Raw frequencies array (ordered by class):
[3891 3623 3523 3475 3436 3381 3329 3254 3175 3082 2995 2886 2753 2624
 2486 2354 2221 2082 1887 1750 1599 1471 1374 1251 1131 1044  947  853
  771  696  630]

Raw weights array:
[0.5666602  0.60857713 0.6258516  0.6344964  0.6416982  0.6521369
 0.66232353 0.6775891  0.6944488  0.715404   0.7361853  0.7639899
 0.800899   0.8402725  0.88691676 0.9366504  0.99273974 1.0590178
 1.1684552  1.2599286  1.3789086  1.4988953  1.6047125  1.76249
 1.9494916  2.1119492  2.3282735  2.5848477  2.85976    3.167924
 3.4998016 ]
 
Epoch 1/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 141s 95ms/step - loss: 3.5063 - sparse_categorical_accuracy: 0.0847 - val_loss: 3.1195 - val_sparse_categorical_accuracy: 0.1229
Epoch 2/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 128ms/step - loss: 3.0440 - sparse_categorical_accuracy: 0.1313 - val_loss: 2.7783 - val_sparse_categorical_accuracy: 0.1651
Epoch 3/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 128ms/step - loss: 2.7280 - sparse_categorical_accuracy: 0.1687 - val_loss: 2.5787 - val_sparse_categorical_accuracy: 0.1986
Epoch 4/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 2.5022 - sparse_categorical_accuracy: 0.2061 - val_loss: 2.4241 - val_sparse_categorical_accuracy: 0.2252
Epoch 5/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 93ms/step - loss: 2.3103 - sparse_categorical_accuracy: 0.2415 - val_loss: 2.2807 - val_sparse_categorical_accuracy: 0.2441
Epoch 6/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 129ms/step - loss: 2.1711 - sparse_categorical_accuracy: 0.2652 - val_loss: 2.1897 - val_sparse_categorical_accuracy: 0.2713
Epoch 7/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 141s 128ms/step - loss: 2.0315 - sparse_categorical_accuracy: 0.2954 - val_loss: 2.1995 - val_sparse_categorical_accuracy: 0.2669
Epoch 8/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 129ms/step - loss: 1.9447 - sparse_categorical_accuracy: 0.3209 - val_loss: 1.9481 - val_sparse_categorical_accuracy: 0.3292
Epoch 9/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 103s 94ms/step - loss: 1.8347 - sparse_categorical_accuracy: 0.3450 - val_loss: 1.8937 - val_sparse_categorical_accuracy: 0.3489
Epoch 10/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 104s 94ms/step - loss: 1.7520 - sparse_categorical_accuracy: 0.3678 - val_loss: 1.8557 - val_sparse_categorical_accuracy: 0.3702
Epoch 11/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 104s 94ms/step - loss: 1.6540 - sparse_categorical_accuracy: 0.3958 - val_loss: 1.8170 - val_sparse_categorical_accuracy: 0.3537
Epoch 12/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 104s 94ms/step - loss: 1.6188 - sparse_categorical_accuracy: 0.4055 - val_loss: 1.6951 - val_sparse_categorical_accuracy: 0.3967
Epoch 13/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 128ms/step - loss: 1.4945 - sparse_categorical_accuracy: 0.4373 - val_loss: 1.6790 - val_sparse_categorical_accuracy: 0.3949
Epoch 14/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 1.4210 - sparse_categorical_accuracy: 0.4654 - val_loss: 1.5994 - val_sparse_categorical_accuracy: 0.4376
Epoch 15/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 129ms/step - loss: 1.3640 - sparse_categorical_accuracy: 0.4809 - val_loss: 1.5162 - val_sparse_categorical_accuracy: 0.4657
Epoch 16/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 128ms/step - loss: 1.2975 - sparse_categorical_accuracy: 0.5027 - val_loss: 1.4959 - val_sparse_categorical_accuracy: 0.4490
Epoch 17/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 141s 128ms/step - loss: 1.2401 - sparse_categorical_accuracy: 0.5328 - val_loss: 1.5350 - val_sparse_categorical_accuracy: 0.4238
Epoch 18/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 93ms/step - loss: 1.2230 - sparse_categorical_accuracy: 0.5319 - val_loss: 1.3559 - val_sparse_categorical_accuracy: 0.5294
Epoch 19/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 93ms/step - loss: 1.1551 - sparse_categorical_accuracy: 0.5639 - val_loss: 1.4109 - val_sparse_categorical_accuracy: 0.5018
Epoch 20/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 1.0733 - sparse_categorical_accuracy: 0.5930 - val_loss: 1.2997 - val_sparse_categorical_accuracy: 0.5425
Epoch 21/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 128ms/step - loss: 1.0192 - sparse_categorical_accuracy: 0.6166 - val_loss: 1.2861 - val_sparse_categorical_accuracy: 0.5418
Epoch 22/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.9883 - sparse_categorical_accuracy: 0.6246 - val_loss: 1.1966 - val_sparse_categorical_accuracy: 0.5571
Epoch 23/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 101s 92ms/step - loss: 0.9461 - sparse_categorical_accuracy: 0.6495 - val_loss: 1.1995 - val_sparse_categorical_accuracy: 0.5889
Epoch 24/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 129ms/step - loss: 0.9066 - sparse_categorical_accuracy: 0.6570 - val_loss: 1.1706 - val_sparse_categorical_accuracy: 0.5886
Epoch 25/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 129ms/step - loss: 0.8842 - sparse_categorical_accuracy: 0.6680 - val_loss: 1.1144 - val_sparse_categorical_accuracy: 0.6112
Epoch 26/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.8388 - sparse_categorical_accuracy: 0.6880 - val_loss: 1.0847 - val_sparse_categorical_accuracy: 0.6237
Epoch 27/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 93ms/step - loss: 0.8316 - sparse_categorical_accuracy: 0.6938 - val_loss: 1.0527 - val_sparse_categorical_accuracy: 0.6260
Epoch 28/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 128ms/step - loss: 0.7728 - sparse_categorical_accuracy: 0.7138 - val_loss: 0.9861 - val_sparse_categorical_accuracy: 0.6737
Epoch 29/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.7240 - sparse_categorical_accuracy: 0.7320 - val_loss: 1.0753 - val_sparse_categorical_accuracy: 0.6237
Epoch 30/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 129ms/step - loss: 0.7918 - sparse_categorical_accuracy: 0.7112 - val_loss: 1.0001 - val_sparse_categorical_accuracy: 0.6674
Epoch 31/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.7373 - sparse_categorical_accuracy: 0.7346 - val_loss: 0.9500 - val_sparse_categorical_accuracy: 0.6798
Epoch 32/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.6236 - sparse_categorical_accuracy: 0.7750 - val_loss: 1.0343 - val_sparse_categorical_accuracy: 0.6480
Epoch 33/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.6385 - sparse_categorical_accuracy: 0.7667 - val_loss: 0.8546 - val_sparse_categorical_accuracy: 0.7237
Epoch 34/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 101s 92ms/step - loss: 0.5606 - sparse_categorical_accuracy: 0.7985 - val_loss: 0.8846 - val_sparse_categorical_accuracy: 0.7022
Epoch 35/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 128ms/step - loss: 0.5422 - sparse_categorical_accuracy: 0.8009 - val_loss: 1.3372 - val_sparse_categorical_accuracy: 0.5792
Epoch 36/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.7459 - sparse_categorical_accuracy: 0.7277 - val_loss: 0.7844 - val_sparse_categorical_accuracy: 0.7296
Epoch 37/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 141s 128ms/step - loss: 0.4957 - sparse_categorical_accuracy: 0.8270 - val_loss: 0.7892 - val_sparse_categorical_accuracy: 0.7478
Epoch 38/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 93ms/step - loss: 0.4920 - sparse_categorical_accuracy: 0.8266 - val_loss: 0.7312 - val_sparse_categorical_accuracy: 0.7721
Epoch 39/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.4362 - sparse_categorical_accuracy: 0.8448 - val_loss: 0.7643 - val_sparse_categorical_accuracy: 0.7507
Epoch 40/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 128ms/step - loss: 0.6042 - sparse_categorical_accuracy: 0.7819 - val_loss: 0.7490 - val_sparse_categorical_accuracy: 0.7595
Epoch 41/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.4159 - sparse_categorical_accuracy: 0.8561 - val_loss: 0.7051 - val_sparse_categorical_accuracy: 0.7744
Epoch 42/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.4226 - sparse_categorical_accuracy: 0.8507 - val_loss: 0.9141 - val_sparse_categorical_accuracy: 0.7137
Epoch 43/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.6913 - sparse_categorical_accuracy: 0.7599 - val_loss: 0.6967 - val_sparse_categorical_accuracy: 0.7871
Epoch 44/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 129ms/step - loss: 0.3741 - sparse_categorical_accuracy: 0.8736 - val_loss: 0.6096 - val_sparse_categorical_accuracy: 0.8193
Epoch 45/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 103s 93ms/step - loss: 0.3536 - sparse_categorical_accuracy: 0.8755 - val_loss: 0.7451 - val_sparse_categorical_accuracy: 0.7699
Epoch 46/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.3835 - sparse_categorical_accuracy: 0.8663 - val_loss: 0.9191 - val_sparse_categorical_accuracy: 0.7137
Epoch 47/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 103s 93ms/step - loss: 0.4594 - sparse_categorical_accuracy: 0.8399 - val_loss: 0.5755 - val_sparse_categorical_accuracy: 0.8265
Epoch 48/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 103s 93ms/step - loss: 0.3152 - sparse_categorical_accuracy: 0.8922 - val_loss: 0.7857 - val_sparse_categorical_accuracy: 0.7494
Epoch 49/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 128ms/step - loss: 0.4080 - sparse_categorical_accuracy: 0.8530 - val_loss: 0.6122 - val_sparse_categorical_accuracy: 0.8197
Epoch 50/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 103s 93ms/step - loss: 0.2776 - sparse_categorical_accuracy: 0.9056 - val_loss: 0.6253 - val_sparse_categorical_accuracy: 0.8138
Epoch 51/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 128ms/step - loss: 0.3147 - sparse_categorical_accuracy: 0.8882 - val_loss: 0.6713 - val_sparse_categorical_accuracy: 0.7982
Epoch 52/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 129ms/step - loss: 0.3284 - sparse_categorical_accuracy: 0.8829 - val_loss: 0.6955 - val_sparse_categorical_accuracy: 0.7932
Epoch 53/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 103s 93ms/step - loss: 0.3345 - sparse_categorical_accuracy: 0.8820 - val_loss: 0.8909 - val_sparse_categorical_accuracy: 0.7349
Epoch 54/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 129ms/step - loss: 0.3876 - sparse_categorical_accuracy: 0.8667 - val_loss: 0.6236 - val_sparse_categorical_accuracy: 0.8161
Epoch 55/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 128ms/step - loss: 0.3574 - sparse_categorical_accuracy: 0.8808 - val_loss: 0.6451 - val_sparse_categorical_accuracy: 0.8177
Epoch 56/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 104s 94ms/step - loss: 0.4551 - sparse_categorical_accuracy: 0.8550 - val_loss: 0.5218 - val_sparse_categorical_accuracy: 0.8510
Epoch 57/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 141s 128ms/step - loss: 0.2240 - sparse_categorical_accuracy: 0.9264 - val_loss: 0.6082 - val_sparse_categorical_accuracy: 0.8137
Epoch 58/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 103s 94ms/step - loss: 0.5220 - sparse_categorical_accuracy: 0.8386 - val_loss: 0.5610 - val_sparse_categorical_accuracy: 0.8402
Epoch 59/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 93ms/step - loss: 0.2638 - sparse_categorical_accuracy: 0.9162 - val_loss: 0.5923 - val_sparse_categorical_accuracy: 0.8222
Epoch 60/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.2752 - sparse_categorical_accuracy: 0.9055 - val_loss: 0.5278 - val_sparse_categorical_accuracy: 0.8459
Epoch 61/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 103s 93ms/step - loss: 0.2645 - sparse_categorical_accuracy: 0.9166 - val_loss: 0.5084 - val_sparse_categorical_accuracy: 0.8557
Epoch 62/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 103s 93ms/step - loss: 0.2239 - sparse_categorical_accuracy: 0.9264 - val_loss: 0.5300 - val_sparse_categorical_accuracy: 0.8535
Epoch 63/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 129ms/step - loss: 0.2263 - sparse_categorical_accuracy: 0.9216 - val_loss: 0.6185 - val_sparse_categorical_accuracy: 0.8187
Epoch 64/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 129ms/step - loss: 0.3703 - sparse_categorical_accuracy: 0.8752 - val_loss: 0.4914 - val_sparse_categorical_accuracy: 0.8537
Epoch 65/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 103s 93ms/step - loss: 0.1856 - sparse_categorical_accuracy: 0.9364 - val_loss: 0.5522 - val_sparse_categorical_accuracy: 0.8436
Epoch 66/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.3678 - sparse_categorical_accuracy: 0.8830 - val_loss: 0.5898 - val_sparse_categorical_accuracy: 0.8336
Epoch 67/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.2207 - sparse_categorical_accuracy: 0.9305 - val_loss: 0.5002 - val_sparse_categorical_accuracy: 0.8605
Epoch 68/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 128ms/step - loss: 0.2984 - sparse_categorical_accuracy: 0.9015 - val_loss: 0.4992 - val_sparse_categorical_accuracy: 0.8666
Epoch 69/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 129ms/step - loss: 0.2326 - sparse_categorical_accuracy: 0.9267 - val_loss: 0.5811 - val_sparse_categorical_accuracy: 0.8404
Epoch 70/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 103s 93ms/step - loss: 0.1997 - sparse_categorical_accuracy: 0.9342 - val_loss: 0.4364 - val_sparse_categorical_accuracy: 0.8776
Epoch 71/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 141s 128ms/step - loss: 0.2431 - sparse_categorical_accuracy: 0.9214 - val_loss: 0.5514 - val_sparse_categorical_accuracy: 0.8507
Epoch 72/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.2293 - sparse_categorical_accuracy: 0.9317 - val_loss: 0.4445 - val_sparse_categorical_accuracy: 0.8888
Epoch 73/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 128ms/step - loss: 0.1723 - sparse_categorical_accuracy: 0.9461 - val_loss: 0.6261 - val_sparse_categorical_accuracy: 0.8226
Epoch 74/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 101s 92ms/step - loss: 0.3360 - sparse_categorical_accuracy: 0.8895 - val_loss: 0.5033 - val_sparse_categorical_accuracy: 0.8746
Epoch 75/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 101s 91ms/step - loss: 0.1620 - sparse_categorical_accuracy: 0.9528 - val_loss: 0.4880 - val_sparse_categorical_accuracy: 0.8767
Epoch 76/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 129ms/step - loss: 0.1875 - sparse_categorical_accuracy: 0.9372 - val_loss: 0.6711 - val_sparse_categorical_accuracy: 0.8076
Epoch 77/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 101s 92ms/step - loss: 0.2677 - sparse_categorical_accuracy: 0.9088 - val_loss: 0.4544 - val_sparse_categorical_accuracy: 0.8767
Epoch 78/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.1540 - sparse_categorical_accuracy: 0.9521 - val_loss: 0.3757 - val_sparse_categorical_accuracy: 0.9022
Epoch 79/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 101s 92ms/step - loss: 0.1394 - sparse_categorical_accuracy: 0.9568 - val_loss: 0.4317 - val_sparse_categorical_accuracy: 0.8833
Epoch 80/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 101s 92ms/step - loss: 0.1928 - sparse_categorical_accuracy: 0.9375 - val_loss: 0.4686 - val_sparse_categorical_accuracy: 0.8736
Epoch 81/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 129ms/step - loss: 0.1520 - sparse_categorical_accuracy: 0.9516 - val_loss: 0.5845 - val_sparse_categorical_accuracy: 0.8456
Epoch 82/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 129ms/step - loss: 0.3194 - sparse_categorical_accuracy: 0.8989 - val_loss: 0.4601 - val_sparse_categorical_accuracy: 0.8819
Epoch 83/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 103s 93ms/step - loss: 0.1643 - sparse_categorical_accuracy: 0.9480 - val_loss: 0.4936 - val_sparse_categorical_accuracy: 0.8682
Epoch 84/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 101s 92ms/step - loss: 0.1859 - sparse_categorical_accuracy: 0.9398 - val_loss: 0.4400 - val_sparse_categorical_accuracy: 0.8843
Epoch 85/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 129ms/step - loss: 0.1281 - sparse_categorical_accuracy: 0.9594 - val_loss: 0.3993 - val_sparse_categorical_accuracy: 0.8983
Epoch 86/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 129ms/step - loss: 0.1076 - sparse_categorical_accuracy: 0.9638 - val_loss: 0.6158 - val_sparse_categorical_accuracy: 0.8481
Epoch 87/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.3873 - sparse_categorical_accuracy: 0.8805 - val_loss: 0.4991 - val_sparse_categorical_accuracy: 0.8757
Epoch 88/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 128ms/step - loss: 0.1475 - sparse_categorical_accuracy: 0.9591 - val_loss: 0.3787 - val_sparse_categorical_accuracy: 0.9029
Epoch 89/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 93ms/step - loss: 0.1576 - sparse_categorical_accuracy: 0.9514 - val_loss: 0.7678 - val_sparse_categorical_accuracy: 0.7984
Epoch 90/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 129ms/step - loss: 0.2998 - sparse_categorical_accuracy: 0.9038 - val_loss: 0.3672 - val_sparse_categorical_accuracy: 0.9085
Epoch 91/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 141s 128ms/step - loss: 0.1307 - sparse_categorical_accuracy: 0.9629 - val_loss: 0.3913 - val_sparse_categorical_accuracy: 0.9057
Epoch 92/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 128ms/step - loss: 0.1078 - sparse_categorical_accuracy: 0.9642 - val_loss: 0.4339 - val_sparse_categorical_accuracy: 0.8909
Epoch 93/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 128ms/step - loss: 0.3010 - sparse_categorical_accuracy: 0.9071 - val_loss: 0.3868 - val_sparse_categorical_accuracy: 0.8993
Epoch 94/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 128ms/step - loss: 0.0985 - sparse_categorical_accuracy: 0.9703 - val_loss: 0.4927 - val_sparse_categorical_accuracy: 0.8788
Epoch 95/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 128ms/step - loss: 0.3044 - sparse_categorical_accuracy: 0.9028 - val_loss: 0.4289 - val_sparse_categorical_accuracy: 0.8960
Epoch 96/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 143s 129ms/step - loss: 0.1062 - sparse_categorical_accuracy: 0.9699 - val_loss: 0.3635 - val_sparse_categorical_accuracy: 0.9121
Epoch 97/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 141s 128ms/step - loss: 0.1017 - sparse_categorical_accuracy: 0.9685 - val_loss: 0.5956 - val_sparse_categorical_accuracy: 0.8388
Epoch 98/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.3230 - sparse_categorical_accuracy: 0.8998 - val_loss: 0.3868 - val_sparse_categorical_accuracy: 0.9121
Epoch 99/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.1094 - sparse_categorical_accuracy: 0.9681 - val_loss: 0.4522 - val_sparse_categorical_accuracy: 0.8957
Epoch 100/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.1137 - sparse_categorical_accuracy: 0.9654 - val_loss: 0.4857 - val_sparse_categorical_accuracy: 0.8863
Epoch 101/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.1328 - sparse_categorical_accuracy: 0.9592 - val_loss: 0.4403 - val_sparse_categorical_accuracy: 0.8954
Epoch 102/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 128ms/step - loss: 0.1971 - sparse_categorical_accuracy: 0.9391 - val_loss: 0.3760 - val_sparse_categorical_accuracy: 0.9091
Epoch 103/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 128ms/step - loss: 0.1286 - sparse_categorical_accuracy: 0.9614 - val_loss: 0.3866 - val_sparse_categorical_accuracy: 0.9076
Epoch 104/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 128ms/step - loss: 0.1390 - sparse_categorical_accuracy: 0.9566 - val_loss: 0.3867 - val_sparse_categorical_accuracy: 0.9058
Epoch 105/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.1711 - sparse_categorical_accuracy: 0.9499 - val_loss: 0.4288 - val_sparse_categorical_accuracy: 0.9055
Epoch 106/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 129ms/step - loss: 0.1133 - sparse_categorical_accuracy: 0.9675 - val_loss: 0.3636 - val_sparse_categorical_accuracy: 0.9156
Epoch 107/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 101s 92ms/step - loss: 0.0866 - sparse_categorical_accuracy: 0.9759 - val_loss: 0.5217 - val_sparse_categorical_accuracy: 0.8656
Epoch 108/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 92ms/step - loss: 0.2134 - sparse_categorical_accuracy: 0.9340 - val_loss: 0.3395 - val_sparse_categorical_accuracy: 0.9204
Epoch 109/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 101s 92ms/step - loss: 0.1215 - sparse_categorical_accuracy: 0.9673 - val_loss: 0.4090 - val_sparse_categorical_accuracy: 0.9007
Epoch 110/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 142s 128ms/step - loss: 0.2466 - sparse_categorical_accuracy: 0.9280 - val_loss: 0.3594 - val_sparse_categorical_accuracy: 0.9154
Epoch 111/561
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 0s 85ms/step - loss: 0.0762 - sparse_categorical_accuracy: 0.9775
Accuracy alcanzada (0.9831 >= 0.98). Deteniendo entrenamiento.
1105/1105 ━━━━━━━━━━━━━━━━━━━━ 102s 93ms/step - loss: 0.0761 - sparse_categorical_accuracy: 0.9776 - val_loss: 0.3963 - val_sparse_categorical_accuracy: 0.9051
350/350 ━━━━━━━━━━━━━━━━━━━━ 13s 27ms/step - loss: 0.3287 - sparse_categorical_accuracy: 0.9255
Test Loss: 0.3325
Test Accuracy (Pitstop): 0.9249

Classification Report
              precision    recall  f1-score   support

     Class 0       0.94      0.92      0.93       604
     Class 1       0.90      0.90      0.90       536
     Class 2       0.91      0.92      0.92       556
     Class 3       0.95      0.92      0.94       535
     Class 4       0.95      0.94      0.94       516
     Class 5       0.95      0.94      0.95       504
     Class 6       0.96      0.95      0.95       468
     Class 7       0.95      0.94      0.95       514
     Class 8       0.92      0.94      0.93       492
     Class 9       0.93      0.94      0.94       454
    Class 10       0.93      0.95      0.94       437
    Class 11       0.94      0.92      0.93       447
    Class 12       0.90      0.94      0.92       397
    Class 13       0.92      0.92      0.92       396
    Class 14       0.94      0.93      0.93       403
    Class 15       0.94      0.95      0.94       333
    Class 16       0.93      0.94      0.94       315
    Class 17       0.94      0.92      0.93       297
    Class 18       0.93      0.92      0.93       309
    Class 19       0.88      0.93      0.90       270
    Class 20       0.87      0.86      0.87       241
    Class 21       0.84      0.90      0.87       220
    Class 22       0.91      0.89      0.90       206
    Class 23       0.93      0.88      0.90       189
    Class 24       0.88      0.94      0.91       158
    Class 25       0.84      0.92      0.88       133
    Class 26       0.92      0.87      0.90       148
    Class 27       0.89      0.89      0.89       123
    Class 28       0.84      0.88      0.86       105
    Class 29       0.82      0.66      0.73       101
    Class 30       0.95      0.96      0.95       784

    accuracy                           0.92     11191
   macro avg       0.91      0.91      0.91     11191
weighted avg       0.93      0.92      0.92     11191


Mean Absolute Error (MAE):  0.2535
Root Mean Squared Error (RMSE): 1.8230

Top-2 Accuracy: 0.9704
Top-3 Accuracy: 0.9808

Expected Calibration Error (ECE): 0.0122