916 time per batch: 0.371\n", |
||
| 869 | "Batch 500 device: cuda time passed: 182.928 time per batch: 0.366\n", |
||
| 870 | "Batch 50 device: cuda time passed: 7.564 time per batch: 0.151\n", |
||
| 871 | "Batch 100 device: cuda time passed: 14.464 time per batch: 0.145\n", |
||
| 872 | "v35, d14, e13, f3, trn ll: 0.0313, val ll: 0.0621, ll_w: 0.0546, cor: 0.8417, auc: 0.9890, lr: 2e-06\n", |
||
| 873 | "total running time 444.2737958431244\n", |
||
| 874 | "total time 5680.686395645142\n", |
||
| 875 | "completed epochs: 0 starting now: 4\n", |
||
| 876 | "DataSet 14 train size 17376 fold 4\n", |
||
| 877 | "adding dummy serieses 16\n", |
||
| 878 | "DataSet 14 valid size 4384 fold 4\n", |
||
| 879 | "setFeats, augmentation 0\n", |
||
| 880 | "dataset train: 17376 valid: 4384 loader train: 543 valid: 137\n", |
||
| 881 | "starting from scratch\n", |
||
| 882 | "setFeats, augmentation -1\n", |
||
| 883 | "Batch 50 device: cuda time passed: 21.233 time per batch: 0.425\n", |
||
| 884 | "Batch 100 device: cuda time passed: 37.840 time per batch: 0.378\n", |
||
| 885 | "Batch 150 device: cuda time passed: 54.944 time per batch: 0.366\n", |
||
| 886 | "Batch 200 device: cuda time passed: 72.824 time per batch: 0.364\n", |
||
| 887 | "Batch 250 device: cuda time passed: 89.779 time per batch: 0.359\n", |
||
| 888 | "Batch 300 device: cuda time passed: 106.930 time per batch: 0.356\n", |
||
| 889 | "Batch 350 device: cuda time passed: 123.451 time per batch: 0.353\n", |
||
| 890 | "Batch 400 device: cuda time passed: 139.893 time per batch: 0.350\n", |
||
| 891 | "Batch 450 device: cuda time passed: 157.031 time per batch: 0.349\n", |
||
| 892 | "Batch 500 device: cuda time passed: 173.987 time per batch: 0.348\n", |
||
| 893 | "Batch 50 device: cuda time passed: 8.944 time per batch: 0.179\n", |
||
| 894 | "Batch 100 device: cuda time passed: 14.936 time per batch: 0.149\n", |
||
| 895 | "v35, d14, e1, f4, trn ll: 0.0625, val ll: 0.0667, ll_w: 0.0586, cor: 0.8303, auc: 0.9854, lr: 0.0002\n", |
||
| 896 | "setFeats, augmentation -1\n", |
||
| 897 | "Batch 50 device: cuda time passed: 21.754 time per batch: 0.435\n", |
||
| 898 | "Batch 100 device: cuda time passed: 38.725 time per batch: 0.387\n", |
||
| 899 | "Batch 150 device: cuda time passed: 55.236 time per batch: 0.368\n", |
||
| 900 | "Batch 200 device: cuda time passed: 72.718 time per batch: 0.364\n", |
||
| 901 | "Batch 250 device: cuda time passed: 88.735 time per batch: 0.355\n", |
||
| 902 | "Batch 300 device: cuda time passed: 105.104 time per batch: 0.350\n", |
||
| 903 | "Batch 350 device: cuda time passed: 122.012 time per batch: 0.349\n", |
||
| 904 | "Batch 400 device: cuda time passed: 137.964 time per batch: 0.345\n", |
||
| 905 | "Batch 450 device: cuda time passed: 156.284 time per batch: 0.347\n", |
||
| 906 | "Batch 500 device: cuda time passed: 173.980 time per batch: 0.348\n", |
||
| 907 | "Batch 50 device: cuda time passed: 8.316 time per batch: 0.166\n", |
||
| 908 | "Batch 100 device: cuda time passed: 14.987 time per batch: 0.150\n", |
||
| 909 | "v35, d14, e2, f4, trn ll: 0.0359, val ll: 0.0657, ll_w: 0.0577, cor: 0.8311, auc: 0.9863, lr: 0.0002\n", |
||
| 910 | "setFeats, augmentation -1\n", |
||
| 911 | "Batch 50 device: cuda time passed: 22.364 time per batch: 0.447\n", |
||
| 912 | "Batch 100 device: cuda time passed: 40.987 time per batch: 0.410\n", |
||
| 913 | "Batch 150 device: cuda time passed: 58.507 time per batch: 0.390\n", |
||
| 914 | "Batch 200 device: cuda time passed: 77.763 time per batch: 0.389\n", |
||
| 915 | "Batch 250 device: cuda time passed: 95.192 time per batch: 0.381\n", |
||
| 916 | "Batch 300 device: cuda time passed: 111.754 time per batch: 0.373\n", |
||
| 917 | "Batch 350 device: cuda time passed: 129.000 time per batch: 0.369\n", |
||
| 918 | "Batch 400 device: cuda time passed: 146.293 time per batch: 0.366\n", |
||
| 919 | "Batch 450 device: cuda time passed: 165.444 time per batch: 0.368\n", |
||
| 920 | "Batch 500 device: cuda time passed: 183.020 time per batch: 0.366\n", |
||
| 921 | "Batch 50 device: cuda time passed: 7.861 time per batch: 0.157\n", |
||
| 922 | "Batch 100 device: cuda time passed: 15.124 time per batch: 0.151\n", |
||
| 923 | "v35, d14, e3, f4, trn ll: 0.0343, val ll: 0.0632, ll_w: 0.0554, cor: 0.8399, auc: 0.9873, lr: 0.0002\n", |
||
| 924 | "setFeats, augmentation -1\n", |
||
| 925 | "Batch 50 device: cuda time passed: 21.633 time per batch: 0.433\n", |
||
| 926 | "Batch 100 device: cuda time passed: 37.934 time per batch: 0.379\n", |
||
| 927 | "Batch 150 device: cuda time passed: 55.032 time per batch: 0.367\n", |
||
| 928 | "Batch 200 device: cuda time passed: 72.134 time per batch: 0.361\n", |
||
| 929 | "Batch 250 device: cuda time passed: 89.244 time per batch: 0.357\n", |
||
| 930 | "Batch 300 device: cuda time passed: 107.215 time per batch: 0.357\n", |
||
| 931 | "Batch 350 device: cuda time passed: 125.071 time per batch: 0.357\n", |
||
| 932 | "Batch 400 device: cuda time passed: 142.857 time per batch: 0.357\n", |
||
| 933 | "Batch 450 device: cuda time passed: 164.440 time per batch: 0.365\n", |
||
| 934 | "Batch 500 device: cuda time passed: 181.712 time per batch: 0.363\n", |
||
| 935 | "Batch 50 device: cuda time passed: 8.480 time per batch: 0.170\n", |
||
| 936 | "Batch 100 device: cuda time passed: 15.129 time per batch: 0.151\n", |
||
| 937 | "v35, d14, e4, f4, trn ll: 0.0335, val ll: 0.0664, ll_w: 0.0588, cor: 0.8346, auc: 0.9881, lr: 0.0002\n", |
||
| 938 | "total running time 953.7901792526245\n", |
||
| 939 | "completed epochs: 4 starting now: 4\n", |
||
| 940 | "DataSet 14 train size 17376 fold 4\n", |
||
| 941 | "adding dummy serieses 16\n", |
||
| 942 | "DataSet 14 valid size 4384 fold 4\n", |
||
| 943 | "setFeats, augmentation 0\n", |
||
| 944 | "dataset train: 17376 valid: 4384 loader train: 543 valid: 137\n", |
||
| 945 | "loading model model.b4.f4.d14.v35\n", |
||
| 946 | "setFeats, augmentation -1\n", |
||
| 947 | "Batch 50 device: cuda time passed: 23.867 time per batch: 0.477\n", |
||
| 948 | "Batch 100 device: cuda time passed: 41.869 time per batch: 0.419\n", |
||
| 949 | "Batch 150 device: cuda time passed: 59.945 time per batch: 0.400\n", |
||
| 950 | "Batch 200 device: cuda time passed: 78.035 time per batch: 0.390\n", |
||
| 951 | "Batch 250 device: cuda time passed: 95.686 time per batch: 0.383\n", |
||
| 952 | "Batch 300 device: cuda time passed: 113.281 time per batch: 0.378\n", |
||
| 953 | "Batch 350 device: cuda time passed: 130.764 time per batch: 0.374\n", |
||
| 954 | "Batch 400 device: cuda time passed: 148.630 time per batch: 0.372\n", |
||
| 955 | "Batch 450 device: cuda time passed: 170.233 time per batch: 0.378\n", |
||
| 956 | "Batch 500 device: cuda time passed: 188.222 time per batch: 0.376\n", |
||
| 957 | "Batch 50 device: cuda time passed: 8.176 time per batch: 0.164\n", |
||
| 958 | "Batch 100 device: cuda time passed: 14.735 time per batch: 0.147\n", |
||
| 959 | "v35, d14, e5, f4, trn ll: 0.0317, val ll: 0.0608, ll_w: 0.0533, cor: 0.8448, auc: 0.9887, lr: 2e-05\n", |
||
| 960 | "setFeats, augmentation -1\n", |
||
| 961 | "Batch 50 device: cuda time passed: 21.737 time per batch: 0.435\n", |
||
| 962 | "Batch 100 device: cuda time passed: 37.853 time per batch: 0.379\n", |
||
| 963 | "Batch 150 device: cuda time passed: 55.337 time per batch: 0.369\n", |
||
| 964 | "Batch 200 device: cuda time passed: 71.157 time per batch: 0.356\n", |
||
| 965 | "Batch 250 device: cuda time passed: 87.010 time per batch: 0.348\n", |
||
| 966 | "Batch 300 device: cuda time passed: 103.209 time per batch: 0.344\n", |
||
| 967 | "Batch 350 device: cuda time passed: 119.077 time per batch: 0.340\n", |
||
| 968 | "Batch 400 device: cuda time passed: 135.723 time per batch: 0.339\n", |
||
| 969 | "Batch 450 device: cuda time passed: 154.558 time per batch: 0.343\n", |
||
| 970 | "Batch 500 device: cuda time passed: 170.455 time per batch: 0.341\n", |
||
| 971 | "Batch 50 device: cuda time passed: 7.589 time per batch: 0.152\n", |
||
| 972 | "Batch 100 device: cuda time passed: 14.520 time per batch: 0.145\n", |
||
| 973 | "v35, d14, e6, f4, trn ll: 0.0314, val ll: 0.0611, ll_w: 0.0535, cor: 0.8444, auc: 0.9886, lr: 2e-05\n", |
||
| 974 | "setFeats, augmentation -1\n", |
||
| 975 | "Batch 50 device: cuda time passed: 20.682 time per batch: 0.414\n", |
||
| 976 | "Batch 100 device: cuda time passed: 36.792 time per batch: 0.368\n", |
||
| 977 | "Batch 150 device: cuda time passed: 52.970 time per batch: 0.353\n", |
||
| 978 | "Batch 200 device: cuda time passed: 69.095 time per batch: 0.345\n", |
||
| 979 | "Batch 250 device: cuda time passed: 85.616 time per batch: 0.342\n", |
||
| 980 | "Batch 300 device: cuda time passed: 101.163 time per batch: 0.337\n", |
||
| 981 | "Batch 350 device: cuda time passed: 117.018 time per batch: 0.334\n", |
||
| 982 | "Batch 400 device: cuda time passed: 133.178 time per batch: 0.333\n", |
||
| 983 | "Batch 450 device: cuda time passed: 151.207 time per batch: 0.336\n", |
||
| 984 | "Batch 500 device: cuda time passed: 168.530 time per batch: 0.337\n", |
||
| 985 | "Batch 50 device: cuda time passed: 7.677 time per batch: 0.154\n", |
||
| 986 | "Batch 100 device: cuda time passed: 14.814 time per batch: 0.148\n", |
||
| 987 | "v35, d14, e7, f4, trn ll: 0.0312, val ll: 0.0609, ll_w: 0.0534, cor: 0.8449, auc: 0.9886, lr: 2e-05\n", |
||
| 988 | "setFeats, augmentation -1\n" |
||
| 989 | ] |
||
| 990 | }, |
||
| 991 | { |
||
| 992 | "name": "stdout", |
||
| 993 | "output_type": "stream", |
||
| 994 | "text": [ |
||
| 995 | "Batch 50 device: cuda time passed: 21.214 time per batch: 0.424\n", |
||
| 996 | "Batch 100 device: cuda time passed: 37.518 time per batch: 0.375\n", |
||
| 997 | "Batch 150 device: cuda time passed: 54.071 time per batch: 0.360\n", |
||
| 998 | "Batch 200 device: cuda time passed: 69.747 time per batch: 0.349\n", |
||
| 999 | "Batch 250 device: cuda time passed: 85.969 time per batch: 0.344\n", |
||
| 1000 | "Batch 300 device: cuda time passed: 102.031 time per batch: 0.340\n", |
||
| 1001 | "Batch 350 device: cuda time passed: 119.208 time per batch: 0.341\n", |
||
| 1002 | "Batch 400 device: cuda time passed: 134.735 time per batch: 0.337\n", |
||
| 1003 | "Batch 450 device: cuda time passed: 154.078 time per batch: 0.342\n", |
||
| 1004 | "Batch 500 device: cuda time passed: 170.411 time per batch: 0.341\n", |
||
| 1005 | "Batch 50 device: cuda time passed: 8.323 time per batch: 0.166\n", |
||
| 1006 | "Batch 100 device: cuda time passed: 14.637 time per batch: 0.146\n", |
||
| 1007 | "v35, d14, e8, f4, trn ll: 0.0311, val ll: 0.0610, ll_w: 0.0534, cor: 0.8453, auc: 0.9885, lr: 2e-05\n", |
||
| 1008 | "total running time 855.8814930915833\n", |
||
| 1009 | "completed epochs: 8 starting now: 3\n", |
||
| 1010 | "DataSet 14 train size 17376 fold 4\n", |
||
| 1011 | "adding dummy serieses 16\n", |
||
| 1012 | "DataSet 14 valid size 4384 fold 4\n", |
||
| 1013 | "setFeats, augmentation 0\n", |
||
| 1014 | "dataset train: 17376 valid: 4384 loader train: 543 valid: 137\n", |
||
| 1015 | "loading model model.b8.f4.d14.v35\n", |
||
| 1016 | "setFeats, augmentation -1\n", |
||
| 1017 | "Batch 50 device: cuda time passed: 21.184 time per batch: 0.424\n", |
||
| 1018 | "Batch 100 device: cuda time passed: 37.215 time per batch: 0.372\n", |
||
| 1019 | "Batch 150 device: cuda time passed: 53.050 time per batch: 0.354\n", |
||
| 1020 | "Batch 200 device: cuda time passed: 69.171 time per batch: 0.346\n", |
||
| 1021 | "Batch 250 device: cuda time passed: 85.650 time per batch: 0.343\n", |
||
| 1022 | "Batch 300 device: cuda time passed: 101.736 time per batch: 0.339\n", |
||
| 1023 | "Batch 350 device: cuda time passed: 117.355 time per batch: 0.335\n", |
||
| 1024 | "Batch 400 device: cuda time passed: 133.001 time per batch: 0.333\n", |
||
| 1025 | "Batch 450 device: cuda time passed: 152.997 time per batch: 0.340\n", |
||
| 1026 | "Batch 500 device: cuda time passed: 169.252 time per batch: 0.339\n", |
||
| 1027 | "Batch 50 device: cuda time passed: 7.640 time per batch: 0.153\n", |
||
| 1028 | "Batch 100 device: cuda time passed: 14.457 time per batch: 0.145\n", |
||
| 1029 | "v35, d14, e9, f4, trn ll: 0.0310, val ll: 0.0609, ll_w: 0.0532, cor: 0.8452, auc: 0.9886, lr: 5e-06\n", |
||
| 1030 | "setFeats, augmentation -1\n", |
||
| 1031 | "Batch 50 device: cuda time passed: 20.694 time per batch: 0.414\n", |
||
| 1032 | "Batch 100 device: cuda time passed: 37.491 time per batch: 0.375\n", |
||
| 1033 | "Batch 150 device: cuda time passed: 53.734 time per batch: 0.358\n", |
||
| 1034 | "Batch 200 device: cuda time passed: 69.955 time per batch: 0.350\n", |
||
| 1035 | "Batch 250 device: cuda time passed: 85.941 time per batch: 0.344\n", |
||
| 1036 | "Batch 300 device: cuda time passed: 101.942 time per batch: 0.340\n", |
||
| 1037 | "Batch 350 device: cuda time passed: 117.779 time per batch: 0.337\n", |
||
| 1038 | "Batch 400 device: cuda time passed: 133.697 time per batch: 0.334\n", |
||
| 1039 | "Batch 450 device: cuda time passed: 151.893 time per batch: 0.338\n", |
||
| 1040 | "Batch 500 device: cuda time passed: 169.235 time per batch: 0.338\n", |
||
| 1041 | "Batch 50 device: cuda time passed: 8.345 time per batch: 0.167\n", |
||
| 1042 | "Batch 100 device: cuda time passed: 14.826 time per batch: 0.148\n", |
||
| 1043 | "v35, d14, e10, f4, trn ll: 0.0308, val ll: 0.0608, ll_w: 0.0532, cor: 0.8453, auc: 0.9887, lr: 5e-06\n", |
||
| 1044 | "setFeats, augmentation -1\n", |
||
| 1045 | "Batch 50 device: cuda time passed: 21.099 time per batch: 0.422\n", |
||
| 1046 | "Batch 100 device: cuda time passed: 36.777 time per batch: 0.368\n", |
||
| 1047 | "Batch 150 device: cuda time passed: 53.978 time per batch: 0.360\n", |
||
| 1048 | "Batch 200 device: cuda time passed: 69.323 time per batch: 0.347\n", |
||
| 1049 | "Batch 250 device: cuda time passed: 85.573 time per batch: 0.342\n", |
||
| 1050 | "Batch 300 device: cuda time passed: 102.080 time per batch: 0.340\n", |
||
| 1051 | "Batch 350 device: cuda time passed: 118.682 time per batch: 0.339\n", |
||
| 1052 | "Batch 400 device: cuda time passed: 135.171 time per batch: 0.338\n", |
||
| 1053 | "Batch 450 device: cuda time passed: 152.631 time per batch: 0.339\n", |
||
| 1054 | "Batch 500 device: cuda time passed: 167.938 time per batch: 0.336\n", |
||
| 1055 | "Batch 50 device: cuda time passed: 8.310 time per batch: 0.166\n", |
||
| 1056 | "Batch 100 device: cuda time passed: 14.317 time per batch: 0.143\n", |
||
| 1057 | "v35, d14, e11, f4, trn ll: 0.0308, val ll: 0.0607, ll_w: 0.0532, cor: 0.8454, auc: 0.9887, lr: 5e-06\n", |
||
| 1058 | "total running time 623.4176635742188\n", |
||
| 1059 | "completed epochs: 11 starting now: 2\n", |
||
| 1060 | "DataSet 14 train size 17376 fold 4\n", |
||
| 1061 | "adding dummy serieses 16\n", |
||
| 1062 | "DataSet 14 valid size 4384 fold 4\n", |
||
| 1063 | "setFeats, augmentation 0\n", |
||
| 1064 | "dataset train: 17376 valid: 4384 loader train: 543 valid: 137\n", |
||
| 1065 | "loading model model.b11.f4.d14.v35\n", |
||
| 1066 | "setFeats, augmentation -1\n", |
||
| 1067 | "Batch 50 device: cuda time passed: 21.779 time per batch: 0.436\n", |
||
| 1068 | "Batch 100 device: cuda time passed: 38.087 time per batch: 0.381\n", |
||
| 1069 | "Batch 150 device: cuda time passed: 53.619 time per batch: 0.357\n", |
||
| 1070 | "Batch 200 device: cuda time passed: 69.523 time per batch: 0.348\n", |
||
| 1071 | "Batch 250 device: cuda time passed: 85.874 time per batch: 0.343\n", |
||
| 1072 | "Batch 300 device: cuda time passed: 101.439 time per batch: 0.338\n", |
||
| 1073 | "Batch 350 device: cuda time passed: 117.336 time per batch: 0.335\n", |
||
| 1074 | "Batch 400 device: cuda time passed: 133.035 time per batch: 0.333\n", |
||
| 1075 | "Batch 450 device: cuda time passed: 152.595 time per batch: 0.339\n", |
||
| 1076 | "Batch 500 device: cuda time passed: 169.052 time per batch: 0.338\n", |
||
| 1077 | "Batch 50 device: cuda time passed: 8.452 time per batch: 0.169\n", |
||
| 1078 | "Batch 100 device: cuda time passed: 14.411 time per batch: 0.144\n", |
||
| 1079 | "v35, d14, e12, f4, trn ll: 0.0307, val ll: 0.0609, ll_w: 0.0532, cor: 0.8456, auc: 0.9886, lr: 2e-06\n", |
||
| 1080 | "setFeats, augmentation -1\n", |
||
| 1081 | "Batch 50 device: cuda time passed: 20.947 time per batch: 0.419\n", |
||
| 1082 | "Batch 100 device: cuda time passed: 37.425 time per batch: 0.374\n", |
||
| 1083 | "Batch 150 device: cuda time passed: 52.922 time per batch: 0.353\n", |
||
| 1084 | "Batch 200 device: cuda time passed: 69.971 time per batch: 0.350\n", |
||
| 1085 | "Batch 250 device: cuda time passed: 85.655 time per batch: 0.343\n", |
||
| 1086 | "Batch 300 device: cuda time passed: 101.705 time per batch: 0.339\n", |
||
| 1087 | "Batch 350 device: cuda time passed: 117.494 time per batch: 0.336\n", |
||
| 1088 | "Batch 400 device: cuda time passed: 134.239 time per batch: 0.336\n", |
||
| 1089 | "Batch 450 device: cuda time passed: 154.606 time per batch: 0.344\n", |
||
| 1090 | "Batch 500 device: cuda time passed: 171.257 time per batch: 0.343\n", |
||
| 1091 | "Batch 50 device: cuda time passed: 8.181 time per batch: 0.164\n", |
||
| 1092 | "Batch 100 device: cuda time passed: 14.339 time per batch: 0.143\n", |
||
| 1093 | "v35, d14, e13, f4, trn ll: 0.0308, val ll: 0.0607, ll_w: 0.0532, cor: 0.8454, auc: 0.9887, lr: 2e-06\n", |
||
| 1094 | "total running time 417.99802231788635\n", |
||
| 1095 | "total time 8532.541821241379\n", |
||
| 1096 | "total time 8532.541992664337\n", |
||
| 1097 | "total time 8532.54287481308\n" |
||
| 1098 | ] |
||
| 1099 | } |
||
| 1100 | ], |
||
| 1101 | "source": [ |
||
| 1102 | "weight_decay = 1e-4\n", |
||
| 1103 | "lrs = np.array([2e-4, 2e-5, 5e-6, 2e-6])\n", |
||
| 1104 | "epochs = np.array([4, 4, 3, 2])\n", |
||
| 1105 | "stg = time.time()\n", |
||
| 1106 | "for ds in [14]:\n", |
||
| 1107 | " #folds = getNFolds(ds)\n", |
||
| 1108 | " for f in [2,3,4]:#range(folds):\n", |
||
| 1109 | " for i,lr in enumerate(lrs):\n", |
||
| 1110 | " learning_rate = lr\n", |
||
| 1111 | " model, predictions, val_results = train_one(dataset=ds, epochs=epochs[i], bs=32, fold=f)\n", |
||
| 1112 | " print('total time', time.time() - stg)\n", |
||
| 1113 | " print('total time', time.time() - stg)\n", |
||
| 1114 | "print('total time', time.time() - stg)" |
||
| 1115 | ] |
||
| 1116 | }, |
||
| 1117 | { |
||
| 1118 | "cell_type": "code", |
||
| 1119 | "execution_count": null, |
||
| 1120 | "metadata": {}, |
||
| 1121 | "outputs": [], |
||
| 1122 | "source": [] |
||
| 1123 | }, |
||
| 1124 | { |
||
| 1125 | "cell_type": "code", |
||
| 1126 | "execution_count": 11, |
||
| 1127 | "metadata": { |
||
| 1128 | "scrolled": true |
||
| 1129 | }, |
||
| 1130 | "outputs": [ |
||
| 1131 | { |
||
| 1132 | "name": "stdout", |
||
| 1133 | "output_type": "stream", |
||
| 1134 | "text": [ |
||
| 1135 | "completed epochs: 0 starting now: 2\n", |
||
| 1136 | "DataSet 14 train size 17369 fold 0\n", |
||
| 1137 | "adding dummy serieses 9\n", |
||
| 1138 | "DataSet 14 valid size 4384 fold 0\n", |
||
| 1139 | "setFeats, augmentation 0\n", |
||
| 1140 | "WeightedRandomSampler\n", |
||
| 1141 | "dataset train: 17369 valid: 4384 loader train: 542 valid: 137\n", |
||
| 1142 | "loading model model.b13.f0.d14.v35\n", |
||
| 1143 | "setFeats, augmentation -1\n", |
||
| 1144 | "Batch 50 device: cuda time passed: 21.626 time per batch: 0.433\n", |
||
| 1145 | "Batch 100 device: cuda time passed: 37.191 time per batch: 0.372\n", |
||
| 1146 | "Batch 150 device: cuda time passed: 53.924 time per batch: 0.359\n", |
||
| 1147 | "Batch 200 device: cuda time passed: 69.954 time per batch: 0.350\n", |
||
| 1148 | "Batch 250 device: cuda time passed: 85.591 time per batch: 0.342\n", |
||
| 1149 | "Batch 300 device: cuda time passed: 101.332 time per batch: 0.338\n", |
||
| 1150 | "Batch 350 device: cuda time passed: 118.288 time per batch: 0.338\n", |
||
| 1151 | "Batch 400 device: cuda time passed: 134.411 time per batch: 0.336\n", |
||
| 1152 | "Batch 450 device: cuda time passed: 155.215 time per batch: 0.345\n", |
||
| 1153 | "Batch 500 device: cuda time passed: 171.357 time per batch: 0.343\n", |
||
| 1154 | "Batch 50 device: cuda time passed: 8.519 time per batch: 0.170\n", |
||
| 1155 | "Batch 100 device: cuda time passed: 14.697 time per batch: 0.147\n", |
||
| 1156 | "v36, d14, e1, f0, trn ll: 0.0293, val ll: 0.0595, ll_w: 0.0575, cor: 0.8474, auc: 0.9893, lr: 1e-05\n", |
||
| 1157 | "setFeats, augmentation -1\n", |
||
| 1158 | "Batch 50 device: cuda time passed: 20.234 time per batch: 0.405\n", |
||
| 1159 | "Batch 100 device: cuda time passed: 37.254 time per batch: 0.373\n", |
||
| 1160 | "Batch 150 device: cuda time passed: 53.470 time per batch: 0.356\n", |
||
| 1161 | "Batch 200 device: cuda time passed: 69.176 time per batch: 0.346\n", |
||
| 1162 | "Batch 250 device: cuda time passed: 85.543 time per batch: 0.342\n", |
||
| 1163 | "Batch 300 device: cuda time passed: 102.066 time per batch: 0.340\n", |
||
| 1164 | "Batch 350 device: cuda time passed: 118.857 time per batch: 0.340\n", |
||
| 1165 | "Batch 400 device: cuda time passed: 134.521 time per batch: 0.336\n", |
||
| 1166 | "Batch 450 device: cuda time passed: 153.072 time per batch: 0.340\n", |
||
| 1167 | "Batch 500 device: cuda time passed: 170.818 time per batch: 0.342\n", |
||
| 1168 | "Batch 50 device: cuda time passed: 8.401 time per batch: 0.168\n", |
||
| 1169 | "Batch 100 device: cuda time passed: 14.616 time per batch: 0.146\n", |
||
| 1170 | "v36, d14, e2, f0, trn ll: 0.0302, val ll: 0.0595, ll_w: 0.0574, cor: 0.8477, auc: 0.9893, lr: 1e-05\n", |
||
| 1171 | "total running time 458.30859661102295\n", |
||
| 1172 | "completed epochs: 2 starting now: 1\n", |
||
| 1173 | "DataSet 14 train size 17369 fold 0\n", |
||
| 1174 | "adding dummy serieses 9\n", |
||
| 1175 | "DataSet 14 valid size 4384 fold 0\n", |
||
| 1176 | "setFeats, augmentation 0\n", |
||
| 1177 | "WeightedRandomSampler\n", |
||
| 1178 | "dataset train: 17369 valid: 4384 loader train: 542 valid: 137\n", |
||
| 1179 | "loading model model.b2.f0.d14.v36\n", |
||
| 1180 | "setFeats, augmentation -1\n", |
||
| 1181 | "Batch 50 device: cuda time passed: 21.426 time per batch: 0.429\n", |
||
| 1182 | "Batch 100 device: cuda time passed: 38.129 time per batch: 0.381\n", |
||
| 1183 | "Batch 150 device: cuda time passed: 53.906 time per batch: 0.359\n", |
||
| 1184 | "Batch 200 device: cuda time passed: 70.144 time per batch: 0.351\n", |
||
| 1185 | "Batch 250 device: cuda time passed: 86.070 time per batch: 0.344\n", |
||
| 1186 | "Batch 300 device: cuda time passed: 102.134 time per batch: 0.340\n", |
||
| 1187 | "Batch 350 device: cuda time passed: 118.405 time per batch: 0.338\n", |
||
| 1188 | "Batch 400 device: cuda time passed: 134.645 time per batch: 0.337\n", |
||
| 1189 | "Batch 450 device: cuda time passed: 155.131 time per batch: 0.345\n", |
||
| 1190 | "Batch 500 device: cuda time passed: 171.499 time per batch: 0.343\n", |
||
| 1191 | "Batch 50 device: cuda time passed: 8.219 time per batch: 0.164\n", |
||
| 1192 | "Batch 100 device: cuda time passed: 14.580 time per batch: 0.146\n", |
||
| 1193 | "v36, d14, e3, f0, trn ll: 0.0298, val ll: 0.0595, ll_w: 0.0575, cor: 0.8472, auc: 0.9893, lr: 5e-06\n", |
||
| 1194 | "total running time 213.19121074676514\n", |
||
| 1195 | "total time 671.833601474762\n", |
||
| 1196 | "completed epochs: 0 starting now: 2\n", |
||
| 1197 | "DataSet 14 train size 17468 fold 1\n", |
||
| 1198 | "adding dummy serieses 12\n", |
||
| 1199 | "DataSet 14 valid size 4288 fold 1\n", |
||
| 1200 | "setFeats, augmentation 0\n", |
||
| 1201 | "WeightedRandomSampler\n", |
||
| 1202 | "dataset train: 17468 valid: 4288 loader train: 545 valid: 134\n", |
||
| 1203 | "loading model model.b13.f1.d14.v35\n", |
||
| 1204 | "setFeats, augmentation -1\n", |
||
| 1205 | "Batch 50 device: cuda time passed: 21.207 time per batch: 0.424\n", |
||
| 1206 | "Batch 100 device: cuda time passed: 37.348 time per batch: 0.373\n", |
||
| 1207 | "Batch 150 device: cuda time passed: 53.336 time per batch: 0.356\n", |
||
| 1208 | "Batch 200 device: cuda time passed: 69.851 time per batch: 0.349\n", |
||
| 1209 | "Batch 250 device: cuda time passed: 86.062 time per batch: 0.344\n", |
||
| 1210 | "Batch 300 device: cuda time passed: 102.322 time per batch: 0.341\n", |
||
| 1211 | "Batch 350 device: cuda time passed: 119.087 time per batch: 0.340\n", |
||
| 1212 | "Batch 400 device: cuda time passed: 135.502 time per batch: 0.339\n", |
||
| 1213 | "Batch 450 device: cuda time passed: 154.983 time per batch: 0.344\n", |
||
| 1214 | "Batch 500 device: cuda time passed: 172.005 time per batch: 0.344\n", |
||
| 1215 | "Batch 50 device: cuda time passed: 8.149 time per batch: 0.163\n", |
||
| 1216 | "Batch 100 device: cuda time passed: 14.844 time per batch: 0.148\n", |
||
| 1217 | "v36, d14, e1, f1, trn ll: 0.0290, val ll: 0.0593, ll_w: 0.0580, cor: 0.8483, auc: 0.9901, lr: 1e-05\n", |
||
| 1218 | "setFeats, augmentation -1\n", |
||
| 1219 | "Batch 50 device: cuda time passed: 20.749 time per batch: 0.415\n", |
||
| 1220 | "Batch 100 device: cuda time passed: 37.137 time per batch: 0.371\n", |
||
| 1221 | "Batch 150 device: cuda time passed: 53.310 time per batch: 0.355\n", |
||
| 1222 | "Batch 200 device: cuda time passed: 69.517 time per batch: 0.348\n", |
||
| 1223 | "Batch 250 device: cuda time passed: 85.902 time per batch: 0.344\n", |
||
| 1224 | "Batch 300 device: cuda time passed: 101.682 time per batch: 0.339\n", |
||
| 1225 | "Batch 350 device: cuda time passed: 118.095 time per batch: 0.337\n", |
||
| 1226 | "Batch 400 device: cuda time passed: 134.853 time per batch: 0.337\n", |
||
| 1227 | "Batch 450 device: cuda time passed: 155.186 time per batch: 0.345\n", |
||
| 1228 | "Batch 500 device: cuda time passed: 171.021 time per batch: 0.342\n", |
||
| 1229 | "Batch 50 device: cuda time passed: 7.627 time per batch: 0.153\n", |
||
| 1230 | "Batch 100 device: cuda time passed: 13.832 time per batch: 0.138\n", |
||
| 1231 | "v36, d14, e2, f1, trn ll: 0.0294, val ll: 0.0592, ll_w: 0.0579, cor: 0.8485, auc: 0.9901, lr: 1e-05\n", |
||
| 1232 | "total running time 450.5849003791809\n", |
||
| 1233 | "completed epochs: 2 starting now: 1\n", |
||
| 1234 | "DataSet 14 train size 17468 fold 1\n", |
||
| 1235 | "adding dummy serieses 12\n", |
||
| 1236 | "DataSet 14 valid size 4288 fold 1\n", |
||
| 1237 | "setFeats, augmentation 0\n", |
||
| 1238 | "WeightedRandomSampler\n", |
||
| 1239 | "dataset train: 17468 valid: 4288 loader train: 545 valid: 134\n", |
||
| 1240 | "loading model model.b2.f1.d14.v36\n", |
||
| 1241 | "setFeats, augmentation -1\n", |
||
| 1242 | "Batch 50 device: cuda time passed: 21.513 time per batch: 0.430\n", |
||
| 1243 | "Batch 100 device: cuda time passed: 37.783 time per batch: 0.378\n", |
||
| 1244 | "Batch 150 device: cuda time passed: 53.955 time per batch: 0.360\n", |
||
| 1245 | "Batch 200 device: cuda time passed: 70.656 time per batch: 0.353\n", |
||
| 1246 | "Batch 250 device: cuda time passed: 86.881 time per batch: 0.348\n", |
||
| 1247 | "Batch 300 device: cuda time passed: 102.464 time per batch: 0.342\n", |
||
| 1248 | "Batch 350 device: cuda time passed: 119.210 time per batch: 0.341\n", |
||
| 1249 | "Batch 400 device: cuda time passed: 135.295 time per batch: 0.338\n", |
||
| 1250 | "Batch 450 device: cuda time passed: 155.318 time per batch: 0.345\n", |
||
| 1251 | "Batch 500 device: cuda time passed: 171.368 time per batch: 0.343\n", |
||
| 1252 | "Batch 50 device: cuda time passed: 8.426 time per batch: 0.169\n", |
||
| 1253 | "Batch 100 device: cuda time passed: 14.857 time per batch: 0.149\n", |
||
| 1254 | "v36, d14, e3, f1, trn ll: 0.0287, val ll: 0.0593, ll_w: 0.0580, cor: 0.8484, auc: 0.9900, lr: 5e-06\n", |
||
| 1255 | "total running time 213.8144974708557\n", |
||
| 1256 | "total time 1336.568071603775\n", |
||
| 1257 | "completed epochs: 0 starting now: 2\n", |
||
| 1258 | "DataSet 14 train size 17355 fold 2\n", |
||
| 1259 | "adding dummy serieses 27\n", |
||
| 1260 | "DataSet 14 valid size 4416 fold 2\n", |
||
| 1261 | "setFeats, augmentation 0\n", |
||
| 1262 | "WeightedRandomSampler\n", |
||
| 1263 | "dataset train: 17355 valid: 4416 loader train: 542 valid: 138\n", |
||
| 1264 | "loading model model.b13.f2.d14.v35\n", |
||
| 1265 | "setFeats, augmentation -1\n", |
||
| 1266 | "Batch 50 device: cuda time passed: 21.352 time per batch: 0.427\n", |
||
| 1267 | "Batch 100 device: cuda time passed: 37.326 time per batch: 0.373\n", |
||
| 1268 | "Batch 150 device: cuda time passed: 53.162 time per batch: 0.354\n", |
||
| 1269 | "Batch 200 device: cuda time passed: 68.927 time per batch: 0.345\n", |
||
| 1270 | "Batch 250 device: cuda time passed: 84.995 time per batch: 0.340\n", |
||
| 1271 | "Batch 300 device: cuda time passed: 101.175 time per batch: 0.337\n", |
||
| 1272 | "Batch 350 device: cuda time passed: 117.550 time per batch: 0.336\n", |
||
| 1273 | "Batch 400 device: cuda time passed: 134.080 time per batch: 0.335\n", |
||
| 1274 | "Batch 450 device: cuda time passed: 153.286 time per batch: 0.341\n", |
||
| 1275 | "Batch 500 device: cuda time passed: 169.635 time per batch: 0.339\n", |
||
| 1276 | "Batch 50 device: cuda time passed: 8.047 time per batch: 0.161\n", |
||
| 1277 | "Batch 100 device: cuda time passed: 14.520 time per batch: 0.145\n", |
||
| 1278 | "v36, d14, e1, f2, trn ll: 0.0284, val ll: 0.0606, ll_w: 0.0577, cor: 0.8449, auc: 0.9889, lr: 1e-05\n", |
||
| 1279 | "setFeats, augmentation -1\n", |
||
| 1280 | "Batch 50 device: cuda time passed: 20.672 time per batch: 0.413\n", |
||
| 1281 | "Batch 100 device: cuda time passed: 37.469 time per batch: 0.375\n", |
||
| 1282 | "Batch 150 device: cuda time passed: 54.116 time per batch: 0.361\n", |
||
| 1283 | "Batch 200 device: cuda time passed: 69.517 time per batch: 0.348\n" |
||
| 1284 | ] |
||
| 1285 | }, |
||
| 1286 | { |
||
| 1287 | "name": "stdout", |
||
| 1288 | "output_type": "stream", |
||
| 1289 | "text": [ |
||
| 1290 | "Batch 250 device: cuda time passed: 86.149 time per batch: 0.345\n", |
||
| 1291 | "Batch 300 device: cuda time passed: 102.999 time per batch: 0.343\n", |
||
| 1292 | "Batch 350 device: cuda time passed: 119.363 time per batch: 0.341\n", |
||
| 1293 | "Batch 400 device: cuda time passed: 135.685 time per batch: 0.339\n", |
||
| 1294 | "Batch 450 device: cuda time passed: 152.529 time per batch: 0.339\n", |
||
| 1295 | "Batch 500 device: cuda time passed: 172.402 time per batch: 0.345\n", |
||
| 1296 | "Batch 50 device: cuda time passed: 8.181 time per batch: 0.164\n", |
||
| 1297 | "Batch 100 device: cuda time passed: 14.485 time per batch: 0.145\n", |
||
| 1298 | "v36, d14, e2, f2, trn ll: 0.0292, val ll: 0.0600, ll_w: 0.0571, cor: 0.8455, auc: 0.9891, lr: 1e-05\n", |
||
| 1299 | "total running time 443.0156455039978\n", |
||
| 1300 | "completed epochs: 2 starting now: 1\n", |
||
| 1301 | "DataSet 14 train size 17355 fold 2\n", |
||
| 1302 | "adding dummy serieses 27\n", |
||
| 1303 | "DataSet 14 valid size 4416 fold 2\n", |
||
| 1304 | "setFeats, augmentation 0\n", |
||
| 1305 | "WeightedRandomSampler\n", |
||
| 1306 | "dataset train: 17355 valid: 4416 loader train: 542 valid: 138\n", |
||
| 1307 | "loading model model.b2.f2.d14.v36\n", |
||
| 1308 | "setFeats, augmentation -1\n", |
||
| 1309 | "Batch 50 device: cuda time passed: 20.755 time per batch: 0.415\n", |
||
| 1310 | "Batch 100 device: cuda time passed: 36.901 time per batch: 0.369\n", |
||
| 1311 | "Batch 150 device: cuda time passed: 52.968 time per batch: 0.353\n", |
||
| 1312 | "Batch 200 device: cuda time passed: 69.214 time per batch: 0.346\n", |
||
| 1313 | "Batch 250 device: cuda time passed: 85.613 time per batch: 0.342\n", |
||
| 1314 | "Batch 300 device: cuda time passed: 102.234 time per batch: 0.341\n", |
||
| 1315 | "Batch 350 device: cuda time passed: 118.636 time per batch: 0.339\n", |
||
| 1316 | "Batch 400 device: cuda time passed: 135.389 time per batch: 0.338\n", |
||
| 1317 | "Batch 450 device: cuda time passed: 155.574 time per batch: 0.346\n", |
||
| 1318 | "Batch 500 device: cuda time passed: 171.428 time per batch: 0.343\n", |
||
| 1319 | "Batch 50 device: cuda time passed: 8.167 time per batch: 0.163\n", |
||
| 1320 | "Batch 100 device: cuda time passed: 14.550 time per batch: 0.145\n", |
||
| 1321 | "v36, d14, e3, f2, trn ll: 0.0292, val ll: 0.0600, ll_w: 0.0571, cor: 0.8454, auc: 0.9892, lr: 5e-06\n", |
||
| 1322 | "total running time 213.9665548801422\n", |
||
| 1323 | "total time 1993.8867774009705\n", |
||
| 1324 | "completed epochs: 0 starting now: 2\n", |
||
| 1325 | "DataSet 14 train size 17408 fold 3\n", |
||
| 1326 | "adding dummy serieses 16\n", |
||
| 1327 | "DataSet 14 valid size 4352 fold 3\n", |
||
| 1328 | "setFeats, augmentation 0\n", |
||
| 1329 | "WeightedRandomSampler\n", |
||
| 1330 | "dataset train: 17408 valid: 4352 loader train: 544 valid: 136\n", |
||
| 1331 | "loading model model.b13.f3.d14.v35\n", |
||
| 1332 | "setFeats, augmentation -1\n", |
||
| 1333 | "Batch 50 device: cuda time passed: 21.250 time per batch: 0.425\n", |
||
| 1334 | "Batch 100 device: cuda time passed: 37.196 time per batch: 0.372\n", |
||
| 1335 | "Batch 150 device: cuda time passed: 53.011 time per batch: 0.353\n", |
||
| 1336 | "Batch 200 device: cuda time passed: 69.612 time per batch: 0.348\n", |
||
| 1337 | "Batch 250 device: cuda time passed: 85.879 time per batch: 0.344\n", |
||
| 1338 | "Batch 300 device: cuda time passed: 102.447 time per batch: 0.341\n", |
||
| 1339 | "Batch 350 device: cuda time passed: 118.245 time per batch: 0.338\n", |
||
| 1340 | "Batch 400 device: cuda time passed: 135.061 time per batch: 0.338\n", |
||
| 1341 | "Batch 450 device: cuda time passed: 153.103 time per batch: 0.340\n", |
||
| 1342 | "Batch 500 device: cuda time passed: 170.886 time per batch: 0.342\n", |
||
| 1343 | "Batch 50 device: cuda time passed: 8.188 time per batch: 0.164\n", |
||
| 1344 | "Batch 100 device: cuda time passed: 14.597 time per batch: 0.146\n", |
||
| 1345 | "v36, d14, e1, f3, trn ll: 0.0290, val ll: 0.0626, ll_w: 0.0604, cor: 0.8411, auc: 0.9889, lr: 1e-05\n", |
||
| 1346 | "setFeats, augmentation -1\n", |
||
| 1347 | "Batch 50 device: cuda time passed: 20.856 time per batch: 0.417\n", |
||
| 1348 | "Batch 100 device: cuda time passed: 36.492 time per batch: 0.365\n", |
||
| 1349 | "Batch 150 device: cuda time passed: 52.552 time per batch: 0.350\n", |
||
| 1350 | "Batch 200 device: cuda time passed: 68.865 time per batch: 0.344\n", |
||
| 1351 | "Batch 250 device: cuda time passed: 85.231 time per batch: 0.341\n", |
||
| 1352 | "Batch 300 device: cuda time passed: 102.115 time per batch: 0.340\n", |
||
| 1353 | "Batch 350 device: cuda time passed: 118.472 time per batch: 0.338\n", |
||
| 1354 | "Batch 400 device: cuda time passed: 134.599 time per batch: 0.336\n", |
||
| 1355 | "Batch 450 device: cuda time passed: 152.687 time per batch: 0.339\n", |
||
| 1356 | "Batch 500 device: cuda time passed: 170.115 time per batch: 0.340\n", |
||
| 1357 | "Batch 50 device: cuda time passed: 8.548 time per batch: 0.171\n", |
||
| 1358 | "Batch 100 device: cuda time passed: 14.807 time per batch: 0.148\n", |
||
| 1359 | "v36, d14, e2, f3, trn ll: 0.0295, val ll: 0.0629, ll_w: 0.0605, cor: 0.8408, auc: 0.9889, lr: 1e-05\n", |
||
| 1360 | "total running time 447.1415765285492\n", |
||
| 1361 | "completed epochs: 2 starting now: 1\n", |
||
| 1362 | "DataSet 14 train size 17408 fold 3\n", |
||
| 1363 | "adding dummy serieses 16\n", |
||
| 1364 | "DataSet 14 valid size 4352 fold 3\n", |
||
| 1365 | "setFeats, augmentation 0\n", |
||
| 1366 | "WeightedRandomSampler\n", |
||
| 1367 | "dataset train: 17408 valid: 4352 loader train: 544 valid: 136\n", |
||
| 1368 | "loading model model.b2.f3.d14.v36\n", |
||
| 1369 | "setFeats, augmentation -1\n", |
||
| 1370 | "Batch 50 device: cuda time passed: 20.516 time per batch: 0.410\n", |
||
| 1371 | "Batch 100 device: cuda time passed: 36.334 time per batch: 0.363\n", |
||
| 1372 | "Batch 150 device: cuda time passed: 53.084 time per batch: 0.354\n", |
||
| 1373 | "Batch 200 device: cuda time passed: 69.037 time per batch: 0.345\n", |
||
| 1374 | "Batch 250 device: cuda time passed: 85.908 time per batch: 0.344\n", |
||
| 1375 | "Batch 300 device: cuda time passed: 102.228 time per batch: 0.341\n", |
||
| 1376 | "Batch 350 device: cuda time passed: 118.540 time per batch: 0.339\n", |
||
| 1377 | "Batch 400 device: cuda time passed: 134.860 time per batch: 0.337\n", |
||
| 1378 | "Batch 450 device: cuda time passed: 153.588 time per batch: 0.341\n", |
||
| 1379 | "Batch 500 device: cuda time passed: 170.057 time per batch: 0.340\n", |
||
| 1380 | "Batch 50 device: cuda time passed: 8.858 time per batch: 0.177\n", |
||
| 1381 | "Batch 100 device: cuda time passed: 15.062 time per batch: 0.151\n", |
||
| 1382 | "v36, d14, e3, f3, trn ll: 0.0290, val ll: 0.0624, ll_w: 0.0601, cor: 0.8414, auc: 0.9889, lr: 5e-06\n", |
||
| 1383 | "total running time 212.96735048294067\n", |
||
| 1384 | "total time 2654.3308753967285\n", |
||
| 1385 | "completed epochs: 0 starting now: 2\n", |
||
| 1386 | "DataSet 14 train size 17376 fold 4\n", |
||
| 1387 | "adding dummy serieses 16\n", |
||
| 1388 | "DataSet 14 valid size 4384 fold 4\n", |
||
| 1389 | "setFeats, augmentation 0\n", |
||
| 1390 | "WeightedRandomSampler\n", |
||
| 1391 | "dataset train: 17376 valid: 4384 loader train: 543 valid: 137\n", |
||
| 1392 | "loading model model.b13.f4.d14.v35\n", |
||
| 1393 | "setFeats, augmentation -1\n", |
||
| 1394 | "Batch 50 device: cuda time passed: 20.938 time per batch: 0.419\n", |
||
| 1395 | "Batch 100 device: cuda time passed: 36.742 time per batch: 0.367\n", |
||
| 1396 | "Batch 150 device: cuda time passed: 53.118 time per batch: 0.354\n", |
||
| 1397 | "Batch 200 device: cuda time passed: 69.207 time per batch: 0.346\n", |
||
| 1398 | "Batch 250 device: cuda time passed: 85.657 time per batch: 0.343\n", |
||
| 1399 | "Batch 300 device: cuda time passed: 102.577 time per batch: 0.342\n", |
||
| 1400 | "Batch 350 device: cuda time passed: 118.931 time per batch: 0.340\n", |
||
| 1401 | "Batch 400 device: cuda time passed: 135.803 time per batch: 0.340\n", |
||
| 1402 | "Batch 450 device: cuda time passed: 152.349 time per batch: 0.339\n", |
||
| 1403 | "Batch 500 device: cuda time passed: 171.693 time per batch: 0.343\n", |
||
| 1404 | "Batch 50 device: cuda time passed: 8.196 time per batch: 0.164\n", |
||
| 1405 | "Batch 100 device: cuda time passed: 14.573 time per batch: 0.146\n", |
||
| 1406 | "v36, d14, e1, f4, trn ll: 0.0293, val ll: 0.0609, ll_w: 0.0584, cor: 0.8450, auc: 0.9886, lr: 1e-05\n", |
||
| 1407 | "setFeats, augmentation -1\n", |
||
| 1408 | "Batch 50 device: cuda time passed: 20.888 time per batch: 0.418\n", |
||
| 1409 | "Batch 100 device: cuda time passed: 37.072 time per batch: 0.371\n", |
||
| 1410 | "Batch 150 device: cuda time passed: 52.913 time per batch: 0.353\n", |
||
| 1411 | "Batch 200 device: cuda time passed: 69.316 time per batch: 0.347\n", |
||
| 1412 | "Batch 250 device: cuda time passed: 85.225 time per batch: 0.341\n", |
||
| 1413 | "Batch 300 device: cuda time passed: 101.227 time per batch: 0.337\n", |
||
| 1414 | "Batch 350 device: cuda time passed: 117.882 time per batch: 0.337\n", |
||
| 1415 | "Batch 400 device: cuda time passed: 134.412 time per batch: 0.336\n", |
||
| 1416 | "Batch 450 device: cuda time passed: 153.441 time per batch: 0.341\n", |
||
| 1417 | "Batch 500 device: cuda time passed: 169.712 time per batch: 0.339\n", |
||
| 1418 | "Batch 50 device: cuda time passed: 8.684 time per batch: 0.174\n", |
||
| 1419 | "Batch 100 device: cuda time passed: 15.135 time per batch: 0.151\n", |
||
| 1420 | "v36, d14, e2, f4, trn ll: 0.0288, val ll: 0.0610, ll_w: 0.0585, cor: 0.8453, auc: 0.9885, lr: 1e-05\n", |
||
| 1421 | "total running time 445.4769241809845\n", |
||
| 1422 | "completed epochs: 2 starting now: 1\n", |
||
| 1423 | "DataSet 14 train size 17376 fold 4\n", |
||
| 1424 | "adding dummy serieses 16\n", |
||
| 1425 | "DataSet 14 valid size 4384 fold 4\n", |
||
| 1426 | "setFeats, augmentation 0\n", |
||
| 1427 | "WeightedRandomSampler\n", |
||
| 1428 | "dataset train: 17376 valid: 4384 loader train: 543 valid: 137\n", |
||
| 1429 | "loading model model.b2.f4.d14.v36\n", |
||
| 1430 | "setFeats, augmentation -1\n", |
||
| 1431 | "Batch 50 device: cuda time passed: 20.951 time per batch: 0.419\n", |
||
| 1432 | "Batch 100 device: cuda time passed: 37.131 time per batch: 0.371\n", |
||
| 1433 | "Batch 150 device: cuda time passed: 53.374 time per batch: 0.356\n", |
||
| 1434 | "Batch 200 device: cuda time passed: 69.208 time per batch: 0.346\n", |
||
| 1435 | "Batch 250 device: cuda time passed: 85.747 time per batch: 0.343\n", |
||
| 1436 | "Batch 300 device: cuda time passed: 102.371 time per batch: 0.341\n", |
||
| 1437 | "Batch 350 device: cuda time passed: 118.719 time per batch: 0.339\n", |
||
| 1438 | "Batch 400 device: cuda time passed: 134.930 time per batch: 0.337\n" |
||
| 1439 | ] |
||
| 1440 | }, |
||
| 1441 | { |
||
| 1442 | "name": "stdout", |
||
| 1443 | "output_type": "stream", |
||
| 1444 | "text": [ |
||
| 1445 | "Batch 450 device: cuda time passed: 154.019 time per batch: 0.342\n", |
||
| 1446 | "Batch 500 device: cuda time passed: 170.163 time per batch: 0.340\n", |
||
| 1447 | "Batch 50 device: cuda time passed: 7.538 time per batch: 0.151\n", |
||
| 1448 | "Batch 100 device: cuda time passed: 15.825 time per batch: 0.158\n", |
||
| 1449 | "v36, d14, e3, f4, trn ll: 0.0284, val ll: 0.0610, ll_w: 0.0585, cor: 0.8453, auc: 0.9885, lr: 5e-06\n", |
||
| 1450 | "total running time 213.95540952682495\n", |
||
| 1451 | "total time 3314.099096775055\n", |
||
| 1452 | "total time 3314.0992426872253\n", |
||
| 1453 | "total time 3314.099636554718\n" |
||
| 1454 | ] |
||
| 1455 | } |
||
| 1456 | ], |
||
| 1457 | "source": [ |
||
| 1458 | "weight_decay = 1e-4\n", |
||
| 1459 | "lrs = np.array([1e-5, 5e-6])\n", |
||
| 1460 | "epochs = np.array([2, 1])\n", |
||
| 1461 | "stg = time.time()\n", |
||
| 1462 | "for ds in [14]:#my_datasets3+my_datasets5:\n", |
||
| 1463 | " folds = getNFolds(ds)\n", |
||
| 1464 | " #folds = 2\n", |
||
| 1465 | " for f in range(folds):\n", |
||
| 1466 | " for i,lr in enumerate(lrs):\n", |
||
| 1467 | " learning_rate = lr\n", |
||
| 1468 | " model, predictions, val_results = train_one(dataset=ds, epochs=epochs[i], bs=32, fold=f, init_ver=35)\n", |
||
| 1469 | " print('total time', time.time() - stg)\n", |
||
| 1470 | " print('total time', time.time() - stg)\n", |
||
| 1471 | "print('total time', time.time() - stg)" |
||
| 1472 | ] |
||
| 1473 | }, |
||
| 1474 | { |
||
| 1475 | "cell_type": "code", |
||
| 1476 | "execution_count": null, |
||
| 1477 | "metadata": {}, |
||
| 1478 | "outputs": [], |
||
| 1479 | "source": [] |
||
| 1480 | }, |
||
| 1481 | { |
||
| 1482 | "cell_type": "code", |
||
| 1483 | "execution_count": null, |
||
| 1484 | "metadata": {}, |
||
| 1485 | "outputs": [], |
||
| 1486 | "source": [] |
||
| 1487 | }, |
||
| 1488 | { |
||
| 1489 | "cell_type": "code", |
||
| 1490 | "execution_count": 12, |
||
| 1491 | "metadata": {}, |
||
| 1492 | "outputs": [ |
||
| 1493 | { |
||
| 1494 | "name": "stdout", |
||
| 1495 | "output_type": "stream", |
||
| 1496 | "text": [ |
||
| 1497 | "31 0 65 5 0\n", |
||
| 1498 | "31 1 65 5 0\n", |
||
| 1499 | "31 2 65 5 0\n", |
||
| 1500 | "31 3 39 3 0\n", |
||
| 1501 | "31 4 39 3 0\n", |
||
| 1502 | "33 0 65 5 0\n", |
||
| 1503 | "33 1 65 5 0\n", |
||
| 1504 | "33 2 65 5 0\n", |
||
| 1505 | "33 3 39 3 0\n", |
||
| 1506 | "33 4 39 3 0\n", |
||
| 1507 | "34 0 15 0 0\n", |
||
| 1508 | "34 1 15 0 0\n", |
||
| 1509 | "34 2 15 0 0\n", |
||
| 1510 | "34 3 9 0 0\n", |
||
| 1511 | "34 4 9 0 0\n", |
||
| 1512 | "35 0 13 1 0\n", |
||
| 1513 | "35 1 13 1 0\n", |
||
| 1514 | "35 2 13 1 0\n", |
||
| 1515 | "35 3 13 1 0\n", |
||
| 1516 | "35 4 13 1 0\n", |
||
| 1517 | "36 0 3 0 0\n", |
||
| 1518 | "36 1 3 0 0\n", |
||
| 1519 | "36 2 3 0 0\n", |
||
| 1520 | "36 3 3 0 0\n", |
||
| 1521 | "36 4 3 0 0\n" |
||
| 1522 | ] |
||
| 1523 | } |
||
| 1524 | ], |
||
| 1525 | "source": [ |
||
| 1526 | "for ver in [31,33,34,35,36]:\n", |
||
| 1527 | " for i in range(5):\n", |
||
| 1528 | " stats_filename = PATH_WORK/'stats.f{}.v{}'.format(i,ver)\n", |
||
| 1529 | " stats = pd.read_csv(stats_filename)\n", |
||
| 1530 | " #stats = stats.loc[stats.epoch != 13]\n", |
||
| 1531 | " #stats.to_csv(stats_filename, index=False)\n", |
||
| 1532 | " print(ver,i,len(stats),len(stats.loc[stats.epoch==13]),len(stats.loc[stats.epoch>13]))" |
||
| 1533 | ] |
||
| 1534 | }, |
||
| 1535 | { |
||
| 1536 | "cell_type": "code", |
||
| 1537 | "execution_count": null, |
||
| 1538 | "metadata": {}, |
||
| 1539 | "outputs": [], |
||
| 1540 | "source": [] |
||
| 1541 | }, |
||
| 1542 | { |
||
| 1543 | "cell_type": "code", |
||
| 1544 | "execution_count": 59, |
||
| 1545 | "metadata": {}, |
||
| 1546 | "outputs": [], |
||
| 1547 | "source": [ |
||
| 1548 | "stats1 = pd.concat([pd.read_csv(PATH_WORK/'stats.f{}.v{}'.format(i,31)) for i in range(5)] +\n", |
||
| 1549 | " [pd.read_csv(PATH_WORK/'stats.f{}.v{}'.format(i,33)) for i in range(5)] + \n", |
||
| 1550 | " [pd.read_csv(PATH_WORK/'stats.f{}.v{}'.format(i,35)) for i in range(5)], axis=0, sort=False)" |
||
| 1551 | ] |
||
| 1552 | }, |
||
| 1553 | { |
||
| 1554 | "cell_type": "code", |
||
| 1555 | "execution_count": 70, |
||
| 1556 | "metadata": {}, |
||
| 1557 | "outputs": [], |
||
| 1558 | "source": [ |
||
| 1559 | "stats1 = pd.concat([pd.read_csv(PATH_WORK/'stats.f{}.v{}'.format(i,33)) for i in range(5)] + \n", |
||
| 1560 | " [pd.read_csv(PATH_WORK/'stats.f{}.v{}'.format(i,35)) for i in range(5)], axis=0, sort=False)" |
||
| 1561 | ] |
||
| 1562 | }, |
||
| 1563 | { |
||
| 1564 | "cell_type": "code", |
||
| 1565 | "execution_count": 71, |
||
| 1566 | "metadata": { |
||
| 1567 | "scrolled": false |
||
| 1568 | }, |
||
| 1569 | "outputs": [ |
||
| 1570 | { |
||
| 1571 | "data": { |
||
| 1572 | "text/html": [ |
||
| 1573 | "<div>\n", |
||
| 1574 | "<style scoped>\n", |
||
| 1575 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 1576 | " vertical-align: middle;\n", |
||
| 1577 | " }\n", |
||
| 1578 | "\n", |
||
| 1579 | " .dataframe tbody tr th {\n", |
||
| 1580 | " vertical-align: top;\n", |
||
| 1581 | " }\n", |
||
| 1582 | "\n", |
||
| 1583 | " .dataframe thead th {\n", |
||
| 1584 | " text-align: right;\n", |
||
| 1585 | " }\n", |
||
| 1586 | "</style>\n", |
||
| 1587 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 1588 | " <thead>\n", |
||
| 1589 | " <tr style=\"text-align: right;\">\n", |
||
| 1590 | " <th></th>\n", |
||
| 1591 | " <th></th>\n", |
||
| 1592 | " <th>val_loss</th>\n", |
||
| 1593 | " <th>val_w_loss</th>\n", |
||
| 1594 | " </tr>\n", |
||
| 1595 | " <tr>\n", |
||
| 1596 | " <th>dataset</th>\n", |
||
| 1597 | " <th>ver</th>\n", |
||
| 1598 | " <th></th>\n", |
||
| 1599 | " <th></th>\n", |
||
| 1600 | " </tr>\n", |
||
| 1601 | " </thead>\n", |
||
| 1602 | " <tbody>\n", |
||
| 1603 | " <tr>\n", |
||
| 1604 | " <td>7</td>\n", |
||
| 1605 | " <td>33.0</td>\n", |
||
| 1606 | " <td>0.062216</td>\n", |
||
| 1607 | " <td>0.059966</td>\n", |
||
| 1608 | " </tr>\n", |
||
| 1609 | " <tr>\n", |
||
| 1610 | " <td>9</td>\n", |
||
| 1611 | " <td>33.0</td>\n", |
||
| 1612 | " <td>0.061798</td>\n", |
||
| 1613 | " <td>0.059631</td>\n", |
||
| 1614 | " </tr>\n", |
||
| 1615 | " <tr>\n", |
||
| 1616 | " <td>11</td>\n", |
||
| 1617 | " <td>33.0</td>\n", |
||
| 1618 | " <td>0.060567</td>\n", |
||
| 1619 | " <td>0.058444</td>\n", |
||
| 1620 | " </tr>\n", |
||
| 1621 | " <tr>\n", |
||
| 1622 | " <td>12</td>\n", |
||
| 1623 | " <td>33.0</td>\n", |
||
| 1624 | " <td>0.060435</td>\n", |
||
| 1625 | " <td>0.058339</td>\n", |
||
| 1626 | " </tr>\n", |
||
| 1627 | " <tr>\n", |
||
| 1628 | " <td>13</td>\n", |
||
| 1629 | " <td>33.0</td>\n", |
||
| 1630 | " <td>0.060730</td>\n", |
||
| 1631 | " <td>0.058572</td>\n", |
||
| 1632 | " </tr>\n", |
||
| 1633 | " <tr>\n", |
||
| 1634 | " <td>14</td>\n", |
||
| 1635 | " <td>35.0</td>\n", |
||
| 1636 | " <td>0.060279</td>\n", |
||
| 1637 | " <td>0.058197</td>\n", |
||
| 1638 | " </tr>\n", |
||
| 1639 | " </tbody>\n", |
||
| 1640 | "</table>\n", |
||
| 1641 | "</div>" |
||
| 1642 | ], |
||
| 1643 | "text/plain": [ |
||
| 1644 | " val_loss val_w_loss\n", |
||
| 1645 | "dataset ver \n", |
||
| 1646 | "7 33.0 0.062216 0.059966\n", |
||
| 1647 | "9 33.0 0.061798 0.059631\n", |
||
| 1648 | "11 33.0 0.060567 0.058444\n", |
||
| 1649 | "12 33.0 0.060435 0.058339\n", |
||
| 1650 | "13 33.0 0.060730 0.058572\n", |
||
| 1651 | "14 35.0 0.060279 0.058197" |
||
| 1652 | ] |
||
| 1653 | }, |
||
| 1654 | "execution_count": 71, |
||
| 1655 | "metadata": {}, |
||
| 1656 | "output_type": "execute_result" |
||
| 1657 | } |
||
| 1658 | ], |
||
| 1659 | "source": [ |
||
| 1660 | "stats1.loc[stats1.epoch==13].groupby(['dataset','ver'])['val_loss','val_w_loss'].mean()" |
||
| 1661 | ] |
||
| 1662 | }, |
||
| 1663 | { |
||
| 1664 | "cell_type": "code", |
||
| 1665 | "execution_count": 76, |
||
| 1666 | "metadata": {}, |
||
| 1667 | "outputs": [ |
||
| 1668 | { |
||
| 1669 | "data": { |
||
| 1670 | "text/plain": [ |
||
| 1671 | "epoch\n", |
||
| 1672 | "1 0.069373\n", |
||
| 1673 | "2 0.066851\n", |
||
| 1674 | "3 0.066766\n", |
||
| 1675 | "4 0.065325\n", |
||
| 1676 | "5 0.063819\n", |
||
| 1677 | "6 0.063702\n", |
||
| 1678 | "7 0.063659\n", |
||
| 1679 | "8 0.063762\n", |
||
| 1680 | "9 0.063641\n", |
||
| 1681 | "10 0.063510\n", |
||
| 1682 | "11 0.063465\n", |
||
| 1683 | "12 0.063588\n", |
||
| 1684 | "13 0.058714\n", |
||
| 1685 | "Name: val_w_loss, dtype: float64" |
||
| 1686 | ] |
||
| 1687 | }, |
||
| 1688 | "execution_count": 76, |
||
| 1689 | "metadata": {}, |
||
| 1690 | "output_type": "execute_result" |
||
| 1691 | } |
||
| 1692 | ], |
||
| 1693 | "source": [ |
||
| 1694 | "stats1.groupby('epoch')['val_w_loss'].mean()" |
||
| 1695 | ] |
||
| 1696 | }, |
||
| 1697 | { |
||
| 1698 | "cell_type": "code", |
||
| 1699 | "execution_count": 77, |
||
| 1700 | "metadata": {}, |
||
| 1701 | "outputs": [ |
||
| 1702 | { |
||
| 1703 | "data": { |
||
| 1704 | "text/plain": [ |
||
| 1705 | "epoch\n", |
||
| 1706 | "1 0.058880\n", |
||
| 1707 | "2 0.058748\n", |
||
| 1708 | "3 0.058762\n", |
||
| 1709 | "Name: val_w_loss, dtype: float64" |
||
| 1710 | ] |
||
| 1711 | }, |
||
| 1712 | "execution_count": 77, |
||
| 1713 | "metadata": {}, |
||
| 1714 | "output_type": "execute_result" |
||
| 1715 | } |
||
| 1716 | ], |
||
| 1717 | "source": [ |
||
| 1718 | "stats2.groupby('epoch')['val_w_loss'].mean()" |
||
| 1719 | ] |
||
| 1720 | }, |
||
| 1721 | { |
||
| 1722 | "cell_type": "code", |
||
| 1723 | "execution_count": 78, |
||
| 1724 | "metadata": {}, |
||
| 1725 | "outputs": [ |
||
| 1726 | { |
||
| 1727 | "data": { |
||
| 1728 | "text/html": [ |
||
| 1729 | "<div>\n", |
||
| 1730 | "<style scoped>\n", |
||
| 1731 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 1732 | " vertical-align: middle;\n", |
||
| 1733 | " }\n", |
||
| 1734 | "\n", |
||
| 1735 | " .dataframe tbody tr th {\n", |
||
| 1736 | " vertical-align: top;\n", |
||
| 1737 | " }\n", |
||
| 1738 | "\n", |
||
| 1739 | " .dataframe thead th {\n", |
||
| 1740 | " text-align: right;\n", |
||
| 1741 | " }\n", |
||
| 1742 | "</style>\n", |
||
| 1743 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 1744 | " <thead>\n", |
||
| 1745 | " <tr style=\"text-align: right;\">\n", |
||
| 1746 | " <th></th>\n", |
||
| 1747 | " <th>ver</th>\n", |
||
| 1748 | " <th>dataset</th>\n", |
||
| 1749 | " <th>epoch</th>\n", |
||
| 1750 | " <th>fold</th>\n", |
||
| 1751 | " <th>train_loss</th>\n", |
||
| 1752 | " <th>val_loss</th>\n", |
||
| 1753 | " <th>val_w_loss</th>\n", |
||
| 1754 | " <th>val_loss2</th>\n", |
||
| 1755 | " <th>val_w_loss2</th>\n", |
||
| 1756 | " <th>cor</th>\n", |
||
| 1757 | " <th>any</th>\n", |
||
| 1758 | " <th>epidural</th>\n", |
||
| 1759 | " <th>intraparenchymal</th>\n", |
||
| 1760 | " <th>intraventricular</th>\n", |
||
| 1761 | " <th>subarachnoid</th>\n", |
||
| 1762 | " <th>subdural</th>\n", |
||
| 1763 | " <th>train_sz</th>\n", |
||
| 1764 | " <th>val_sz</th>\n", |
||
| 1765 | " <th>bs</th>\n", |
||
| 1766 | " <th>train_time</th>\n", |
||
| 1767 | " <th>valid_time</th>\n", |
||
| 1768 | " <th>lr</th>\n", |
||
| 1769 | " <th>wd</th>\n", |
||
| 1770 | " </tr>\n", |
||
| 1771 | " </thead>\n", |
||
| 1772 | " <tbody>\n", |
||
| 1773 | " <tr>\n", |
||
| 1774 | " <td>0</td>\n", |
||
| 1775 | " <td>34</td>\n", |
||
| 1776 | " <td>7</td>\n", |
||
| 1777 | " <td>1</td>\n", |
||
| 1778 | " <td>0</td>\n", |
||
| 1779 | " <td>0.026721</td>\n", |
||
| 1780 | " <td>0.064065</td>\n", |
||
| 1781 | " <td>0.061943</td>\n", |
||
| 1782 | " <td>0.058069</td>\n", |
||
| 1783 | " <td>0.041959</td>\n", |
||
| 1784 | " <td>0.841664</td>\n", |
||
| 1785 | " <td>0.094596</td>\n", |
||
| 1786 | " <td>0.017690</td>\n", |
||
| 1787 | " <td>0.048768</td>\n", |
||
| 1788 | " <td>0.022488</td>\n", |
||
| 1789 | " <td>0.050100</td>\n", |
||
| 1790 | " <td>0.078243</td>\n", |
||
| 1791 | " <td>14526</td>\n", |
||
| 1792 | " <td>7232</td>\n", |
||
| 1793 | " <td>32</td>\n", |
||
| 1794 | " <td>188.513041</td>\n", |
||
| 1795 | " <td>42.595724</td>\n", |
||
| 1796 | " <td>0.000010</td>\n", |
||
| 1797 | " <td>0.0001</td>\n", |
||
| 1798 | " </tr>\n", |
||
| 1799 | " <tr>\n", |
||
| 1800 | " <td>1</td>\n", |
||
| 1801 | " <td>34</td>\n", |
||
| 1802 | " <td>7</td>\n", |
||
| 1803 | " <td>2</td>\n", |
||
| 1804 | " <td>0</td>\n", |
||
| 1805 | " <td>0.026779</td>\n", |
||
| 1806 | " <td>0.063986</td>\n", |
||
| 1807 | " <td>0.061799</td>\n", |
||
| 1808 | " <td>0.058277</td>\n", |
||
| 1809 | " <td>0.042019</td>\n", |
||
| 1810 | " <td>0.841992</td>\n", |
||
| 1811 | " <td>0.095012</td>\n", |
||
| 1812 | " <td>0.017891</td>\n", |
||
| 1813 | " <td>0.048536</td>\n", |
||
| 1814 | " <td>0.022399</td>\n", |
||
| 1815 | " <td>0.050454</td>\n", |
||
| 1816 | " <td>0.078633</td>\n", |
||
| 1817 | " <td>14526</td>\n", |
||
| 1818 | " <td>7232</td>\n", |
||
| 1819 | " <td>32</td>\n", |
||
| 1820 | " <td>148.325198</td>\n", |
||
| 1821 | " <td>42.840445</td>\n", |
||
| 1822 | " <td>0.000010</td>\n", |
||
| 1823 | " <td>0.0001</td>\n", |
||
| 1824 | " </tr>\n", |
||
| 1825 | " <tr>\n", |
||
| 1826 | " <td>2</td>\n", |
||
| 1827 | " <td>34</td>\n", |
||
| 1828 | " <td>7</td>\n", |
||
| 1829 | " <td>3</td>\n", |
||
| 1830 | " <td>0</td>\n", |
||
| 1831 | " <td>0.026806</td>\n", |
||
| 1832 | " <td>0.063772</td>\n", |
||
| 1833 | " <td>0.061700</td>\n", |
||
| 1834 | " <td>0.057858</td>\n", |
||
| 1835 | " <td>0.041902</td>\n", |
||
| 1836 | " <td>0.841932</td>\n", |
||
| 1837 | " <td>0.094341</td>\n", |
||
| 1838 | " <td>0.017474</td>\n", |
||
| 1839 | " <td>0.048568</td>\n", |
||
| 1840 | " <td>0.022377</td>\n", |
||
| 1841 | " <td>0.050502</td>\n", |
||
| 1842 | " <td>0.077406</td>\n", |
||
| 1843 | " <td>14526</td>\n", |
||
| 1844 | " <td>7232</td>\n", |
||
| 1845 | " <td>32</td>\n", |
||
| 1846 | " <td>148.716054</td>\n", |
||
| 1847 | " <td>42.719312</td>\n", |
||
| 1848 | " <td>0.000005</td>\n", |
||
| 1849 | " <td>0.0001</td>\n", |
||
| 1850 | " </tr>\n", |
||
| 1851 | " <tr>\n", |
||
| 1852 | " <td>3</td>\n", |
||
| 1853 | " <td>34</td>\n", |
||
| 1854 | " <td>9</td>\n", |
||
| 1855 | " <td>1</td>\n", |
||
| 1856 | " <td>0</td>\n", |
||
| 1857 | " <td>0.027112</td>\n", |
||
| 1858 | " <td>0.063366</td>\n", |
||
| 1859 | " <td>0.061400</td>\n", |
||
| 1860 | " <td>0.059194</td>\n", |
||
| 1861 | " <td>0.042473</td>\n", |
||
| 1862 | " <td>0.842161</td>\n", |
||
| 1863 | " <td>0.095822</td>\n", |
||
| 1864 | " <td>0.016753</td>\n", |
||
| 1865 | " <td>0.048794</td>\n", |
||
| 1866 | " <td>0.022736</td>\n", |
||
| 1867 | " <td>0.053430</td>\n", |
||
| 1868 | " <td>0.081001</td>\n", |
||
| 1869 | " <td>14526</td>\n", |
||
| 1870 | " <td>7232</td>\n", |
||
| 1871 | " <td>32</td>\n", |
||
| 1872 | " <td>154.520063</td>\n", |
||
| 1873 | " <td>41.107329</td>\n", |
||
| 1874 | " <td>0.000010</td>\n", |
||
| 1875 | " <td>0.0001</td>\n", |
||
| 1876 | " </tr>\n", |
||
| 1877 | " <tr>\n", |
||
| 1878 | " <td>4</td>\n", |
||
| 1879 | " <td>34</td>\n", |
||
| 1880 | " <td>9</td>\n", |
||
| 1881 | " <td>2</td>\n", |
||
| 1882 | " <td>0</td>\n", |
||
| 1883 | " <td>0.028070</td>\n", |
||
| 1884 | " <td>0.063492</td>\n", |
||
| 1885 | " <td>0.061455</td>\n", |
||
| 1886 | " <td>0.059902</td>\n", |
||
| 1887 | " <td>0.042804</td>\n", |
||
| 1888 | " <td>0.842046</td>\n", |
||
| 1889 | " <td>0.097219</td>\n", |
||
| 1890 | " <td>0.016762</td>\n", |
||
| 1891 | " <td>0.048958</td>\n", |
||
| 1892 | " <td>0.023702</td>\n", |
||
| 1893 | " <td>0.053533</td>\n", |
||
| 1894 | " <td>0.081922</td>\n", |
||
| 1895 | " <td>14526</td>\n", |
||
| 1896 | " <td>7232</td>\n", |
||
| 1897 | " <td>32</td>\n", |
||
| 1898 | " <td>136.198384</td>\n", |
||
| 1899 | " <td>41.837500</td>\n", |
||
| 1900 | " <td>0.000010</td>\n", |
||
| 1901 | " <td>0.0001</td>\n", |
||
| 1902 | " </tr>\n", |
||
| 1903 | " <tr>\n", |
||
| 1904 | " <td>...</td>\n", |
||
| 1905 | " <td>...</td>\n", |
||
| 1906 | " <td>...</td>\n", |
||
| 1907 | " <td>...</td>\n", |
||
| 1908 | " <td>...</td>\n", |
||
| 1909 | " <td>...</td>\n", |
||
| 1910 | " <td>...</td>\n", |
||
| 1911 | " <td>...</td>\n", |
||
| 1912 | " <td>...</td>\n", |
||
| 1913 | " <td>...</td>\n", |
||
| 1914 | " <td>...</td>\n", |
||
| 1915 | " <td>...</td>\n", |
||
| 1916 | " <td>...</td>\n", |
||
| 1917 | " <td>...</td>\n", |
||
| 1918 | " <td>...</td>\n", |
||
| 1919 | " <td>...</td>\n", |
||
| 1920 | " <td>...</td>\n", |
||
| 1921 | " <td>...</td>\n", |
||
| 1922 | " <td>...</td>\n", |
||
| 1923 | " <td>...</td>\n", |
||
| 1924 | " <td>...</td>\n", |
||
| 1925 | " <td>...</td>\n", |
||
| 1926 | " <td>...</td>\n", |
||
| 1927 | " <td>...</td>\n", |
||
| 1928 | " </tr>\n", |
||
| 1929 | " <tr>\n", |
||
| 1930 | " <td>1</td>\n", |
||
| 1931 | " <td>36</td>\n", |
||
| 1932 | " <td>14</td>\n", |
||
| 1933 | " <td>2</td>\n", |
||
| 1934 | " <td>3</td>\n", |
||
| 1935 | " <td>0.029522</td>\n", |
||
| 1936 | " <td>0.062853</td>\n", |
||
| 1937 | " <td>0.060485</td>\n", |
||
| 1938 | " <td>0.063770</td>\n", |
||
| 1939 | " <td>0.045538</td>\n", |
||
| 1940 | " <td>0.840799</td>\n", |
||
| 1941 | " <td>0.101509</td>\n", |
||
| 1942 | " <td>0.012685</td>\n", |
||
| 1943 | " <td>0.049486</td>\n", |
||
| 1944 | " <td>0.034019</td>\n", |
||
| 1945 | " <td>0.059630</td>\n", |
||
| 1946 | " <td>0.087555</td>\n", |
||
| 1947 | " <td>17408</td>\n", |
||
| 1948 | " <td>4352</td>\n", |
||
| 1949 | " <td>32</td>\n", |
||
| 1950 | " <td>195.092067</td>\n", |
||
| 1951 | " <td>19.647925</td>\n", |
||
| 1952 | " <td>0.000010</td>\n", |
||
| 1953 | " <td>0.0001</td>\n", |
||
| 1954 | " </tr>\n", |
||
| 1955 | " <tr>\n", |
||
| 1956 | " <td>2</td>\n", |
||
| 1957 | " <td>36</td>\n", |
||
| 1958 | " <td>14</td>\n", |
||
| 1959 | " <td>3</td>\n", |
||
| 1960 | " <td>3</td>\n", |
||
| 1961 | " <td>0.029033</td>\n", |
||
| 1962 | " <td>0.062372</td>\n", |
||
| 1963 | " <td>0.060134</td>\n", |
||
| 1964 | " <td>0.062729</td>\n", |
||
| 1965 | " <td>0.044978</td>\n", |
||
| 1966 | " <td>0.841355</td>\n", |
||
| 1967 | " <td>0.099212</td>\n", |
||
| 1968 | " <td>0.012550</td>\n", |
||
| 1969 | " <td>0.048394</td>\n", |
||
| 1970 | " <td>0.033793</td>\n", |
||
| 1971 | " <td>0.059500</td>\n", |
||
| 1972 | " <td>0.086445</td>\n", |
||
| 1973 | " <td>17408</td>\n", |
||
| 1974 | " <td>4352</td>\n", |
||
| 1975 | " <td>32</td>\n", |
||
| 1976 | " <td>188.747055</td>\n", |
||
| 1977 | " <td>19.592905</td>\n", |
||
| 1978 | " <td>0.000005</td>\n", |
||
| 1979 | " <td>0.0001</td>\n", |
||
| 1980 | " </tr>\n", |
||
| 1981 | " <tr>\n", |
||
| 1982 | " <td>0</td>\n", |
||
| 1983 | " <td>36</td>\n", |
||
| 1984 | " <td>14</td>\n", |
||
| 1985 | " <td>1</td>\n", |
||
| 1986 | " <td>4</td>\n", |
||
| 1987 | " <td>0.029257</td>\n", |
||
| 1988 | " <td>0.060873</td>\n", |
||
| 1989 | " <td>0.058421</td>\n", |
||
| 1990 | " <td>0.061626</td>\n", |
||
| 1991 | " <td>0.045347</td>\n", |
||
| 1992 | " <td>0.845014</td>\n", |
||
| 1993 | " <td>0.102233</td>\n", |
||
| 1994 | " <td>0.018479</td>\n", |
||
| 1995 | " <td>0.052477</td>\n", |
||
| 1996 | " <td>0.020628</td>\n", |
||
| 1997 | " <td>0.056853</td>\n", |
||
| 1998 | " <td>0.078477</td>\n", |
||
| 1999 | " <td>17376</td>\n", |
||
| 2000 | " <td>4384</td>\n", |
||
| 2001 | " <td>32</td>\n", |
||
| 2002 | " <td>208.909939</td>\n", |
||
| 2003 | " <td>19.676935</td>\n", |
||
| 2004 | " <td>0.000010</td>\n", |
||
| 2005 | " <td>0.0001</td>\n", |
||
| 2006 | " </tr>\n", |
||
| 2007 | " <tr>\n", |
||
| 2008 | " <td>1</td>\n", |
||
| 2009 | " <td>36</td>\n", |
||
| 2010 | " <td>14</td>\n", |
||
| 2011 | " <td>2</td>\n", |
||
| 2012 | " <td>4</td>\n", |
||
| 2013 | " <td>0.028809</td>\n", |
||
| 2014 | " <td>0.060978</td>\n", |
||
| 2015 | " <td>0.058489</td>\n", |
||
| 2016 | " <td>0.061709</td>\n", |
||
| 2017 | " <td>0.045331</td>\n", |
||
| 2018 | " <td>0.845300</td>\n", |
||
| 2019 | " <td>0.102328</td>\n", |
||
| 2020 | " <td>0.018075</td>\n", |
||
| 2021 | " <td>0.052644</td>\n", |
||
| 2022 | " <td>0.021467</td>\n", |
||
| 2023 | " <td>0.056481</td>\n", |
||
| 2024 | " <td>0.078641</td>\n", |
||
| 2025 | " <td>17376</td>\n", |
||
| 2026 | " <td>4384</td>\n", |
||
| 2027 | " <td>32</td>\n", |
||
| 2028 | " <td>192.605031</td>\n", |
||
| 2029 | " <td>19.740591</td>\n", |
||
| 2030 | " <td>0.000010</td>\n", |
||
| 2031 | " <td>0.0001</td>\n", |
||
| 2032 | " </tr>\n", |
||
| 2033 | " <tr>\n", |
||
| 2034 | " <td>2</td>\n", |
||
| 2035 | " <td>36</td>\n", |
||
| 2036 | " <td>14</td>\n", |
||
| 2037 | " <td>3</td>\n", |
||
| 2038 | " <td>4</td>\n", |
||
| 2039 | " <td>0.028370</td>\n", |
||
| 2040 | " <td>0.060988</td>\n", |
||
| 2041 | " <td>0.058506</td>\n", |
||
| 2042 | " <td>0.061573</td>\n", |
||
| 2043 | " <td>0.045219</td>\n", |
||
| 2044 | " <td>0.845341</td>\n", |
||
| 2045 | " <td>0.102488</td>\n", |
||
| 2046 | " <td>0.018332</td>\n", |
||
| 2047 | " <td>0.052359</td>\n", |
||
| 2048 | " <td>0.020422</td>\n", |
||
| 2049 | " <td>0.056385</td>\n", |
||
| 2050 | " <td>0.078535</td>\n", |
||
| 2051 | " <td>17376</td>\n", |
||
| 2052 | " <td>4384</td>\n", |
||
| 2053 | " <td>32</td>\n", |
||
| 2054 | " <td>189.093271</td>\n", |
||
| 2055 | " <td>20.038952</td>\n", |
||
| 2056 | " <td>0.000005</td>\n", |
||
| 2057 | " <td>0.0001</td>\n", |
||
| 2058 | " </tr>\n", |
||
| 2059 | " </tbody>\n", |
||
| 2060 | "</table>\n", |
||
| 2061 | "<p>78 rows × 23 columns</p>\n", |
||
| 2062 | "</div>" |
||
| 2063 | ], |
||
| 2064 | "text/plain": [ |
||
| 2065 | " ver dataset epoch fold train_loss val_loss val_w_loss val_loss2 \\\n", |
||
| 2066 | "0 34 7 1 0 0.026721 0.064065 0.061943 0.058069 \n", |
||
| 2067 | "1 34 7 2 0 0.026779 0.063986 0.061799 0.058277 \n", |
||
| 2068 | "2 34 7 3 0 0.026806 0.063772 0.061700 0.057858 \n", |
||
| 2069 | "3 34 9 1 0 0.027112 0.063366 0.061400 0.059194 \n", |
||
| 2070 | "4 34 9 2 0 0.028070 0.063492 0.061455 0.059902 \n", |
||
| 2071 | ".. ... ... ... ... ... ... ... ... \n", |
||
| 2072 | "1 36 14 2 3 0.029522 0.062853 0.060485 0.063770 \n", |
||
| 2073 | "2 36 14 3 3 0.029033 0.062372 0.060134 0.062729 \n", |
||
| 2074 | "0 36 14 1 4 0.029257 0.060873 0.058421 0.061626 \n", |
||
| 2075 | "1 36 14 2 4 0.028809 0.060978 0.058489 0.061709 \n", |
||
| 2076 | "2 36 14 3 4 0.028370 0.060988 0.058506 0.061573 \n", |
||
| 2077 | "\n", |
||
| 2078 | " val_w_loss2 cor any epidural intraparenchymal \\\n", |
||
| 2079 | "0 0.041959 0.841664 0.094596 0.017690 0.048768 \n", |
||
| 2080 | "1 0.042019 0.841992 0.095012 0.017891 0.048536 \n", |
||
| 2081 | "2 0.041902 0.841932 0.094341 0.017474 0.048568 \n", |
||
| 2082 | "3 0.042473 0.842161 0.095822 0.016753 0.048794 \n", |
||
| 2083 | "4 0.042804 0.842046 0.097219 0.016762 0.048958 \n", |
||
| 2084 | ".. ... ... ... ... ... \n", |
||
| 2085 | "1 0.045538 0.840799 0.101509 0.012685 0.049486 \n", |
||
| 2086 | "2 0.044978 0.841355 0.099212 0.012550 0.048394 \n", |
||
| 2087 | "0 0.045347 0.845014 0.102233 0.018479 0.052477 \n", |
||
| 2088 | "1 0.045331 0.845300 0.102328 0.018075 0.052644 \n", |
||
| 2089 | "2 0.045219 0.845341 0.102488 0.018332 0.052359 \n", |
||
| 2090 | "\n", |
||
| 2091 | " intraventricular subarachnoid subdural train_sz val_sz bs \\\n", |
||
| 2092 | "0 0.022488 0.050100 0.078243 14526 7232 32 \n", |
||
| 2093 | "1 0.022399 0.050454 0.078633 14526 7232 32 \n", |
||
| 2094 | "2 0.022377 0.050502 0.077406 14526 7232 32 \n", |
||
| 2095 | "3 0.022736 0.053430 0.081001 14526 7232 32 \n", |
||
| 2096 | "4 0.023702 0.053533 0.081922 14526 7232 32 \n", |
||
| 2097 | ".. ... ... ... ... ... .. \n", |
||
| 2098 | "1 0.034019 0.059630 0.087555 17408 4352 32 \n", |
||
| 2099 | "2 0.033793 0.059500 0.086445 17408 4352 32 \n", |
||
| 2100 | "0 0.020628 0.056853 0.078477 17376 4384 32 \n", |
||
| 2101 | "1 0.021467 0.056481 0.078641 17376 4384 32 \n", |
||
| 2102 | "2 0.020422 0.056385 0.078535 17376 4384 32 \n", |
||
| 2103 | "\n", |
||
| 2104 | " train_time valid_time lr wd \n", |
||
| 2105 | "0 188.513041 42.595724 0.000010 0.0001 \n", |
||
| 2106 | "1 148.325198 42.840445 0.000010 0.0001 \n", |
||
| 2107 | "2 148.716054 42.719312 0.000005 0.0001 \n", |
||
| 2108 | "3 154.520063 41.107329 0.000010 0.0001 \n", |
||
| 2109 | "4 136.198384 41.837500 0.000010 0.0001 \n", |
||
| 2110 | ".. ... ... ... ... \n", |
||
| 2111 | "1 195.092067 19.647925 0.000010 0.0001 \n", |
||
| 2112 | "2 188.747055 19.592905 0.000005 0.0001 \n", |
||
| 2113 | "0 208.909939 19.676935 0.000010 0.0001 \n", |
||
| 2114 | "1 192.605031 19.740591 0.000010 0.0001 \n", |
||
| 2115 | "2 189.093271 20.038952 0.000005 0.0001 \n", |
||
| 2116 | "\n", |
||
| 2117 | "[78 rows x 23 columns]" |
||
| 2118 | ] |
||
| 2119 | }, |
||
| 2120 | "execution_count": 78, |
||
| 2121 | "metadata": {}, |
||
| 2122 | "output_type": "execute_result" |
||
| 2123 | } |
||
| 2124 | ], |
||
| 2125 | "source": [ |
||
| 2126 | "stats2" |
||
| 2127 | ] |
||
| 2128 | }, |
||
| 2129 | { |
||
| 2130 | "cell_type": "code", |
||
| 2131 | "execution_count": null, |
||
| 2132 | "metadata": {}, |
||
| 2133 | "outputs": [], |
||
| 2134 | "source": [] |
||
| 2135 | }, |
||
| 2136 | { |
||
| 2137 | "cell_type": "code", |
||
| 2138 | "execution_count": null, |
||
| 2139 | "metadata": {}, |
||
| 2140 | "outputs": [], |
||
| 2141 | "source": [] |
||
| 2142 | }, |
||
| 2143 | { |
||
| 2144 | "cell_type": "code", |
||
| 2145 | "execution_count": 18, |
||
| 2146 | "metadata": {}, |
||
| 2147 | "outputs": [], |
||
| 2148 | "source": [ |
||
| 2149 | "stats1 = stats1.loc[stats1.epoch==13]" |
||
| 2150 | ] |
||
| 2151 | }, |
||
| 2152 | { |
||
| 2153 | "cell_type": "code", |
||
| 2154 | "execution_count": 64, |
||
| 2155 | "metadata": {}, |
||
| 2156 | "outputs": [], |
||
| 2157 | "source": [ |
||
| 2158 | "stats2 = pd.concat([pd.read_csv(PATH_WORK/'stats.f{}.v{}'.format(i,34)) for i in range(5)] +\n", |
||
| 2159 | " [pd.read_csv(PATH_WORK/'stats.f{}.v{}'.format(i,36)) for i in range(5)], axis=0, sort=False)" |
||
| 2160 | ] |
||
| 2161 | }, |
||
| 2162 | { |
||
| 2163 | "cell_type": "code", |
||
| 2164 | "execution_count": 65, |
||
| 2165 | "metadata": { |
||
| 2166 | "scrolled": false |
||
| 2167 | }, |
||
| 2168 | "outputs": [ |
||
| 2169 | { |
||
| 2170 | "data": { |
||
| 2171 | "text/html": [ |
||
| 2172 | "<div>\n", |
||
| 2173 | "<style scoped>\n", |
||
| 2174 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 2175 | " vertical-align: middle;\n", |
||
| 2176 | " }\n", |
||
| 2177 | "\n", |
||
| 2178 | " .dataframe tbody tr th {\n", |
||
| 2179 | " vertical-align: top;\n", |
||
| 2180 | " }\n", |
||
| 2181 | "\n", |
||
| 2182 | " .dataframe thead th {\n", |
||
| 2183 | " text-align: right;\n", |
||
| 2184 | " }\n", |
||
| 2185 | "</style>\n", |
||
| 2186 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 2187 | " <thead>\n", |
||
| 2188 | " <tr style=\"text-align: right;\">\n", |
||
| 2189 | " <th></th>\n", |
||
| 2190 | " <th></th>\n", |
||
| 2191 | " <th>val_loss</th>\n", |
||
| 2192 | " <th>val_w_loss</th>\n", |
||
| 2193 | " </tr>\n", |
||
| 2194 | " <tr>\n", |
||
| 2195 | " <th>dataset</th>\n", |
||
| 2196 | " <th>ver</th>\n", |
||
| 2197 | " <th></th>\n", |
||
| 2198 | " <th></th>\n", |
||
| 2199 | " </tr>\n", |
||
| 2200 | " </thead>\n", |
||
| 2201 | " <tbody>\n", |
||
| 2202 | " <tr>\n", |
||
| 2203 | " <td>7</td>\n", |
||
| 2204 | " <td>34</td>\n", |
||
| 2205 | " <td>0.062340</td>\n", |
||
| 2206 | " <td>0.060022</td>\n", |
||
| 2207 | " </tr>\n", |
||
| 2208 | " <tr>\n", |
||
| 2209 | " <td>9</td>\n", |
||
| 2210 | " <td>34</td>\n", |
||
| 2211 | " <td>0.061991</td>\n", |
||
| 2212 | " <td>0.059712</td>\n", |
||
| 2213 | " </tr>\n", |
||
| 2214 | " <tr>\n", |
||
| 2215 | " <td>11</td>\n", |
||
| 2216 | " <td>34</td>\n", |
||
| 2217 | " <td>0.060771</td>\n", |
||
| 2218 | " <td>0.058518</td>\n", |
||
| 2219 | " </tr>\n", |
||
| 2220 | " <tr>\n", |
||
| 2221 | " <td>12</td>\n", |
||
| 2222 | " <td>34</td>\n", |
||
| 2223 | " <td>0.060592</td>\n", |
||
| 2224 | " <td>0.058365</td>\n", |
||
| 2225 | " </tr>\n", |
||
| 2226 | " <tr>\n", |
||
| 2227 | " <td>13</td>\n", |
||
| 2228 | " <td>34</td>\n", |
||
| 2229 | " <td>0.060883</td>\n", |
||
| 2230 | " <td>0.058596</td>\n", |
||
| 2231 | " </tr>\n", |
||
| 2232 | " <tr>\n", |
||
| 2233 | " <td>14</td>\n", |
||
| 2234 | " <td>36</td>\n", |
||
| 2235 | " <td>0.060440</td>\n", |
||
| 2236 | " <td>0.058245</td>\n", |
||
| 2237 | " </tr>\n", |
||
| 2238 | " </tbody>\n", |
||
| 2239 | "</table>\n", |
||
| 2240 | "</div>" |
||
| 2241 | ], |
||
| 2242 | "text/plain": [ |
||
| 2243 | " val_loss val_w_loss\n", |
||
| 2244 | "dataset ver \n", |
||
| 2245 | "7 34 0.062340 0.060022\n", |
||
| 2246 | "9 34 0.061991 0.059712\n", |
||
| 2247 | "11 34 0.060771 0.058518\n", |
||
| 2248 | "12 34 0.060592 0.058365\n", |
||
| 2249 | "13 34 0.060883 0.058596\n", |
||
| 2250 | "14 36 0.060440 0.058245" |
||
| 2251 | ] |
||
| 2252 | }, |
||
| 2253 | "execution_count": 65, |
||
| 2254 | "metadata": {}, |
||
| 2255 | "output_type": "execute_result" |
||
| 2256 | } |
||
| 2257 | ], |
||
| 2258 | "source": [ |
||
| 2259 | "stats2.loc[stats2.epoch==3].groupby(['dataset','ver'])['val_loss','val_w_loss'].mean()" |
||
| 2260 | ] |
||
| 2261 | }, |
||
| 2262 | { |
||
| 2263 | "cell_type": "code", |
||
| 2264 | "execution_count": 19, |
||
| 2265 | "metadata": {}, |
||
| 2266 | "outputs": [], |
||
| 2267 | "source": [ |
||
| 2268 | "stats2 = stats2.loc[stats2.epoch==3]" |
||
| 2269 | ] |
||
| 2270 | }, |
||
| 2271 | { |
||
| 2272 | "cell_type": "code", |
||
| 2273 | "execution_count": 24, |
||
| 2274 | "metadata": {}, |
||
| 2275 | "outputs": [], |
||
| 2276 | "source": [ |
||
| 2277 | "stats1['weighted'] = False\n", |
||
| 2278 | "stats2['weighted'] = True" |
||
| 2279 | ] |
||
| 2280 | }, |
||
| 2281 | { |
||
| 2282 | "cell_type": "code", |
||
| 2283 | "execution_count": 25, |
||
| 2284 | "metadata": {}, |
||
| 2285 | "outputs": [], |
||
| 2286 | "source": [ |
||
| 2287 | "stats = pd.concat([stats1,stats2],axis=0,sort=False)" |
||
| 2288 | ] |
||
| 2289 | }, |
||
| 2290 | { |
||
| 2291 | "cell_type": "code", |
||
| 2292 | "execution_count": 28, |
||
| 2293 | "metadata": {}, |
||
| 2294 | "outputs": [], |
||
| 2295 | "source": [ |
||
| 2296 | "stats['name'] = [getDSName(ds) for ds in stats.dataset.values]" |
||
| 2297 | ] |
||
| 2298 | }, |
||
| 2299 | { |
||
| 2300 | "cell_type": "code", |
||
| 2301 | "execution_count": 31, |
||
| 2302 | "metadata": {}, |
||
| 2303 | "outputs": [], |
||
| 2304 | "source": [ |
||
| 2305 | "stats['type'] = np.where(stats.ver.isin([31,32]), 'old feats, no stage1', \n", |
||
| 2306 | " np.where(stats.ver.isin([33,34]), 'old feats, with stage1', 'new feats, with stage 1'))" |
||
| 2307 | ] |
||
| 2308 | }, |
||
| 2309 | { |
||
| 2310 | "cell_type": "code", |
||
| 2311 | "execution_count": 41, |
||
| 2312 | "metadata": {}, |
||
| 2313 | "outputs": [], |
||
| 2314 | "source": [ |
||
| 2315 | "stats['name'] = pd.Categorical(stats['name'], \\\n", |
||
| 2316 | " ['Densenet161_F3','se_resnext101_32x4d_F3','se_resnet101_F5','se_resnet101_focal_F5','se_resnext101_32x4d_F5'])" |
||
| 2317 | ] |
||
| 2318 | }, |
||
| 2319 | { |
||
| 2320 | "cell_type": "code", |
||
| 2321 | "execution_count": 40, |
||
| 2322 | "metadata": {}, |
||
| 2323 | "outputs": [], |
||
| 2324 | "source": [ |
||
| 2325 | "stats['type'] = pd.Categorical(stats['type'], \\\n", |
||
| 2326 | " ['old feats, no stage1', 'old feats, with stage1', 'new feats, with stage 1'])" |
||
| 2327 | ] |
||
| 2328 | }, |
||
| 2329 | { |
||
| 2330 | "cell_type": "code", |
||
| 2331 | "execution_count": 44, |
||
| 2332 | "metadata": {}, |
||
| 2333 | "outputs": [], |
||
| 2334 | "source": [ |
||
| 2335 | "stats.val_loss2 = np.where(stats.val_loss2 == 0, np.nan, stats.val_loss2)\n", |
||
| 2336 | "stats.val_w_loss2 = np.where(stats.val_w_loss2 == 0, np.nan, stats.val_w_loss2)" |
||
| 2337 | ] |
||
| 2338 | }, |
||
| 2339 | { |
||
| 2340 | "cell_type": "code", |
||
| 2341 | "execution_count": 46, |
||
| 2342 | "metadata": {}, |
||
| 2343 | "outputs": [ |
||
| 2344 | { |
||
| 2345 | "data": { |
||
| 2346 | "text/html": [ |
||
| 2347 | "<div>\n", |
||
| 2348 | "<style scoped>\n", |
||
| 2349 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 2350 | " vertical-align: middle;\n", |
||
| 2351 | " }\n", |
||
| 2352 | "\n", |
||
| 2353 | " .dataframe tbody tr th {\n", |
||
| 2354 | " vertical-align: top;\n", |
||
| 2355 | " }\n", |
||
| 2356 | "\n", |
||
| 2357 | " .dataframe thead th {\n", |
||
| 2358 | " text-align: right;\n", |
||
| 2359 | " }\n", |
||
| 2360 | "</style>\n", |
||
| 2361 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 2362 | " <thead>\n", |
||
| 2363 | " <tr style=\"text-align: right;\">\n", |
||
| 2364 | " <th></th>\n", |
||
| 2365 | " <th></th>\n", |
||
| 2366 | " <th></th>\n", |
||
| 2367 | " <th>val_loss</th>\n", |
||
| 2368 | " <th>val_w_loss</th>\n", |
||
| 2369 | " <th>val_loss2</th>\n", |
||
| 2370 | " <th>val_w_loss2</th>\n", |
||
| 2371 | " </tr>\n", |
||
| 2372 | " <tr>\n", |
||
| 2373 | " <th>name</th>\n", |
||
| 2374 | " <th>weighted</th>\n", |
||
| 2375 | " <th>type</th>\n", |
||
| 2376 | " <th></th>\n", |
||
| 2377 | " <th></th>\n", |
||
| 2378 | " <th></th>\n", |
||
| 2379 | " <th></th>\n", |
||
| 2380 | " </tr>\n", |
||
| 2381 | " </thead>\n", |
||
| 2382 | " <tbody>\n", |
||
| 2383 | " <tr>\n", |
||
| 2384 | " <td rowspan=\"6\" valign=\"top\">Densenet161_F3</td>\n", |
||
| 2385 | " <td rowspan=\"3\" valign=\"top\">False</td>\n", |
||
| 2386 | " <td>old feats, no stage1</td>\n", |
||
| 2387 | " <td>0.062832</td>\n", |
||
| 2388 | " <td>0.060421</td>\n", |
||
| 2389 | " <td>NaN</td>\n", |
||
| 2390 | " <td>NaN</td>\n", |
||
| 2391 | " </tr>\n", |
||
| 2392 | " <tr>\n", |
||
| 2393 | " <td>old feats, with stage1</td>\n", |
||
| 2394 | " <td>0.062216</td>\n", |
||
| 2395 | " <td>0.059966</td>\n", |
||
| 2396 | " <td>0.063667</td>\n", |
||
| 2397 | " <td>0.045864</td>\n", |
||
| 2398 | " </tr>\n", |
||
| 2399 | " <tr>\n", |
||
| 2400 | " <td>new feats, with stage 1</td>\n", |
||
| 2401 | " <td>NaN</td>\n", |
||
| 2402 | " <td>NaN</td>\n", |
||
| 2403 | " <td>NaN</td>\n", |
||
| 2404 | " <td>NaN</td>\n", |
||
| 2405 | " </tr>\n", |
||
| 2406 | " <tr>\n", |
||
| 2407 | " <td rowspan=\"3\" valign=\"top\">True</td>\n", |
||
| 2408 | " <td>old feats, no stage1</td>\n", |
||
| 2409 | " <td>NaN</td>\n", |
||
| 2410 | " <td>NaN</td>\n", |
||
| 2411 | " <td>NaN</td>\n", |
||
| 2412 | " <td>NaN</td>\n", |
||
| 2413 | " </tr>\n", |
||
| 2414 | " <tr>\n", |
||
| 2415 | " <td>old feats, with stage1</td>\n", |
||
| 2416 | " <td>0.062340</td>\n", |
||
| 2417 | " <td>0.060022</td>\n", |
||
| 2418 | " <td>0.064111</td>\n", |
||
| 2419 | " <td>0.045960</td>\n", |
||
| 2420 | " </tr>\n", |
||
| 2421 | " <tr>\n", |
||
| 2422 | " <td>new feats, with stage 1</td>\n", |
||
| 2423 | " <td>NaN</td>\n", |
||
| 2424 | " <td>NaN</td>\n", |
||
| 2425 | " <td>NaN</td>\n", |
||
| 2426 | " <td>NaN</td>\n", |
||
| 2427 | " </tr>\n", |
||
| 2428 | " <tr>\n", |
||
| 2429 | " <td rowspan=\"6\" valign=\"top\">se_resnext101_32x4d_F3</td>\n", |
||
| 2430 | " <td rowspan=\"3\" valign=\"top\">False</td>\n", |
||
| 2431 | " <td>old feats, no stage1</td>\n", |
||
| 2432 | " <td>0.062391</td>\n", |
||
| 2433 | " <td>0.060030</td>\n", |
||
| 2434 | " <td>NaN</td>\n", |
||
| 2435 | " <td>NaN</td>\n", |
||
| 2436 | " </tr>\n", |
||
| 2437 | " <tr>\n", |
||
| 2438 | " <td>old feats, with stage1</td>\n", |
||
| 2439 | " <td>0.061798</td>\n", |
||
| 2440 | " <td>0.059631</td>\n", |
||
| 2441 | " <td>0.063498</td>\n", |
||
| 2442 | " <td>0.045743</td>\n", |
||
| 2443 | " </tr>\n", |
||
| 2444 | " <tr>\n", |
||
| 2445 | " <td>new feats, with stage 1</td>\n", |
||
| 2446 | " <td>NaN</td>\n", |
||
| 2447 | " <td>NaN</td>\n", |
||
| 2448 | " <td>NaN</td>\n", |
||
| 2449 | " <td>NaN</td>\n", |
||
| 2450 | " </tr>\n", |
||
| 2451 | " <tr>\n", |
||
| 2452 | " <td rowspan=\"3\" valign=\"top\">True</td>\n", |
||
| 2453 | " <td>old feats, no stage1</td>\n", |
||
| 2454 | " <td>NaN</td>\n", |
||
| 2455 | " <td>NaN</td>\n", |
||
| 2456 | " <td>NaN</td>\n", |
||
| 2457 | " <td>NaN</td>\n", |
||
| 2458 | " </tr>\n", |
||
| 2459 | " <tr>\n", |
||
| 2460 | " <td>old feats, with stage1</td>\n", |
||
| 2461 | " <td>0.061991</td>\n", |
||
| 2462 | " <td>0.059712</td>\n", |
||
| 2463 | " <td>0.064051</td>\n", |
||
| 2464 | " <td>0.045793</td>\n", |
||
| 2465 | " </tr>\n", |
||
| 2466 | " <tr>\n", |
||
| 2467 | " <td>new feats, with stage 1</td>\n", |
||
| 2468 | " <td>NaN</td>\n", |
||
| 2469 | " <td>NaN</td>\n", |
||
| 2470 | " <td>NaN</td>\n", |
||
| 2471 | " <td>NaN</td>\n", |
||
| 2472 | " </tr>\n", |
||
| 2473 | " <tr>\n", |
||
| 2474 | " <td rowspan=\"6\" valign=\"top\">se_resnet101_F5</td>\n", |
||
| 2475 | " <td rowspan=\"3\" valign=\"top\">False</td>\n", |
||
| 2476 | " <td>old feats, no stage1</td>\n", |
||
| 2477 | " <td>0.060777</td>\n", |
||
| 2478 | " <td>0.058524</td>\n", |
||
| 2479 | " <td>NaN</td>\n", |
||
| 2480 | " <td>NaN</td>\n", |
||
| 2481 | " </tr>\n", |
||
| 2482 | " <tr>\n", |
||
| 2483 | " <td>old feats, with stage1</td>\n", |
||
| 2484 | " <td>0.060435</td>\n", |
||
| 2485 | " <td>0.058339</td>\n", |
||
| 2486 | " <td>0.062473</td>\n", |
||
| 2487 | " <td>0.045330</td>\n", |
||
| 2488 | " </tr>\n", |
||
| 2489 | " <tr>\n", |
||
| 2490 | " <td>new feats, with stage 1</td>\n", |
||
| 2491 | " <td>0.060279</td>\n", |
||
| 2492 | " <td>0.058197</td>\n", |
||
| 2493 | " <td>0.059201</td>\n", |
||
| 2494 | " <td>0.042987</td>\n", |
||
| 2495 | " </tr>\n", |
||
| 2496 | " <tr>\n", |
||
| 2497 | " <td rowspan=\"3\" valign=\"top\">True</td>\n", |
||
| 2498 | " <td>old feats, no stage1</td>\n", |
||
| 2499 | " <td>NaN</td>\n", |
||
| 2500 | " <td>NaN</td>\n", |
||
| 2501 | " <td>NaN</td>\n", |
||
| 2502 | " <td>NaN</td>\n", |
||
| 2503 | " </tr>\n", |
||
| 2504 | " <tr>\n", |
||
| 2505 | " <td>old feats, with stage1</td>\n", |
||
| 2506 | " <td>0.060592</td>\n", |
||
| 2507 | " <td>0.058365</td>\n", |
||
| 2508 | " <td>0.063225</td>\n", |
||
| 2509 | " <td>0.045505</td>\n", |
||
| 2510 | " </tr>\n", |
||
| 2511 | " <tr>\n", |
||
| 2512 | " <td>new feats, with stage 1</td>\n", |
||
| 2513 | " <td>0.060440</td>\n", |
||
| 2514 | " <td>0.058245</td>\n", |
||
| 2515 | " <td>0.059749</td>\n", |
||
| 2516 | " <td>0.043057</td>\n", |
||
| 2517 | " </tr>\n", |
||
| 2518 | " <tr>\n", |
||
| 2519 | " <td rowspan=\"6\" valign=\"top\">se_resnet101_focal_F5</td>\n", |
||
| 2520 | " <td rowspan=\"3\" valign=\"top\">False</td>\n", |
||
| 2521 | " <td>old feats, no stage1</td>\n", |
||
| 2522 | " <td>0.061076</td>\n", |
||
| 2523 | " <td>0.058784</td>\n", |
||
| 2524 | " <td>NaN</td>\n", |
||
| 2525 | " <td>NaN</td>\n", |
||
| 2526 | " </tr>\n", |
||
| 2527 | " <tr>\n", |
||
| 2528 | " <td>old feats, with stage1</td>\n", |
||
| 2529 | " <td>0.060730</td>\n", |
||
| 2530 | " <td>0.058572</td>\n", |
||
| 2531 | " <td>0.062898</td>\n", |
||
| 2532 | " <td>0.045629</td>\n", |
||
| 2533 | " </tr>\n", |
||
| 2534 | " <tr>\n", |
||
| 2535 | " <td>new feats, with stage 1</td>\n", |
||
| 2536 | " <td>NaN</td>\n", |
||
| 2537 | " <td>NaN</td>\n", |
||
| 2538 | " <td>NaN</td>\n", |
||
| 2539 | " <td>NaN</td>\n", |
||
| 2540 | " </tr>\n", |
||
| 2541 | " <tr>\n", |
||
| 2542 | " <td rowspan=\"3\" valign=\"top\">True</td>\n", |
||
| 2543 | " <td>old feats, no stage1</td>\n", |
||
| 2544 | " <td>NaN</td>\n", |
||
| 2545 | " <td>NaN</td>\n", |
||
| 2546 | " <td>NaN</td>\n", |
||
| 2547 | " <td>NaN</td>\n", |
||
| 2548 | " </tr>\n", |
||
| 2549 | " <tr>\n", |
||
| 2550 | " <td>old feats, with stage1</td>\n", |
||
| 2551 | " <td>0.060883</td>\n", |
||
| 2552 | " <td>0.058596</td>\n", |
||
| 2553 | " <td>0.063621</td>\n", |
||
| 2554 | " <td>0.045774</td>\n", |
||
| 2555 | " </tr>\n", |
||
| 2556 | " <tr>\n", |
||
| 2557 | " <td>new feats, with stage 1</td>\n", |
||
| 2558 | " <td>NaN</td>\n", |
||
| 2559 | " <td>NaN</td>\n", |
||
| 2560 | " <td>NaN</td>\n", |
||
| 2561 | " <td>NaN</td>\n", |
||
| 2562 | " </tr>\n", |
||
| 2563 | " <tr>\n", |
||
| 2564 | " <td rowspan=\"6\" valign=\"top\">se_resnext101_32x4d_F5</td>\n", |
||
| 2565 | " <td rowspan=\"3\" valign=\"top\">False</td>\n", |
||
| 2566 | " <td>old feats, no stage1</td>\n", |
||
| 2567 | " <td>0.061160</td>\n", |
||
| 2568 | " <td>0.058838</td>\n", |
||
| 2569 | " <td>NaN</td>\n", |
||
| 2570 | " <td>NaN</td>\n", |
||
| 2571 | " </tr>\n", |
||
| 2572 | " <tr>\n", |
||
| 2573 | " <td>old feats, with stage1</td>\n", |
||
| 2574 | " <td>0.060567</td>\n", |
||
| 2575 | " <td>0.058444</td>\n", |
||
| 2576 | " <td>0.063178</td>\n", |
||
| 2577 | " <td>0.045846</td>\n", |
||
| 2578 | " </tr>\n", |
||
| 2579 | " <tr>\n", |
||
| 2580 | " <td>new feats, with stage 1</td>\n", |
||
| 2581 | " <td>NaN</td>\n", |
||
| 2582 | " <td>NaN</td>\n", |
||
| 2583 | " <td>NaN</td>\n", |
||
| 2584 | " <td>NaN</td>\n", |
||
| 2585 | " </tr>\n", |
||
| 2586 | " <tr>\n", |
||
| 2587 | " <td rowspan=\"3\" valign=\"top\">True</td>\n", |
||
| 2588 | " <td>old feats, no stage1</td>\n", |
||
| 2589 | " <td>NaN</td>\n", |
||
| 2590 | " <td>NaN</td>\n", |
||
| 2591 | " <td>NaN</td>\n", |
||
| 2592 | " <td>NaN</td>\n", |
||
| 2593 | " </tr>\n", |
||
| 2594 | " <tr>\n", |
||
| 2595 | " <td>old feats, with stage1</td>\n", |
||
| 2596 | " <td>0.060771</td>\n", |
||
| 2597 | " <td>0.058518</td>\n", |
||
| 2598 | " <td>0.063957</td>\n", |
||
| 2599 | " <td>0.046079</td>\n", |
||
| 2600 | " </tr>\n", |
||
| 2601 | " <tr>\n", |
||
| 2602 | " <td>new feats, with stage 1</td>\n", |
||
| 2603 | " <td>NaN</td>\n", |
||
| 2604 | " <td>NaN</td>\n", |
||
| 2605 | " <td>NaN</td>\n", |
||
| 2606 | " <td>NaN</td>\n", |
||
| 2607 | " </tr>\n", |
||
| 2608 | " </tbody>\n", |
||
| 2609 | "</table>\n", |
||
| 2610 | "</div>" |
||
| 2611 | ], |
||
| 2612 | "text/plain": [ |
||
| 2613 | " val_loss val_w_loss \\\n", |
||
| 2614 | "name weighted type \n", |
||
| 2615 | "Densenet161_F3 False old feats, no stage1 0.062832 0.060421 \n", |
||
| 2616 | " old feats, with stage1 0.062216 0.059966 \n", |
||
| 2617 | " new feats, with stage 1 NaN NaN \n", |
||
| 2618 | " True old feats, no stage1 NaN NaN \n", |
||
| 2619 | " old feats, with stage1 0.062340 0.060022 \n", |
||
| 2620 | " new feats, with stage 1 NaN NaN \n", |
||
| 2621 | "se_resnext101_32x4d_F3 False old feats, no stage1 0.062391 0.060030 \n", |
||
| 2622 | " old feats, with stage1 0.061798 0.059631 \n", |
||
| 2623 | " new feats, with stage 1 NaN NaN \n", |
||
| 2624 | " True old feats, no stage1 NaN NaN \n", |
||
| 2625 | " old feats, with stage1 0.061991 0.059712 \n", |
||
| 2626 | " new feats, with stage 1 NaN NaN \n", |
||
| 2627 | "se_resnet101_F5 False old feats, no stage1 0.060777 0.058524 \n", |
||
| 2628 | " old feats, with stage1 0.060435 0.058339 \n", |
||
| 2629 | " new feats, with stage 1 0.060279 0.058197 \n", |
||
| 2630 | " True old feats, no stage1 NaN NaN \n", |
||
| 2631 | " old feats, with stage1 0.060592 0.058365 \n", |
||
| 2632 | " new feats, with stage 1 0.060440 0.058245 \n", |
||
| 2633 | "se_resnet101_focal_F5 False old feats, no stage1 0.061076 0.058784 \n", |
||
| 2634 | " old feats, with stage1 0.060730 0.058572 \n", |
||
| 2635 | " new feats, with stage 1 NaN NaN \n", |
||
| 2636 | " True old feats, no stage1 NaN NaN \n", |
||
| 2637 | " old feats, with stage1 0.060883 0.058596 \n", |
||
| 2638 | " new feats, with stage 1 NaN NaN \n", |
||
| 2639 | "se_resnext101_32x4d_F5 False old feats, no stage1 0.061160 0.058838 \n", |
||
| 2640 | " old feats, with stage1 0.060567 0.058444 \n", |
||
| 2641 | " new feats, with stage 1 NaN NaN \n", |
||
| 2642 | " True old feats, no stage1 NaN NaN \n", |
||
| 2643 | " old feats, with stage1 0.060771 0.058518 \n", |
||
| 2644 | " new feats, with stage 1 NaN NaN \n", |
||
| 2645 | "\n", |
||
| 2646 | " val_loss2 \\\n", |
||
| 2647 | "name weighted type \n", |
||
| 2648 | "Densenet161_F3 False old feats, no stage1 NaN \n", |
||
| 2649 | " old feats, with stage1 0.063667 \n", |
||
| 2650 | " new feats, with stage 1 NaN \n", |
||
| 2651 | " True old feats, no stage1 NaN \n", |
||
| 2652 | " old feats, with stage1 0.064111 \n", |
||
| 2653 | " new feats, with stage 1 NaN \n", |
||
| 2654 | "se_resnext101_32x4d_F3 False old feats, no stage1 NaN \n", |
||
| 2655 | " old feats, with stage1 0.063498 \n", |
||
| 2656 | " new feats, with stage 1 NaN \n", |
||
| 2657 | " True old feats, no stage1 NaN \n", |
||
| 2658 | " old feats, with stage1 0.064051 \n", |
||
| 2659 | " new feats, with stage 1 NaN \n", |
||
| 2660 | "se_resnet101_F5 False old feats, no stage1 NaN \n", |
||
| 2661 | " old feats, with stage1 0.062473 \n", |
||
| 2662 | " new feats, with stage 1 0.059201 \n", |
||
| 2663 | " True old feats, no stage1 NaN \n", |
||
| 2664 | " old feats, with stage1 0.063225 \n", |
||
| 2665 | " new feats, with stage 1 0.059749 \n", |
||
| 2666 | "se_resnet101_focal_F5 False old feats, no stage1 NaN \n", |
||
| 2667 | " old feats, with stage1 0.062898 \n", |
||
| 2668 | " new feats, with stage 1 NaN \n", |
||
| 2669 | " True old feats, no stage1 NaN \n", |
||
| 2670 | " old feats, with stage1 0.063621 \n", |
||
| 2671 | " new feats, with stage 1 NaN \n", |
||
| 2672 | "se_resnext101_32x4d_F5 False old feats, no stage1 NaN \n", |
||
| 2673 | " old feats, with stage1 0.063178 \n", |
||
| 2674 | " new feats, with stage 1 NaN \n", |
||
| 2675 | " True old feats, no stage1 NaN \n", |
||
| 2676 | " old feats, with stage1 0.063957 \n", |
||
| 2677 | " new feats, with stage 1 NaN \n", |
||
| 2678 | "\n", |
||
| 2679 | " val_w_loss2 \n", |
||
| 2680 | "name weighted type \n", |
||
| 2681 | "Densenet161_F3 False old feats, no stage1 NaN \n", |
||
| 2682 | " old feats, with stage1 0.045864 \n", |
||
| 2683 | " new feats, with stage 1 NaN \n", |
||
| 2684 | " True old feats, no stage1 NaN \n", |
||
| 2685 | " old feats, with stage1 0.045960 \n", |
||
| 2686 | " new feats, with stage 1 NaN \n", |
||
| 2687 | "se_resnext101_32x4d_F3 False old feats, no stage1 NaN \n", |
||
| 2688 | " old feats, with stage1 0.045743 \n", |
||
| 2689 | " new feats, with stage 1 NaN \n", |
||
| 2690 | " True old feats, no stage1 NaN \n", |
||
| 2691 | " old feats, with stage1 0.045793 \n", |
||
| 2692 | " new feats, with stage 1 NaN \n", |
||
| 2693 | "se_resnet101_F5 False old feats, no stage1 NaN \n", |
||
| 2694 | " old feats, with stage1 0.045330 \n", |
||
| 2695 | " new feats, with stage 1 0.042987 \n", |
||
| 2696 | " True old feats, no stage1 NaN \n", |
||
| 2697 | " old feats, with stage1 0.045505 \n", |
||
| 2698 | " new feats, with stage 1 0.043057 \n", |
||
| 2699 | "se_resnet101_focal_F5 False old feats, no stage1 NaN \n", |
||
| 2700 | " old feats, with stage1 0.045629 \n", |
||
| 2701 | " new feats, with stage 1 NaN \n", |
||
| 2702 | " True old feats, no stage1 NaN \n", |
||
| 2703 | " old feats, with stage1 0.045774 \n", |
||
| 2704 | " new feats, with stage 1 NaN \n", |
||
| 2705 | "se_resnext101_32x4d_F5 False old feats, no stage1 NaN \n", |
||
| 2706 | " old feats, with stage1 0.045846 \n", |
||
| 2707 | " new feats, with stage 1 NaN \n", |
||
| 2708 | " True old feats, no stage1 NaN \n", |
||
| 2709 | " old feats, with stage1 0.046079 \n", |
||
| 2710 | " new feats, with stage 1 NaN " |
||
| 2711 | ] |
||
| 2712 | }, |
||
| 2713 | "execution_count": 46, |
||
| 2714 | "metadata": {}, |
||
| 2715 | "output_type": "execute_result" |
||
| 2716 | } |
||
| 2717 | ], |
||
| 2718 | "source": [ |
||
| 2719 | "stats.groupby(['name','weighted','type'])['val_loss','val_w_loss','val_loss2','val_w_loss2'].mean()" |
||
| 2720 | ] |
||
| 2721 | }, |
||
| 2722 | { |
||
| 2723 | "cell_type": "code", |
||
| 2724 | "execution_count": 53, |
||
| 2725 | "metadata": { |
||
| 2726 | "scrolled": false |
||
| 2727 | }, |
||
| 2728 | "outputs": [ |
||
| 2729 | { |
||
| 2730 | "data": { |
||
| 2731 | "text/html": [ |
||
| 2732 | "<div>\n", |
||
| 2733 | "<style scoped>\n", |
||
| 2734 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 2735 | " vertical-align: middle;\n", |
||
| 2736 | " }\n", |
||
| 2737 | "\n", |
||
| 2738 | " .dataframe tbody tr th {\n", |
||
| 2739 | " vertical-align: top;\n", |
||
| 2740 | " }\n", |
||
| 2741 | "\n", |
||
| 2742 | " .dataframe thead th {\n", |
||
| 2743 | " text-align: right;\n", |
||
| 2744 | " }\n", |
||
| 2745 | "</style>\n", |
||
| 2746 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 2747 | " <thead>\n", |
||
| 2748 | " <tr style=\"text-align: right;\">\n", |
||
| 2749 | " <th></th>\n", |
||
| 2750 | " <th></th>\n", |
||
| 2751 | " <th></th>\n", |
||
| 2752 | " <th>val_loss</th>\n", |
||
| 2753 | " <th>val_w_loss</th>\n", |
||
| 2754 | " <th>val_loss2</th>\n", |
||
| 2755 | " <th>val_w_loss2</th>\n", |
||
| 2756 | " </tr>\n", |
||
| 2757 | " <tr>\n", |
||
| 2758 | " <th>fold</th>\n", |
||
| 2759 | " <th>weighted</th>\n", |
||
| 2760 | " <th>type</th>\n", |
||
| 2761 | " <th></th>\n", |
||
| 2762 | " <th></th>\n", |
||
| 2763 | " <th></th>\n", |
||
| 2764 | " <th></th>\n", |
||
| 2765 | " </tr>\n", |
||
| 2766 | " </thead>\n", |
||
| 2767 | " <tbody>\n", |
||
| 2768 | " <tr>\n", |
||
| 2769 | " <td rowspan=\"6\" valign=\"top\">0</td>\n", |
||
| 2770 | " <td rowspan=\"3\" valign=\"top\">False</td>\n", |
||
| 2771 | " <td>old feats, no stage1</td>\n", |
||
| 2772 | " <td>0.059207</td>\n", |
||
| 2773 | " <td>0.057173</td>\n", |
||
| 2774 | " <td>NaN</td>\n", |
||
| 2775 | " <td>NaN</td>\n", |
||
| 2776 | " </tr>\n", |
||
| 2777 | " <tr>\n", |
||
| 2778 | " <td>old feats, with stage1</td>\n", |
||
| 2779 | " <td>0.059376</td>\n", |
||
| 2780 | " <td>0.057322</td>\n", |
||
| 2781 | " <td>0.071586</td>\n", |
||
| 2782 | " <td>0.052126</td>\n", |
||
| 2783 | " </tr>\n", |
||
| 2784 | " <tr>\n", |
||
| 2785 | " <td>new feats, with stage 1</td>\n", |
||
| 2786 | " <td>0.059336</td>\n", |
||
| 2787 | " <td>0.057380</td>\n", |
||
| 2788 | " <td>0.067331</td>\n", |
||
| 2789 | " <td>0.048938</td>\n", |
||
| 2790 | " </tr>\n", |
||
| 2791 | " <tr>\n", |
||
| 2792 | " <td rowspan=\"3\" valign=\"top\">True</td>\n", |
||
| 2793 | " <td>old feats, no stage1</td>\n", |
||
| 2794 | " <td>NaN</td>\n", |
||
| 2795 | " <td>NaN</td>\n", |
||
| 2796 | " <td>NaN</td>\n", |
||
| 2797 | " <td>NaN</td>\n", |
||
| 2798 | " </tr>\n", |
||
| 2799 | " <tr>\n", |
||
| 2800 | " <td>old feats, with stage1</td>\n", |
||
| 2801 | " <td>0.059580</td>\n", |
||
| 2802 | " <td>0.057412</td>\n", |
||
| 2803 | " <td>0.072157</td>\n", |
||
| 2804 | " <td>0.052435</td>\n", |
||
| 2805 | " </tr>\n", |
||
| 2806 | " <tr>\n", |
||
| 2807 | " <td>new feats, with stage 1</td>\n", |
||
| 2808 | " <td>0.059511</td>\n", |
||
| 2809 | " <td>0.057492</td>\n", |
||
| 2810 | " <td>0.067691</td>\n", |
||
| 2811 | " <td>0.049024</td>\n", |
||
| 2812 | " </tr>\n", |
||
| 2813 | " <tr>\n", |
||
| 2814 | " <td rowspan=\"6\" valign=\"top\">1</td>\n", |
||
| 2815 | " <td rowspan=\"3\" valign=\"top\">False</td>\n", |
||
| 2816 | " <td>old feats, no stage1</td>\n", |
||
| 2817 | " <td>0.059903</td>\n", |
||
| 2818 | " <td>0.058524</td>\n", |
||
| 2819 | " <td>NaN</td>\n", |
||
| 2820 | " <td>NaN</td>\n", |
||
| 2821 | " </tr>\n", |
||
| 2822 | " <tr>\n", |
||
| 2823 | " <td>old feats, with stage1</td>\n", |
||
| 2824 | " <td>0.059548</td>\n", |
||
| 2825 | " <td>0.058294</td>\n", |
||
| 2826 | " <td>0.055482</td>\n", |
||
| 2827 | " <td>0.040188</td>\n", |
||
| 2828 | " </tr>\n", |
||
| 2829 | " <tr>\n", |
||
| 2830 | " <td>new feats, with stage 1</td>\n", |
||
| 2831 | " <td>0.059209</td>\n", |
||
| 2832 | " <td>0.057936</td>\n", |
||
| 2833 | " <td>0.052200</td>\n", |
||
| 2834 | " <td>0.038043</td>\n", |
||
| 2835 | " </tr>\n", |
||
| 2836 | " <tr>\n", |
||
| 2837 | " <td rowspan=\"3\" valign=\"top\">True</td>\n", |
||
| 2838 | " <td>old feats, no stage1</td>\n", |
||
| 2839 | " <td>NaN</td>\n", |
||
| 2840 | " <td>NaN</td>\n", |
||
| 2841 | " <td>NaN</td>\n", |
||
| 2842 | " <td>NaN</td>\n", |
||
| 2843 | " </tr>\n", |
||
| 2844 | " <tr>\n", |
||
| 2845 | " <td>old feats, with stage1</td>\n", |
||
| 2846 | " <td>0.059670</td>\n", |
||
| 2847 | " <td>0.058308</td>\n", |
||
| 2848 | " <td>0.056408</td>\n", |
||
| 2849 | " <td>0.040399</td>\n", |
||
| 2850 | " </tr>\n", |
||
| 2851 | " <tr>\n", |
||
| 2852 | " <td>new feats, with stage 1</td>\n", |
||
| 2853 | " <td>0.059323</td>\n", |
||
| 2854 | " <td>0.057955</td>\n", |
||
| 2855 | " <td>0.052909</td>\n", |
||
| 2856 | " <td>0.038214</td>\n", |
||
| 2857 | " </tr>\n", |
||
| 2858 | " <tr>\n", |
||
| 2859 | " <td rowspan=\"6\" valign=\"top\">2</td>\n", |
||
| 2860 | " <td rowspan=\"3\" valign=\"top\">False</td>\n", |
||
| 2861 | " <td>old feats, no stage1</td>\n", |
||
| 2862 | " <td>0.060600</td>\n", |
||
| 2863 | " <td>0.057828</td>\n", |
||
| 2864 | " <td>NaN</td>\n", |
||
| 2865 | " <td>NaN</td>\n", |
||
| 2866 | " </tr>\n", |
||
| 2867 | " <tr>\n", |
||
| 2868 | " <td>old feats, with stage1</td>\n", |
||
| 2869 | " <td>0.060391</td>\n", |
||
| 2870 | " <td>0.057761</td>\n", |
||
| 2871 | " <td>0.056373</td>\n", |
||
| 2872 | " <td>0.040194</td>\n", |
||
| 2873 | " </tr>\n", |
||
| 2874 | " <tr>\n", |
||
| 2875 | " <td>new feats, with stage 1</td>\n", |
||
| 2876 | " <td>0.059884</td>\n", |
||
| 2877 | " <td>0.057178</td>\n", |
||
| 2878 | " <td>0.053371</td>\n", |
||
| 2879 | " <td>0.037849</td>\n", |
||
| 2880 | " </tr>\n", |
||
| 2881 | " <tr>\n", |
||
| 2882 | " <td rowspan=\"3\" valign=\"top\">True</td>\n", |
||
| 2883 | " <td>old feats, no stage1</td>\n", |
||
| 2884 | " <td>NaN</td>\n", |
||
| 2885 | " <td>NaN</td>\n", |
||
| 2886 | " <td>NaN</td>\n", |
||
| 2887 | " <td>NaN</td>\n", |
||
| 2888 | " </tr>\n", |
||
| 2889 | " <tr>\n", |
||
| 2890 | " <td>old feats, with stage1</td>\n", |
||
| 2891 | " <td>0.060492</td>\n", |
||
| 2892 | " <td>0.057737</td>\n", |
||
| 2893 | " <td>0.056875</td>\n", |
||
| 2894 | " <td>0.040117</td>\n", |
||
| 2895 | " </tr>\n", |
||
| 2896 | " <tr>\n", |
||
| 2897 | " <td>new feats, with stage 1</td>\n", |
||
| 2898 | " <td>0.060004</td>\n", |
||
| 2899 | " <td>0.057138</td>\n", |
||
| 2900 | " <td>0.053842</td>\n", |
||
| 2901 | " <td>0.037853</td>\n", |
||
| 2902 | " </tr>\n", |
||
| 2903 | " <tr>\n", |
||
| 2904 | " <td rowspan=\"6\" valign=\"top\">3</td>\n", |
||
| 2905 | " <td rowspan=\"3\" valign=\"top\">False</td>\n", |
||
| 2906 | " <td>old feats, no stage1</td>\n", |
||
| 2907 | " <td>0.062978</td>\n", |
||
| 2908 | " <td>0.060445</td>\n", |
||
| 2909 | " <td>NaN</td>\n", |
||
| 2910 | " <td>NaN</td>\n", |
||
| 2911 | " </tr>\n", |
||
| 2912 | " <tr>\n", |
||
| 2913 | " <td>old feats, with stage1</td>\n", |
||
| 2914 | " <td>0.062238</td>\n", |
||
| 2915 | " <td>0.060029</td>\n", |
||
| 2916 | " <td>0.063756</td>\n", |
||
| 2917 | " <td>0.045654</td>\n", |
||
| 2918 | " </tr>\n", |
||
| 2919 | " <tr>\n", |
||
| 2920 | " <td>new feats, with stage 1</td>\n", |
||
| 2921 | " <td>0.062283</td>\n", |
||
| 2922 | " <td>0.060144</td>\n", |
||
| 2923 | " <td>0.062267</td>\n", |
||
| 2924 | " <td>0.044982</td>\n", |
||
| 2925 | " </tr>\n", |
||
| 2926 | " <tr>\n", |
||
| 2927 | " <td rowspan=\"3\" valign=\"top\">True</td>\n", |
||
| 2928 | " <td>old feats, no stage1</td>\n", |
||
| 2929 | " <td>NaN</td>\n", |
||
| 2930 | " <td>NaN</td>\n", |
||
| 2931 | " <td>NaN</td>\n", |
||
| 2932 | " <td>NaN</td>\n", |
||
| 2933 | " </tr>\n", |
||
| 2934 | " <tr>\n", |
||
| 2935 | " <td>old feats, with stage1</td>\n", |
||
| 2936 | " <td>0.062409</td>\n", |
||
| 2937 | " <td>0.060069</td>\n", |
||
| 2938 | " <td>0.064277</td>\n", |
||
| 2939 | " <td>0.045677</td>\n", |
||
| 2940 | " </tr>\n", |
||
| 2941 | " <tr>\n", |
||
| 2942 | " <td>new feats, with stage 1</td>\n", |
||
| 2943 | " <td>0.062372</td>\n", |
||
| 2944 | " <td>0.060134</td>\n", |
||
| 2945 | " <td>0.062729</td>\n", |
||
| 2946 | " <td>0.044978</td>\n", |
||
| 2947 | " </tr>\n", |
||
| 2948 | " <tr>\n", |
||
| 2949 | " <td rowspan=\"6\" valign=\"top\">4</td>\n", |
||
| 2950 | " <td rowspan=\"3\" valign=\"top\">False</td>\n", |
||
| 2951 | " <td>old feats, no stage1</td>\n", |
||
| 2952 | " <td>0.061198</td>\n", |
||
| 2953 | " <td>0.058650</td>\n", |
||
| 2954 | " <td>NaN</td>\n", |
||
| 2955 | " <td>NaN</td>\n", |
||
| 2956 | " </tr>\n", |
||
| 2957 | " <tr>\n", |
||
| 2958 | " <td>old feats, with stage1</td>\n", |
||
| 2959 | " <td>0.060621</td>\n", |
||
| 2960 | " <td>0.058288</td>\n", |
||
| 2961 | " <td>0.065170</td>\n", |
||
| 2962 | " <td>0.048486</td>\n", |
||
| 2963 | " </tr>\n", |
||
| 2964 | " <tr>\n", |
||
| 2965 | " <td>new feats, with stage 1</td>\n", |
||
| 2966 | " <td>0.060685</td>\n", |
||
| 2967 | " <td>0.058348</td>\n", |
||
| 2968 | " <td>0.060837</td>\n", |
||
| 2969 | " <td>0.045122</td>\n", |
||
| 2970 | " </tr>\n", |
||
| 2971 | " <tr>\n", |
||
| 2972 | " <td rowspan=\"3\" valign=\"top\">True</td>\n", |
||
| 2973 | " <td>old feats, no stage1</td>\n", |
||
| 2974 | " <td>NaN</td>\n", |
||
| 2975 | " <td>NaN</td>\n", |
||
| 2976 | " <td>NaN</td>\n", |
||
| 2977 | " <td>NaN</td>\n", |
||
| 2978 | " </tr>\n", |
||
| 2979 | " <tr>\n", |
||
| 2980 | " <td>old feats, with stage1</td>\n", |
||
| 2981 | " <td>0.060810</td>\n", |
||
| 2982 | " <td>0.058297</td>\n", |
||
| 2983 | " <td>0.066407</td>\n", |
||
| 2984 | " <td>0.048896</td>\n", |
||
| 2985 | " </tr>\n", |
||
| 2986 | " <tr>\n", |
||
| 2987 | " <td>new feats, with stage 1</td>\n", |
||
| 2988 | " <td>0.060988</td>\n", |
||
| 2989 | " <td>0.058506</td>\n", |
||
| 2990 | " <td>0.061573</td>\n", |
||
| 2991 | " <td>0.045219</td>\n", |
||
| 2992 | " </tr>\n", |
||
| 2993 | " </tbody>\n", |
||
| 2994 | "</table>\n", |
||
| 2995 | "</div>" |
||
| 2996 | ], |
||
| 2997 | "text/plain": [ |
||
| 2998 | " val_loss val_w_loss val_loss2 \\\n", |
||
| 2999 | "fold weighted type \n", |
||
| 3000 | "0 False old feats, no stage1 0.059207 0.057173 NaN \n", |
||
| 3001 | " old feats, with stage1 0.059376 0.057322 0.071586 \n", |
||
| 3002 | " new feats, with stage 1 0.059336 0.057380 0.067331 \n", |
||
| 3003 | " True old feats, no stage1 NaN NaN NaN \n", |
||
| 3004 | " old feats, with stage1 0.059580 0.057412 0.072157 \n", |
||
| 3005 | " new feats, with stage 1 0.059511 0.057492 0.067691 \n", |
||
| 3006 | "1 False old feats, no stage1 0.059903 0.058524 NaN \n", |
||
| 3007 | " old feats, with stage1 0.059548 0.058294 0.055482 \n", |
||
| 3008 | " new feats, with stage 1 0.059209 0.057936 0.052200 \n", |
||
| 3009 | " True old feats, no stage1 NaN NaN NaN \n", |
||
| 3010 | " old feats, with stage1 0.059670 0.058308 0.056408 \n", |
||
| 3011 | " new feats, with stage 1 0.059323 0.057955 0.052909 \n", |
||
| 3012 | "2 False old feats, no stage1 0.060600 0.057828 NaN \n", |
||
| 3013 | " old feats, with stage1 0.060391 0.057761 0.056373 \n", |
||
| 3014 | " new feats, with stage 1 0.059884 0.057178 0.053371 \n", |
||
| 3015 | " True old feats, no stage1 NaN NaN NaN \n", |
||
| 3016 | " old feats, with stage1 0.060492 0.057737 0.056875 \n", |
||
| 3017 | " new feats, with stage 1 0.060004 0.057138 0.053842 \n", |
||
| 3018 | "3 False old feats, no stage1 0.062978 0.060445 NaN \n", |
||
| 3019 | " old feats, with stage1 0.062238 0.060029 0.063756 \n", |
||
| 3020 | " new feats, with stage 1 0.062283 0.060144 0.062267 \n", |
||
| 3021 | " True old feats, no stage1 NaN NaN NaN \n", |
||
| 3022 | " old feats, with stage1 0.062409 0.060069 0.064277 \n", |
||
| 3023 | " new feats, with stage 1 0.062372 0.060134 0.062729 \n", |
||
| 3024 | "4 False old feats, no stage1 0.061198 0.058650 NaN \n", |
||
| 3025 | " old feats, with stage1 0.060621 0.058288 0.065170 \n", |
||
| 3026 | " new feats, with stage 1 0.060685 0.058348 0.060837 \n", |
||
| 3027 | " True old feats, no stage1 NaN NaN NaN \n", |
||
| 3028 | " old feats, with stage1 0.060810 0.058297 0.066407 \n", |
||
| 3029 | " new feats, with stage 1 0.060988 0.058506 0.061573 \n", |
||
| 3030 | "\n", |
||
| 3031 | " val_w_loss2 \n", |
||
| 3032 | "fold weighted type \n", |
||
| 3033 | "0 False old feats, no stage1 NaN \n", |
||
| 3034 | " old feats, with stage1 0.052126 \n", |
||
| 3035 | " new feats, with stage 1 0.048938 \n", |
||
| 3036 | " True old feats, no stage1 NaN \n", |
||
| 3037 | " old feats, with stage1 0.052435 \n", |
||
| 3038 | " new feats, with stage 1 0.049024 \n", |
||
| 3039 | "1 False old feats, no stage1 NaN \n", |
||
| 3040 | " old feats, with stage1 0.040188 \n", |
||
| 3041 | " new feats, with stage 1 0.038043 \n", |
||
| 3042 | " True old feats, no stage1 NaN \n", |
||
| 3043 | " old feats, with stage1 0.040399 \n", |
||
| 3044 | " new feats, with stage 1 0.038214 \n", |
||
| 3045 | "2 False old feats, no stage1 NaN \n", |
||
| 3046 | " old feats, with stage1 0.040194 \n", |
||
| 3047 | " new feats, with stage 1 0.037849 \n", |
||
| 3048 | " True old feats, no stage1 NaN \n", |
||
| 3049 | " old feats, with stage1 0.040117 \n", |
||
| 3050 | " new feats, with stage 1 0.037853 \n", |
||
| 3051 | "3 False old feats, no stage1 NaN \n", |
||
| 3052 | " old feats, with stage1 0.045654 \n", |
||
| 3053 | " new feats, with stage 1 0.044982 \n", |
||
| 3054 | " True old feats, no stage1 NaN \n", |
||
| 3055 | " old feats, with stage1 0.045677 \n", |
||
| 3056 | " new feats, with stage 1 0.044978 \n", |
||
| 3057 | "4 False old feats, no stage1 NaN \n", |
||
| 3058 | " old feats, with stage1 0.048486 \n", |
||
| 3059 | " new feats, with stage 1 0.045122 \n", |
||
| 3060 | " True old feats, no stage1 NaN \n", |
||
| 3061 | " old feats, with stage1 0.048896 \n", |
||
| 3062 | " new feats, with stage 1 0.045219 " |
||
| 3063 | ] |
||
| 3064 | }, |
||
| 3065 | "execution_count": 53, |
||
| 3066 | "metadata": {}, |
||
| 3067 | "output_type": "execute_result" |
||
| 3068 | } |
||
| 3069 | ], |
||
| 3070 | "source": [ |
||
| 3071 | "stats.loc[stats.name=='se_resnet101_F5']\\\n", |
||
| 3072 | " .groupby(['fold','weighted','type'])['val_loss','val_w_loss','val_loss2','val_w_loss2'].mean()" |
||
| 3073 | ] |
||
| 3074 | }, |
||
| 3075 | { |
||
| 3076 | "cell_type": "code", |
||
| 3077 | "execution_count": null, |
||
| 3078 | "metadata": {}, |
||
| 3079 | "outputs": [], |
||
| 3080 | "source": [] |
||
| 3081 | }, |
||
| 3082 | { |
||
| 3083 | "cell_type": "code", |
||
| 3084 | "execution_count": null, |
||
| 3085 | "metadata": {}, |
||
| 3086 | "outputs": [], |
||
| 3087 | "source": [] |
||
| 3088 | }, |
||
| 3089 | { |
||
| 3090 | "cell_type": "code", |
||
| 3091 | "execution_count": 21, |
||
| 3092 | "metadata": {}, |
||
| 3093 | "outputs": [ |
||
| 3094 | { |
||
| 3095 | "data": { |
||
| 3096 | "text/plain": [ |
||
| 3097 | "14 5\n", |
||
| 3098 | "13 5\n", |
||
| 3099 | "12 5\n", |
||
| 3100 | "11 5\n", |
||
| 3101 | "9 3\n", |
||
| 3102 | "7 3\n", |
||
| 3103 | "Name: dataset, dtype: int64" |
||
| 3104 | ] |
||
| 3105 | }, |
||
| 3106 | "execution_count": 21, |
||
| 3107 | "metadata": {}, |
||
| 3108 | "output_type": "execute_result" |
||
| 3109 | } |
||
| 3110 | ], |
||
| 3111 | "source": [ |
||
| 3112 | "stats2.dataset.value_counts()" |
||
| 3113 | ] |
||
| 3114 | }, |
||
| 3115 | { |
||
| 3116 | "cell_type": "code", |
||
| 3117 | "execution_count": 39, |
||
| 3118 | "metadata": {}, |
||
| 3119 | "outputs": [], |
||
| 3120 | "source": [ |
||
| 3121 | "stats2 = pd.concat([pd.read_csv(PATH_WORK/'stats.f{}.v{}'.format(0,32)),\n", |
||
| 3122 | " pd.read_csv(PATH_WORK/'stats.f{}.v{}'.format(1,32)),\n", |
||
| 3123 | " pd.read_csv(PATH_WORK/'stats.f{}.v{}'.format(0,34)),\n", |
||
| 3124 | " pd.read_csv(PATH_WORK/'stats.f{}.v{}'.format(1,34))], axis=0, sort=False)" |
||
| 3125 | ] |
||
| 3126 | }, |
||
| 3127 | { |
||
| 3128 | "cell_type": "code", |
||
| 3129 | "execution_count": 40, |
||
| 3130 | "metadata": {}, |
||
| 3131 | "outputs": [ |
||
| 3132 | { |
||
| 3133 | "data": { |
||
| 3134 | "text/html": [ |
||
| 3135 | "<div>\n", |
||
| 3136 | "<style scoped>\n", |
||
| 3137 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 3138 | " vertical-align: middle;\n", |
||
| 3139 | " }\n", |
||
| 3140 | "\n", |
||
| 3141 | " .dataframe tbody tr th {\n", |
||
| 3142 | " vertical-align: top;\n", |
||
| 3143 | " }\n", |
||
| 3144 | "\n", |
||
| 3145 | " .dataframe thead th {\n", |
||
| 3146 | " text-align: right;\n", |
||
| 3147 | " }\n", |
||
| 3148 | "</style>\n", |
||
| 3149 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 3150 | " <thead>\n", |
||
| 3151 | " <tr style=\"text-align: right;\">\n", |
||
| 3152 | " <th></th>\n", |
||
| 3153 | " <th>dataset</th>\n", |
||
| 3154 | " <th>epoch</th>\n", |
||
| 3155 | " <th>fold</th>\n", |
||
| 3156 | " <th>train_loss</th>\n", |
||
| 3157 | " <th>val_loss</th>\n", |
||
| 3158 | " <th>val_w_loss</th>\n", |
||
| 3159 | " <th>val_loss2</th>\n", |
||
| 3160 | " <th>val_w_loss2</th>\n", |
||
| 3161 | " <th>cor</th>\n", |
||
| 3162 | " <th>any</th>\n", |
||
| 3163 | " <th>epidural</th>\n", |
||
| 3164 | " <th>intraparenchymal</th>\n", |
||
| 3165 | " <th>intraventricular</th>\n", |
||
| 3166 | " <th>subarachnoid</th>\n", |
||
| 3167 | " <th>subdural</th>\n", |
||
| 3168 | " <th>train_sz</th>\n", |
||
| 3169 | " <th>val_sz</th>\n", |
||
| 3170 | " <th>bs</th>\n", |
||
| 3171 | " <th>train_time</th>\n", |
||
| 3172 | " <th>valid_time</th>\n", |
||
| 3173 | " <th>lr</th>\n", |
||
| 3174 | " <th>wd</th>\n", |
||
| 3175 | " <th>ver</th>\n", |
||
| 3176 | " </tr>\n", |
||
| 3177 | " </thead>\n", |
||
| 3178 | " <tbody>\n", |
||
| 3179 | " <tr>\n", |
||
| 3180 | " <td>12</td>\n", |
||
| 3181 | " <td>12</td>\n", |
||
| 3182 | " <td>13</td>\n", |
||
| 3183 | " <td>0</td>\n", |
||
| 3184 | " <td>0.031208</td>\n", |
||
| 3185 | " <td>0.059201</td>\n", |
||
| 3186 | " <td>0.064282</td>\n", |
||
| 3187 | " <td>0.000000</td>\n", |
||
| 3188 | " <td>0.0</td>\n", |
||
| 3189 | " <td>0.847493</td>\n", |
||
| 3190 | " <td>0.094982</td>\n", |
||
| 3191 | " <td>0.014763</td>\n", |
||
| 3192 | " <td>0.044750</td>\n", |
||
| 3193 | " <td>0.025390</td>\n", |
||
| 3194 | " <td>0.064951</td>\n", |
||
| 3195 | " <td>0.074592</td>\n", |
||
| 3196 | " <td>15619</td>\n", |
||
| 3197 | " <td>3936</td>\n", |
||
| 3198 | " <td>32</td>\n", |
||
| 3199 | " <td>85.367667</td>\n", |
||
| 3200 | " <td>10.784082</td>\n", |
||
| 3201 | " <td>0.000002</td>\n", |
||
| 3202 | " <td>0.0001</td>\n", |
||
| 3203 | " <td>NaN</td>\n", |
||
| 3204 | " </tr>\n", |
||
| 3205 | " <tr>\n", |
||
| 3206 | " <td>25</td>\n", |
||
| 3207 | " <td>14</td>\n", |
||
| 3208 | " <td>13</td>\n", |
||
| 3209 | " <td>0</td>\n", |
||
| 3210 | " <td>0.031730</td>\n", |
||
| 3211 | " <td>0.059394</td>\n", |
||
| 3212 | " <td>0.063065</td>\n", |
||
| 3213 | " <td>0.067177</td>\n", |
||
| 3214 | " <td>NaN</td>\n", |
||
| 3215 | " <td>0.847427</td>\n", |
||
| 3216 | " <td>0.114279</td>\n", |
||
| 3217 | " <td>0.018076</td>\n", |
||
| 3218 | " <td>0.043661</td>\n", |
||
| 3219 | " <td>0.037124</td>\n", |
||
| 3220 | " <td>0.069421</td>\n", |
||
| 3221 | " <td>0.073398</td>\n", |
||
| 3222 | " <td>17369</td>\n", |
||
| 3223 | " <td>4384</td>\n", |
||
| 3224 | " <td>32</td>\n", |
||
| 3225 | " <td>101.753389</td>\n", |
||
| 3226 | " <td>11.775365</td>\n", |
||
| 3227 | " <td>0.000002</td>\n", |
||
| 3228 | " <td>0.0001</td>\n", |
||
| 3229 | " <td>NaN</td>\n", |
||
| 3230 | " </tr>\n", |
||
| 3231 | " <tr>\n", |
||
| 3232 | " <td>12</td>\n", |
||
| 3233 | " <td>12</td>\n", |
||
| 3234 | " <td>13</td>\n", |
||
| 3235 | " <td>1</td>\n", |
||
| 3236 | " <td>0.031786</td>\n", |
||
| 3237 | " <td>0.059864</td>\n", |
||
| 3238 | " <td>0.058066</td>\n", |
||
| 3239 | " <td>0.000000</td>\n", |
||
| 3240 | " <td>0.0</td>\n", |
||
| 3241 | " <td>0.846629</td>\n", |
||
| 3242 | " <td>0.097579</td>\n", |
||
| 3243 | " <td>0.014948</td>\n", |
||
| 3244 | " <td>0.040305</td>\n", |
||
| 3245 | " <td>0.025653</td>\n", |
||
| 3246 | " <td>0.063112</td>\n", |
||
| 3247 | " <td>0.079871</td>\n", |
||
| 3248 | " <td>15699</td>\n", |
||
| 3249 | " <td>3840</td>\n", |
||
| 3250 | " <td>32</td>\n", |
||
| 3251 | " <td>85.526455</td>\n", |
||
| 3252 | " <td>10.400574</td>\n", |
||
| 3253 | " <td>0.000002</td>\n", |
||
| 3254 | " <td>0.0001</td>\n", |
||
| 3255 | " <td>NaN</td>\n", |
||
| 3256 | " </tr>\n", |
||
| 3257 | " <tr>\n", |
||
| 3258 | " <td>25</td>\n", |
||
| 3259 | " <td>14</td>\n", |
||
| 3260 | " <td>13</td>\n", |
||
| 3261 | " <td>1</td>\n", |
||
| 3262 | " <td>0.031240</td>\n", |
||
| 3263 | " <td>0.059391</td>\n", |
||
| 3264 | " <td>0.057033</td>\n", |
||
| 3265 | " <td>0.052189</td>\n", |
||
| 3266 | " <td>NaN</td>\n", |
||
| 3267 | " <td>0.848211</td>\n", |
||
| 3268 | " <td>0.093570</td>\n", |
||
| 3269 | " <td>0.009090</td>\n", |
||
| 3270 | " <td>0.037775</td>\n", |
||
| 3271 | " <td>0.020982</td>\n", |
||
| 3272 | " <td>0.047940</td>\n", |
||
| 3273 | " <td>0.062393</td>\n", |
||
| 3274 | " <td>17468</td>\n", |
||
| 3275 | " <td>4288</td>\n", |
||
| 3276 | " <td>32</td>\n", |
||
| 3277 | " <td>103.794368</td>\n", |
||
| 3278 | " <td>11.503633</td>\n", |
||
| 3279 | " <td>0.000002</td>\n", |
||
| 3280 | " <td>0.0001</td>\n", |
||
| 3281 | " <td>NaN</td>\n", |
||
| 3282 | " </tr>\n", |
||
| 3283 | " <tr>\n", |
||
| 3284 | " <td>12</td>\n", |
||
| 3285 | " <td>12</td>\n", |
||
| 3286 | " <td>13</td>\n", |
||
| 3287 | " <td>0</td>\n", |
||
| 3288 | " <td>0.031486</td>\n", |
||
| 3289 | " <td>0.059400</td>\n", |
||
| 3290 | " <td>0.063696</td>\n", |
||
| 3291 | " <td>0.071379</td>\n", |
||
| 3292 | " <td>NaN</td>\n", |
||
| 3293 | " <td>0.847333</td>\n", |
||
| 3294 | " <td>0.121656</td>\n", |
||
| 3295 | " <td>0.020638</td>\n", |
||
| 3296 | " <td>0.043654</td>\n", |
||
| 3297 | " <td>0.038130</td>\n", |
||
| 3298 | " <td>0.077089</td>\n", |
||
| 3299 | " <td>0.076830</td>\n", |
||
| 3300 | " <td>17369</td>\n", |
||
| 3301 | " <td>4384</td>\n", |
||
| 3302 | " <td>32</td>\n", |
||
| 3303 | " <td>99.668121</td>\n", |
||
| 3304 | " <td>10.958552</td>\n", |
||
| 3305 | " <td>0.000002</td>\n", |
||
| 3306 | " <td>0.0001</td>\n", |
||
| 3307 | " <td>33.0</td>\n", |
||
| 3308 | " </tr>\n", |
||
| 3309 | " <tr>\n", |
||
| 3310 | " <td>12</td>\n", |
||
| 3311 | " <td>12</td>\n", |
||
| 3312 | " <td>13</td>\n", |
||
| 3313 | " <td>1</td>\n", |
||
| 3314 | " <td>0.032215</td>\n", |
||
| 3315 | " <td>0.059726</td>\n", |
||
| 3316 | " <td>0.057000</td>\n", |
||
| 3317 | " <td>0.055488</td>\n", |
||
| 3318 | " <td>NaN</td>\n", |
||
| 3319 | " <td>0.846940</td>\n", |
||
| 3320 | " <td>0.098863</td>\n", |
||
| 3321 | " <td>0.011571</td>\n", |
||
| 3322 | " <td>0.040962</td>\n", |
||
| 3323 | " <td>0.021129</td>\n", |
||
| 3324 | " <td>0.051022</td>\n", |
||
| 3325 | " <td>0.066003</td>\n", |
||
| 3326 | " <td>17468</td>\n", |
||
| 3327 | " <td>4288</td>\n", |
||
| 3328 | " <td>32</td>\n", |
||
| 3329 | " <td>103.740352</td>\n", |
||
| 3330 | " <td>10.660052</td>\n", |
||
| 3331 | " <td>0.000002</td>\n", |
||
| 3332 | " <td>0.0001</td>\n", |
||
| 3333 | " <td>33.0</td>\n", |
||
| 3334 | " </tr>\n", |
||
| 3335 | " </tbody>\n", |
||
| 3336 | "</table>\n", |
||
| 3337 | "</div>" |
||
| 3338 | ], |
||
| 3339 | "text/plain": [ |
||
| 3340 | " dataset epoch fold train_loss val_loss val_w_loss val_loss2 \\\n", |
||
| 3341 | "12 12 13 0 0.031208 0.059201 0.064282 0.000000 \n", |
||
| 3342 | "25 14 13 0 0.031730 0.059394 0.063065 0.067177 \n", |
||
| 3343 | "12 12 13 1 0.031786 0.059864 0.058066 0.000000 \n", |
||
| 3344 | "25 14 13 1 0.031240 0.059391 0.057033 0.052189 \n", |
||
| 3345 | "12 12 13 0 0.031486 0.059400 0.063696 0.071379 \n", |
||
| 3346 | "12 12 13 1 0.032215 0.059726 0.057000 0.055488 \n", |
||
| 3347 | "\n", |
||
| 3348 | " val_w_loss2 cor any epidural intraparenchymal \\\n", |
||
| 3349 | "12 0.0 0.847493 0.094982 0.014763 0.044750 \n", |
||
| 3350 | "25 NaN 0.847427 0.114279 0.018076 0.043661 \n", |
||
| 3351 | "12 0.0 0.846629 0.097579 0.014948 0.040305 \n", |
||
| 3352 | "25 NaN 0.848211 0.093570 0.009090 0.037775 \n", |
||
| 3353 | "12 NaN 0.847333 0.121656 0.020638 0.043654 \n", |
||
| 3354 | "12 NaN 0.846940 0.098863 0.011571 0.040962 \n", |
||
| 3355 | "\n", |
||
| 3356 | " intraventricular subarachnoid subdural train_sz val_sz bs \\\n", |
||
| 3357 | "12 0.025390 0.064951 0.074592 15619 3936 32 \n", |
||
| 3358 | "25 0.037124 0.069421 0.073398 17369 4384 32 \n", |
||
| 3359 | "12 0.025653 0.063112 0.079871 15699 3840 32 \n", |
||
| 3360 | "25 0.020982 0.047940 0.062393 17468 4288 32 \n", |
||
| 3361 | "12 0.038130 0.077089 0.076830 17369 4384 32 \n", |
||
| 3362 | "12 0.021129 0.051022 0.066003 17468 4288 32 \n", |
||
| 3363 | "\n", |
||
| 3364 | " train_time valid_time lr wd ver \n", |
||
| 3365 | "12 85.367667 10.784082 0.000002 0.0001 NaN \n", |
||
| 3366 | "25 101.753389 11.775365 0.000002 0.0001 NaN \n", |
||
| 3367 | "12 85.526455 10.400574 0.000002 0.0001 NaN \n", |
||
| 3368 | "25 103.794368 11.503633 0.000002 0.0001 NaN \n", |
||
| 3369 | "12 99.668121 10.958552 0.000002 0.0001 33.0 \n", |
||
| 3370 | "12 103.740352 10.660052 0.000002 0.0001 33.0 " |
||
| 3371 | ] |
||
| 3372 | }, |
||
| 3373 | "execution_count": 40, |
||
| 3374 | "metadata": {}, |
||
| 3375 | "output_type": "execute_result" |
||
| 3376 | } |
||
| 3377 | ], |
||
| 3378 | "source": [ |
||
| 3379 | "stats1.loc[stats1.epoch == 13]" |
||
| 3380 | ] |
||
| 3381 | }, |
||
| 3382 | { |
||
| 3383 | "cell_type": "code", |
||
| 3384 | "execution_count": 41, |
||
| 3385 | "metadata": {}, |
||
| 3386 | "outputs": [ |
||
| 3387 | { |
||
| 3388 | "data": { |
||
| 3389 | "text/html": [ |
||
| 3390 | "<div>\n", |
||
| 3391 | "<style scoped>\n", |
||
| 3392 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 3393 | " vertical-align: middle;\n", |
||
| 3394 | " }\n", |
||
| 3395 | "\n", |
||
| 3396 | " .dataframe tbody tr th {\n", |
||
| 3397 | " vertical-align: top;\n", |
||
| 3398 | " }\n", |
||
| 3399 | "\n", |
||
| 3400 | " .dataframe thead th {\n", |
||
| 3401 | " text-align: right;\n", |
||
| 3402 | " }\n", |
||
| 3403 | "</style>\n", |
||
| 3404 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 3405 | " <thead>\n", |
||
| 3406 | " <tr style=\"text-align: right;\">\n", |
||
| 3407 | " <th></th>\n", |
||
| 3408 | " <th>dataset</th>\n", |
||
| 3409 | " <th>epoch</th>\n", |
||
| 3410 | " <th>fold</th>\n", |
||
| 3411 | " <th>train_loss</th>\n", |
||
| 3412 | " <th>val_loss</th>\n", |
||
| 3413 | " <th>val_w_loss</th>\n", |
||
| 3414 | " <th>val_loss2</th>\n", |
||
| 3415 | " <th>val_w_loss2</th>\n", |
||
| 3416 | " <th>cor</th>\n", |
||
| 3417 | " <th>any</th>\n", |
||
| 3418 | " <th>epidural</th>\n", |
||
| 3419 | " <th>intraparenchymal</th>\n", |
||
| 3420 | " <th>intraventricular</th>\n", |
||
| 3421 | " <th>subarachnoid</th>\n", |
||
| 3422 | " <th>subdural</th>\n", |
||
| 3423 | " <th>train_sz</th>\n", |
||
| 3424 | " <th>val_sz</th>\n", |
||
| 3425 | " <th>bs</th>\n", |
||
| 3426 | " <th>train_time</th>\n", |
||
| 3427 | " <th>valid_time</th>\n", |
||
| 3428 | " <th>lr</th>\n", |
||
| 3429 | " <th>wd</th>\n", |
||
| 3430 | " <th>ver</th>\n", |
||
| 3431 | " </tr>\n", |
||
| 3432 | " </thead>\n", |
||
| 3433 | " <tbody>\n", |
||
| 3434 | " <tr>\n", |
||
| 3435 | " <td>5</td>\n", |
||
| 3436 | " <td>14</td>\n", |
||
| 3437 | " <td>3</td>\n", |
||
| 3438 | " <td>0</td>\n", |
||
| 3439 | " <td>0.032872</td>\n", |
||
| 3440 | " <td>0.061043</td>\n", |
||
| 3441 | " <td>0.062914</td>\n", |
||
| 3442 | " <td>0.066554</td>\n", |
||
| 3443 | " <td>0.066554</td>\n", |
||
| 3444 | " <td>0.844028</td>\n", |
||
| 3445 | " <td>0.112525</td>\n", |
||
| 3446 | " <td>0.017403</td>\n", |
||
| 3447 | " <td>0.044180</td>\n", |
||
| 3448 | " <td>0.036614</td>\n", |
||
| 3449 | " <td>0.069472</td>\n", |
||
| 3450 | " <td>0.073159</td>\n", |
||
| 3451 | " <td>17369</td>\n", |
||
| 3452 | " <td>4384</td>\n", |
||
| 3453 | " <td>32</td>\n", |
||
| 3454 | " <td>101.308828</td>\n", |
||
| 3455 | " <td>11.260699</td>\n", |
||
| 3456 | " <td>0.000005</td>\n", |
||
| 3457 | " <td>0.0001</td>\n", |
||
| 3458 | " <td>NaN</td>\n", |
||
| 3459 | " </tr>\n", |
||
| 3460 | " <tr>\n", |
||
| 3461 | " <td>8</td>\n", |
||
| 3462 | " <td>12</td>\n", |
||
| 3463 | " <td>3</td>\n", |
||
| 3464 | " <td>0</td>\n", |
||
| 3465 | " <td>0.033388</td>\n", |
||
| 3466 | " <td>0.060360</td>\n", |
||
| 3467 | " <td>0.063039</td>\n", |
||
| 3468 | " <td>0.000000</td>\n", |
||
| 3469 | " <td>0.000000</td>\n", |
||
| 3470 | " <td>0.845265</td>\n", |
||
| 3471 | " <td>0.097268</td>\n", |
||
| 3472 | " <td>0.014937</td>\n", |
||
| 3473 | " <td>0.045735</td>\n", |
||
| 3474 | " <td>0.025769</td>\n", |
||
| 3475 | " <td>0.065610</td>\n", |
||
| 3476 | " <td>0.075936</td>\n", |
||
| 3477 | " <td>15619</td>\n", |
||
| 3478 | " <td>3936</td>\n", |
||
| 3479 | " <td>32</td>\n", |
||
| 3480 | " <td>82.747959</td>\n", |
||
| 3481 | " <td>10.047513</td>\n", |
||
| 3482 | " <td>0.000005</td>\n", |
||
| 3483 | " <td>0.0001</td>\n", |
||
| 3484 | " <td>NaN</td>\n", |
||
| 3485 | " </tr>\n", |
||
| 3486 | " <tr>\n", |
||
| 3487 | " <td>2</td>\n", |
||
| 3488 | " <td>14</td>\n", |
||
| 3489 | " <td>3</td>\n", |
||
| 3490 | " <td>1</td>\n", |
||
| 3491 | " <td>0.033915</td>\n", |
||
| 3492 | " <td>0.060324</td>\n", |
||
| 3493 | " <td>0.056965</td>\n", |
||
| 3494 | " <td>0.051529</td>\n", |
||
| 3495 | " <td>0.051529</td>\n", |
||
| 3496 | " <td>0.846076</td>\n", |
||
| 3497 | " <td>0.091700</td>\n", |
||
| 3498 | " <td>0.009166</td>\n", |
||
| 3499 | " <td>0.037559</td>\n", |
||
| 3500 | " <td>0.020248</td>\n", |
||
| 3501 | " <td>0.049256</td>\n", |
||
| 3502 | " <td>0.061077</td>\n", |
||
| 3503 | " <td>17468</td>\n", |
||
| 3504 | " <td>4288</td>\n", |
||
| 3505 | " <td>32</td>\n", |
||
| 3506 | " <td>102.540290</td>\n", |
||
| 3507 | " <td>10.781580</td>\n", |
||
| 3508 | " <td>0.000005</td>\n", |
||
| 3509 | " <td>0.0001</td>\n", |
||
| 3510 | " <td>NaN</td>\n", |
||
| 3511 | " </tr>\n", |
||
| 3512 | " <tr>\n", |
||
| 3513 | " <td>5</td>\n", |
||
| 3514 | " <td>12</td>\n", |
||
| 3515 | " <td>3</td>\n", |
||
| 3516 | " <td>1</td>\n", |
||
| 3517 | " <td>0.034051</td>\n", |
||
| 3518 | " <td>0.060730</td>\n", |
||
| 3519 | " <td>0.057532</td>\n", |
||
| 3520 | " <td>0.000000</td>\n", |
||
| 3521 | " <td>0.000000</td>\n", |
||
| 3522 | " <td>0.844560</td>\n", |
||
| 3523 | " <td>0.099342</td>\n", |
||
| 3524 | " <td>0.015278</td>\n", |
||
| 3525 | " <td>0.041240</td>\n", |
||
| 3526 | " <td>0.025786</td>\n", |
||
| 3527 | " <td>0.063912</td>\n", |
||
| 3528 | " <td>0.080207</td>\n", |
||
| 3529 | " <td>15699</td>\n", |
||
| 3530 | " <td>3840</td>\n", |
||
| 3531 | " <td>32</td>\n", |
||
| 3532 | " <td>83.967543</td>\n", |
||
| 3533 | " <td>9.888514</td>\n", |
||
| 3534 | " <td>0.000005</td>\n", |
||
| 3535 | " <td>0.0001</td>\n", |
||
| 3536 | " <td>NaN</td>\n", |
||
| 3537 | " </tr>\n", |
||
| 3538 | " <tr>\n", |
||
| 3539 | " <td>2</td>\n", |
||
| 3540 | " <td>12</td>\n", |
||
| 3541 | " <td>3</td>\n", |
||
| 3542 | " <td>0</td>\n", |
||
| 3543 | " <td>0.032771</td>\n", |
||
| 3544 | " <td>0.060638</td>\n", |
||
| 3545 | " <td>0.063045</td>\n", |
||
| 3546 | " <td>0.070920</td>\n", |
||
| 3547 | " <td>0.070920</td>\n", |
||
| 3548 | " <td>0.844702</td>\n", |
||
| 3549 | " <td>0.120086</td>\n", |
||
| 3550 | " <td>0.020185</td>\n", |
||
| 3551 | " <td>0.044548</td>\n", |
||
| 3552 | " <td>0.037809</td>\n", |
||
| 3553 | " <td>0.075970</td>\n", |
||
| 3554 | " <td>0.077759</td>\n", |
||
| 3555 | " <td>17369</td>\n", |
||
| 3556 | " <td>4384</td>\n", |
||
| 3557 | " <td>32</td>\n", |
||
| 3558 | " <td>95.730286</td>\n", |
||
| 3559 | " <td>10.998797</td>\n", |
||
| 3560 | " <td>0.000005</td>\n", |
||
| 3561 | " <td>0.0001</td>\n", |
||
| 3562 | " <td>34.0</td>\n", |
||
| 3563 | " </tr>\n", |
||
| 3564 | " <tr>\n", |
||
| 3565 | " <td>2</td>\n", |
||
| 3566 | " <td>12</td>\n", |
||
| 3567 | " <td>3</td>\n", |
||
| 3568 | " <td>1</td>\n", |
||
| 3569 | " <td>0.035328</td>\n", |
||
| 3570 | " <td>0.060772</td>\n", |
||
| 3571 | " <td>0.057422</td>\n", |
||
| 3572 | " <td>0.055588</td>\n", |
||
| 3573 | " <td>0.055588</td>\n", |
||
| 3574 | " <td>0.844641</td>\n", |
||
| 3575 | " <td>0.098851</td>\n", |
||
| 3576 | " <td>0.011631</td>\n", |
||
| 3577 | " <td>0.040441</td>\n", |
||
| 3578 | " <td>0.021717</td>\n", |
||
| 3579 | " <td>0.052439</td>\n", |
||
| 3580 | " <td>0.065184</td>\n", |
||
| 3581 | " <td>17468</td>\n", |
||
| 3582 | " <td>4288</td>\n", |
||
| 3583 | " <td>32</td>\n", |
||
| 3584 | " <td>98.306380</td>\n", |
||
| 3585 | " <td>10.804755</td>\n", |
||
| 3586 | " <td>0.000005</td>\n", |
||
| 3587 | " <td>0.0001</td>\n", |
||
| 3588 | " <td>34.0</td>\n", |
||
| 3589 | " </tr>\n", |
||
| 3590 | " </tbody>\n", |
||
| 3591 | "</table>\n", |
||
| 3592 | "</div>" |
||
| 3593 | ], |
||
| 3594 | "text/plain": [ |
||
| 3595 | " dataset epoch fold train_loss val_loss val_w_loss val_loss2 \\\n", |
||
| 3596 | "5 14 3 0 0.032872 0.061043 0.062914 0.066554 \n", |
||
| 3597 | "8 12 3 0 0.033388 0.060360 0.063039 0.000000 \n", |
||
| 3598 | "2 14 3 1 0.033915 0.060324 0.056965 0.051529 \n", |
||
| 3599 | "5 12 3 1 0.034051 0.060730 0.057532 0.000000 \n", |
||
| 3600 | "2 12 3 0 0.032771 0.060638 0.063045 0.070920 \n", |
||
| 3601 | "2 12 3 1 0.035328 0.060772 0.057422 0.055588 \n", |
||
| 3602 | "\n", |
||
| 3603 | " val_w_loss2 cor any epidural intraparenchymal \\\n", |
||
| 3604 | "5 0.066554 0.844028 0.112525 0.017403 0.044180 \n", |
||
| 3605 | "8 0.000000 0.845265 0.097268 0.014937 0.045735 \n", |
||
| 3606 | "2 0.051529 0.846076 0.091700 0.009166 0.037559 \n", |
||
| 3607 | "5 0.000000 0.844560 0.099342 0.015278 0.041240 \n", |
||
| 3608 | "2 0.070920 0.844702 0.120086 0.020185 0.044548 \n", |
||
| 3609 | "2 0.055588 0.844641 0.098851 0.011631 0.040441 \n", |
||
| 3610 | "\n", |
||
| 3611 | " intraventricular subarachnoid subdural train_sz val_sz bs train_time \\\n", |
||
| 3612 | "5 0.036614 0.069472 0.073159 17369 4384 32 101.308828 \n", |
||
| 3613 | "8 0.025769 0.065610 0.075936 15619 3936 32 82.747959 \n", |
||
| 3614 | "2 0.020248 0.049256 0.061077 17468 4288 32 102.540290 \n", |
||
| 3615 | "5 0.025786 0.063912 0.080207 15699 3840 32 83.967543 \n", |
||
| 3616 | "2 0.037809 0.075970 0.077759 17369 4384 32 95.730286 \n", |
||
| 3617 | "2 0.021717 0.052439 0.065184 17468 4288 32 98.306380 \n", |
||
| 3618 | "\n", |
||
| 3619 | " valid_time lr wd ver \n", |
||
| 3620 | "5 11.260699 0.000005 0.0001 NaN \n", |
||
| 3621 | "8 10.047513 0.000005 0.0001 NaN \n", |
||
| 3622 | "2 10.781580 0.000005 0.0001 NaN \n", |
||
| 3623 | "5 9.888514 0.000005 0.0001 NaN \n", |
||
| 3624 | "2 10.998797 0.000005 0.0001 34.0 \n", |
||
| 3625 | "2 10.804755 0.000005 0.0001 34.0 " |
||
| 3626 | ] |
||
| 3627 | }, |
||
| 3628 | "execution_count": 41, |
||
| 3629 | "metadata": {}, |
||
| 3630 | "output_type": "execute_result" |
||
| 3631 | } |
||
| 3632 | ], |
||
| 3633 | "source": [ |
||
| 3634 | "stats2.loc[stats2.epoch == 3]" |
||
| 3635 | ] |
||
| 3636 | }, |
||
| 3637 | { |
||
| 3638 | "cell_type": "code", |
||
| 3639 | "execution_count": 64, |
||
| 3640 | "metadata": {}, |
||
| 3641 | "outputs": [], |
||
| 3642 | "source": [ |
||
| 3643 | "stats = pd.concat([stats1.loc[stats1.epoch == 13], stats2.loc[stats2.epoch == 3]], sort=False)" |
||
| 3644 | ] |
||
| 3645 | }, |
||
| 3646 | { |
||
| 3647 | "cell_type": "code", |
||
| 3648 | "execution_count": 68, |
||
| 3649 | "metadata": {}, |
||
| 3650 | "outputs": [], |
||
| 3651 | "source": [ |
||
| 3652 | "stats['name'] = np.where(stats['dataset'] == 14, 'new feats', \n", |
||
| 3653 | " np.where(stats['ver'].isnull(), 'old feats, train', 'old feats, test+train'))" |
||
| 3654 | ] |
||
| 3655 | }, |
||
| 3656 | { |
||
| 3657 | "cell_type": "code", |
||
| 3658 | "execution_count": 69, |
||
| 3659 | "metadata": {}, |
||
| 3660 | "outputs": [], |
||
| 3661 | "source": [ |
||
| 3662 | "stats['weighted_training'] = stats.epoch == 3" |
||
| 3663 | ] |
||
| 3664 | }, |
||
| 3665 | { |
||
| 3666 | "cell_type": "code", |
||
| 3667 | "execution_count": 70, |
||
| 3668 | "metadata": {}, |
||
| 3669 | "outputs": [ |
||
| 3670 | { |
||
| 3671 | "data": { |
||
| 3672 | "text/html": [ |
||
| 3673 | "<div>\n", |
||
| 3674 | "<style scoped>\n", |
||
| 3675 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 3676 | " vertical-align: middle;\n", |
||
| 3677 | " }\n", |
||
| 3678 | "\n", |
||
| 3679 | " .dataframe tbody tr th {\n", |
||
| 3680 | " vertical-align: top;\n", |
||
| 3681 | " }\n", |
||
| 3682 | "\n", |
||
| 3683 | " .dataframe thead th {\n", |
||
| 3684 | " text-align: right;\n", |
||
| 3685 | " }\n", |
||
| 3686 | "</style>\n", |
||
| 3687 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 3688 | " <thead>\n", |
||
| 3689 | " <tr style=\"text-align: right;\">\n", |
||
| 3690 | " <th></th>\n", |
||
| 3691 | " <th></th>\n", |
||
| 3692 | " <th></th>\n", |
||
| 3693 | " <th>val_loss</th>\n", |
||
| 3694 | " <th>val_w_loss</th>\n", |
||
| 3695 | " </tr>\n", |
||
| 3696 | " <tr>\n", |
||
| 3697 | " <th>fold</th>\n", |
||
| 3698 | " <th>weighted_training</th>\n", |
||
| 3699 | " <th>name</th>\n", |
||
| 3700 | " <th></th>\n", |
||
| 3701 | " <th></th>\n", |
||
| 3702 | " </tr>\n", |
||
| 3703 | " </thead>\n", |
||
| 3704 | " <tbody>\n", |
||
| 3705 | " <tr>\n", |
||
| 3706 | " <td rowspan=\"6\" valign=\"top\">0</td>\n", |
||
| 3707 | " <td rowspan=\"3\" valign=\"top\">False</td>\n", |
||
| 3708 | " <td>new feats</td>\n", |
||
| 3709 | " <td>0.059394</td>\n", |
||
| 3710 | " <td>0.063065</td>\n", |
||
| 3711 | " </tr>\n", |
||
| 3712 | " <tr>\n", |
||
| 3713 | " <td>old feats, test+train</td>\n", |
||
| 3714 | " <td>0.059400</td>\n", |
||
| 3715 | " <td>0.063696</td>\n", |
||
| 3716 | " </tr>\n", |
||
| 3717 | " <tr>\n", |
||
| 3718 | " <td>old feats, train</td>\n", |
||
| 3719 | " <td>0.059201</td>\n", |
||
| 3720 | " <td>0.064282</td>\n", |
||
| 3721 | " </tr>\n", |
||
| 3722 | " <tr>\n", |
||
| 3723 | " <td rowspan=\"3\" valign=\"top\">True</td>\n", |
||
| 3724 | " <td>new feats</td>\n", |
||
| 3725 | " <td>0.061043</td>\n", |
||
| 3726 | " <td>0.062914</td>\n", |
||
| 3727 | " </tr>\n", |
||
| 3728 | " <tr>\n", |
||
| 3729 | " <td>old feats, test+train</td>\n", |
||
| 3730 | " <td>0.060638</td>\n", |
||
| 3731 | " <td>0.063045</td>\n", |
||
| 3732 | " </tr>\n", |
||
| 3733 | " <tr>\n", |
||
| 3734 | " <td>old feats, train</td>\n", |
||
| 3735 | " <td>0.060360</td>\n", |
||
| 3736 | " <td>0.063039</td>\n", |
||
| 3737 | " </tr>\n", |
||
| 3738 | " <tr>\n", |
||
| 3739 | " <td rowspan=\"6\" valign=\"top\">1</td>\n", |
||
| 3740 | " <td rowspan=\"3\" valign=\"top\">False</td>\n", |
||
| 3741 | " <td>new feats</td>\n", |
||
| 3742 | " <td>0.059391</td>\n", |
||
| 3743 | " <td>0.057033</td>\n", |
||
| 3744 | " </tr>\n", |
||
| 3745 | " <tr>\n", |
||
| 3746 | " <td>old feats, test+train</td>\n", |
||
| 3747 | " <td>0.059726</td>\n", |
||
| 3748 | " <td>0.057000</td>\n", |
||
| 3749 | " </tr>\n", |
||
| 3750 | " <tr>\n", |
||
| 3751 | " <td>old feats, train</td>\n", |
||
| 3752 | " <td>0.059864</td>\n", |
||
| 3753 | " <td>0.058066</td>\n", |
||
| 3754 | " </tr>\n", |
||
| 3755 | " <tr>\n", |
||
| 3756 | " <td rowspan=\"3\" valign=\"top\">True</td>\n", |
||
| 3757 | " <td>new feats</td>\n", |
||
| 3758 | " <td>0.060324</td>\n", |
||
| 3759 | " <td>0.056965</td>\n", |
||
| 3760 | " </tr>\n", |
||
| 3761 | " <tr>\n", |
||
| 3762 | " <td>old feats, test+train</td>\n", |
||
| 3763 | " <td>0.060772</td>\n", |
||
| 3764 | " <td>0.057422</td>\n", |
||
| 3765 | " </tr>\n", |
||
| 3766 | " <tr>\n", |
||
| 3767 | " <td>old feats, train</td>\n", |
||
| 3768 | " <td>0.060730</td>\n", |
||
| 3769 | " <td>0.057532</td>\n", |
||
| 3770 | " </tr>\n", |
||
| 3771 | " </tbody>\n", |
||
| 3772 | "</table>\n", |
||
| 3773 | "</div>" |
||
| 3774 | ], |
||
| 3775 | "text/plain": [ |
||
| 3776 | " val_loss val_w_loss\n", |
||
| 3777 | "fold weighted_training name \n", |
||
| 3778 | "0 False new feats 0.059394 0.063065\n", |
||
| 3779 | " old feats, test+train 0.059400 0.063696\n", |
||
| 3780 | " old feats, train 0.059201 0.064282\n", |
||
| 3781 | " True new feats 0.061043 0.062914\n", |
||
| 3782 | " old feats, test+train 0.060638 0.063045\n", |
||
| 3783 | " old feats, train 0.060360 0.063039\n", |
||
| 3784 | "1 False new feats 0.059391 0.057033\n", |
||
| 3785 | " old feats, test+train 0.059726 0.057000\n", |
||
| 3786 | " old feats, train 0.059864 0.058066\n", |
||
| 3787 | " True new feats 0.060324 0.056965\n", |
||
| 3788 | " old feats, test+train 0.060772 0.057422\n", |
||
| 3789 | " old feats, train 0.060730 0.057532" |
||
| 3790 | ] |
||
| 3791 | }, |
||
| 3792 | "execution_count": 70, |
||
| 3793 | "metadata": {}, |
||
| 3794 | "output_type": "execute_result" |
||
| 3795 | } |
||
| 3796 | ], |
||
| 3797 | "source": [ |
||
| 3798 | "stats.groupby(['fold','weighted_training','name'])[['val_loss','val_w_loss']].mean()" |
||
| 3799 | ] |
||
| 3800 | }, |
||
| 3801 | { |
||
| 3802 | "cell_type": "code", |
||
| 3803 | "execution_count": null, |
||
| 3804 | "metadata": {}, |
||
| 3805 | "outputs": [], |
||
| 3806 | "source": [] |
||
| 3807 | }, |
||
| 3808 | { |
||
| 3809 | "cell_type": "markdown", |
||
| 3810 | "metadata": {}, |
||
| 3811 | "source": [ |
||
| 3812 | "# Analysis" |
||
| 3813 | ] |
||
| 3814 | }, |
||
| 3815 | { |
||
| 3816 | "cell_type": "code", |
||
| 3817 | "execution_count": 13, |
||
| 3818 | "metadata": { |
||
| 3819 | "scrolled": true |
||
| 3820 | }, |
||
| 3821 | "outputs": [ |
||
| 3822 | { |
||
| 3823 | "data": { |
||
| 3824 | "text/html": [ |
||
| 3825 | "<div>\n", |
||
| 3826 | "<style scoped>\n", |
||
| 3827 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 3828 | " vertical-align: middle;\n", |
||
| 3829 | " }\n", |
||
| 3830 | "\n", |
||
| 3831 | " .dataframe tbody tr th {\n", |
||
| 3832 | " vertical-align: top;\n", |
||
| 3833 | " }\n", |
||
| 3834 | "\n", |
||
| 3835 | " .dataframe thead th {\n", |
||
| 3836 | " text-align: right;\n", |
||
| 3837 | " }\n", |
||
| 3838 | "</style>\n", |
||
| 3839 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 3840 | " <thead>\n", |
||
| 3841 | " <tr style=\"text-align: right;\">\n", |
||
| 3842 | " <th></th>\n", |
||
| 3843 | " <th>val_loss</th>\n", |
||
| 3844 | " <th>val_w_loss</th>\n", |
||
| 3845 | " </tr>\n", |
||
| 3846 | " <tr>\n", |
||
| 3847 | " <th>dataset</th>\n", |
||
| 3848 | " <th></th>\n", |
||
| 3849 | " <th></th>\n", |
||
| 3850 | " </tr>\n", |
||
| 3851 | " </thead>\n", |
||
| 3852 | " <tbody>\n", |
||
| 3853 | " <tr>\n", |
||
| 3854 | " <td>6</td>\n", |
||
| 3855 | " <td>0.063542</td>\n", |
||
| 3856 | " <td>0.069056</td>\n", |
||
| 3857 | " </tr>\n", |
||
| 3858 | " <tr>\n", |
||
| 3859 | " <td>7</td>\n", |
||
| 3860 | " <td>0.062726</td>\n", |
||
| 3861 | " <td>0.068622</td>\n", |
||
| 3862 | " </tr>\n", |
||
| 3863 | " <tr>\n", |
||
| 3864 | " <td>8</td>\n", |
||
| 3865 | " <td>0.064020</td>\n", |
||
| 3866 | " <td>0.069777</td>\n", |
||
| 3867 | " </tr>\n", |
||
| 3868 | " <tr>\n", |
||
| 3869 | " <td>9</td>\n", |
||
| 3870 | " <td>0.062367</td>\n", |
||
| 3871 | " <td>0.067991</td>\n", |
||
| 3872 | " </tr>\n", |
||
| 3873 | " <tr>\n", |
||
| 3874 | " <td>10</td>\n", |
||
| 3875 | " <td>0.062012</td>\n", |
||
| 3876 | " <td>0.067773</td>\n", |
||
| 3877 | " </tr>\n", |
||
| 3878 | " <tr>\n", |
||
| 3879 | " <td>11</td>\n", |
||
| 3880 | " <td>0.061149</td>\n", |
||
| 3881 | " <td>0.066677</td>\n", |
||
| 3882 | " </tr>\n", |
||
| 3883 | " <tr>\n", |
||
| 3884 | " <td>12</td>\n", |
||
| 3885 | " <td>0.060799</td>\n", |
||
| 3886 | " <td>0.066053</td>\n", |
||
| 3887 | " </tr>\n", |
||
| 3888 | " <tr>\n", |
||
| 3889 | " <td>13</td>\n", |
||
| 3890 | " <td>0.061087</td>\n", |
||
| 3891 | " <td>0.066270</td>\n", |
||
| 3892 | " </tr>\n", |
||
| 3893 | " </tbody>\n", |
||
| 3894 | "</table>\n", |
||
| 3895 | "</div>" |
||
| 3896 | ], |
||
| 3897 | "text/plain": [ |
||
| 3898 | " val_loss val_w_loss\n", |
||
| 3899 | "dataset \n", |
||
| 3900 | "6 0.063542 0.069056\n", |
||
| 3901 | "7 0.062726 0.068622\n", |
||
| 3902 | "8 0.064020 0.069777\n", |
||
| 3903 | "9 0.062367 0.067991\n", |
||
| 3904 | "10 0.062012 0.067773\n", |
||
| 3905 | "11 0.061149 0.066677\n", |
||
| 3906 | "12 0.060799 0.066053\n", |
||
| 3907 | "13 0.061087 0.066270" |
||
| 3908 | ] |
||
| 3909 | }, |
||
| 3910 | "execution_count": 13, |
||
| 3911 | "metadata": {}, |
||
| 3912 | "output_type": "execute_result" |
||
| 3913 | } |
||
| 3914 | ], |
||
| 3915 | "source": [ |
||
| 3916 | "stats = pd.concat([pd.read_csv(PATH_WORK/'stats.f{}.v{}'.format(f,31)) for f in range(5)],axis=0)\n", |
||
| 3917 | "stats.loc[stats.epoch==13].groupby('dataset')[['val_loss','val_w_loss']].mean()" |
||
| 3918 | ] |
||
| 3919 | }, |
||
| 3920 | { |
||
| 3921 | "cell_type": "code", |
||
| 3922 | "execution_count": 11, |
||
| 3923 | "metadata": { |
||
| 3924 | "scrolled": true |
||
| 3925 | }, |
||
| 3926 | "outputs": [ |
||
| 3927 | { |
||
| 3928 | "data": { |
||
| 3929 | "text/html": [ |
||
| 3930 | "<div>\n", |
||
| 3931 | "<style scoped>\n", |
||
| 3932 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 3933 | " vertical-align: middle;\n", |
||
| 3934 | " }\n", |
||
| 3935 | "\n", |
||
| 3936 | " .dataframe tbody tr th {\n", |
||
| 3937 | " vertical-align: top;\n", |
||
| 3938 | " }\n", |
||
| 3939 | "\n", |
||
| 3940 | " .dataframe thead th {\n", |
||
| 3941 | " text-align: right;\n", |
||
| 3942 | " }\n", |
||
| 3943 | "</style>\n", |
||
| 3944 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 3945 | " <thead>\n", |
||
| 3946 | " <tr style=\"text-align: right;\">\n", |
||
| 3947 | " <th></th>\n", |
||
| 3948 | " <th>val_loss</th>\n", |
||
| 3949 | " <th>val_w_loss</th>\n", |
||
| 3950 | " </tr>\n", |
||
| 3951 | " <tr>\n", |
||
| 3952 | " <th>dataset</th>\n", |
||
| 3953 | " <th></th>\n", |
||
| 3954 | " <th></th>\n", |
||
| 3955 | " </tr>\n", |
||
| 3956 | " </thead>\n", |
||
| 3957 | " <tbody>\n", |
||
| 3958 | " <tr>\n", |
||
| 3959 | " <td>6</td>\n", |
||
| 3960 | " <td>0.064378</td>\n", |
||
| 3961 | " <td>0.068053</td>\n", |
||
| 3962 | " </tr>\n", |
||
| 3963 | " <tr>\n", |
||
| 3964 | " <td>7</td>\n", |
||
| 3965 | " <td>0.063824</td>\n", |
||
| 3966 | " <td>0.067963</td>\n", |
||
| 3967 | " </tr>\n", |
||
| 3968 | " <tr>\n", |
||
| 3969 | " <td>8</td>\n", |
||
| 3970 | " <td>0.065129</td>\n", |
||
| 3971 | " <td>0.068768</td>\n", |
||
| 3972 | " </tr>\n", |
||
| 3973 | " <tr>\n", |
||
| 3974 | " <td>9</td>\n", |
||
| 3975 | " <td>0.062979</td>\n", |
||
| 3976 | " <td>0.067057</td>\n", |
||
| 3977 | " </tr>\n", |
||
| 3978 | " <tr>\n", |
||
| 3979 | " <td>10</td>\n", |
||
| 3980 | " <td>0.062737</td>\n", |
||
| 3981 | " <td>0.067054</td>\n", |
||
| 3982 | " </tr>\n", |
||
| 3983 | " <tr>\n", |
||
| 3984 | " <td>11</td>\n", |
||
| 3985 | " <td>0.061973</td>\n", |
||
| 3986 | " <td>0.065464</td>\n", |
||
| 3987 | " </tr>\n", |
||
| 3988 | " <tr>\n", |
||
| 3989 | " <td>12</td>\n", |
||
| 3990 | " <td>0.061613</td>\n", |
||
| 3991 | " <td>0.064652</td>\n", |
||
| 3992 | " </tr>\n", |
||
| 3993 | " <tr>\n", |
||
| 3994 | " <td>13</td>\n", |
||
| 3995 | " <td>0.061888</td>\n", |
||
| 3996 | " <td>0.064962</td>\n", |
||
| 3997 | " </tr>\n", |
||
| 3998 | " </tbody>\n", |
||
| 3999 | "</table>\n", |
||
| 4000 | "</div>" |
||
| 4001 | ], |
||
| 4002 | "text/plain": [ |
||
| 4003 | " val_loss val_w_loss\n", |
||
| 4004 | "dataset \n", |
||
| 4005 | "6 0.064378 0.068053\n", |
||
| 4006 | "7 0.063824 0.067963\n", |
||
| 4007 | "8 0.065129 0.068768\n", |
||
| 4008 | "9 0.062979 0.067057\n", |
||
| 4009 | "10 0.062737 0.067054\n", |
||
| 4010 | "11 0.061973 0.065464\n", |
||
| 4011 | "12 0.061613 0.064652\n", |
||
| 4012 | "13 0.061888 0.064962" |
||
| 4013 | ] |
||
| 4014 | }, |
||
| 4015 | "execution_count": 11, |
||
| 4016 | "metadata": {}, |
||
| 4017 | "output_type": "execute_result" |
||
| 4018 | } |
||
| 4019 | ], |
||
| 4020 | "source": [ |
||
| 4021 | "stats = pd.concat([pd.read_csv(PATH_WORK/'stats.f{}.v{}'.format(f,32)) for f in range(5)],axis=0)\n", |
||
| 4022 | "stats.loc[stats.epoch==3].groupby('dataset')[['val_loss','val_w_loss']].mean()" |
||
| 4023 | ] |
||
| 4024 | }, |
||
| 4025 | { |
||
| 4026 | "cell_type": "code", |
||
| 4027 | "execution_count": 14, |
||
| 4028 | "metadata": {}, |
||
| 4029 | "outputs": [ |
||
| 4030 | { |
||
| 4031 | "data": { |
||
| 4032 | "text/plain": [ |
||
| 4033 | "[<matplotlib.lines.Line2D at 0x7efd58fd4b90>]" |
||
| 4034 | ] |
||
| 4035 | }, |
||
| 4036 | "execution_count": 14, |
||
| 4037 | "metadata": {}, |
||
| 4038 | "output_type": "execute_result" |
||
| 4039 | }, |
||
| 4040 | { |
||
| 4041 | "data": { |
||
| 4042 | "image/png": "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\n", |
||
| 4043 | "text/plain": [ |
||
| 4044 | "<Figure size 432x288 with 1 Axes>" |
||
| 4045 | ] |
||
| 4046 | }, |
||
| 4047 | "metadata": { |
||
| 4048 | "needs_background": "light" |
||
| 4049 | }, |
||
| 4050 | "output_type": "display_data" |
||
| 4051 | } |
||
| 4052 | ], |
||
| 4053 | "source": [ |
||
| 4054 | "plt.plot(stats.groupby('epoch').mean().val_loss)" |
||
| 4055 | ] |
||
| 4056 | }, |
||
| 4057 | { |
||
| 4058 | "cell_type": "code", |
||
| 4059 | "execution_count": null, |
||
| 4060 | "metadata": {}, |
||
| 4061 | "outputs": [], |
||
| 4062 | "source": [] |
||
| 4063 | }, |
||
| 4064 | { |
||
| 4065 | "cell_type": "code", |
||
| 4066 | "execution_count": 34, |
||
| 4067 | "metadata": { |
||
| 4068 | "scrolled": true |
||
| 4069 | }, |
||
| 4070 | "outputs": [ |
||
| 4071 | { |
||
| 4072 | "data": { |
||
| 4073 | "text/plain": [ |
||
| 4074 | "(4368, 60, 6)" |
||
| 4075 | ] |
||
| 4076 | }, |
||
| 4077 | "execution_count": 34, |
||
| 4078 | "metadata": {}, |
||
| 4079 | "output_type": "execute_result" |
||
| 4080 | } |
||
| 4081 | ], |
||
| 4082 | "source": [ |
||
| 4083 | "predictions.shape" |
||
| 4084 | ] |
||
| 4085 | }, |
||
| 4086 | { |
||
| 4087 | "cell_type": "code", |
||
| 4088 | "execution_count": 35, |
||
| 4089 | "metadata": {}, |
||
| 4090 | "outputs": [ |
||
| 4091 | { |
||
| 4092 | "data": { |
||
| 4093 | "text/plain": [ |
||
| 4094 | "array([0.26533565, 0.14922237, 0.21536556, 0.21641548, 0.21140262,\n", |
||
| 4095 | " 0.19743267], dtype=float32)" |
||
| 4096 | ] |
||
| 4097 | }, |
||
| 4098 | "execution_count": 35, |
||
| 4099 | "metadata": {}, |
||
| 4100 | "output_type": "execute_result" |
||
| 4101 | } |
||
| 4102 | ], |
||
| 4103 | "source": [ |
||
| 4104 | "predictions.mean((0,1))" |
||
| 4105 | ] |
||
| 4106 | }, |
||
| 4107 | { |
||
| 4108 | "cell_type": "code", |
||
| 4109 | "execution_count": 36, |
||
| 4110 | "metadata": {}, |
||
| 4111 | "outputs": [ |
||
| 4112 | { |
||
| 4113 | "data": { |
||
| 4114 | "text/plain": [ |
||
| 4115 | "[<matplotlib.lines.Line2D at 0x7f7449493790>]" |
||
| 4116 | ] |
||
| 4117 | }, |
||
| 4118 | "execution_count": 36, |
||
| 4119 | "metadata": {}, |
||
| 4120 | "output_type": "execute_result" |
||
| 4121 | }, |
||
| 4122 | { |
||
| 4123 | "data": { |
||
| 4124 | "image/png": "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\n", |
||
| 4125 | "text/plain": [ |
||
| 4126 | "<Figure size 432x288 with 1 Axes>" |
||
| 4127 | ] |
||
| 4128 | }, |
||
| 4129 | "metadata": { |
||
| 4130 | "needs_background": "light" |
||
| 4131 | }, |
||
| 4132 | "output_type": "display_data" |
||
| 4133 | } |
||
| 4134 | ], |
||
| 4135 | "source": [ |
||
| 4136 | "plt.plot(predictions.mean(0)[:,0])" |
||
| 4137 | ] |
||
| 4138 | }, |
||
| 4139 | { |
||
| 4140 | "cell_type": "code", |
||
| 4141 | "execution_count": 37, |
||
| 4142 | "metadata": {}, |
||
| 4143 | "outputs": [ |
||
| 4144 | { |
||
| 4145 | "data": { |
||
| 4146 | "text/plain": [ |
||
| 4147 | "[<matplotlib.lines.Line2D at 0x7f744941c650>]" |
||
| 4148 | ] |
||
| 4149 | }, |
||
| 4150 | "execution_count": 37, |
||
| 4151 | "metadata": {}, |
||
| 4152 | "output_type": "execute_result" |
||
| 4153 | }, |
||
| 4154 | { |
||
| 4155 | "data": { |
||
| 4156 | "image/png": "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\n", |
||
| 4157 | "text/plain": [ |
||
| 4158 | "<Figure size 432x288 with 1 Axes>" |
||
| 4159 | ] |
||
| 4160 | }, |
||
| 4161 | "metadata": { |
||
| 4162 | "needs_background": "light" |
||
| 4163 | }, |
||
| 4164 | "output_type": "display_data" |
||
| 4165 | } |
||
| 4166 | ], |
||
| 4167 | "source": [ |
||
| 4168 | "dd = train_md.loc[train_md.fold5==4].copy()\n", |
||
| 4169 | "dd['res'] = val_results[:,0]\n", |
||
| 4170 | "\n", |
||
| 4171 | "plt.plot(dd[['res','pos_idx']].groupby('pos_idx').mean().values)" |
||
| 4172 | ] |
||
| 4173 | }, |
||
| 4174 | { |
||
| 4175 | "cell_type": "code", |
||
| 4176 | "execution_count": null, |
||
| 4177 | "metadata": {}, |
||
| 4178 | "outputs": [], |
||
| 4179 | "source": [] |
||
| 4180 | } |
||
| 4181 | ], |
||
| 4182 | "metadata": { |
||
| 4183 | "kernelspec": { |
||
| 4184 | "display_name": "Python 3", |
||
| 4185 | "language": "python", |
||
| 4186 | "name": "python3" |
||
| 4187 | }, |
||
| 4188 | "language_info": { |
||
| 4189 | "codemirror_mode": { |
||
| 4190 | "name": "ipython", |
||
| 4191 | "version": 3 |
||
| 4192 | }, |
||
| 4193 | "file_extension": ".py", |
||
| 4194 | "mimetype": "text/x-python", |
||
| 4195 | "name": "python", |
||
| 4196 | "nbconvert_exporter": "python", |
||
| 4197 | "pygments_lexer": "ipython3", |
||
| 4198 | "version": "3.7.4" |
||
| 4199 | } |
||
| 4200 | }, |
||
| 4201 | "nbformat": 4, |
||
| 4202 | "nbformat_minor": 2 |
||
| 4203 | } |