(minerva_venv) patryk.miziula@pascal01:/mnt/ml-team/homes/patryk.miziula/Minerva/minerva$ CUDA_VISIBLE_DEVICES=2 python run_minerva.py -- dry_run --problem fashion_mnist
2018-01-30 17-10-26 minerva >>> starting experiment...
Using TensorFlow backend.
2018-01-30 17-10-27 minerva >>> running: None
neptune: Executing in Offline Mode.
2018-01-30 17-10-27 minerva >>> Saving graph to output/path_to_your_solution/class_predictions_graph.json
2018-01-30 17-10-28 minerva >>> step input unpacking inputs
2018-01-30 17-10-28 minerva >>> step input loading...
2018-01-30 17-10-28 minerva >>> step input transforming...
2018-01-30 17-10-28 minerva >>> step keras_model unpacking inputs
Epoch 1/200
2018-01-30 17:10:28.435787: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2018-01-30 17:10:28.435811: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2018-01-30 17:10:28.435816: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2018-01-30 17:10:28.435821: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2018-01-30 17:10:28.435826: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
2018-01-30 17:10:31.195282: I tensorflow/core/common_runtime/gpu/gpu_device.cc:940] Found device 0 with properties:
name: GeForce GTX 1070
major: 6 minor: 1 memoryClockRate (GHz) 1.721
pciBusID 0000:09:00.0
Total memory: 7.92GiB
Free memory: 7.83GiB
2018-01-30 17:10:31.195309: I tensorflow/core/common_runtime/gpu/gpu_device.cc:961] DMA: 0
2018-01-30 17:10:31.195315: I tensorflow/core/common_runtime/gpu/gpu_device.cc:971] 0:   Y
2018-01-30 17:10:31.195322: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1070, pci bus id: 0000:09:00.0)
188/188 [==============================] - 11s 57ms/step - loss: 1.7692 - acc: 0.3435 - val_loss: 0.9480 - val_acc: 0.6308
Epoch 2/200
188/188 [==============================] - 7s 38ms/step - loss: 0.9336 - acc: 0.6457 - val_loss: 0.6975 - val_acc: 0.7243
Epoch 3/200
188/188 [==============================] - 7s 37ms/step - loss: 0.7753 - acc: 0.7008 - val_loss: 0.6136 - val_acc: 0.7528
Epoch 4/200
188/188 [==============================] - 6s 35ms/step - loss: 0.7086 - acc: 0.7254 - val_loss: 0.5709 - val_acc: 0.7702
Epoch 5/200
188/188 [==============================] - 7s 36ms/step - loss: 0.6619 - acc: 0.7417 - val_loss: 0.5489 - val_acc: 0.7899
Epoch 6/200
188/188 [==============================] - 7s 36ms/step - loss: 0.6254 - acc: 0.7585 - val_loss: 0.5142 - val_acc: 0.7982
Epoch 7/200
188/188 [==============================] - 7s 36ms/step - loss: 0.6018 - acc: 0.7690 - val_loss: 0.4885 - val_acc: 0.8122
Epoch 8/200
188/188 [==============================] - 7s 36ms/step - loss: 0.5769 - acc: 0.7788 - val_loss: 0.4948 - val_acc: 0.8119
Epoch 9/200
188/188 [==============================] - 7s 36ms/step - loss: 0.5581 - acc: 0.7849 - val_loss: 0.4590 - val_acc: 0.8235
Epoch 10/200
188/188 [==============================] - 7s 36ms/step - loss: 0.5459 - acc: 0.7922 - val_loss: 0.4569 - val_acc: 0.8238
Epoch 11/200
188/188 [==============================] - 7s 38ms/step - loss: 0.5315 - acc: 0.7969 - val_loss: 0.4402 - val_acc: 0.8330
Epoch 12/200
188/188 [==============================] - 7s 36ms/step - loss: 0.5167 - acc: 0.8037 - val_loss: 0.4322 - val_acc: 0.8368
Epoch 13/200
188/188 [==============================] - 7s 35ms/step - loss: 0.5012 - acc: 0.8111 - val_loss: 0.4068 - val_acc: 0.8466
Epoch 14/200
188/188 [==============================] - 7s 35ms/step - loss: 0.4870 - acc: 0.8169 - val_loss: 0.4149 - val_acc: 0.8425
Epoch 15/200
188/188 [==============================] - 7s 36ms/step - loss: 0.4864 - acc: 0.8185 - val_loss: 0.3933 - val_acc: 0.8515
Epoch 16/200
188/188 [==============================] - 7s 37ms/step - loss: 0.4695 - acc: 0.8233 - val_loss: 0.3903 - val_acc: 0.8564
Epoch 17/200
188/188 [==============================] - 7s 36ms/step - loss: 0.4577 - acc: 0.8268 - val_loss: 0.3909 - val_acc: 0.8532
Epoch 18/200
188/188 [==============================] - 7s 37ms/step - loss: 0.4509 - acc: 0.8325 - val_loss: 0.3758 - val_acc: 0.8586
Epoch 19/200
188/188 [==============================] - 7s 37ms/step - loss: 0.4418 - acc: 0.8334 - val_loss: 0.3662 - val_acc: 0.8627
Epoch 20/200
188/188 [==============================] - 7s 38ms/step - loss: 0.4341 - acc: 0.8382 - val_loss: 0.3587 - val_acc: 0.8660
Epoch 21/200
188/188 [==============================] - 7s 36ms/step - loss: 0.4288 - acc: 0.8393 - val_loss: 0.3530 - val_acc: 0.8659
Epoch 22/200
188/188 [==============================] - 7s 37ms/step - loss: 0.4222 - acc: 0.8427 - val_loss: 0.3490 - val_acc: 0.8698
Epoch 23/200
188/188 [==============================] - 7s 36ms/step - loss: 0.4179 - acc: 0.8468 - val_loss: 0.3451 - val_acc: 0.8716
Epoch 24/200
188/188 [==============================] - 7s 39ms/step - loss: 0.4129 - acc: 0.8465 - val_loss: 0.3434 - val_acc: 0.8720
Epoch 25/200
188/188 [==============================] - 7s 35ms/step - loss: 0.4054 - acc: 0.8510 - val_loss: 0.3393 - val_acc: 0.8697
Epoch 26/200
188/188 [==============================] - 7s 35ms/step - loss: 0.3990 - acc: 0.8528 - val_loss: 0.3281 - val_acc: 0.8763
Epoch 27/200
188/188 [==============================] - 7s 38ms/step - loss: 0.3954 - acc: 0.8538 - val_loss: 0.3241 - val_acc: 0.8787
Epoch 28/200
188/188 [==============================] - 7s 36ms/step - loss: 0.3899 - acc: 0.8547 - val_loss: 0.3219 - val_acc: 0.8788
Epoch 29/200
188/188 [==============================] - 7s 37ms/step - loss: 0.3861 - acc: 0.8560 - val_loss: 0.3100 - val_acc: 0.8847
Epoch 30/200
188/188 [==============================] - 7s 36ms/step - loss: 0.3844 - acc: 0.8586 - val_loss: 0.3066 - val_acc: 0.8857
Epoch 31/200
188/188 [==============================] - 7s 36ms/step - loss: 0.3782 - acc: 0.8605 - val_loss: 0.3103 - val_acc: 0.8839
Epoch 32/200
188/188 [==============================] - 7s 37ms/step - loss: 0.3746 - acc: 0.8611 - val_loss: 0.3055 - val_acc: 0.8883
Epoch 33/200
188/188 [==============================] - 7s 37ms/step - loss: 0.3680 - acc: 0.8644 - val_loss: 0.3192 - val_acc: 0.8808
Epoch 34/200
188/188 [==============================] - 7s 36ms/step - loss: 0.3643 - acc: 0.8662 - val_loss: 0.3020 - val_acc: 0.8877
Epoch 35/200
188/188 [==============================] - 7s 37ms/step - loss: 0.3603 - acc: 0.8660 - val_loss: 0.2974 - val_acc: 0.8890
Epoch 36/200
188/188 [==============================] - 7s 36ms/step - loss: 0.3595 - acc: 0.8667 - val_loss: 0.3025 - val_acc: 0.8922
Epoch 37/200
188/188 [==============================] - 7s 38ms/step - loss: 0.3561 - acc: 0.8690 - val_loss: 0.3020 - val_acc: 0.8896
Epoch 38/200
188/188 [==============================] - 7s 35ms/step - loss: 0.3503 - acc: 0.8710 - val_loss: 0.2977 - val_acc: 0.8889
Epoch 39/200
188/188 [==============================] - 7s 36ms/step - loss: 0.3495 - acc: 0.8709 - val_loss: 0.2985 - val_acc: 0.8900
Epoch 40/200
188/188 [==============================] - 7s 36ms/step - loss: 0.3476 - acc: 0.8731 - val_loss: 0.2979 - val_acc: 0.8893
Epoch 41/200
188/188 [==============================] - 7s 37ms/step - loss: 0.3464 - acc: 0.8717 - val_loss: 0.2962 - val_acc: 0.8886
Epoch 42/200
188/188 [==============================] - 7s 37ms/step - loss: 0.3396 - acc: 0.8747 - val_loss: 0.2969 - val_acc: 0.8891
Epoch 43/200
188/188 [==============================] - 7s 38ms/step - loss: 0.3360 - acc: 0.8757 - val_loss: 0.2813 - val_acc: 0.8958
Epoch 44/200
188/188 [==============================] - 7s 35ms/step - loss: 0.3365 - acc: 0.8757 - val_loss: 0.2960 - val_acc: 0.8870
Epoch 45/200
188/188 [==============================] - 7s 36ms/step - loss: 0.3345 - acc: 0.8759 - val_loss: 0.2781 - val_acc: 0.8962
Epoch 46/200
188/188 [==============================] - 7s 37ms/step - loss: 0.3324 - acc: 0.8771 - val_loss: 0.2826 - val_acc: 0.8960
Epoch 47/200
188/188 [==============================] - 7s 35ms/step - loss: 0.3331 - acc: 0.8776 - val_loss: 0.2857 - val_acc: 0.8932
Epoch 48/200
188/188 [==============================] - 7s 35ms/step - loss: 0.3237 - acc: 0.8817 - val_loss: 0.2714 - val_acc: 0.9000
Epoch 49/200
188/188 [==============================] - 7s 36ms/step - loss: 0.3264 - acc: 0.8799 - val_loss: 0.2814 - val_acc: 0.8963
Epoch 50/200
188/188 [==============================] - 7s 36ms/step - loss: 0.3188 - acc: 0.8837 - val_loss: 0.2725 - val_acc: 0.8987
Epoch 51/200
188/188 [==============================] - 7s 37ms/step - loss: 0.3186 - acc: 0.8814 - val_loss: 0.2694 - val_acc: 0.9007
Epoch 52/200
188/188 [==============================] - 7s 36ms/step - loss: 0.3165 - acc: 0.8842 - val_loss: 0.2686 - val_acc: 0.9016
Epoch 53/200
188/188 [==============================] - 7s 36ms/step - loss: 0.3173 - acc: 0.8821 - val_loss: 0.2633 - val_acc: 0.9022
Epoch 54/200
188/188 [==============================] - 7s 37ms/step - loss: 0.3135 - acc: 0.8850 - val_loss: 0.2794 - val_acc: 0.8973
Epoch 55/200
188/188 [==============================] - 7s 37ms/step - loss: 0.3108 - acc: 0.8862 - val_loss: 0.2597 - val_acc: 0.9042
Epoch 56/200
188/188 [==============================] - 7s 35ms/step - loss: 0.3118 - acc: 0.8839 - val_loss: 0.2621 - val_acc: 0.9039
Epoch 57/200
188/188 [==============================] - 7s 36ms/step - loss: 0.3074 - acc: 0.8884 - val_loss: 0.2611 - val_acc: 0.9045
Epoch 58/200
188/188 [==============================] - 7s 36ms/step - loss: 0.3077 - acc: 0.8866 - val_loss: 0.2611 - val_acc: 0.9025
Epoch 59/200
188/188 [==============================] - 7s 38ms/step - loss: 0.3058 - acc: 0.8863 - val_loss: 0.2581 - val_acc: 0.9038
Epoch 60/200
188/188 [==============================] - 7s 35ms/step - loss: 0.3051 - acc: 0.8881 - val_loss: 0.2678 - val_acc: 0.8989
Epoch 61/200
188/188 [==============================] - 7s 37ms/step - loss: 0.3007 - acc: 0.8891 - val_loss: 0.2560 - val_acc: 0.9077
Epoch 62/200
188/188 [==============================] - 7s 37ms/step - loss: 0.3009 - acc: 0.8885 - val_loss: 0.2591 - val_acc: 0.9048
Epoch 63/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2993 - acc: 0.8887 - val_loss: 0.2525 - val_acc: 0.9080
Epoch 64/200
188/188 [==============================] - 7s 37ms/step - loss: 0.2950 - acc: 0.8907 - val_loss: 0.2619 - val_acc: 0.9020
Epoch 65/200
188/188 [==============================] - 7s 38ms/step - loss: 0.2945 - acc: 0.8931 - val_loss: 0.2547 - val_acc: 0.9074
Epoch 66/200
188/188 [==============================] - 7s 35ms/step - loss: 0.2958 - acc: 0.8910 - val_loss: 0.2525 - val_acc: 0.9053
Epoch 67/200
188/188 [==============================] - 7s 35ms/step - loss: 0.2943 - acc: 0.8919 - val_loss: 0.2551 - val_acc: 0.9066
Epoch 68/200
188/188 [==============================] - 7s 37ms/step - loss: 0.2909 - acc: 0.8932 - val_loss: 0.2546 - val_acc: 0.9061
Epoch 69/200
188/188 [==============================] - 6s 34ms/step - loss: 0.2901 - acc: 0.8947 - val_loss: 0.2448 - val_acc: 0.9111
Epoch 70/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2885 - acc: 0.8932 - val_loss: 0.2491 - val_acc: 0.9098
Epoch 71/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2883 - acc: 0.8946 - val_loss: 0.2464 - val_acc: 0.9092
Epoch 72/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2865 - acc: 0.8936 - val_loss: 0.2515 - val_acc: 0.9066
Epoch 73/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2843 - acc: 0.8962 - val_loss: 0.2480 - val_acc: 0.9090
Epoch 74/200
188/188 [==============================] - 7s 37ms/step - loss: 0.2847 - acc: 0.8948 - val_loss: 0.2466 - val_acc: 0.9101
Epoch 75/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2808 - acc: 0.8969 - val_loss: 0.2543 - val_acc: 0.9062
Epoch 76/200
188/188 [==============================] - 6s 35ms/step - loss: 0.2824 - acc: 0.8968 - val_loss: 0.2571 - val_acc: 0.9047
Epoch 77/200
188/188 [==============================] - 7s 38ms/step - loss: 0.2797 - acc: 0.8966 - val_loss: 0.2460 - val_acc: 0.9064
Epoch 78/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2788 - acc: 0.8977 - val_loss: 0.2445 - val_acc: 0.9097
Epoch 79/200
188/188 [==============================] - 7s 35ms/step - loss: 0.2778 - acc: 0.8978 - val_loss: 0.2477 - val_acc: 0.9092
Epoch 80/200
188/188 [==============================] - 7s 35ms/step - loss: 0.2745 - acc: 0.8993 - val_loss: 0.2395 - val_acc: 0.9119
Epoch 81/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2752 - acc: 0.8985 - val_loss: 0.2451 - val_acc: 0.9092
Epoch 82/200
188/188 [==============================] - 7s 37ms/step - loss: 0.2779 - acc: 0.8983 - val_loss: 0.2378 - val_acc: 0.9116
Epoch 83/200
188/188 [==============================] - 7s 35ms/step - loss: 0.2742 - acc: 0.8992 - val_loss: 0.2395 - val_acc: 0.9115
Epoch 84/200
188/188 [==============================] - 7s 35ms/step - loss: 0.2709 - acc: 0.9002 - val_loss: 0.2406 - val_acc: 0.9102
Epoch 85/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2686 - acc: 0.9009 - val_loss: 0.2385 - val_acc: 0.9147
Epoch 86/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2678 - acc: 0.9012 - val_loss: 0.2377 - val_acc: 0.9105
Epoch 87/200
188/188 [==============================] - 7s 35ms/step - loss: 0.2691 - acc: 0.9015 - val_loss: 0.2423 - val_acc: 0.9093
Epoch 88/200
188/188 [==============================] - 7s 35ms/step - loss: 0.2666 - acc: 0.9017 - val_loss: 0.2320 - val_acc: 0.9136
Epoch 89/200
188/188 [==============================] - 7s 37ms/step - loss: 0.2683 - acc: 0.9019 - val_loss: 0.2362 - val_acc: 0.9125
Epoch 90/200
188/188 [==============================] - 7s 38ms/step - loss: 0.2631 - acc: 0.9038 - val_loss: 0.2301 - val_acc: 0.9161
Epoch 91/200
188/188 [==============================] - 7s 37ms/step - loss: 0.2623 - acc: 0.9035 - val_loss: 0.2337 - val_acc: 0.9147
Epoch 92/200
188/188 [==============================] - 7s 35ms/step - loss: 0.2642 - acc: 0.9026 - val_loss: 0.2348 - val_acc: 0.9127
Epoch 93/200
188/188 [==============================] - 6s 34ms/step - loss: 0.2610 - acc: 0.9030 - val_loss: 0.2347 - val_acc: 0.9120
Epoch 94/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2606 - acc: 0.9047 - val_loss: 0.2295 - val_acc: 0.9175
Epoch 95/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2622 - acc: 0.9040 - val_loss: 0.2393 - val_acc: 0.9128
Epoch 96/200
188/188 [==============================] - 7s 35ms/step - loss: 0.2616 - acc: 0.9045 - val_loss: 0.2367 - val_acc: 0.9122
Epoch 97/200
188/188 [==============================] - 7s 37ms/step - loss: 0.2570 - acc: 0.9049 - val_loss: 0.2385 - val_acc: 0.9127
Epoch 98/200
188/188 [==============================] - 7s 35ms/step - loss: 0.2545 - acc: 0.9075 - val_loss: 0.2428 - val_acc: 0.9109
Epoch 99/200
188/188 [==============================] - 7s 38ms/step - loss: 0.2569 - acc: 0.9059 - val_loss: 0.2325 - val_acc: 0.9143
Epoch 100/200
188/188 [==============================] - 7s 35ms/step - loss: 0.2559 - acc: 0.9045 - val_loss: 0.2292 - val_acc: 0.9146
Epoch 101/200
188/188 [==============================] - 7s 37ms/step - loss: 0.2551 - acc: 0.9059 - val_loss: 0.2260 - val_acc: 0.9170
Epoch 102/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2521 - acc: 0.9071 - val_loss: 0.2380 - val_acc: 0.9132
Epoch 103/200
188/188 [==============================] - 7s 35ms/step - loss: 0.2519 - acc: 0.9066 - val_loss: 0.2305 - val_acc: 0.9164
Epoch 104/200
188/188 [==============================] - 7s 37ms/step - loss: 0.2528 - acc: 0.9076 - val_loss: 0.2306 - val_acc: 0.9162
Epoch 105/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2502 - acc: 0.9067 - val_loss: 0.2290 - val_acc: 0.9157
Epoch 106/200
188/188 [==============================] - 7s 39ms/step - loss: 0.2478 - acc: 0.9102 - val_loss: 0.2234 - val_acc: 0.9179
Epoch 107/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2469 - acc: 0.9097 - val_loss: 0.2316 - val_acc: 0.9155
Epoch 108/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2477 - acc: 0.9082 - val_loss: 0.2321 - val_acc: 0.9148
Epoch 109/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2464 - acc: 0.9088 - val_loss: 0.2260 - val_acc: 0.9166
Epoch 110/200
188/188 [==============================] - 7s 37ms/step - loss: 0.2454 - acc: 0.9089 - val_loss: 0.2246 - val_acc: 0.9184
Epoch 111/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2453 - acc: 0.9101 - val_loss: 0.2300 - val_acc: 0.9152
Epoch 112/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2456 - acc: 0.9097 - val_loss: 0.2271 - val_acc: 0.9177
Epoch 113/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2402 - acc: 0.9115 - val_loss: 0.2252 - val_acc: 0.9164
Epoch 114/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2401 - acc: 0.9108 - val_loss: 0.2239 - val_acc: 0.9177
Epoch 115/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2422 - acc: 0.9115 - val_loss: 0.2191 - val_acc: 0.9173
Epoch 116/200
188/188 [==============================] - 7s 35ms/step - loss: 0.2395 - acc: 0.9113 - val_loss: 0.2253 - val_acc: 0.9172
Epoch 117/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2404 - acc: 0.9117 - val_loss: 0.2239 - val_acc: 0.9164
Epoch 118/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2406 - acc: 0.9111 - val_loss: 0.2234 - val_acc: 0.9191
Epoch 119/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2381 - acc: 0.9114 - val_loss: 0.2309 - val_acc: 0.9171
Epoch 120/200
188/188 [==============================] - 6s 34ms/step - loss: 0.2360 - acc: 0.9126 - val_loss: 0.2184 - val_acc: 0.9207
Epoch 121/200
188/188 [==============================] - 7s 38ms/step - loss: 0.2359 - acc: 0.9131 - val_loss: 0.2213 - val_acc: 0.9175
Epoch 122/200
188/188 [==============================] - 7s 35ms/step - loss: 0.2346 - acc: 0.9121 - val_loss: 0.2267 - val_acc: 0.9170
Epoch 123/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2331 - acc: 0.9135 - val_loss: 0.2177 - val_acc: 0.9191
Epoch 124/200
188/188 [==============================] - 7s 35ms/step - loss: 0.2323 - acc: 0.9147 - val_loss: 0.2204 - val_acc: 0.9208
Epoch 125/200
188/188 [==============================] - 7s 35ms/step - loss: 0.2324 - acc: 0.9146 - val_loss: 0.2259 - val_acc: 0.9161
Epoch 126/200
188/188 [==============================] - 7s 37ms/step - loss: 0.2321 - acc: 0.9143 - val_loss: 0.2247 - val_acc: 0.9153
Epoch 127/200
188/188 [==============================] - 7s 35ms/step - loss: 0.2294 - acc: 0.9150 - val_loss: 0.2237 - val_acc: 0.9196
Epoch 128/200
188/188 [==============================] - 7s 35ms/step - loss: 0.2273 - acc: 0.9154 - val_loss: 0.2240 - val_acc: 0.9171
Epoch 129/200
188/188 [==============================] - 7s 35ms/step - loss: 0.2312 - acc: 0.9159 - val_loss: 0.2189 - val_acc: 0.9223
Epoch 130/200
188/188 [==============================] - 7s 39ms/step - loss: 0.2271 - acc: 0.9158 - val_loss: 0.2205 - val_acc: 0.9194
Epoch 131/200
188/188 [==============================] - 7s 35ms/step - loss: 0.2291 - acc: 0.9152 - val_loss: 0.2238 - val_acc: 0.9188
Epoch 132/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2279 - acc: 0.9172 - val_loss: 0.2282 - val_acc: 0.9172
Epoch 133/200
188/188 [==============================] - 7s 36ms/step - loss: 0.2286 - acc: 0.9161 - val_loss: 0.2273 - val_acc: 0.9177
188/188 [==============================] - 6s 31ms/step
2018-01-30 17-25-42 minerva >>> step keras_model saving transformer...
Traceback (most recent call last):
  File "run_minerva.py", line 46, in <module>
    action()
  File "/home/patryk.miziula/Minerva/minerva_venv/lib/python3.5/site-packages/click/core.py", line 722, in __call__
    return self.main(*args, **kwargs)
  File "/home/patryk.miziula/Minerva/minerva_venv/lib/python3.5/site-packages/click/core.py", line 697, in main
    rv = self.invoke(ctx)
  File "/home/patryk.miziula/Minerva/minerva_venv/lib/python3.5/site-packages/click/core.py", line 1066, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/home/patryk.miziula/Minerva/minerva_venv/lib/python3.5/site-packages/click/core.py", line 895, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/home/patryk.miziula/Minerva/minerva_venv/lib/python3.5/site-packages/click/core.py", line 535, in invoke
    return callback(*args, **kwargs)
  File "run_minerva.py", line 27, in dry_run
    pm.dry_run(sub_problem, train_mode, dev_mode, cloud_mode)
  File "/mnt/ml-team/homes/patryk.miziula/Minerva/minerva/minerva/fashion_mnist/problem_manager.py", line 16, in dry_run
    trainer.train()
  File "/mnt/ml-team/homes/patryk.miziula/Minerva/minerva/minerva/fashion_mnist/trainer.py", line 23, in train
    'inference': False}})
  File "/mnt/ml-team/homes/patryk.miziula/Minerva/minerva/minerva/backend/base.py", line 68, in fit_transform
    step_inputs[input_step.name] = input_step.fit_transform(data)
  File "/mnt/ml-team/homes/patryk.miziula/Minerva/minerva/minerva/backend/base.py", line 74, in fit_transform
    step_output_data = self._cached_fit_transform(step_inputs)
  File "/mnt/ml-team/homes/patryk.miziula/Minerva/minerva/minerva/backend/base.py", line 86, in _cached_fit_transform
    self.transformer.save(self.cache_filepath_step_transformer)
  File "/mnt/ml-team/homes/patryk.miziula/Minerva/minerva/minerva/backend/models/keras/models_keras.py", line 50, in save
    self.model.save(filepath)
  File "/home/patryk.miziula/Minerva/minerva_venv/lib/python3.5/site-packages/keras/engine/topology.py", line 2573, in save
    save_model(self, filepath, overwrite, include_optimizer)
  File "/home/patryk.miziula/Minerva/minerva_venv/lib/python3.5/site-packages/keras/models.py", line 60, in save_model
    raise ImportError('`save_model` requires h5py.')
ImportError: `save_model` requires h5py.
Sentry is attempting to send 1 pending error messages
Waiting up to 10 seconds
Press Ctrl-C to quit