blanchon commited on
Commit
198e819
1 Parent(s): 4b3147f

updateupdate

Browse files
__pycache__/dataloading.cpython-310.pyc CHANGED
Binary files a/__pycache__/dataloading.cpython-310.pyc and b/__pycache__/dataloading.cpython-310.pyc differ
 
__pycache__/gradio_utils.cpython-310.pyc CHANGED
Binary files a/__pycache__/gradio_utils.cpython-310.pyc and b/__pycache__/gradio_utils.cpython-310.pyc differ
 
__pycache__/preprocessing.cpython-310.pyc CHANGED
Binary files a/__pycache__/preprocessing.cpython-310.pyc and b/__pycache__/preprocessing.cpython-310.pyc differ
 
__pycache__/resnet.cpython-310.pyc CHANGED
Binary files a/__pycache__/resnet.cpython-310.pyc and b/__pycache__/resnet.cpython-310.pyc differ
 
best_model_gradio.ipynb CHANGED
@@ -9,7 +9,7 @@
9
  },
10
  {
11
  "cell_type": "code",
12
- "execution_count": 42,
13
  "metadata": {},
14
  "outputs": [
15
  {
@@ -60,11 +60,11 @@
60
  "\n",
61
  "# Dataloading params\n",
62
  "PATHS: list = [\n",
63
- " \"../data/\",\n",
64
- " \"../new_data/JulienNestor\",\n",
65
- " \"../new_data/classroom_data\",\n",
66
- " \"../new_data/class\",\n",
67
- " \"../new_data/JulienRaph\",\n",
68
  "]\n",
69
  "REMOVE_LABEL: list = [\n",
70
  " \"penduleinverse\", \"pendule\", \n",
@@ -243,112 +243,112 @@
243
  "text": [
244
  " epoch train_loss dur\n",
245
  "------- ------------ ------\n",
246
- " 1 \u001b[36m2.8646\u001b[0m 0.4461\n",
247
- " 2 \u001b[36m1.9534\u001b[0m 0.4322\n",
248
- " 3 \u001b[36m1.8164\u001b[0m 0.4331\n",
249
- " 4 \u001b[36m1.6889\u001b[0m 0.4318\n",
250
- " 5 \u001b[36m1.5808\u001b[0m 0.4329\n",
251
- " 6 \u001b[36m1.4659\u001b[0m 0.4355\n",
252
- " 7 \u001b[36m1.2894\u001b[0m 0.4285\n",
253
- " 8 1.3207 0.4280\n",
254
- " 9 \u001b[36m1.1546\u001b[0m 0.4274\n",
255
- " 10 \u001b[36m1.0586\u001b[0m 0.4287\n",
256
- " 11 \u001b[36m1.0195\u001b[0m 0.4313\n",
257
- " 12 \u001b[36m0.8246\u001b[0m 0.4302\n",
258
- " 13 \u001b[36m0.7612\u001b[0m 0.4330\n",
259
- " 14 \u001b[36m0.7296\u001b[0m 0.4315\n",
260
- " 15 \u001b[36m0.6690\u001b[0m 0.4293\n",
261
- " 16 \u001b[36m0.6205\u001b[0m 0.4291\n",
262
- " 17 \u001b[36m0.5764\u001b[0m 0.4290\n",
263
- " 18 \u001b[36m0.4839\u001b[0m 0.4284\n",
264
- " 19 0.4984 0.4314\n",
265
- " 20 \u001b[36m0.4666\u001b[0m 0.4324\n",
266
- " 21 \u001b[36m0.4132\u001b[0m 0.4322\n",
267
- " 22 0.4440 0.4300\n",
268
- " 23 0.4463 0.4300\n",
269
- " 24 \u001b[36m0.4075\u001b[0m 0.4287\n",
270
- " 25 \u001b[36m0.3908\u001b[0m 0.4282\n",
271
- " 26 \u001b[36m0.3759\u001b[0m 0.4278\n",
272
- " 27 \u001b[36m0.3612\u001b[0m 0.4296\n",
273
- " 28 \u001b[36m0.3189\u001b[0m 0.4281\n",
274
- " 29 0.3489 0.4308\n",
275
- " 30 0.3308 0.4301\n",
276
- " 31 0.3353 0.4299\n",
277
- " 32 \u001b[36m0.3074\u001b[0m 0.4298\n",
278
- " 33 0.3339 0.4350\n",
279
- " 34 \u001b[36m0.2921\u001b[0m 0.4383\n",
280
- " 35 \u001b[36m0.2852\u001b[0m 0.4345\n",
281
- " 36 0.3170 0.4334\n",
282
- " 37 0.2853 0.4304\n",
283
- " 38 0.2857 0.4307\n",
284
- " 39 \u001b[36m0.2607\u001b[0m 0.4310\n",
285
- " 40 0.2765 0.4292\n",
286
- " 41 0.2831 0.4305\n",
287
- " 42 0.2836 0.4295\n",
288
- " 43 0.2742 0.4307\n",
289
- " 44 0.2653 0.4302\n",
290
- " 45 \u001b[36m0.2370\u001b[0m 0.4335\n",
291
- " 46 0.2475 0.4292\n",
292
- " 47 0.2692 0.4329\n",
293
- " 48 0.2657 0.4306\n",
294
- " 49 0.2875 0.4305\n",
295
- " 50 0.2839 0.4315\n",
296
- " 51 0.2555 0.4307\n",
297
- " 52 0.2794 0.4332\n",
298
- " 53 \u001b[36m0.2272\u001b[0m 0.4302\n",
299
- " 54 0.2519 0.4305\n",
300
- " 55 0.2388 0.4307\n",
301
- " 56 0.2504 0.4314\n",
302
- " 57 0.2345 0.4328\n",
303
- " 58 \u001b[36m0.2252\u001b[0m 0.4316\n",
304
- " 59 0.2436 0.4329\n",
305
- " 60 0.2297 0.4309\n",
306
- " 61 0.2594 0.4306\n",
307
- " 62 0.2412 0.4300\n",
308
- " 63 0.2399 0.4319\n",
309
- " 64 0.2600 0.4334\n",
310
- " 65 0.2599 0.4304\n",
311
- " 66 0.2360 0.4317\n",
312
- " 67 0.2537 0.4301\n",
313
- " 68 0.2268 0.4299\n",
314
- " 69 0.2436 0.4301\n",
315
- " 70 \u001b[36m0.2193\u001b[0m 0.4308\n",
316
- " 71 0.2284 0.4322\n",
317
- " 72 0.2339 0.4317\n",
318
- " 73 0.2330 0.4331\n",
319
- " 74 \u001b[36m0.2063\u001b[0m 0.4327\n",
320
- " 75 0.2568 0.4332\n",
321
- " 76 0.2372 0.4324\n",
322
- " 77 0.2249 0.4327\n",
323
- " 78 0.2449 0.4314\n",
324
- " 79 0.2455 0.4310\n",
325
- " 80 \u001b[36m0.2003\u001b[0m 0.4321\n",
326
- " 81 0.2172 0.4318\n",
327
- " 82 0.2278 0.4333\n",
328
- " 83 0.2178 0.4334\n",
329
- " 84 0.2240 0.4312\n",
330
- " 85 0.2329 0.4338\n",
331
- " 86 0.2267 0.4326\n",
332
- " 87 0.2479 0.4341\n",
333
- " 88 0.2266 0.4355\n",
334
- " 89 0.2541 0.4350\n",
335
- " 90 0.2167 0.4324\n",
336
- " 91 0.2282 0.4353\n",
337
- " 92 0.2097 0.4367\n",
338
- " 93 0.2038 0.4351\n",
339
- " 94 0.2078 0.4372\n",
340
- " 95 0.2437 0.4344\n",
341
- " 96 0.2283 0.4333\n",
342
- " 97 0.2263 0.4329\n",
343
- " 98 0.2146 0.4346\n",
344
- " 99 0.2238 0.4323\n",
345
- " 100 0.2035 0.4348\n",
346
- " 101 0.2287 0.4348\n",
347
- " 102 0.2231 0.4328\n",
348
- " 103 0.2171 0.4326\n",
349
- " 104 0.2417 0.4329\n",
350
  "Stopping since train_loss has not improved in the last 25 epochs.\n",
351
- "0.941908713692946\n"
352
  ]
353
  }
354
  ],
@@ -383,7 +383,121 @@
383
  {
384
  "data": {
385
  "text/plain": [
386
- "['./model/HOP_LENGHT.joblib']"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
387
  ]
388
  },
389
  "execution_count": 39,
@@ -391,6 +505,27 @@
391
  "output_type": "execute_result"
392
  }
393
  ],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
394
  "source": [
395
  "from joblib import dump, load\n",
396
  "\n",
@@ -406,7 +541,7 @@
406
  },
407
  {
408
  "cell_type": "code",
409
- "execution_count": 40,
410
  "metadata": {},
411
  "outputs": [],
412
  "source": [
@@ -433,16 +568,7 @@
433
  "cell_type": "code",
434
  "execution_count": 43,
435
  "metadata": {},
436
- "outputs": [
437
- {
438
- "ename": "",
439
- "evalue": "",
440
- "output_type": "error",
441
- "traceback": [
442
- "\u001b[1;31mThe Kernel crashed while executing code in the the current cell or a previous cell. Please review the code in the cell(s) to identify a possible cause of the failure. Click <a href='https://aka.ms/vscodeJupyterKernelCrash'>here</a> for more info. View Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details."
443
- ]
444
- }
445
- ],
446
  "source": [
447
  "title = r\"ResNet 9\"\n",
448
  "\n",
@@ -473,6 +599,13 @@
473
  " # flagging_dir = \"./flag/men\"\n",
474
  ")"
475
  ]
 
 
 
 
 
 
 
476
  }
477
  ],
478
  "metadata": {
 
9
  },
10
  {
11
  "cell_type": "code",
12
+ "execution_count": 26,
13
  "metadata": {},
14
  "outputs": [
15
  {
 
60
  "\n",
61
  "# Dataloading params\n",
62
  "PATHS: list = [\n",
63
+ " \"../Projet-ML/data/\",\n",
64
+ " \"../Projet-ML/new_data/JulienNestor\",\n",
65
+ " \"../Projet-ML/new_data/classroom_data\",\n",
66
+ " \"../Projet-ML/new_data/class\",\n",
67
+ " \"../Projet-ML/new_data/JulienRaph\",\n",
68
  "]\n",
69
  "REMOVE_LABEL: list = [\n",
70
  " \"penduleinverse\", \"pendule\", \n",
 
243
  "text": [
244
  " epoch train_loss dur\n",
245
  "------- ------------ ------\n",
246
+ " 1 \u001b[36m2.8636\u001b[0m 1.9894\n",
247
+ " 2 \u001b[36m1.9484\u001b[0m 0.4326\n",
248
+ " 3 \u001b[36m1.8183\u001b[0m 0.4312\n",
249
+ " 4 \u001b[36m1.6839\u001b[0m 0.4318\n",
250
+ " 5 \u001b[36m1.5514\u001b[0m 0.4326\n",
251
+ " 6 \u001b[36m1.4672\u001b[0m 0.4309\n",
252
+ " 7 \u001b[36m1.2708\u001b[0m 0.4323\n",
253
+ " 8 1.2842 0.4308\n",
254
+ " 9 \u001b[36m1.0673\u001b[0m 0.4316\n",
255
+ " 10 \u001b[36m0.9857\u001b[0m 0.4307\n",
256
+ " 11 \u001b[36m0.9400\u001b[0m 0.4322\n",
257
+ " 12 \u001b[36m0.9096\u001b[0m 0.4310\n",
258
+ " 13 \u001b[36m0.7838\u001b[0m 0.4313\n",
259
+ " 14 \u001b[36m0.7031\u001b[0m 0.4330\n",
260
+ " 15 \u001b[36m0.6361\u001b[0m 0.4313\n",
261
+ " 16 \u001b[36m0.5983\u001b[0m 0.4325\n",
262
+ " 17 \u001b[36m0.5712\u001b[0m 0.4318\n",
263
+ " 18 \u001b[36m0.4825\u001b[0m 0.4315\n",
264
+ " 19 0.4951 0.4323\n",
265
+ " 20 \u001b[36m0.4653\u001b[0m 0.4320\n",
266
+ " 21 \u001b[36m0.4050\u001b[0m 0.4333\n",
267
+ " 22 0.4351 0.4317\n",
268
+ " 23 0.4365 0.4314\n",
269
+ " 24 \u001b[36m0.4000\u001b[0m 0.4304\n",
270
+ " 25 \u001b[36m0.3876\u001b[0m 0.4319\n",
271
+ " 26 \u001b[36m0.3740\u001b[0m 0.4327\n",
272
+ " 27 \u001b[36m0.3589\u001b[0m 0.4323\n",
273
+ " 28 \u001b[36m0.3173\u001b[0m 0.4330\n",
274
+ " 29 0.3412 0.4322\n",
275
+ " 30 0.3263 0.4335\n",
276
+ " 31 0.3313 0.4322\n",
277
+ " 32 \u001b[36m0.3033\u001b[0m 0.4327\n",
278
+ " 33 0.3333 0.4325\n",
279
+ " 34 \u001b[36m0.2912\u001b[0m 0.4328\n",
280
+ " 35 \u001b[36m0.2834\u001b[0m 0.4330\n",
281
+ " 36 0.3150 0.4326\n",
282
+ " 37 0.2842 0.4339\n",
283
+ " 38 0.2854 0.4335\n",
284
+ " 39 \u001b[36m0.2588\u001b[0m 0.4341\n",
285
+ " 40 0.2775 0.4340\n",
286
+ " 41 0.2823 0.4336\n",
287
+ " 42 0.2826 0.4344\n",
288
+ " 43 0.2723 0.4328\n",
289
+ " 44 0.2638 0.4354\n",
290
+ " 45 \u001b[36m0.2350\u001b[0m 0.4348\n",
291
+ " 46 0.2463 0.4334\n",
292
+ " 47 0.2688 0.4333\n",
293
+ " 48 0.2652 0.4343\n",
294
+ " 49 0.2869 0.4348\n",
295
+ " 50 0.2833 0.4338\n",
296
+ " 51 0.2541 0.4335\n",
297
+ " 52 0.2796 0.4318\n",
298
+ " 53 \u001b[36m0.2273\u001b[0m 0.4350\n",
299
+ " 54 0.2516 0.4341\n",
300
+ " 55 0.2392 0.4332\n",
301
+ " 56 0.2480 0.4332\n",
302
+ " 57 0.2341 0.4331\n",
303
+ " 58 \u001b[36m0.2240\u001b[0m 0.4332\n",
304
+ " 59 0.2441 0.4333\n",
305
+ " 60 0.2313 0.4329\n",
306
+ " 61 0.2590 0.4348\n",
307
+ " 62 0.2412 0.4344\n",
308
+ " 63 0.2391 0.4323\n",
309
+ " 64 0.2591 0.4331\n",
310
+ " 65 0.2595 0.4336\n",
311
+ " 66 0.2356 0.4328\n",
312
+ " 67 0.2529 0.4351\n",
313
+ " 68 0.2262 0.4330\n",
314
+ " 69 0.2438 0.4322\n",
315
+ " 70 \u001b[36m0.2189\u001b[0m 0.4323\n",
316
+ " 71 0.2283 0.4318\n",
317
+ " 72 0.2333 0.4325\n",
318
+ " 73 0.2327 0.4333\n",
319
+ " 74 \u001b[36m0.2062\u001b[0m 0.4350\n",
320
+ " 75 0.2566 0.4323\n",
321
+ " 76 0.2373 0.4333\n",
322
+ " 77 0.2253 0.4332\n",
323
+ " 78 0.2446 0.4328\n",
324
+ " 79 0.2459 0.4328\n",
325
+ " 80 \u001b[36m0.2006\u001b[0m 0.4322\n",
326
+ " 81 0.2170 0.4337\n",
327
+ " 82 0.2270 0.4324\n",
328
+ " 83 0.2177 0.4324\n",
329
+ " 84 0.2235 0.4318\n",
330
+ " 85 0.2326 0.4341\n",
331
+ " 86 0.2260 0.4330\n",
332
+ " 87 0.2479 0.4318\n",
333
+ " 88 0.2267 0.4335\n",
334
+ " 89 0.2544 0.4324\n",
335
+ " 90 0.2167 0.4347\n",
336
+ " 91 0.2280 0.4328\n",
337
+ " 92 0.2093 0.4334\n",
338
+ " 93 0.2035 0.4337\n",
339
+ " 94 0.2077 0.4327\n",
340
+ " 95 0.2437 0.4341\n",
341
+ " 96 0.2278 0.4330\n",
342
+ " 97 0.2265 0.4359\n",
343
+ " 98 0.2145 0.4328\n",
344
+ " 99 0.2239 0.4336\n",
345
+ " 100 0.2034 0.4333\n",
346
+ " 101 0.2286 0.4332\n",
347
+ " 102 0.2231 0.4325\n",
348
+ " 103 0.2169 0.4327\n",
349
+ " 104 0.2415 0.4337\n",
350
  "Stopping since train_loss has not improved in the last 25 epochs.\n",
351
+ "0.946058091286307\n"
352
  ]
353
  }
354
  ],
 
383
  {
384
  "data": {
385
  "text/plain": [
386
+ "ResNet(\n",
387
+ " (conv1): ConvBlock(\n",
388
+ " (pool_block): Sequential(\n",
389
+ " (0): ReLU(inplace=True)\n",
390
+ " )\n",
391
+ " (block): Sequential(\n",
392
+ " (0): Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
393
+ " (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
394
+ " (2): Sequential(\n",
395
+ " (0): ReLU(inplace=True)\n",
396
+ " )\n",
397
+ " )\n",
398
+ " )\n",
399
+ " (conv2): ConvBlock(\n",
400
+ " (pool_block): Sequential(\n",
401
+ " (0): ReLU(inplace=True)\n",
402
+ " (1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
403
+ " )\n",
404
+ " (block): Sequential(\n",
405
+ " (0): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
406
+ " (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
407
+ " (2): Sequential(\n",
408
+ " (0): ReLU(inplace=True)\n",
409
+ " (1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
410
+ " )\n",
411
+ " )\n",
412
+ " )\n",
413
+ " (res1): Sequential(\n",
414
+ " (0): ConvBlock(\n",
415
+ " (pool_block): Sequential(\n",
416
+ " (0): ReLU(inplace=True)\n",
417
+ " )\n",
418
+ " (block): Sequential(\n",
419
+ " (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
420
+ " (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
421
+ " (2): Sequential(\n",
422
+ " (0): ReLU(inplace=True)\n",
423
+ " )\n",
424
+ " )\n",
425
+ " )\n",
426
+ " (1): ConvBlock(\n",
427
+ " (pool_block): Sequential(\n",
428
+ " (0): ReLU(inplace=True)\n",
429
+ " )\n",
430
+ " (block): Sequential(\n",
431
+ " (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
432
+ " (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
433
+ " (2): Sequential(\n",
434
+ " (0): ReLU(inplace=True)\n",
435
+ " )\n",
436
+ " )\n",
437
+ " )\n",
438
+ " )\n",
439
+ " (conv3): ConvBlock(\n",
440
+ " (pool_block): Sequential(\n",
441
+ " (0): ReLU(inplace=True)\n",
442
+ " )\n",
443
+ " (block): Sequential(\n",
444
+ " (0): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
445
+ " (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
446
+ " (2): Sequential(\n",
447
+ " (0): ReLU(inplace=True)\n",
448
+ " )\n",
449
+ " )\n",
450
+ " )\n",
451
+ " (conv4): ConvBlock(\n",
452
+ " (pool_block): Sequential(\n",
453
+ " (0): ReLU(inplace=True)\n",
454
+ " (1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
455
+ " )\n",
456
+ " (block): Sequential(\n",
457
+ " (0): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
458
+ " (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
459
+ " (2): Sequential(\n",
460
+ " (0): ReLU(inplace=True)\n",
461
+ " (1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
462
+ " )\n",
463
+ " )\n",
464
+ " )\n",
465
+ " (res2): Sequential(\n",
466
+ " (0): ConvBlock(\n",
467
+ " (pool_block): Sequential(\n",
468
+ " (0): ReLU(inplace=True)\n",
469
+ " )\n",
470
+ " (block): Sequential(\n",
471
+ " (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
472
+ " (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
473
+ " (2): Sequential(\n",
474
+ " (0): ReLU(inplace=True)\n",
475
+ " )\n",
476
+ " )\n",
477
+ " )\n",
478
+ " (1): ConvBlock(\n",
479
+ " (pool_block): Sequential(\n",
480
+ " (0): ReLU(inplace=True)\n",
481
+ " )\n",
482
+ " (block): Sequential(\n",
483
+ " (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n",
484
+ " (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
485
+ " (2): Sequential(\n",
486
+ " (0): ReLU(inplace=True)\n",
487
+ " )\n",
488
+ " )\n",
489
+ " )\n",
490
+ " )\n",
491
+ " (classifier): Sequential(\n",
492
+ " (0): MaxPool2d(kernel_size=(4, 4), stride=(4, 4), padding=0, dilation=1, ceil_mode=False)\n",
493
+ " (1): AdaptiveAvgPool2d(output_size=1)\n",
494
+ " (2): Flatten(start_dim=1, end_dim=-1)\n",
495
+ " (3): Linear(in_features=512, out_features=128, bias=True)\n",
496
+ " (4): Dropout(p=0.25, inplace=False)\n",
497
+ " (5): Linear(in_features=128, out_features=7, bias=True)\n",
498
+ " (6): Dropout(p=0.25, inplace=False)\n",
499
+ " )\n",
500
+ ")"
501
  ]
502
  },
503
  "execution_count": 39,
 
505
  "output_type": "execute_result"
506
  }
507
  ],
508
+ "source": [
509
+ "model.device = torch.device(\"cpu\")\n",
510
+ "model.module.to(torch.device(\"cpu\"))"
511
+ ]
512
+ },
513
+ {
514
+ "cell_type": "code",
515
+ "execution_count": 41,
516
+ "metadata": {},
517
+ "outputs": [
518
+ {
519
+ "data": {
520
+ "text/plain": [
521
+ "['./model/HOP_LENGHT.joblib']"
522
+ ]
523
+ },
524
+ "execution_count": 41,
525
+ "metadata": {},
526
+ "output_type": "execute_result"
527
+ }
528
+ ],
529
  "source": [
530
  "from joblib import dump, load\n",
531
  "\n",
 
541
  },
542
  {
543
  "cell_type": "code",
544
+ "execution_count": 42,
545
  "metadata": {},
546
  "outputs": [],
547
  "source": [
 
568
  "cell_type": "code",
569
  "execution_count": 43,
570
  "metadata": {},
571
+ "outputs": [],
 
 
 
 
 
 
 
 
 
572
  "source": [
573
  "title = r\"ResNet 9\"\n",
574
  "\n",
 
599
  " # flagging_dir = \"./flag/men\"\n",
600
  ")"
601
  ]
602
+ },
603
+ {
604
+ "cell_type": "code",
605
+ "execution_count": null,
606
+ "metadata": {},
607
+ "outputs": [],
608
+ "source": []
609
  }
610
  ],
611
  "metadata": {
model/model.joblib CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c88130d5500b9e58fb2bc8e5b3cce918c83fdb94c2361d991e24f79452328b00
3
- size 53219183
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2389a5deeaf1ee5e83c187d772dd2cba6c827f055a263ccdae392f833c3a987
3
+ size 53218172