alihan/inzpeech
1
0
Fork 0
mirror of https://github.com/inzva/inzpeech.git synced 2021-06-01 09:25:07 +03:00
Code Issues Projects Releases Wiki Activity
Files
master
inzpeech/Train_VCTK_Keras.ipynb
Bekci 9e03b876bb Merged
2020-11-13 20:58:59 +03:00

836 lines
62 KiB
Plaintext
Raw Permalink Blame History

{
"cells": [
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"1\"\n",
"from tensorflow.keras.utils import Sequence, to_categorical\n",
"from tensorflow.keras.models import Model\n",
"from tensorflow.keras.optimizers import Adam\n",
"from models.vggish import VGGish\n",
"from utils import apply_melspectrogram_to_file\n",
"import math\n",
"import numpy as np\n",
"from models.model_keras_dropout import vgg_att\n",
"from dataloaders.DatagenVoxCeleb import get_keras_datagens"
]
},
{
"cell_type": "code",
<<<<<<< HEAD
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"data_dir = '/media/data/bbekci/voxceleb2/data/dev/pkls/'\n",
"tr_txt = 'txts/tr_voxceleb_video_pkl_paths.txt'\n",
"val_txt = 'txts/val_voxceleb_video_pkl_paths.txt' \n",
"batch_size = 32"
=======
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"sample_per_person = 10\n",
"batch_size = 64\n",
]
},
{
"cell_type": "code",
<<<<<<< HEAD
"execution_count": 14,
>>>>>>> 90355144ce4a7d9932e7274ea8bfbec292c5288f
},
"[3636 1114 831 4209 866 529 3704 2501 2403 2645 1307 386 4005 4568\n",
" 5172 5787 4859 4257 547 1116 268 1585 354 1716 5165 1408 5708 4017\n",
" 3690 4062 4107 602]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[ 592 381 1795 1333 5038 3831 4154 5876 5845 168 5659 2375 4812 4068\n",
" 5806 1244 5672 2005 2416 3612 1101 4249 5884 3992 3385 4303 3103 5586\n",
" 4038 4148 139 5458]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[1374 5100 5892 2967 1174 3046 3818 4641 5891 4187 1212 4310 4210 2796\n",
" 592 3003 4590 1918 2457 3856 3692 4718 3635 3314 5029 4960 1683 10\n",
" 5867 2898 826 5025]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[5856 3013 3428 3755 3080 2667 5730 7 2841 3147 1519 793 3551 3098\n",
" 818 528 216 302 695 3115 1450 302 2475 4594 1595 5073 372 4836\n",
" 266 3012 2619 2905]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[3064 4663 3212 5901 1248 3894 116 3284 4043 388 5904 162 2889 2444\n",
" 3755 2 1685 1095 4169 5486 5113 2235 5558 460 3657 4148 2138 1702\n",
" 4362 1437 5170 5415]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[4789 1600 793 5460 5571 5074 2069 5383 5884 959 4637 3846 4748 3840\n",
" 3948 2562 3689 4302 4408 4558 3745 3000 3779 3155 3011 1656 3179 2235\n",
" 3748 2297 2176 5257]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[5165 3259 4202 3536 2545 5784 4765 2015 5280 4562 4448 2262 4377 100\n",
" 3864 4011 3787 4301 4307 1666 3583 4402 835 3339 3678 5789 1354 3211\n",
" 3092 5935 1736 249]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[4875 5844 4131 5100 3996 4222 2733 4666 5479 3199 2098 4869 4644 2420\n",
" 5384 4918 4804 403 1464 5059 2202 236 1814 5462 3696 3837 3095 4024\n",
" 4937 2809 5134 2014]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[3395 1061 2385 5608 1499 2550 3185 678 5415 4573 5590 4458 5584 3732\n",
" 278 114 1274 5152 2053 2122 4318 4040 5700 98 873 2555 2529 2796\n",
" 10 3617 3105 471]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[2438 3190 5925 5483 720 4630 690 1564 2772 5705 2125 4647 2519 476\n",
" 2053 2938 5409 1966 4315 4123 2011 3763 4064 1437 5818 2327 2844 4666\n",
" 2887 2753 3188 683]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[5392 1333 4178 73 2472 4321 134 975 1681 3818 2925 3211 3651 4321\n",
" 5447 1397 1379 1351 2433 5226 4275 1068 405 2933 4585 5839 3662 653\n",
" 1098 4337 4072 620]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[1219 3569 2549 1912 2066 2362 1887 781 2385 5730 41 5060 4376 449\n",
" 5133 1390 2098 5916 4656 2632 4011 5406 1589 1690 4212 2430 2176 3590\n",
" 2782 92 4893 5392]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[2599 1904 3732 5206 1007 2857 5600 33 2366 3077 4534 3807 2080 4197\n",
" 4808 5321 1007 4827 2450 200 4595 3039 4821 3987 3337 811 1276 2007\n",
" 2778 4318 5153 1554]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[1033 3157 2085 5760 3713 3213 4969 5806 4862 5022 2973 1291 2677 2504\n",
" 2289 2877 4660 3306 541 5117 3133 5695 1790 1451 4969 32 5864 290\n",
" 3394 3569 1638 4083]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[2716 5294 5461 2563 5825 4565 3402 3595 4267 2793 940 1629 271 1438\n",
" 1662 4781 2945 2450 1169 485 2951 3893 1075 4179 5392 3448 2163 2491\n",
" 434 2069 5912 3228]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[1770 4103 2267 1149 2558 4236 3083 2992 3634 5813 2096 4486 3847 1078\n",
" 569 5784 5426 4491 4588 5282 1661 3704 3324 1432 5430 554 1268 807\n",
" 1095 519 41 230]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[3992 2733 3214 1015 336 4270 2028 1015 1834 4893 5260 5323 2923 2258\n",
" 3590 5618 3996 5126 347 5925 3303 3718 2409 5452 3598 3260 3160 3926\n",
" 3563 4015 3095 2266]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[3098 57 5419 3739 1355 534 2082 1799 472 2165 2577 3207 164 2551\n",
" 3382 615 3227 4422 106 3430 2964 4773 3781 2192 5242 3675 5109 5941\n",
" 4839 2048 3490 1178]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[5757 2110 1124 489 5880 5022 2997 1110 4784 966 4305 1834 89 482\n",
" 3821 1352 5787 5843 5368 89 522 2075 4213 954 1205 3496 651 4050\n",
" 5217 2053 1044 5601]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[2610 5629 636 4937 4370 896 1974 452 2148 3729 3696 2475 5312 3359\n",
" 2533 3815 3595 5702 1089 217 3802 2670 1637 2063 4568 991 3089 5555\n",
" 2573 1935 5383 3129]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[5725 3669 1642 5205 151 4755 358 853 175 5951 690 5852 3632 5480\n",
" 326 508 5352 358 1529 4471 2718 615 2866 1358 2363 650 2915 3943\n",
" 933 3031 3652 1134]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[1753 1096 3334 5107 2915 3279 1839 146 4234 3248 1498 5680 4686 4358\n",
" 3629 2552 2396 890 843 433 1836 3430 899 1254 1531 2867 3848 2153\n",
" 1687 1060 4637 1528]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[ 611 1244 568 4955 4817 771 4255 3697 2721 2113 5453 3481 1376 1249\n",
" 3339 194 3569 5563 2811 697 5057 3178 4294 3133 2549 2858 2289 1778\n",
" 2819 5083 2305 20]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[1880 1977 1273 2573 1360 3319 4314 4147 1947 604 3236 1326 3393 1541\n",
" 2107 4877 5402 5634 2555 5353 926 2010 5411 4584 2895 2076 1502 4932\n",
" 4742 5272 5597 5514]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[2994 5286 2005 1647 4391 1695 5331 2463 3227 4466 5876 5636 5190 110\n",
" 4320 3740 5450 587 3401 1084 3481 3917 4244 3180 386 5608 5844 168\n",
" 3823 3707 1574 3287]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[5764 18 2731 2764 5685 2475 2877 1063 4875 3532 1076 114 3055 801\n",
" 59 1405 3230 2008 3012 3780 1615 3540 4775 434 4730 382 5704 870\n",
" 4739 92 5644 3452]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[3465 4347 3551 2249 4517 3608 5358 5392 1733 4231 1360 5825 404 363\n",
" 1385 3680 784 3152 3762 2003 2148 2994 2181 624 5565 2780 233 981\n",
" 3272 748 3917 4937]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[2381 2245 387 5353 436 3076 1023 3823 2271 3288 2244 5231 3844 1814\n",
" 826 781 294 3716 2293 3277 405 2162 1201 247 2096 2214 5935 5116\n",
" 1694 2692 1913 4377]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[3577 4489 3044 5818 1242 1884 2164 697 4562 5115 3755 3642 4209 4716\n",
" 3422 3819 1964 3456 2014 4555 2897 4685 5358 2925 1934 1054 4335 2805\n",
" 3493 121 3316 2205]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[4179 854 4138 4604 4641 1334 1933 1579 4199 139 2114 4948 1308 3449\n",
" 5758 516 275 1913 1574 3840 5607 1653 5126 1351 5379 3110 4614 1117\n",
" 4857 1182 3691 5971]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[3952 386 3601 4271 978 5932 2848 651 5198 1925 1685 1841 2208 3319\n",
" 4582 1964 1178 2250 4699 2838 526 5498 1913 105 2676 2069 4764 1685\n",
" 4193 128 456 4336]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[2829 2254 4013 4811 4914 1615 452 117 3547 2498 93 4491 4530 5288\n",
" 2008 2396 4957 2369 104 1407 2639 2755 4026 5196 3065 3326 411 2864\n",
" 3079 2593 3168 63]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[ 231 5621 115 3171 4265 3575 2118 1099 4461 2549 3925 3709 2597 11\n",
" 3157 5455 939 2233 553 5002 5028 3143 358 232 3821 1220 117 5547\n",
" 1999 4039 3232 3717]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[1615 4463 4923 1506 2533 939 132 836 4814 1761 4178 913 5740 4490\n",
" 2283 4601 5014 3450 4565 2517 4485 160 2488 3287 1736 2478 5554 4931\n",
" 4103 1529 2437 2084]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[1520 973 4257 1216 2312 3408 2449 5111 547 5488 3550 1279 3740 2423\n",
" 5008 2491 2465 2831 3795 5904 1553 3048 1913 2463 2795 380 117 3445\n",
" 4867 1689 3801 2113]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[ 137 2844 570 2796 690 5037 2371 3996 5165 5833 95 1827 2807 2236\n",
" 5558 800 2639 3486 1693 2287 2977 3957 1621 1307 5165 5518 3718 5503\n",
" 4822 1959 2713 4096]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[2745 5107 899 4387 2673 1007 1469 2851 4569 5099 5166 4345 4852 5164\n",
" 4463 117 476 1199 4257 1700 4322 4446 74 1721 5517 1942 4552 1430\n",
" 1254 2001 601 571]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[3835 4615 5057 5580 2819 3406 4867 2445 320 4680 4023 4492 43 996\n",
" 1023 4536 2858 2186 747 4301 2961 2654 1390 260 2639 1658 5460 3199\n",
" 4867 1665 5381 3394]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[ 177 2808 2297 4859 210 3111 1673 447 379 2751 4243 2148 4459 2918\n",
" 4271 4381 2549 3069 3773 663 1809 3084 1182 1517 1145 3025 3265 4709\n",
" 5089 1569 3446 3001]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[2090 4615 2621 3270 5562 4756 2698 5402 1219 3519 2220 2247 3765 5172\n",
" 5157 1937 3424 4266 2048 1881 1889 5048 4709 5771 406 5605 2231 288\n",
" 1397 2773 4422 3691]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[1950 204 2807 2342 1630 3668 2291 5729 655 4159 1595 5058 3147 5860\n",
" 4843 447 4197 5408 4201 4932 5833 1429 1595 3780 4481 4835 3025 196\n",
" 2042 52 4220 5153]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[3944 5481 5051 552 2237 892 4582 207 2608 5117 1060 2893 5458 677\n",
" 2600 254 3583 2784 1262 933 2611 5138 2680 5884 5876 3392 59 2541\n",
" 4217 4600 3576 5025]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[3996 5675 3663 4907 5074 4212 2023 1715 276 3200 2749 1713 1702 1420\n",
" 372 5375 244 3540 2056 5924 1015 1738 5589 2813 2508 5793 2971 4266\n",
" 4136 4750 1655 4702]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[ 816 5425 2929 1133 5366 2843 776 3606 1887 1465 2699 1095 5909 3459\n",
" 853 4306 1860 5559 5961 3259 5121 1012 5460 3868 264 4462 5207 3452\n",
" 4615 486 1169 2617]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[5853 3826 5584 5709 2878 4329 4806 2888 1889 4585 1940 3934 5699 4831\n",
" 2465 3391 893 5046 4870 4796 5793 4740 4805 167 2595 3298 1419 2133\n",
" 4831 24 1921 47]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[3961 3652 767 207 2715 2439 4639 773 4923 4767 3032 2679 3961 1498\n",
" 3735 624 1742 4734 3209 4427 2765 3790 5243 2445 1294 472 5594 4591\n",
" 378 4397 5825 5899]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[5971 2427 4750 4108 3527 5550 784 2599 2504 159 5631 133 3064 82\n",
" 1152 5444 3707 3077 3319 1461 2857 4834 2936 955 3048 1827 1584 2725\n",
" 3481 996 3069 1607]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[1772 1363 4558 930 2809 3763 4340 1638 3384 5153 3477 5060 4600 4379\n",
" 195 1335 2341 185 2362 5682 2889 400 724 190 4558 1839 225 1064\n",
" 742 3212 1963 1182]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[3763 1959 3106 3844 5783 5396 3076 3376 996 1767 5796 4955 5009 4600\n",
" 4199 2668 2113 1411 5090 4262 3768 3133 783 3718 2846 2831 5477 4826\n",
" 3011 2730 2219 3011]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[1548 3831 2412 5978 5846 4462 3247 2608 3463 2541 1092 5378 5693 591\n",
" 3362 5258 1064 2102 5758 1062 4756 2046 2104 4530 5283 4398 3623 2198\n",
" 2739 3267 245 1398]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[4512 4944 605 4131 5716 2395 4258 69 926 1425 164 5415 3831 5031\n",
" 3984 973 2827 3685 811 3235 3385 519 5842 3392 489 728 193 1341\n",
" 47 2745 1622 471]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[3649 4727 2864 3802 2547 2483 245 1070 4188 4775 4107 5304 4610 508\n",
" 4461 5012 1852 5878 1220 3046 2370 1551 3751 2210 4145 1092 3260 2933\n",
" 2007 5116 3092 2527]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[5034 3290 3567 4441 5354 772 571 387 4839 4330 4466 254 2118 3526\n",
" 1802 5455 2207 5598 649 377 4990 1832 1209 3540 3218 1576 5612 2312\n",
" 5352 932 170 5409]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[3436 1976 5818 4299 1113 1219 1657 2829 907 268 4111 2021 441 557\n",
" 1585 590 569 3471 1022 5713 4021 2712 40 3705 170 5787 5991 5740\n",
" 1968 2360 510 2343]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[2395 2091 598 2785 1135 3383 4215 5067 678 569 1382 2483 2381 3594\n",
" 2342 3788 982 1272 1556 5158 2502 5476 5354 720 3787 1096 508 5479\n",
" 5014 5878 4695 1652]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[4912 85 124 2164 3834 3402 3848 3961 2884 2485 4459 1852 5703 3415\n",
" 1963 2337 4894 2887 4062 5873 1088 1700 5504 3441 3256 2169 3929 5809\n",
" 698 5571 1836 2077]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[4610 3206 880 3766 1259 2532 2617 2369 966 2285 1558 3456 5895 3011\n",
" 3013 3331 1300 694 3966 3756 4825 2240 2508 3639 3408 4278 5580 4114\n",
" 285 2955 2102 1514]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[2317 1142 4614 1796 914 1904 4678 4154 3062 4209 1399 5068 5724 60\n",
" 2361 3242 2963 1785 5389 2966 4040 5166 2883 3791 4149 3072 4105 1698\n",
" 1925 220 5729 2492]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[4846 178 3133 3404 4569 2072 3721 2153 2448 1624 4271 5322 1736 4943\n",
" 381 2208 846 4300 4488 2098 2472 4580 4951 3083 2629 5591 943 5244\n",
" 5698 4063 3809 2125]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[2481 3857 5661 2854 3064 3517 5536 3649 5172 5040 5430 4986 3046 873\n",
" 2957 1103 5269 3359 5439 4176 1606 1171 4058 834 5873 1098 1793 4947\n",
" 3943 5725 4666 3416]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[ 783 2602 5707 4343 3087 796 5950 5853 3859 4082 5547 32 1165 1126\n",
" 4189 1452 4300 784 3988 3817 1975 5814 527 831 2034 150 1438 4212\n",
" 2931 1553 2150 4685]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[ 306 4197 4303 1605 1940 5686 3642 1700 1566 4067 2559 5815 4457 3114\n",
" 2199 1602 2507 4699 5501 4727 1195 712 2906 2153 2971 4972 381 1098\n",
" 5621 1407 3856 4521]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[3012 1075 2098 2387 380 5326 1034 3842 5009 4383 2747 931 1990 4450\n",
" 5785 322 3802 4421 2923 3634 778 3772 2483 4059 3939 58 456 4969\n",
" 1224 1959 4280 1522]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[4955 835 4182 1655 5618 3239 278 4285 317 5497 5784 406 3362 1774\n",
" 2662 4701 2667 5388 5747 2337 4379 2104 5622 1367 4937 2624 1178 2675\n",
" 3531 5474 2416 3361]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[3840 2339 3542 5905 3565 3078 2998 4945 1905 2933 3618 675 2574 5029\n",
" 400 2204 14 3861 5783 2249 2654 3709 766 3321 3122 1023 3797 4039\n",
" 5774 2838 4492 112]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[ 231 1083 607 3430 1239 2077 3640 2507 2829 3629 2771 4992 230 4355\n",
" 531 1500 339 175 1722 1964 5828 783 4606 3185 3170 1292 3518 4023\n",
" 167 2577 4862 3785]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[ 55 1685 2505 5068 4310 1499 3337 5400 1702 1702 2103 2433 5973 2858\n",
" 3957 3563 4763 2294 4042 2747 2861 764 5237 5292 2683 1276 2590 2109\n",
" 1244 4875 3230 2591]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[5343 2228 1178 2588 516 4469 4595 5551 5153 1832 1934 168 3704 1964\n",
" 3763 3042 2437 5884 3087 4928 3874 1654 3287 3659 4108 3191 624 1224\n",
" 1521 4728 5443 3875]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[2724 1740 2430 4303 1126 2611 3732 1281 5030 22 5216 4756 5570 1526\n",
" 2506 5698 5698 5356 3622 3087 1047 4584 1998 746 71 467 2590 1636\n",
" 4398 4131 1221 4635]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[ 159 2416 4508 3550 1631 1360 733 3558 1245 5240 1864 720 2773 3478\n",
" 1411 3461 3024 288 2148 53 2787 2931 649 2183 3961 916 2918 1015\n",
" 4446 2670 5536 5980]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[3247 1245 5389 3777 2077 5175 3618 3093 4346 3894 4582 3167 2437 382\n",
" 1749 4015 719 5623 4458 1934 4269 443 2524 2236 1367 1804 5476 362\n",
" 4635 4623 4557 18]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[4727 5732 5515 4599 4547 3958 2778 3421 918 2931 3865 3397 3714 462\n",
" 3691 3092 99 3095 1864 74 2304 3130 1089 621 5022 698 2239 5078\n",
" 5962 1521 1224 3939]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[2294 3948 4615 1574 895 1372 4011 953 4626 3281 5046 1608 5479 423\n",
" 5978 3912 3937 1279 1736 1776 199 2369 3253 3875 5321 5246 1519 4917\n",
" 476 4864 3615 2043]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[4786 2930 3706 708 2729 3284 2379 386 3209 4378 2932 1065 3705 4294\n",
" 2543 3480 3212 1096 1276 1647 296 3358 2869 452 5359 4246 217 3913\n",
" 2562 5458 722 271]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[5231 3077 638 4236 684 4811 2340 1711 1529 2670 5241 2441 4323 4454\n",
" 4932 949 3732 1162 2303 1735 1286 1550 1206 2597 5475 374 5359 4260\n",
" 2299 4582 5812 540]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[4385 2804 4568 1458 5795 5045 4435 3505 333 5505 2574 73 297 1435\n",
" 1235 145 3353 957 264 5515 4702 3003 4582 5405 4100 66 4318 5746\n",
" 2945 278 5961 5214]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[ 634 3600 150 4284 3940 5927 678 5864 2909 4071 75 321 2792 3570\n",
" 3684 873 935 399 2643 4663 778 14 792 1087 1635 3153 4206 4977\n",
" 2522 945 3775 200]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[2755 2963 722 4825 1496 913 3147 1605 5418 1351 1624 5974 666 5877\n",
" 752 4059 5890 2279 1292 1178 2138 444 818 302 5446 5079 178 3121\n",
" 651 4236 1654 1526]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[5991 2766 2676 5237 3394 2436 634 5548 4894 5152 4117 535 5859 3103\n",
" 3913 3568 728 2756 5001 634 5004 4125 5511 3099 4309 2374 3322 4704\n",
" 5078 1519 5433 5081]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[ 207 4008 4204 533 708 4729 2042 3947 2001 780 3408 1905 1655 4009\n",
" 920 3961 4301 3717 2997 4932 1188 5477 2312 638 3033 4710 1336 2665\n",
" 1087 387 628 3209]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[ 294 1534 3437 5799 3804 3799 4602 1545 3803 4847 4614 3918 4164 4580\n",
" 2542 2923 2213 1661 2209 1688 1096 2109 117 3110 4033 4147 4302 950\n",
" 2815 2250 4789 3708]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[1161 3240 17 2386 2645 5650 4380 2310 715 2690 5166 5120 825 204\n",
" 2843 705 3575 1159 4170 4507 4283 1458 4679 3134 4508 2498 2954 4007\n",
" 5312 3398 400 651]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[2091 2504 679 1083 1169 1774 245 4941 994 4524 5580 5154 2096 1770\n",
" 560 1398 5472 2084 4282 2772 89 4093 1736 1495 2608 4955 4424 4694\n",
" 5226 5059 2294 1366]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[1949 5378 1852 1306 137 301 1832 306 3095 5473 4356 603 2668 5400\n",
" 5638 5384 3041 5239 3065 2525 2403 4874 5704 4584 2285 3926 2450 4210\n",
" 4084 397 3326 3512]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[5076 3205 3806 1100 1439 2772 5558 4131 1599 4062 1426 5952 4425 5897\n",
" 4690 3607 5359 124 4867 3745 5046 3013 1577 1635 4146 3883 2050 2642\n",
" 1918 4083 440 3374]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[1526 2685 4633 1977 4800 2790 1291 1846 1243 2007 3848 220 2450 4702\n",
" 2639 95 213 5060 816 4132 5337 4509 501 2562 2667 404 3263 1041\n",
" 2433 5858 2522 3913]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[1263 5384 1220 2572 2878 3625 3303 3392 1713 1832 5525 5610 5274 1151\n",
" 5352 1865 5758 592 3065 2608 1597 2043 3905 4308 4283 32 3238 4852\n",
" 4580 3588 5489 3355]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[1913 1620 1081 3014 4811 3598 1037 5039 5480 5159 231 4908 2498 5356\n",
" 2129 2001 1670 519 1114 4448 3646 4617 4159 5020 464 1935 1172 3618\n",
" 1306 100 2857 2876]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[ 797 5504 581 2585 5700 5216 2883 5774 1407 5524 47 862 3713 4751\n",
" 931 1233 2951 5582 1456 935 5455 5280 2107 5899 18 2202 2406 639\n",
" 3184 4990 5241 3339]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[4773 1652 4685 5229 2739 2199 1695 1884 5921 5698 5504 3755 3831 2020\n",
" 3283 670 440 73 3157 5693 1072 3129 4806 410 2836 793 5782 913\n",
" 1064 2876 3490 533]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[5185 5325 2814 4384 5707 3024 3329 1425 4919 1300 3135 2488 5237 2524\n",
" 5584 121 5959 5688 2014 5647 2306 3430 3528 2784 5919 3557 3298 3728\n",
" 1892 3540 5409 3097]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[4264 1790 3400 4448 1256 1801 2454 907 3558 5730 4789 1964 2743 1048\n",
" 3636 2237 5208 4025 4627 2803 5702 2695 4396 3917 1614 1299 917 4422\n",
" 1514 5833 5366 4557]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[2687 3173 4197 1818 3587 1083 1832 2347 699 4943 1527 5828 5747 5891\n",
" 2769 2698 5971 1168 1942 1964 1548 4178 844 2871 5953 2573 4303 4620\n",
" 318 2994 4981 4862]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[5739 4362 4887 2920 3406 954 5682 3917 1435 1997 4612 2734 159 3988\n",
" 1793 3934 5872 5198 2568 2429 1473 2342 4048 4906 4461 3636 5210 921\n",
" 4164 5765 3560 1505]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[1113 914 859 80 4011 5355 3517 2715 661 838 381 5644 3031 4380\n",
" 4900 3031 942 3074 5990 3156 5288 472 3618 4135 4272 5738 553 1880\n",
" 254 4271 270 4595]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[4814 5383 1389 4446 3732 3259 5970 3419 940 949 3422 470 3326 11\n",
" 1721 5698 3083 3884 1936 4886 3788 5561 697 675 797 774 4246 560\n",
" 3235 3623 1122 5396]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[1764 91 1599 3841 1796 4898 2715 4650 264 2386 4843 1086 4804 1587\n",
" 1122 4197 2750 5339 5352 1087 3086 2626 1376 98 4176 3772 2142 4249\n",
" 1505 4016 5614 5115]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[4736 1702 5331 5438 1584 405 679 2042 4971 4350 5598 3359 3802 3396\n",
" 5856 1758 3144 89 5245 935 4617 3769 134 3994 3301 4351 3168 4347\n",
" 3645 5169 4322 3618]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[1194 2643 1737 3779 5839 3699 3964 4947 5717 2217 2054 5242 3171 5980\n",
" 5207 2905 4928 5332 2605 5565 5827 3207 4270 2708 245 4538 851 4841\n",
" 4041 2500 2654 1856]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[3499 4801 2870 1522 260 3407 3065 3908 1617 2104 352 2865 2579 2573\n",
" 2705 440 1667 3418 3798 1103 5168 4935 5237 3077 4595 796 5667 3105\n",
" 2606 3970 5452 1866]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[2713 5100 3346 1595 4766 2325 2235 5425 382 522 3493 2498 207 4207\n",
" 4511 4366 258 3071 465 3831 379 4868 2882 3592 4525 4145 2865 1425\n",
" 1915 2524 2803 973]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[1312 2971 4193 3001 978 1606 5458 3287 3080 690 5785 4748 2398 1774\n",
" 507 5034 5831 2547 885 480 5458 5093 2895 463 5617 4989 2876 3027\n",
" 1221 5716 2519 3929]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[3709 3976 1851 5014 5229 3248 4345 3909 2647 3675 5643 1986 2769 3988\n",
" 417 1914 5582 1062 400 767 5931 4063 706 4166 5237 3995 4264 5525\n",
" 4863 581 4080 5460]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[5439 5042 3780 2113 1602 3194 1802 3559 2772 5286 4725 2854 4078 4576\n",
" 3874 1929 3215 1703 2150 198 188 960 2109 855 2848 1995 364 1300\n",
" 5427 781 2688 1053]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[1421 3191 5780 139 1656 250 604 1664 1461 5768 5143 4828 2870 4326\n",
" 2613 5558 5955 1807 3874 5381 1666 1905 1074 1653 946 5034 5790 2093\n",
" 2007 1207 765 5736]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[4248 5104 2962 5350 5724 4081 2802 2034 2046 4208 5304 2531 1622 2976\n",
" 3034 3953 3812 1608 3929 4726 3576 1981 4666 1945 1227 3512 4494 406\n",
" 1009 1090 965 5459]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[5799 2311 5727 2747 89 5565 5349 4063 1261 105 4096 3069 22 2489\n",
" 881 2007 4607 522 4038 954 3147 5374 129 5176 5622 2898 5575 3141\n",
" 3230 836 4192 5644]\n",
"(32, 300, 40)\n",
"(32,)\n",
"[1207 3663 3471 508 1999 5930 5584 2180 217 3548 1929 5857 472 4375\n",
" 4041 2186 4009 1861 950 633 2150 1371 3410 4343 3780 2638 1654 2118\n",
" 2021 1435 608 5680]\n"
]
},
{
"output_type": "error",
"ename": "KeyboardInterrupt",
"evalue": "",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-11-977ada5cc803>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0;32mfor\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0my\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mtr_gen\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 2\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/keras/utils/data_utils.py\u001b[0m in \u001b[0;36m__iter__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 469\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m__iter__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\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[1;32m 470\u001b[0m \u001b[0;34m\"\"\"Create a generator that iterate over the Sequence.\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 471\u001b[0;31m \u001b[0;32mfor\u001b[0m \u001b[0mitem\u001b[0m \u001b[0;32min\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\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 472\u001b[0m \u001b[0;32myield\u001b[0m \u001b[0mitem\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 473\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/keras/utils/data_utils.py\u001b[0m in \u001b[0;36m<genexpr>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m 469\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m__iter__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\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[1;32m 470\u001b[0m \u001b[0;34m\"\"\"Create a generator that iterate over the Sequence.\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 471\u001b[0;31m \u001b[0;32mfor\u001b[0m \u001b[0mitem\u001b[0m \u001b[0;32min\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\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 472\u001b[0m \u001b[0;32myield\u001b[0m \u001b[0mitem\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 473\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/inzpeech/dataloaders/DatagenVoxCeleb.py\u001b[0m in \u001b[0;36m__getitem__\u001b[0;34m(self, idx)\u001b[0m\n\u001b[1;32m 87\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 88\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m__getitem__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0midx\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[0;32m---> 89\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdatagen\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_batch_sample\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0midx\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbatch_size\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 90\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 91\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mon_epoch_end\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\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[0;32m~/inzpeech/dataloaders/DatagenVoxCeleb.py\u001b[0m in \u001b[0;36mget_batch_sample\u001b[0;34m(self, idx, batch_size)\u001b[0m\n\u001b[1;32m 49\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpp\u001b[0m \u001b[0;32min\u001b[0m \u001b[0menumerate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msample_pickle_path\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[1;32m 50\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mopen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpp\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'rb'\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mpickle_load\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 51\u001b[0;31m \u001b[0mloaded_sample\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[0mpickle_load\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 52\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 53\u001b[0m \u001b[0midname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvideoname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfeatures\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mloaded_sample\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/miniconda3/envs/inzpeech/lib/python3.8/site-packages/numpy/core/numeric.py\u001b[0m in \u001b[0;36m_frombuffer\u001b[0;34m(buf, dtype, shape, order)\u001b[0m\n\u001b[1;32m 1810\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1811\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1812\u001b[0;31m \u001b[0;32mdef\u001b[0m \u001b[0m_frombuffer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbuf\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mshape\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0morder\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 1813\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mfrombuffer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbuf\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdtype\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreshape\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mshape\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0morder\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0morder\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1814\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
=======
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(64, 100, 40, 1)\n",
"(64, 109)\n"
>>>>>>> 90355144ce4a7d9932e7274ea8bfbec292c5288f
]
}
],
"source": [
<<<<<<< HEAD
"for x,y in tr_gen:\n",
" print(x.shape)\n",
" print(y.shape)\n",
" print(y)"
=======
"for x, y in tr_gen:\n",
" print(x.shape)\n",
" print(y.shape)\n",
" break"
>>>>>>> 90355144ce4a7d9932e7274ea8bfbec292c5288f
]
},
{
"cell_type": "code",
<<<<<<< HEAD
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"sample_per_person = 300\n",
"batch_size = 10\n",
"num_class = 1251 #or 109\n",
"input_shape = (100, 40, 1)\n",
"persons_to_include = ['p228', 'p227', 'p225', 'p245', 'p247', 'p246', 'p228', 'p250', 'p251', 'p248', 'p231', 'p253']"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"'tr_gen, val_gen, te_gen = get_datagen(sample_per_person, batch_size, apply_melspectrogram_to_file, include_person=None)'"
]
},
"metadata": {},
"execution_count": 16
}
],
"source": [
"\"\"\"tr_gen, val_gen, te_gen = get_datagen(sample_per_person, batch_size, apply_melspectrogram_to_file, include_person=None)\"\"\""
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"'for x, y in tr_gen:\\n print(x.shape)\\n print(y.shape)\\n print(np.unique(np.argmax(y, axis=1)))\\n break'"
]
},
"metadata": {},
"execution_count": 17
}
],
"source": [
"\"\"\"for x, y in tr_gen:\n",
" print(x.shape)\n",
" print(y.shape)\n",
" print(np.unique(np.argmax(y, axis=1)))\n",
" break\"\"\""
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"(None, 150, 20, 64)\n(None, 75, 10, 128)\n(None, 38, 5, 256)\n(None, 19, 3, 512)\nafter reshape\n(None, 19, 1536)\nafter attention\n(None, 4, 1536)\nafter avgpool\n(None, 1, 1536)\nModel: \"model_1\"\n_________________________________________________________________\nLayer (type) Output Shape Param # \n=================================================================\ninput_2 (InputLayer) [(None, 300, 40, 1)] 0 \n_________________________________________________________________\nblock1_conv1 (Conv2D) (None, 300, 40, 64) 640 \n_________________________________________________________________\nblock1_conv2 (Conv2D) (None, 300, 40, 64) 36928 \n_________________________________________________________________\nbatch_normalization_4 (Batch (None, 300, 40, 64) 256 \n_________________________________________________________________\nmax_pooling2d_4 (MaxPooling2 (None, 150, 20, 64) 0 \n_________________________________________________________________\nblock2_conv1 (Conv2D) (None, 150, 20, 128) 73856 \n_________________________________________________________________\nblock2_conv2 (Conv2D) (None, 150, 20, 128) 147584 \n_________________________________________________________________\nbatch_normalization_5 (Batch (None, 150, 20, 128) 512 \n_________________________________________________________________\nmax_pooling2d_5 (MaxPooling2 (None, 75, 10, 128) 0 \n_________________________________________________________________\nblock3_conv1 (Conv2D) (None, 75, 10, 256) 295168 \n_________________________________________________________________\nblock3_conv2 (Conv2D) (None, 75, 10, 256) 590080 \n_________________________________________________________________\nbatch_normalization_6 (Batch (None, 75, 10, 256) 1024 \n_________________________________________________________________\nmax_pooling2d_6 (MaxPooling2 (None, 38, 5, 256) 0 \n_________________________________________________________________\nblock4_conv1 (Conv2D) (None, 38, 5, 512) 1180160 \n_________________________________________________________________\nblock4_conv2 (Conv2D) (None, 38, 5, 512) 2359808 \n_________________________________________________________________\nbatch_normalization_7 (Batch (None, 38, 5, 512) 2048 \n_________________________________________________________________\nmax_pooling2d_7 (MaxPooling2 (None, 19, 3, 512) 0 \n_________________________________________________________________\nreshape_1 (Reshape) (None, 19, 1536) 0 \n_________________________________________________________________\nself_attention_1 (SelfAttent (None, 4, 1536) 394240 \n_________________________________________________________________\naverage_pooling1d_1 (Average (None, 1, 1536) 0 \n_________________________________________________________________\nflatten_1 (Flatten) (None, 1536) 0 \n_________________________________________________________________\ndense_2 (Dense) (None, 256) 393472 \n_________________________________________________________________\ndense_3 (Dense) (None, 1251) 321507 \n=================================================================\nTotal params: 5,797,283\nTrainable params: 5,795,363\nNon-trainable params: 1,920\n_________________________________________________________________\n"
]
}
],
"source": [
"model = vgg_att(num_class)"
=======
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"model = VGGish(input_shape, 109)"
>>>>>>> 90355144ce4a7d9932e7274ea8bfbec292c5288f
]
},
{
"cell_type": "code",
<<<<<<< HEAD
"execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
"opt = Adam(lr=1e-3)\n",
"model.compile(optimizer=opt, loss='categorical_crossentropy', metrics=['accuracy'])"
=======
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"opt = Adam(lr=1e-4)\n",
"model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])"
>>>>>>> 90355144ce4a7d9932e7274ea8bfbec292c5288f
]
},
{
"cell_type": "code",
<<<<<<< HEAD
"execution_count": 20,
"metadata": {},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/20\n"
]
},
{
"output_type": "error",
"ename": "ValueError",
"evalue": "in user code:\n\n /home/bbekci/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:571 train_function *\n outputs = self.distribute_strategy.run(\n /home/bbekci/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:951 run **\n return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)\n /home/bbekci/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:2290 call_for_each_replica\n return self._call_for_each_replica(fn, args, kwargs)\n /home/bbekci/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:2649 _call_for_each_replica\n return fn(*args, **kwargs)\n /home/bbekci/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:532 train_step **\n loss = self.compiled_loss(\n /home/bbekci/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/keras/engine/compile_utils.py:205 __call__\n loss_value = loss_obj(y_t, y_p, sample_weight=sw)\n /home/bbekci/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/keras/losses.py:143 __call__\n losses = self.call(y_true, y_pred)\n /home/bbekci/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/keras/losses.py:246 call\n return self.fn(y_true, y_pred, **self._fn_kwargs)\n /home/bbekci/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/keras/losses.py:1527 categorical_crossentropy\n return K.categorical_crossentropy(y_true, y_pred, from_logits=from_logits)\n /home/bbekci/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/keras/backend.py:4561 categorical_crossentropy\n target.shape.assert_is_compatible_with(output.shape)\n /home/bbekci/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/framework/tensor_shape.py:1117 assert_is_compatible_with\n raise ValueError(\"Shapes %s and %s are incompatible\" % (self, other))\n\n ValueError: Shapes (None, 1) and (None, 1251) are incompatible\n",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-20-fc52f26b8f63>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtr_gen\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalidation_data\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mval_gen\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mepochs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m20\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;32m~/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py\u001b[0m in \u001b[0;36m_method_wrapper\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 64\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_method_wrapper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\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[1;32m 65\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_in_multi_worker_mode\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;31m# pylint: disable=protected-access\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 66\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mmethod\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\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 67\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 68\u001b[0m \u001b[0;31m# Running inside `run_distribute_coordinator` already.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)\u001b[0m\n\u001b[1;32m 846\u001b[0m batch_size=batch_size):\n\u001b[1;32m 847\u001b[0m \u001b[0mcallbacks\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_train_batch_begin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstep\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 848\u001b[0;31m \u001b[0mtmp_logs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtrain_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0miterator\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 849\u001b[0m \u001b[0;31m# Catch OutOfRangeError for Datasets of unknown size.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 850\u001b[0m \u001b[0;31m# This blocks until the batch has finished executing.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m 578\u001b[0m \u001b[0mxla_context\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mExit\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[1;32m 579\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 580\u001b[0;31m \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\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 581\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 582\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mtracing_count\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_get_tracing_count\u001b[0m\u001b[0;34m(\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[0;32m~/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py\u001b[0m in \u001b[0;36m_call\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m 625\u001b[0m \u001b[0;31m# This is the first call of __call__, so we have to initialize.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 626\u001b[0m \u001b[0minitializers\u001b[0m \u001b[0;34m=\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[0;32m--> 627\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_initialize\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwds\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0madd_initializers_to\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0minitializers\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 628\u001b[0m \u001b[0;32mfinally\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 629\u001b[0m \u001b[0;31m# At this point we know that the initialization is complete (or less\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py\u001b[0m in \u001b[0;36m_initialize\u001b[0;34m(self, args, kwds, add_initializers_to)\u001b[0m\n\u001b[1;32m 503\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_graph_deleter\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mFunctionDeleter\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_lifted_initializer_graph\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 504\u001b[0m self._concrete_stateful_fn = (\n\u001b[0;32m--> 505\u001b[0;31m self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access\n\u001b[0m\u001b[1;32m 506\u001b[0m *args, **kwds))\n\u001b[1;32m 507\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36m_get_concrete_function_internal_garbage_collected\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 2444\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwargs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2445\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_lock\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2446\u001b[0;31m \u001b[0mgraph_function\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_maybe_define_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwargs\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 2447\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mgraph_function\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2448\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36m_maybe_define_function\u001b[0;34m(self, args, kwargs)\u001b[0m\n\u001b[1;32m 2775\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2776\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_function_cache\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmissed\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0madd\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcall_context_key\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2777\u001b[0;31m \u001b[0mgraph_function\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_create_graph_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwargs\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 2778\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_function_cache\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mprimary\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mcache_key\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgraph_function\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2779\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mgraph_function\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/eager/function.py\u001b[0m in \u001b[0;36m_create_graph_function\u001b[0;34m(self, args, kwargs, override_flat_arg_shapes)\u001b[0m\n\u001b[1;32m 2655\u001b[0m \u001b[0marg_names\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mbase_arg_names\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mmissing_arg_names\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2656\u001b[0m graph_function = ConcreteFunction(\n\u001b[0;32m-> 2657\u001b[0;31m func_graph_module.func_graph_from_py_func(\n\u001b[0m\u001b[1;32m 2658\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_name\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2659\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_python_function\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py\u001b[0m in \u001b[0;36mfunc_graph_from_py_func\u001b[0;34m(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes)\u001b[0m\n\u001b[1;32m 979\u001b[0m \u001b[0m_\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moriginal_func\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtf_decorator\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0munwrap\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpython_func\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 980\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 981\u001b[0;31m \u001b[0mfunc_outputs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpython_func\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0mfunc_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mfunc_kwargs\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 982\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 983\u001b[0m \u001b[0;31m# invariant: `func_outputs` contains only Tensors, CompositeTensors,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py\u001b[0m in \u001b[0;36mwrapped_fn\u001b[0;34m(*args, **kwds)\u001b[0m\n\u001b[1;32m 439\u001b[0m \u001b[0;31m# __wrapped__ allows AutoGraph to swap in a converted function. We give\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 440\u001b[0m \u001b[0;31m# the function a weak reference to itself to avoid a reference cycle.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 441\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mweak_wrapped_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__wrapped__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\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 442\u001b[0m \u001b[0mweak_wrapped_fn\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mweakref\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mref\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mwrapped_fn\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 443\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py\u001b[0m in \u001b[0;36mwrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 966\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;31m# pylint:disable=broad-except\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 967\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mhasattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"ag_error_metadata\"\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[0;32m--> 968\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mag_error_metadata\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_exception\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0me\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 969\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 970\u001b[0m \u001b[0;32mraise\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mValueError\u001b[0m: in user code:\n\n /home/bbekci/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:571 train_function *\n outputs = self.distribute_strategy.run(\n /home/bbekci/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:951 run **\n return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)\n /home/bbekci/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:2290 call_for_each_replica\n return self._call_for_each_replica(fn, args, kwargs)\n /home/bbekci/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:2649 _call_for_each_replica\n return fn(*args, **kwargs)\n /home/bbekci/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:532 train_step **\n loss = self.compiled_loss(\n /home/bbekci/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/keras/engine/compile_utils.py:205 __call__\n loss_value = loss_obj(y_t, y_p, sample_weight=sw)\n /home/bbekci/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/keras/losses.py:143 __call__\n losses = self.call(y_true, y_pred)\n /home/bbekci/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/keras/losses.py:246 call\n return self.fn(y_true, y_pred, **self._fn_kwargs)\n /home/bbekci/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/keras/losses.py:1527 categorical_crossentropy\n return K.categorical_crossentropy(y_true, y_pred, from_logits=from_logits)\n /home/bbekci/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/keras/backend.py:4561 categorical_crossentropy\n target.shape.assert_is_compatible_with(output.shape)\n /home/bbekci/miniconda3/envs/inzpeech/lib/python3.8/site-packages/tensorflow/python/framework/tensor_shape.py:1117 assert_is_compatible_with\n raise ValueError(\"Shapes %s and %s are incompatible\" % (self, other))\n\n ValueError: Shapes (None, 1) and (None, 1251) are incompatible\n"
=======
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/20\n",
"14/14 [==============================] - 31s 2s/step - loss: 9.0328 - accuracy: 0.0238 - val_loss: 32030.5371 - val_accuracy: 0.0202\n",
"Epoch 2/20\n",
"14/14 [==============================] - 31s 2s/step - loss: 5.8168 - accuracy: 0.0306 - val_loss: 12789.2061 - val_accuracy: 0.0202\n",
"Epoch 3/20\n",
"14/14 [==============================] - 32s 2s/step - loss: 5.0801 - accuracy: 0.0522 - val_loss: 4288.9995 - val_accuracy: 0.0000e+00\n",
"Epoch 4/20\n",
"14/14 [==============================] - ETA: 0s - loss: 5.0360 - accuracy: 0.0782"
>>>>>>> 90355144ce4a7d9932e7274ea8bfbec292c5288f
]
}
],
"source": [
"model.fit(tr_gen, validation_data=val_gen, epochs=20)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
<<<<<<< HEAD
"name": "Python 3.8.5 64-bit ('inzpeech': conda)",
"display_name": "Python 3.8.5 64-bit ('inzpeech': conda)",
"metadata": {
"interpreter": {
"hash": "fcc15a4440aa802b6aa76ba989d07fd1e1f9e303ad2563ebf174689c6e63879d"
}
}
=======
"display_name": "Python 3",
"language": "python",
"name": "python3"
>>>>>>> 90355144ce4a7d9932e7274ea8bfbec292c5288f
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
<<<<<<< HEAD
"version": "3.8.5-final"
=======
"version": "3.8.5"
>>>>>>> 90355144ce4a7d9932e7274ea8bfbec292c5288f
}
},
"nbformat": 4,
"nbformat_minor": 4
<<<<<<< HEAD
}
=======
}
>>>>>>> 90355144ce4a7d9932e7274ea8bfbec292c5288f
Reference in New Issue View Git Blame Copy Permalink