Mnist数据集
0~9的手写体图片，该数据默认已经将数据分成训练集和测试集。训练集有60000张图片，测试集有10000张图片。

导入必要库

import tensorflow as tf
from tensorflow import keras
import numpy as np
import matplotlib.pyplot as plt
print(tf.__version__)

下载数据文件

DATA_URL = "https://storage.go`在这里插入代码片`ogleapis.com/tensorflow/tf-keras-datasets/mnist.npz"
path = keras.utils.get_file("mnist.npz",origin=DATA_URL)

解析npz数据文件为numpy格式的数据

with np.load(path) as data:train_data = data['x_train']train_labels = data['y_train']test_data = data['x_test']test_labels = data['y_test']

使用tf.data.Dataset加载numpy数据
我们将图像数据数组和相应的标签数组，作为元组传递给 tf.data.Dataset.from_tensor_slices 以创建 tf.data.Dataset 。

使用tf.data加载numpy数据

train_dataset = tf.data.Dataset.from_tensor_slices((train_data,train_labels))
test_dataset = tf.data.Dataset.from_tensor_slices((test_data,test_labels))
Shuffle和批次化数据进行训练前准备
BATCH_SIZE = 64
SHUFFLE_BUFFER_SIZE = 100train_dataset = train_dataset.shuffle(SHUFFLE_BUFFER_SIZE).batch(BATCH_SIZE)
test_dataset = test_dataset.batch(BATCH_SIZE)

模型构建及训练

model = tf.keras.Sequential([tf.keras.layers.Flatten(input_shape=(28, 28)),tf.keras.layers.Dense(128, activation='relu'),tf.keras.layers.Dense(10, activation='softmax')
])model.compile(optimizer=tf.keras.optimizers.RMSprop(),loss=tf.keras.losses.SparseCategoricalCrossentropy(),metrics=[tf.keras.metrics.SparseCategoricalAccuracy()])model.fit(train_dataset,epochs=10)

Train for 938 steps
Epoch 1/10

1/938 […] - ETA: 11:24 - loss: 111.1329 - sparse_categorical_accuracy: 0.1406
20/938 […] - ETA: 35s - loss: 32.7100 - sparse_categorical_accuracy: 0.5633
40/938 [>…] - ETA: 18s - loss: 21.6791 - sparse_categorical_accuracy: 0.6703
60/938 [>…] - ETA: 12s - loss: 17.2033 - sparse_categorical_accuracy: 0.7174
80/938 [=>…] - ETA: 10s - loss: 14.2442 - sparse_categorical_accuracy: 0.7480
100/938 [>…] - ETA: 8s - loss: 12.2833 - sparse_categorical_accuracy: 0.7709
120/938 [>…] - ETA: 7s - loss: 11.0870 - sparse_categorical_accuracy: 0.7819
140/938 [=>…] - ETA: 6s - loss: 10.1944 - sparse_categorical_accuracy: 0.7903
159/938 [>…] - ETA: 5s - loss: 9.4267 - sparse_categorical_accuracy: 0.7991
179/938 [>…] - ETA: 5s - loss: 8.6361 - sparse_categorical_accuracy: 0.8105
199/938 [=>…] - ETA: 4s - loss: 8.1802 - sparse_categorical_accuracy: 0.8142
219/938 [>…] - ETA: 4s - loss: 7.7128 - sparse_categorical_accuracy: 0.8176
238/938 [>…] - ETA: 3s - loss: 7.3328 - sparse_categorical_accuracy: 0.8210
258/938 [=>…] - ETA: 3s - loss: 6.9488 - sparse_categorical_accuracy: 0.8249
278/938 [=>…] - ETA: 3s - loss: 6.5940 - sparse_categorical_accuracy: 0.8287
298/938 [>…] - ETA: 3s - loss: 6.2636 - sparse_categorical_accuracy: 0.8335
318/938 [=>…] - ETA: 3s - loss: 5.9963 - sparse_categorical_accuracy: 0.8364
339/938 [=>…] - ETA: 2s - loss: 5.7277 - sparse_categorical_accuracy: 0.8406
360/938 [>…] - ETA: 2s - loss: 5.5116 - sparse_categorical_accuracy: 0.8433
380/938 [=>…] - ETA: 2s - loss: 5.3110 - sparse_categorical_accuracy: 0.8459
400/938 [=>…] - ETA: 2s - loss: 5.1290 - sparse_categorical_accuracy: 0.8478
419/938 [>…] - ETA: 2s - loss: 4.9773 - sparse_categorical_accuracy: 0.8498
438/938 [=>…] - ETA: 2s - loss: 4.8220 - sparse_categorical_accuracy: 0.8516
458/938 [=>…] - ETA: 2s - loss: 4.6737 - sparse_categorical_accuracy: 0.8526
478/938 [>…] - ETA: 1s - loss: 4.5308 - sparse_categorical_accuracy: 0.8528
498/938 [>…] - ETA: 1s - loss: 4.4027 - sparse_categorical_accuracy: 0.8532
518/938 [=>…] - ETA: 1s - loss: 4.2768 - sparse_categorical_accuracy: 0.8540
538/938 [>…] - ETA: 1s - loss: 4.1556 - sparse_categorical_accuracy: 0.8555
558/938 [>…] - ETA: 1s - loss: 4.0413 - sparse_categorical_accuracy: 0.8565
578/938 [=>…] - ETA: 1s - loss: 3.9355 - sparse_categorical_accuracy: 0.8574
598/938 [>…] - ETA: 1s - loss: 3.8393 - sparse_categorical_accuracy: 0.8584
617/938 [>…] - ETA: 1s - loss: 3.7514 - sparse_categorical_accuracy: 0.8594
636/938 [=>…] - ETA: 1s - loss: 3.6633 - sparse_categorical_accuracy: 0.8602
656/938 [=>…] - ETA: 1s - loss: 3.5780 - sparse_categorical_accuracy: 0.8609
676/938 [>…] - ETA: 0s - loss: 3.4987 - sparse_categorical_accuracy: 0.8612
696/938 [=>…] - ETA: 0s - loss: 3.4163 - sparse_categorical_accuracy: 0.8624
716/938 [=>…] - ETA: 0s - loss: 3.3439 - sparse_categorical_accuracy: 0.8634
736/938 [>…] - ETA: 0s - loss: 3.2719 - sparse_categorical_accuracy: 0.8642
756/938 [=>…] - ETA: 0s - loss: 3.2039 - sparse_categorical_accuracy: 0.8651
776/938 [=>…] - ETA: 0s - loss: 3.1422 - sparse_categorical_accuracy: 0.8658
797/938 [>…] - ETA: 0s - loss: 3.0772 - sparse_categorical_accuracy: 0.8661
817/938 [=>…] - ETA: 0s - loss: 3.0207 - sparse_categorical_accuracy: 0.8671
838/938 [=>…] - ETA: 0s - loss: 2.9621 - sparse_categorical_accuracy: 0.8677
858/938 [>…] - ETA: 0s - loss: 2.9080 - sparse_categorical_accuracy: 0.8685
878/938 [=>…] - ETA: 0s - loss: 2.8545 - sparse_categorical_accuracy: 0.8695
898/938 [=>…] - ETA: 0s - loss: 2.8005 - sparse_categorical_accuracy: 0.8708
918/938 [>.] - ETA: 0s - loss: 2.7483 - sparse_categorical_accuracy: 0.8722
938/938 [================] - 3s 3ms/step - loss: 2.7024 - sparse_categorical_accuracy: 0.8735
Epoch 2/10

1/938 […] - ETA: 14s - loss: 0.5318 - sparse_categorical_accuracy: 0.9219
20/938 […] - ETA: 3s - loss: 0.7503 - sparse_categorical_accuracy: 0.9016
40/938 [>…] - ETA: 2s - loss: 0.6746 - sparse_categorical_accuracy: 0.9086
60/938 [>…] - ETA: 2s - loss: 0.6212 - sparse_categorical_accuracy: 0.9180
80/938 [=>…] - ETA: 2s - loss: 0.5782 - sparse_categorical_accuracy: 0.9229
100/938 [>…] - ETA: 2s - loss: 0.5659 - sparse_categorical_accuracy: 0.9219
120/938 [>…] - ETA: 2s - loss: 0.5556 - sparse_categorical_accuracy: 0.9204
140/938 [=>…] - ETA: 2s - loss: 0.5685 - sparse_categorical_accuracy: 0.9186
160/938 [>…] - ETA: 2s - loss: 0.5496 - sparse_categorical_accuracy: 0.9188
180/938 [>…] - ETA: 2s - loss: 0.5370 - sparse_categorical_accuracy: 0.9201
200/938 [=>…] - ETA: 1s - loss: 0.5417 - sparse_categorical_accuracy: 0.9184
220/938 [>…] - ETA: 1s - loss: 0.5521 - sparse_categorical_accuracy: 0.9168
240/938 [>…] - ETA: 1s - loss: 0.5637 - sparse_categorical_accuracy: 0.9160
260/938 [=>…] - ETA: 1s - loss: 0.5576 - sparse_categorical_accuracy: 0.9162
280/938 [=>…] - ETA: 1s - loss: 0.5578 - sparse_categorical_accuracy: 0.9165
300/938 [>…] - ETA: 1s - loss: 0.5529 - sparse_categorical_accuracy: 0.9178
320/938 [=>…] - ETA: 1s - loss: 0.5610 - sparse_categorical_accuracy: 0.9179
340/938 [=>…] - ETA: 1s - loss: 0.5577 - sparse_categorical_accuracy: 0.9182
360/938 [>…] - ETA: 1s - loss: 0.5496 - sparse_categorical_accuracy: 0.9185
380/938 [=>…] - ETA: 1s - loss: 0.5465 - sparse_categorical_accuracy: 0.9197
400/938 [=>…] - ETA: 1s - loss: 0.5471 - sparse_categorical_accuracy: 0.9198
420/938 [>…] - ETA: 1s - loss: 0.5545 - sparse_categorical_accuracy: 0.9195
440/938 [=>…] - ETA: 1s - loss: 0.5542 - sparse_categorical_accuracy: 0.9198
459/938 [=>…] - ETA: 1s - loss: 0.5504 - sparse_categorical_accuracy: 0.9198
479/938 [>…] - ETA: 1s - loss: 0.5454 - sparse_categorical_accuracy: 0.9204
499/938 [>…] - ETA: 1s - loss: 0.5435 - sparse_categorical_accuracy: 0.9204
519/938 [=>…] - ETA: 1s - loss: 0.5452 - sparse_categorical_accuracy: 0.9202
539/938 [>…] - ETA: 1s - loss: 0.5422 - sparse_categorical_accuracy: 0.9203
559/938 [>…] - ETA: 0s - loss: 0.5406 - sparse_categorical_accuracy: 0.9207
579/938 [=>…] - ETA: 0s - loss: 0.5392 - sparse_categorical_accuracy: 0.9210
599/938 [>…] - ETA: 0s - loss: 0.5400 - sparse_categorical_accuracy: 0.9209
619/938 [>…] - ETA: 0s - loss: 0.5374 - sparse_categorical_accuracy: 0.9211
640/938 [=>…] - ETA: 0s - loss: 0.5358 - sparse_categorical_accuracy: 0.9214
660/938 [>…] - ETA: 0s - loss: 0.5331 - sparse_categorical_accuracy: 0.9214
679/938 [>…] - ETA: 0s - loss: 0.5339 - sparse_categorical_accuracy: 0.9216
699/938 [=>…] - ETA: 0s - loss: 0.5281 - sparse_categorical_accuracy: 0.9221
719/938 [=>…] - ETA: 0s - loss: 0.5263 - sparse_categorical_accuracy: 0.9223
739/938 [>…] - ETA: 0s - loss: 0.5233 - sparse_categorical_accuracy: 0.9223
759/938 [=>…] - ETA: 0s - loss: 0.5206 - sparse_categorical_accuracy: 0.9226
779/938 [=>…] - ETA: 0s - loss: 0.5235 - sparse_categorical_accuracy: 0.9224
798/938 [>…] - ETA: 0s - loss: 0.5202 - sparse_categorical_accuracy: 0.9225
818/938 [=>…] - ETA: 0s - loss: 0.5193 - sparse_categorical_accuracy: 0.9229
838/938 [=>…] - ETA: 0s - loss: 0.5162 - sparse_categorical_accuracy: 0.9230
858/938 [>…] - ETA: 0s - loss: 0.5116 - sparse_categorical_accuracy: 0.9234
878/938 [=>…] - ETA: 0s - loss: 0.5074 - sparse_categorical_accuracy: 0.9239
898/938 [=>…] - ETA: 0s - loss: 0.5023 - sparse_categorical_accuracy: 0.9246
918/938 [>.] - ETA: 0s - loss: 0.4956 - sparse_categorical_accuracy: 0.9253
936/938 [>.] - ETA: 0s - loss: 0.4938 - sparse_categorical_accuracy: 0.9258
938/938 [==============] - 2s 3ms/step - loss: 0.4945 - sparse_categorical_accuracy: 0.9258
Epoch 3/10

1/938 […] - ETA: 16s - loss: 0.1087 - sparse_categorical_accuracy: 0.9688
20/938 […] - ETA: 3s - loss: 0.5862 - sparse_categorical_accuracy: 0.9328
40/938 [>…] - ETA: 2s - loss: 0.5121 - sparse_categorical_accuracy: 0.9371
54/938 [>…] - ETA: 2s - loss: 0.4385 - sparse_categorical_accuracy: 0.9436
69/938 [=>…] - ETA: 2s - loss: 0.4167 - sparse_categorical_accuracy: 0.9470
85/938 [=>…] - ETA: 2s - loss: 0.3965 - sparse_categorical_accuracy: 0.9460
99/938 [>…] - ETA: 2s - loss: 0.3815 - sparse_categorical_accuracy: 0.9463
118/938 [>…] - ETA: 2s - loss: 0.3754 - sparse_categorical_accuracy: 0.9460
138/938 [=>…] - ETA: 2s - loss: 0.3972 - sparse_categorical_accuracy: 0.9444
158/938 [>…] - ETA: 2s - loss: 0.3866 - sparse_categorical_accuracy: 0.9451
178/938 [>…] - ETA: 2s - loss: 0.3799 - sparse_categorical_accuracy: 0.9445
198/938 [=>…] - ETA: 2s - loss: 0.3837 - sparse_categorical_accuracy: 0.9441
218/938 [=>…] - ETA: 2s - loss: 0.3909 - sparse_categorical_accuracy: 0.9440
238/938 [>…] - ETA: 2s - loss: 0.3994 - sparse_categorical_accuracy: 0.9436
256/938 [=>…] - ETA: 1s - loss: 0.3934 - sparse_categorical_accuracy: 0.9436
276/938 [=>…] - ETA: 1s - loss: 0.3963 - sparse_categorical_accuracy: 0.9440
296/938 [>…] - ETA: 1s - loss: 0.3962 - sparse_categorical_accuracy: 0.9444
316/938 [=>…] - ETA: 1s - loss: 0.4018 - sparse_categorical_accuracy: 0.9439
336/938 [=>…] - ETA: 1s - loss: 0.3980 - sparse_categorical_accuracy: 0.9441
356/938 [>…] - ETA: 1s - loss: 0.3938 - sparse_categorical_accuracy: 0.9443
376/938 [=>…] - ETA: 1s - loss: 0.3945 - sparse_categorical_accuracy: 0.9446
395/938 [=>…] - ETA: 1s - loss: 0.3958 - sparse_categorical_accuracy: 0.9443
415/938 [>…] - ETA: 1s - loss: 0.4061 - sparse_categorical_accuracy: 0.9434
434/938 [>…] - ETA: 1s - loss: 0.4087 - sparse_categorical_accuracy: 0.9430
454/938 [=>…] - ETA: 1s - loss: 0.4035 - sparse_categorical_accuracy: 0.9434
474/938 [>…] - ETA: 1s - loss: 0.4022 - sparse_categorical_accuracy: 0.9433
493/938 [>…] - ETA: 1s - loss: 0.4020 - sparse_categorical_accuracy: 0.9434
513/938 [=>…] - ETA: 1s - loss: 0.4012 - sparse_categorical_accuracy: 0.9430
532/938 [>…] - ETA: 1s - loss: 0.4022 - sparse_categorical_accuracy: 0.9432
552/938 [>…] - ETA: 1s - loss: 0.3987 - sparse_categorical_accuracy: 0.9433
572/938 [=>…] - ETA: 0s - loss: 0.3967 - sparse_categorical_accuracy: 0.9438
592/938 [=>…] - ETA: 0s - loss: 0.3985 - sparse_categorical_accuracy: 0.9437
612/938 [>…] - ETA: 0s - loss: 0.3969 - sparse_categorical_accuracy: 0.9437
631/938 [=>…] - ETA: 0s - loss: 0.4010 - sparse_categorical_accuracy: 0.9432
648/938 [=>…] - ETA: 0s - loss: 0.4017 - sparse_categorical_accuracy: 0.9432
664/938 [>…] - ETA: 0s - loss: 0.4044 - sparse_categorical_accuracy: 0.9430
682/938 [>…] - ETA: 0s - loss: 0.4036 - sparse_categorical_accuracy: 0.9430
701/938 [=>…] - ETA: 0s - loss: 0.4005 - sparse_categorical_accuracy: 0.9434
719/938 [=>…] - ETA: 0s - loss: 0.3999 - sparse_categorical_accuracy: 0.9435
737/938 [>…] - ETA: 0s - loss: 0.3985 - sparse_categorical_accuracy: 0.9436
756/938 [=>…] - ETA: 0s - loss: 0.3978 - sparse_categorical_accuracy: 0.9434
776/938 [=>…] - ETA: 0s - loss: 0.3998 - sparse_categorical_accuracy: 0.9432
795/938 [>…] - ETA: 0s - loss: 0.4008 - sparse_categorical_accuracy: 0.9427
814/938 [=>…] - ETA: 0s - loss: 0.4012 - sparse_categorical_accuracy: 0.9429
833/938 [=>…] - ETA: 0s - loss: 0.4017 - sparse_categorical_accuracy: 0.9426
852/938 [>…] - ETA: 0s - loss: 0.3980 - sparse_categorical_accuracy: 0.9427
872/938 [>…] - ETA: 0s - loss: 0.3960 - sparse_categorical_accuracy: 0.9429
891/938 [=>…] - ETA: 0s - loss: 0.3929 - sparse_categorical_accuracy: 0.9430
911/938 [>.] - ETA: 0s - loss: 0.3891 - sparse_categorical_accuracy: 0.9433
928/938 [>.] - ETA: 0s - loss: 0.3846 - sparse_categorical_accuracy: 0.9438
938/938 [================] - 3s 3ms/step - loss: 0.3855 - sparse_categorical_accuracy: 0.9441
Epoch 4/10

1/938 […] - ETA: 14s - loss: 0.2610 - sparse_categorical_accuracy: 0.9531
9/938 […] - ETA: 7s - loss: 0.3007 - sparse_categorical_accuracy: 0.9583
22/938 […] - ETA: 5s - loss: 0.5099 - sparse_categorical_accuracy: 0.9368
41/938 [>…] - ETA: 3s - loss: 0.4120 - sparse_categorical_accuracy: 0.9417
59/938 [>…] - ETA: 3s - loss: 0.3770 - sparse_categorical_accuracy: 0.9468
79/938 [=>…] - ETA: 3s - loss: 0.3286 - sparse_categorical_accuracy: 0.9517
99/938 [>…] - ETA: 2s - loss: 0.3215 - sparse_categorical_accuracy: 0.9519
119/938 [>…] - ETA: 2s - loss: 0.3062 - sparse_categorical_accuracy: 0.9533
139/938 [=>…] - ETA: 2s - loss: 0.3224 - sparse_categorical_accuracy: 0.9523
159/938 [>…] - ETA: 2s - loss: 0.3189 - sparse_categorical_accuracy: 0.9524
179/938 [>…] - ETA: 2s - loss: 0.3118 - sparse_categorical_accuracy: 0.9530
199/938 [=>…] - ETA: 2s - loss: 0.3121 - sparse_categorical_accuracy: 0.9525
219/938 [>…] - ETA: 2s - loss: 0.3220 - sparse_categorical_accuracy: 0.9526
239/938 [>…] - ETA: 2s - loss: 0.3346 - sparse_categorical_accuracy: 0.9521
260/938 [=>…] - ETA: 1s - loss: 0.3342 - sparse_categorical_accuracy: 0.9523
281/938 [=>…] - ETA: 1s - loss: 0.3488 - sparse_categorical_accuracy: 0.9520
301/938 [>…] - ETA: 1s - loss: 0.3435 - sparse_categorical_accuracy: 0.9522
321/938 [=>…] - ETA: 1s - loss: 0.3462 - sparse_categorical_accuracy: 0.9523
341/938 [=>…] - ETA: 1s - loss: 0.3429 - sparse_categorical_accuracy: 0.9522
361/938 [>…] - ETA: 1s - loss: 0.3400 - sparse_categorical_accuracy: 0.9518
381/938 [=>…] - ETA: 1s - loss: 0.3404 - sparse_categorical_accuracy: 0.9521
401/938 [=>…] - ETA: 1s - loss: 0.3433 - sparse_categorical_accuracy: 0.9524
421/938 [>…] - ETA: 1s - loss: 0.3487 - sparse_categorical_accuracy: 0.9519
441/938 [=>…] - ETA: 1s - loss: 0.3478 - sparse_categorical_accuracy: 0.9522
461/938 [=>…] - ETA: 1s - loss: 0.3468 - sparse_categorical_accuracy: 0.9520
481/938 [>…] - ETA: 1s - loss: 0.3425 - sparse_categorical_accuracy: 0.9522
501/938 [=>…] - ETA: 1s - loss: 0.3423 - sparse_categorical_accuracy: 0.9521
521/938 [=>…] - ETA: 1s - loss: 0.3451 - sparse_categorical_accuracy: 0.9520
541/938 [>…] - ETA: 1s - loss: 0.3415 - sparse_categorical_accuracy: 0.9523
561/938 [>…] - ETA: 1s - loss: 0.3405 - sparse_categorical_accuracy: 0.9526
581/938 [=>…] - ETA: 0s - loss: 0.3396 - sparse_categorical_accuracy: 0.9527
601/938 [>…] - ETA: 0s - loss: 0.3414 - sparse_categorical_accuracy: 0.9523
621/938 [>…] - ETA: 0s - loss: 0.3409 - sparse_categorical_accuracy: 0.9525
641/938 [=>…] - ETA: 0s - loss: 0.3417 - sparse_categorical_accuracy: 0.9526
661/938 [>…] - ETA: 0s - loss: 0.3422 - sparse_categorical_accuracy: 0.9522
681/938 [>…] - ETA: 0s - loss: 0.3463 - sparse_categorical_accuracy: 0.9521
701/938 [=>…] - ETA: 0s - loss: 0.3428 - sparse_categorical_accuracy: 0.9524
721/938 [>…] - ETA: 0s - loss: 0.3392 - sparse_categorical_accuracy: 0.9527
741/938 [>…] - ETA: 0s - loss: 0.3382 - sparse_categorical_accuracy: 0.9525
761/938 [=>…] - ETA: 0s - loss: 0.3360 - sparse_categorical_accuracy: 0.9525
781/938 [=>…] - ETA: 0s - loss: 0.3393 - sparse_categorical_accuracy: 0.9520
801/938 [>…] - ETA: 0s - loss: 0.3398 - sparse_categorical_accuracy: 0.9518
820/938 [=>…] - ETA: 0s - loss: 0.3395 - sparse_categorical_accuracy: 0.9520
840/938 [=>…] - ETA: 0s - loss: 0.3397 - sparse_categorical_accuracy: 0.9518
860/938 [>…] - ETA: 0s - loss: 0.3365 - sparse_categorical_accuracy: 0.9521
880/938 [=>…] - ETA: 0s - loss: 0.3350 - sparse_categorical_accuracy: 0.9520
900/938 [=>…] - ETA: 0s - loss: 0.3333 - sparse_categorical_accuracy: 0.9522
920/938 [>.] - ETA: 0s - loss: 0.3300 - sparse_categorical_accuracy: 0.9526
938/938 [================] - 2s 3ms/step - loss: 0.3288 - sparse_categorical_accuracy: 0.9528
Epoch 5/10

1/938 […] - ETA: 13s - loss: 0.2853 - sparse_categorical_accuracy: 0.9375
20/938 […] - ETA: 2s - loss: 0.4085 - sparse_categorical_accuracy: 0.9563
40/938 [>…] - ETA: 2s - loss: 0.2935 - sparse_categorical_accuracy: 0.9594
60/938 [>…] - ETA: 2s - loss: 0.2836 - sparse_categorical_accuracy: 0.9563
80/938 [=>…] - ETA: 2s - loss: 0.2747 - sparse_categorical_accuracy: 0.9570
100/938 [>…] - ETA: 2s - loss: 0.2865 - sparse_categorical_accuracy: 0.9563
120/938 [>…] - ETA: 2s - loss: 0.2887 - sparse_categorical_accuracy: 0.9570
140/938 [=>…] - ETA: 2s - loss: 0.3004 - sparse_categorical_accuracy: 0.9554
160/938 [>…] - ETA: 2s - loss: 0.2936 - sparse_categorical_accuracy: 0.9563
181/938 [>…] - ETA: 2s - loss: 0.2874 - sparse_categorical_accuracy: 0.9570
201/938 [=>…] - ETA: 1s - loss: 0.2852 - sparse_categorical_accuracy: 0.9569
221/938 [>…] - ETA: 1s - loss: 0.2943 - sparse_categorical_accuracy: 0.9569
241/938 [>…] - ETA: 1s - loss: 0.3028 - sparse_categorical_accuracy: 0.9573
260/938 [=>…] - ETA: 1s - loss: 0.2938 - sparse_categorical_accuracy: 0.9577
281/938 [=>…] - ETA: 1s - loss: 0.3141 - sparse_categorical_accuracy: 0.9577
301/938 [>…] - ETA: 1s - loss: 0.3119 - sparse_categorical_accuracy: 0.9580
321/938 [=>…] - ETA: 1s - loss: 0.3159 - sparse_categorical_accuracy: 0.9573
341/938 [=>…] - ETA: 1s - loss: 0.3143 - sparse_categorical_accuracy: 0.9576
361/938 [>…] - ETA: 1s - loss: 0.3094 - sparse_categorical_accuracy: 0.9578
381/938 [=>…] - ETA: 1s - loss: 0.3078 - sparse_categorical_accuracy: 0.9581
401/938 [=>…] - ETA: 1s - loss: 0.3096 - sparse_categorical_accuracy: 0.9581
421/938 [>…] - ETA: 1s - loss: 0.3170 - sparse_categorical_accuracy: 0.9578
440/938 [=>…] - ETA: 1s - loss: 0.3174 - sparse_categorical_accuracy: 0.9576
460/938 [=>…] - ETA: 1s - loss: 0.3144 - sparse_categorical_accuracy: 0.9579
480/938 [>…] - ETA: 1s - loss: 0.3121 - sparse_categorical_accuracy: 0.9580
500/938 [>…] - ETA: 1s - loss: 0.3116 - sparse_categorical_accuracy: 0.9578
520/938 [=>…] - ETA: 1s - loss: 0.3162 - sparse_categorical_accuracy: 0.9575
540/938 [>…] - ETA: 1s - loss: 0.3132 - sparse_categorical_accuracy: 0.9579
560/938 [>…] - ETA: 0s - loss: 0.3134 - sparse_categorical_accuracy: 0.9580
580/938 [=>…] - ETA: 0s - loss: 0.3143 - sparse_categorical_accuracy: 0.9580
600/938 [>…] - ETA: 0s - loss: 0.3161 - sparse_categorical_accuracy: 0.9578
620/938 [>…] - ETA: 0s - loss: 0.3188 - sparse_categorical_accuracy: 0.9576
640/938 [=>…] - ETA: 0s - loss: 0.3181 - sparse_categorical_accuracy: 0.9573
660/938 [>…] - ETA: 0s - loss: 0.3185 - sparse_categorical_accuracy: 0.9574
680/938 [>…] - ETA: 0s - loss: 0.3209 - sparse_categorical_accuracy: 0.9574
700/938 [=>…] - ETA: 0s - loss: 0.3183 - sparse_categorical_accuracy: 0.9576
720/938 [>…] - ETA: 0s - loss: 0.3170 - sparse_categorical_accuracy: 0.9576
740/938 [>…] - ETA: 0s - loss: 0.3176 - sparse_categorical_accuracy: 0.9576
760/938 [=>…] - ETA: 0s - loss: 0.3182 - sparse_categorical_accuracy: 0.9577
780/938 [=>…] - ETA: 0s - loss: 0.3201 - sparse_categorical_accuracy: 0.9573
800/938 [>…] - ETA: 0s - loss: 0.3192 - sparse_categorical_accuracy: 0.9573
820/938 [=>…] - ETA: 0s - loss: 0.3206 - sparse_categorical_accuracy: 0.9572
840/938 [=>…] - ETA: 0s - loss: 0.3209 - sparse_categorical_accuracy: 0.9570
860/938 [>…] - ETA: 0s - loss: 0.3182 - sparse_categorical_accuracy: 0.9573
880/938 [=>…] - ETA: 0s - loss: 0.3152 - sparse_categorical_accuracy: 0.9575
900/938 [=>…] - ETA: 0s - loss: 0.3124 - sparse_categorical_accuracy: 0.9577
920/938 [>.] - ETA: 0s - loss: 0.3096 - sparse_categorical_accuracy: 0.9579
938/938 [================] - 2s 3ms/step - loss: 0.3096 - sparse_categorical_accuracy: 0.9582
Epoch 6/10

1/938 […] - ETA: 13s - loss: 0.0905 - sparse_categorical_accuracy: 0.9688
20/938 […] - ETA: 2s - loss: 0.3884 - sparse_categorical_accuracy: 0.9555
40/938 [>…] - ETA: 2s - loss: 0.3029 - sparse_categorical_accuracy: 0.9617
60/938 [>…] - ETA: 2s - loss: 0.2930 - sparse_categorical_accuracy: 0.9617
80/938 [=>…] - ETA: 2s - loss: 0.2771 - sparse_categorical_accuracy: 0.9635
100/938 [>…] - ETA: 2s - loss: 0.2690 - sparse_categorical_accuracy: 0.9634
120/938 [>…] - ETA: 2s - loss: 0.2731 - sparse_categorical_accuracy: 0.9641
141/938 [=>…] - ETA: 2s - loss: 0.2968 - sparse_categorical_accuracy: 0.9618
161/938 [>…] - ETA: 2s - loss: 0.2975 - sparse_categorical_accuracy: 0.9607
181/938 [>…] - ETA: 1s - loss: 0.2889 - sparse_categorical_accuracy: 0.9628
200/938 [=>…] - ETA: 1s - loss: 0.2900 - sparse_categorical_accuracy: 0.9628
218/938 [=>…] - ETA: 1s - loss: 0.2925 - sparse_categorical_accuracy: 0.9624
238/938 [>…] - ETA: 1s - loss: 0.3037 - sparse_categorical_accuracy: 0.9615
259/938 [=>…] - ETA: 1s - loss: 0.2987 - sparse_categorical_accuracy: 0.9617
279/938 [=>…] - ETA: 1s - loss: 0.3022 - sparse_categorical_accuracy: 0.9621
299/938 [>…] - ETA: 1s - loss: 0.2986 - sparse_categorical_accuracy: 0.9623
319/938 [=>…] - ETA: 1s - loss: 0.3040 - sparse_categorical_accuracy: 0.9620
339/938 [=>…] - ETA: 1s - loss: 0.3027 - sparse_categorical_accuracy: 0.9620
359/938 [>…] - ETA: 1s - loss: 0.2983 - sparse_categorical_accuracy: 0.9625
380/938 [=>…] - ETA: 1s - loss: 0.2968 - sparse_categorical_accuracy: 0.9625
400/938 [=>…] - ETA: 1s - loss: 0.2942 - sparse_categorical_accuracy: 0.9627
420/938 [>…] - ETA: 1s - loss: 0.2923 - sparse_categorical_accuracy: 0.9625
440/938 [=>…] - ETA: 1s - loss: 0.2966 - sparse_categorical_accuracy: 0.9622
459/938 [=>…] - ETA: 1s - loss: 0.2955 - sparse_categorical_accuracy: 0.9621
479/938 [>…] - ETA: 1s - loss: 0.2928 - sparse_categorical_accuracy: 0.9623
499/938 [>…] - ETA: 1s - loss: 0.2918 - sparse_categorical_accuracy: 0.9623
519/938 [=>…] - ETA: 1s - loss: 0.2968 - sparse_categorical_accuracy: 0.9623
539/938 [>…] - ETA: 1s - loss: 0.2967 - sparse_categorical_accuracy: 0.9625
559/938 [>…] - ETA: 0s - loss: 0.2965 - sparse_categorical_accuracy: 0.9623
572/938 [=>…] - ETA: 0s - loss: 0.2980 - sparse_categorical_accuracy: 0.9624
592/938 [=>…] - ETA: 0s - loss: 0.3026 - sparse_categorical_accuracy: 0.9621
612/938 [>…] - ETA: 0s - loss: 0.3015 - sparse_categorical_accuracy: 0.9623
632/938 [=>…] - ETA: 0s - loss: 0.3034 - sparse_categorical_accuracy: 0.9619
652/938 [=>…] - ETA: 0s - loss: 0.3012 - sparse_categorical_accuracy: 0.9617
659/938 [>…] - ETA: 0s - loss: 0.3007 - sparse_categorical_accuracy: 0.9618
669/938 [>…] - ETA: 0s - loss: 0.3052 - sparse_categorical_accuracy: 0.9617
683/938 [>…] - ETA: 0s - loss: 0.3036 - sparse_categorical_accuracy: 0.9618
698/938 [=>…] - ETA: 0s - loss: 0.3034 - sparse_categorical_accuracy: 0.9618
715/938 [=>…] - ETA: 0s - loss: 0.3023 - sparse_categorical_accuracy: 0.9619
735/938 [>…] - ETA: 0s - loss: 0.3019 - sparse_categorical_accuracy: 0.9619
755/938 [=>…] - ETA: 0s - loss: 0.3008 - sparse_categorical_accuracy: 0.9617
775/938 [=>…] - ETA: 0s - loss: 0.3032 - sparse_categorical_accuracy: 0.9614
795/938 [>…] - ETA: 0s - loss: 0.3049 - sparse_categorical_accuracy: 0.9610
815/938 [=>…] - ETA: 0s - loss: 0.3035 - sparse_categorical_accuracy: 0.9612
835/938 [=>…] - ETA: 0s - loss: 0.3045 - sparse_categorical_accuracy: 0.9611
855/938 [>…] - ETA: 0s - loss: 0.3031 - sparse_categorical_accuracy: 0.9613
875/938 [>…] - ETA: 0s - loss: 0.3006 - sparse_categorical_accuracy: 0.9613
895/938 [=>…] - ETA: 0s - loss: 0.2981 - sparse_categorical_accuracy: 0.9615
915/938 [>.] - ETA: 0s - loss: 0.2965 - sparse_categorical_accuracy: 0.9618
934/938 [>.] - ETA: 0s - loss: 0.2934 - sparse_categorical_accuracy: 0.9622
938/938 [================] - 3s 3ms/step - loss: 0.2942 - sparse_categorical_accuracy: 0.9622
Epoch 7/10

1/938 […] - ETA: 14s - loss: 0.2891 - sparse_categorical_accuracy: 0.9531
20/938 […] - ETA: 3s - loss: 0.5150 - sparse_categorical_accuracy: 0.9516
39/938 [>…] - ETA: 2s - loss: 0.3791 - sparse_categorical_accuracy: 0.9607
58/938 [>…] - ETA: 2s - loss: 0.3416 - sparse_categorical_accuracy: 0.9628
78/938 [=>…] - ETA: 2s - loss: 0.3253 - sparse_categorical_accuracy: 0.9647
95/938 [>…] - ETA: 2s - loss: 0.3040 - sparse_categorical_accuracy: 0.9650
113/938 [>…] - ETA: 2s - loss: 0.3009 - sparse_categorical_accuracy: 0.9653
131/938 [=>…] - ETA: 2s - loss: 0.2967 - sparse_categorical_accuracy: 0.9658
150/938 [=>…] - ETA: 2s - loss: 0.3071 - sparse_categorical_accuracy: 0.9642
170/938 [>…] - ETA: 2s - loss: 0.3032 - sparse_categorical_accuracy: 0.9632
190/938 [=>…] - ETA: 2s - loss: 0.2886 - sparse_categorical_accuracy: 0.9641
210/938 [=>…] - ETA: 2s - loss: 0.2835 - sparse_categorical_accuracy: 0.9641
230/938 [>…] - ETA: 1s - loss: 0.2799 - sparse_categorical_accuracy: 0.9637
250/938 [>…] - ETA: 1s - loss: 0.2875 - sparse_categorical_accuracy: 0.9633
269/938 [=>…] - ETA: 1s - loss: 0.2835 - sparse_categorical_accuracy: 0.9637
289/938 [>…] - ETA: 1s - loss: 0.2860 - sparse_categorical_accuracy: 0.9642
308/938 [>…] - ETA: 1s - loss: 0.2822 - sparse_categorical_accuracy: 0.9645
328/938 [=>…] - ETA: 1s - loss: 0.2818 - sparse_categorical_accuracy: 0.9648
348/938 [>…] - ETA: 1s - loss: 0.2754 - sparse_categorical_accuracy: 0.9652
368/938 [>…] - ETA: 1s - loss: 0.2699 - sparse_categorical_accuracy: 0.9656
388/938 [=>…] - ETA: 1s - loss: 0.2685 - sparse_categorical_accuracy: 0.9656
408/938 [>…] - ETA: 1s - loss: 0.2645 - sparse_categorical_accuracy: 0.9661
427/938 [>…] - ETA: 1s - loss: 0.2708 - sparse_categorical_accuracy: 0.9659
447/938 [=>…] - ETA: 1s - loss: 0.2707 - sparse_categorical_accuracy: 0.9659
467/938 [=>…] - ETA: 1s - loss: 0.2683 - sparse_categorical_accuracy: 0.9659
487/938 [>…] - ETA: 1s - loss: 0.2759 - sparse_categorical_accuracy: 0.9654
507/938 [=>…] - ETA: 1s - loss: 0.2790 - sparse_categorical_accuracy: 0.9650
527/938 [=>…] - ETA: 1s - loss: 0.2810 - sparse_categorical_accuracy: 0.9655
547/938 [>…] - ETA: 1s - loss: 0.2770 - sparse_categorical_accuracy: 0.9658
568/938 [=>…] - ETA: 0s - loss: 0.2746 - sparse_categorical_accuracy: 0.9658
587/938 [=>…] - ETA: 0s - loss: 0.2731 - sparse_categorical_accuracy: 0.9660
607/938 [>…] - ETA: 0s - loss: 0.2742 - sparse_categorical_accuracy: 0.9658
627/938 [=>…] - ETA: 0s - loss: 0.2732 - sparse_categorical_accuracy: 0.9657
646/938 [=>…] - ETA: 0s - loss: 0.2742 - sparse_categorical_accuracy: 0.9655
666/938 [>…] - ETA: 0s - loss: 0.2761 - sparse_categorical_accuracy: 0.9654
686/938 [>…] - ETA: 0s - loss: 0.2751 - sparse_categorical_accuracy: 0.9656
706/938 [=>…] - ETA: 0s - loss: 0.2755 - sparse_categorical_accuracy: 0.9657
726/938 [>…] - ETA: 0s - loss: 0.2738 - sparse_categorical_accuracy: 0.9659
746/938 [>…] - ETA: 0s - loss: 0.2716 - sparse_categorical_accuracy: 0.9658
766/938 [=>…] - ETA: 0s - loss: 0.2711 - sparse_categorical_accuracy: 0.9658
786/938 [>…] - ETA: 0s - loss: 0.2748 - sparse_categorical_accuracy: 0.9655
806/938 [>…] - ETA: 0s - loss: 0.2741 - sparse_categorical_accuracy: 0.9653
826/938 [=>…] - ETA: 0s - loss: 0.2735 - sparse_categorical_accuracy: 0.9655
846/938 [>…] - ETA: 0s - loss: 0.2721 - sparse_categorical_accuracy: 0.9654
866/938 [>…] - ETA: 0s - loss: 0.2708 - sparse_categorical_accuracy: 0.9656
885/938 [=>…] - ETA: 0s - loss: 0.2688 - sparse_categorical_accuracy: 0.9657
905/938 [=>…] - ETA: 0s - loss: 0.2675 - sparse_categorical_accuracy: 0.9658
925/938 [>.] - ETA: 0s - loss: 0.2653 - sparse_categorical_accuracy: 0.9661
938/938 [============] - 2s 3ms/step - loss: 0.2671 - sparse_categorical_accuracy: 0.9661
Epoch 8/10

1/938 […] - ETA: 13s - loss: 0.4572 - sparse_categorical_accuracy: 0.9531
20/938 […] - ETA: 2s - loss: 0.2865 - sparse_categorical_accuracy: 0.9570
40/938 [>…] - ETA: 2s - loss: 0.2358 - sparse_categorical_accuracy: 0.9652
60/938 [>…] - ETA: 2s - loss: 0.2004 - sparse_categorical_accuracy: 0.9698
80/938 [=>…] - ETA: 2s - loss: 0.2039 - sparse_categorical_accuracy: 0.9682
99/938 [>…] - ETA: 2s - loss: 0.2027 - sparse_categorical_accuracy: 0.9684
119/938 [>…] - ETA: 2s - loss: 0.2185 - sparse_categorical_accuracy: 0.9685
139/938 [=>…] - ETA: 2s - loss: 0.2562 - sparse_categorical_accuracy: 0.9666
159/938 [>…] - ETA: 2s - loss: 0.2403 - sparse_categorical_accuracy: 0.9674
179/938 [>…] - ETA: 2s - loss: 0.2248 - sparse_categorical_accuracy: 0.9681
199/938 [=>…] - ETA: 1s - loss: 0.2244 - sparse_categorical_accuracy: 0.9680
219/938 [>…] - ETA: 1s - loss: 0.2178 - sparse_categorical_accuracy: 0.9684
239/938 [>…] - ETA: 1s - loss: 0.2221 - sparse_categorical_accuracy: 0.9682
259/938 [=>…] - ETA: 1s - loss: 0.2192 - sparse_categorical_accuracy: 0.9683
279/938 [=>…] - ETA: 1s - loss: 0.2232 - sparse_categorical_accuracy: 0.9682
300/938 [>…] - ETA: 1s - loss: 0.2235 - sparse_categorical_accuracy: 0.9686
320/938 [=>…] - ETA: 1s - loss: 0.2234 - sparse_categorical_accuracy: 0.9689
339/938 [=>…] - ETA: 1s - loss: 0.2204 - sparse_categorical_accuracy: 0.9692
358/938 [>…] - ETA: 1s - loss: 0.2159 - sparse_categorical_accuracy: 0.9696
377/938 [=>…] - ETA: 1s - loss: 0.2145 - sparse_categorical_accuracy: 0.9695
387/938 [=>…] - ETA: 1s - loss: 0.2137 - sparse_categorical_accuracy: 0.9694
391/938 [=>…] - ETA: 1s - loss: 0.2159 - sparse_categorical_accuracy: 0.9693
401/938 [=>…] - ETA: 1s - loss: 0.2172 - sparse_categorical_accuracy: 0.9692
416/938 [>…] - ETA: 1s - loss: 0.2170 - sparse_categorical_accuracy: 0.9691
434/938 [>…] - ETA: 1s - loss: 0.2176 - sparse_categorical_accuracy: 0.9689
454/938 [=>…] - ETA: 1s - loss: 0.2156 - sparse_categorical_accuracy: 0.9690
474/938 [>…] - ETA: 1s - loss: 0.2162 - sparse_categorical_accuracy: 0.9687
495/938 [>…] - ETA: 1s - loss: 0.2145 - sparse_categorical_accuracy: 0.9688
515/938 [=>…] - ETA: 1s - loss: 0.2161 - sparse_categorical_accuracy: 0.9686
535/938 [>…] - ETA: 1s - loss: 0.2154 - sparse_categorical_accuracy: 0.9690
555/938 [>…] - ETA: 1s - loss: 0.2159 - sparse_categorical_accuracy: 0.9692
575/938 [=>…] - ETA: 1s - loss: 0.2141 - sparse_categorical_accuracy: 0.9693
595/938 [>…] - ETA: 0s - loss: 0.2155 - sparse_categorical_accuracy: 0.9690
615/938 [>…] - ETA: 0s - loss: 0.2167 - sparse_categorical_accuracy: 0.9691
636/938 [=>…] - ETA: 0s - loss: 0.2177 - sparse_categorical_accuracy: 0.9690
656/938 [=>…] - ETA: 0s - loss: 0.2194 - sparse_categorical_accuracy: 0.9689
676/938 [>…] - ETA: 0s - loss: 0.2231 - sparse_categorical_accuracy: 0.9688
696/938 [=>…] - ETA: 0s - loss: 0.2221 - sparse_categorical_accuracy: 0.9690
716/938 [=>…] - ETA: 0s - loss: 0.2217 - sparse_categorical_accuracy: 0.9691
736/938 [>…] - ETA: 0s - loss: 0.2206 - sparse_categorical_accuracy: 0.9692
755/938 [=>…] - ETA: 0s - loss: 0.2203 - sparse_categorical_accuracy: 0.9692
775/938 [=>…] - ETA: 0s - loss: 0.2223 - sparse_categorical_accuracy: 0.9690
795/938 [>…] - ETA: 0s - loss: 0.2256 - sparse_categorical_accuracy: 0.9687
814/938 [=>…] - ETA: 0s - loss: 0.2252 - sparse_categorical_accuracy: 0.9687
834/938 [=>…] - ETA: 0s - loss: 0.2269 - sparse_categorical_accuracy: 0.9684
854/938 [>…] - ETA: 0s - loss: 0.2258 - sparse_categorical_accuracy: 0.9686
874/938 [>…] - ETA: 0s - loss: 0.2245 - sparse_categorical_accuracy: 0.9686
894/938 [=>…] - ETA: 0s - loss: 0.2233 - sparse_categorical_accuracy: 0.9687
913/938 [>.] - ETA: 0s - loss: 0.2245 - sparse_categorical_accuracy: 0.9689
933/938 [>.] - ETA: 0s - loss: 0.2232 - sparse_categorical_accuracy: 0.9690
938/938 [================] - 3s 3ms/step - loss: 0.2250 - sparse_categorical_accuracy: 0.9690
Epoch 9/10

1/938 […] - ETA: 14s - loss: 0.5676 - sparse_categorical_accuracy: 0.9688
19/938 […] - ETA: 3s - loss: 0.3787 - sparse_categorical_accuracy: 0.9704
39/938 [>…] - ETA: 2s - loss: 0.2861 - sparse_categorical_accuracy: 0.9704
58/938 [>…] - ETA: 2s - loss: 0.2416 - sparse_categorical_accuracy: 0.9739
78/938 [=>…] - ETA: 2s - loss: 0.2319 - sparse_categorical_accuracy: 0.9722
98/938 [>…] - ETA: 2s - loss: 0.2357 - sparse_categorical_accuracy: 0.9721
117/938 [>…] - ETA: 2s - loss: 0.2361 - sparse_categorical_accuracy: 0.9728
137/938 [=>…] - ETA: 2s - loss: 0.2492 - sparse_categorical_accuracy: 0.9708
158/938 [>…] - ETA: 2s - loss: 0.2434 - sparse_categorical_accuracy: 0.9704
177/938 [>…] - ETA: 2s - loss: 0.2318 - sparse_categorical_accuracy: 0.9704
197/938 [=>…] - ETA: 2s - loss: 0.2241 - sparse_categorical_accuracy: 0.9714
217/938 [=>…] - ETA: 1s - loss: 0.2207 - sparse_categorical_accuracy: 0.9718
237/938 [>…] - ETA: 1s - loss: 0.2289 - sparse_categorical_accuracy: 0.9708
257/938 [=>…] - ETA: 1s - loss: 0.2276 - sparse_categorical_accuracy: 0.9701
277/938 [=>…] - ETA: 1s - loss: 0.2316 - sparse_categorical_accuracy: 0.9700
297/938 [>…] - ETA: 1s - loss: 0.2343 - sparse_categorical_accuracy: 0.9702
317/938 [=>…] - ETA: 1s - loss: 0.2365 - sparse_categorical_accuracy: 0.9701
337/938 [=>…] - ETA: 1s - loss: 0.2391 - sparse_categorical_accuracy: 0.9702
357/938 [>…] - ETA: 1s - loss: 0.2335 - sparse_categorical_accuracy: 0.9702
378/938 [=>…] - ETA: 1s - loss: 0.2302 - sparse_categorical_accuracy: 0.9707
398/938 [=>…] - ETA: 1s - loss: 0.2274 - sparse_categorical_accuracy: 0.9708
418/938 [>…] - ETA: 1s - loss: 0.2302 - sparse_categorical_accuracy: 0.9704
438/938 [=>…] - ETA: 1s - loss: 0.2325 - sparse_categorical_accuracy: 0.9704
458/938 [=>…] - ETA: 1s - loss: 0.2327 - sparse_categorical_accuracy: 0.9706
478/938 [>…] - ETA: 1s - loss: 0.2289 - sparse_categorical_accuracy: 0.9706
498/938 [>…] - ETA: 1s - loss: 0.2289 - sparse_categorical_accuracy: 0.9707
518/938 [=>…] - ETA: 1s - loss: 0.2293 - sparse_categorical_accuracy: 0.9706
538/938 [>…] - ETA: 1s - loss: 0.2310 - sparse_categorical_accuracy: 0.9707
558/938 [>…] - ETA: 0s - loss: 0.2323 - sparse_categorical_accuracy: 0.9707
578/938 [=>…] - ETA: 0s - loss: 0.2300 - sparse_categorical_accuracy: 0.9708
598/938 [>…] - ETA: 0s - loss: 0.2308 - sparse_categorical_accuracy: 0.9705
618/938 [>…] - ETA: 0s - loss: 0.2370 - sparse_categorical_accuracy: 0.9703
638/938 [=>…] - ETA: 0s - loss: 0.2393 - sparse_categorical_accuracy: 0.9702
659/938 [>…] - ETA: 0s - loss: 0.2435 - sparse_categorical_accuracy: 0.9700
679/938 [>…] - ETA: 0s - loss: 0.2435 - sparse_categorical_accuracy: 0.9700
699/938 [=>…] - ETA: 0s - loss: 0.2425 - sparse_categorical_accuracy: 0.9701
719/938 [=>…] - ETA: 0s - loss: 0.2432 - sparse_categorical_accuracy: 0.9700
739/938 [>…] - ETA: 0s - loss: 0.2412 - sparse_categorical_accuracy: 0.9701
759/938 [=>…] - ETA: 0s - loss: 0.2423 - sparse_categorical_accuracy: 0.9700
779/938 [=>…] - ETA: 0s - loss: 0.2462 - sparse_categorical_accuracy: 0.9698
799/938 [>…] - ETA: 0s - loss: 0.2459 - sparse_categorical_accuracy: 0.9696
819/938 [=>…] - ETA: 0s - loss: 0.2442 - sparse_categorical_accuracy: 0.9697
839/938 [=>…] - ETA: 0s - loss: 0.2433 - sparse_categorical_accuracy: 0.9698
859/938 [>…] - ETA: 0s - loss: 0.2424 - sparse_categorical_accuracy: 0.9698
879/938 [=>…] - ETA: 0s - loss: 0.2405 - sparse_categorical_accuracy: 0.9699
899/938 [=>…] - ETA: 0s - loss: 0.2390 - sparse_categorical_accuracy: 0.9700
919/938 [>.] - ETA: 0s - loss: 0.2380 - sparse_categorical_accuracy: 0.9702
938/938 [================] - 2s 3ms/step - loss: 0.2385 - sparse_categorical_accuracy: 0.9703
Epoch 10/10

1/938 […] - ETA: 14s - loss: 0.0725 - sparse_categorical_accuracy: 0.9844
20/938 […] - ETA: 3s - loss: 0.3122 - sparse_categorical_accuracy: 0.9680
40/938 [>…] - ETA: 2s - loss: 0.2266 - sparse_categorical_accuracy: 0.9727
60/938 [>…] - ETA: 2s - loss: 0.2137 - sparse_categorical_accuracy: 0.9747
80/938 [=>…] - ETA: 2s - loss: 0.2240 - sparse_categorical_accuracy: 0.9740
100/938 [>…] - ETA: 2s - loss: 0.2429 - sparse_categorical_accuracy: 0.9730
120/938 [>…] - ETA: 2s - loss: 0.2390 - sparse_categorical_accuracy: 0.9732
140/938 [=>…] - ETA: 2s - loss: 0.2509 - sparse_categorical_accuracy: 0.9714
160/938 [>…] - ETA: 2s - loss: 0.2450 - sparse_categorical_accuracy: 0.9709
180/938 [>…] - ETA: 2s - loss: 0.2335 - sparse_categorical_accuracy: 0.9713
200/938 [=>…] - ETA: 1s - loss: 0.2335 - sparse_categorical_accuracy: 0.9720
220/938 [>…] - ETA: 1s - loss: 0.2226 - sparse_categorical_accuracy: 0.9723
240/938 [>…] - ETA: 1s - loss: 0.2288 - sparse_categorical_accuracy: 0.9720
260/938 [=>…] - ETA: 1s - loss: 0.2262 - sparse_categorical_accuracy: 0.9726
280/938 [=>…] - ETA: 1s - loss: 0.2322 - sparse_categorical_accuracy: 0.9722
299/938 [>…] - ETA: 1s - loss: 0.2260 - sparse_categorical_accuracy: 0.9725
315/938 [=>…] - ETA: 1s - loss: 0.2245 - sparse_categorical_accuracy: 0.9729
335/938 [=>…] - ETA: 1s - loss: 0.2242 - sparse_categorical_accuracy: 0.9727
355/938 [>…] - ETA: 1s - loss: 0.2235 - sparse_categorical_accuracy: 0.9728
362/938 [>…] - ETA: 1s - loss: 0.2231 - sparse_categorical_accuracy: 0.9728
375/938 [>…] - ETA: 1s - loss: 0.2236 - sparse_categorical_accuracy: 0.9727
389/938 [=>…] - ETA: 1s - loss: 0.2228 - sparse_categorical_accuracy: 0.9728
404/938 [=>…] - ETA: 1s - loss: 0.2269 - sparse_categorical_accuracy: 0.9726
421/938 [>…] - ETA: 1s - loss: 0.2309 - sparse_categorical_accuracy: 0.9725
438/938 [=>…] - ETA: 1s - loss: 0.2292 - sparse_categorical_accuracy: 0.9726
456/938 [=>…] - ETA: 1s - loss: 0.2315 - sparse_categorical_accuracy: 0.9724
475/938 [>…] - ETA: 1s - loss: 0.2302 - sparse_categorical_accuracy: 0.9722
495/938 [>…] - ETA: 1s - loss: 0.2279 - sparse_categorical_accuracy: 0.9725
515/938 [=>…] - ETA: 1s - loss: 0.2301 - sparse_categorical_accuracy: 0.9722
534/938 [>…] - ETA: 1s - loss: 0.2293 - sparse_categorical_accuracy: 0.9724
554/938 [>…] - ETA: 1s - loss: 0.2276 - sparse_categorical_accuracy: 0.9726
574/938 [=>…] - ETA: 1s - loss: 0.2264 - sparse_categorical_accuracy: 0.9726
594/938 [=>…] - ETA: 0s - loss: 0.2265 - sparse_categorical_accuracy: 0.9724
614/938 [>…] - ETA: 0s - loss: 0.2267 - sparse_categorical_accuracy: 0.9725
634/938 [=>…] - ETA: 0s - loss: 0.2255 - sparse_categorical_accuracy: 0.9726
654/938 [=>…] - ETA: 0s - loss: 0.2259 - sparse_categorical_accuracy: 0.9728
673/938 [>…] - ETA: 0s - loss: 0.2284 - sparse_categorical_accuracy: 0.9727
693/938 [=>…] - ETA: 0s - loss: 0.2280 - sparse_categorical_accuracy: 0.9728
711/938 [=>…] - ETA: 0s - loss: 0.2263 - sparse_categorical_accuracy: 0.9729
728/938 [>…] - ETA: 0s - loss: 0.2262 - sparse_categorical_accuracy: 0.9729
745/938 [>…] - ETA: 0s - loss: 0.2286 - sparse_categorical_accuracy: 0.9728
764/938 [=>…] - ETA: 0s - loss: 0.2269 - sparse_categorical_accuracy: 0.9728
783/938 [>…] - ETA: 0s - loss: 0.2305 - sparse_categorical_accuracy: 0.9728
803/938 [>…] - ETA: 0s - loss: 0.2327 - sparse_categorical_accuracy: 0.9726
823/938 [=>…] - ETA: 0s - loss: 0.2306 - sparse_categorical_accuracy: 0.9727
843/938 [=>…] - ETA: 0s - loss: 0.2311 - sparse_categorical_accuracy: 0.9726
863/938 [>…] - ETA: 0s - loss: 0.2303 - sparse_categorical_accuracy: 0.9727
883/938 [=>…] - ETA: 0s - loss: 0.2281 - sparse_categorical_accuracy: 0.9728
902/938 [=>…] - ETA: 0s - loss: 0.2261 - sparse_categorical_accuracy: 0.9730
922/938 [>.] - ETA: 0s - loss: 0.2235 - sparse_categorical_accuracy: 0.9732
938/938 [==============] - 3s 3ms/step - loss: 0.2235 - sparse_categorical_accuracy: 0.9733

模型评估

model.evaluate(test_dataset)

1/157 […] - ETA: 21s - loss: 2.3587e-04 - sparse_categorical_accuracy: 1.0000
34/157 [=>…] - ETA: 0s - loss: 0.7066 - sparse_categorical_accuracy: 0.9453
69/157 [>…] - ETA: 0s - loss: 0.8308 - sparse_categorical_accuracy: 0.9443
81/157 [>…] - ETA: 0s - loss: 0.8148 - sparse_categorical_accuracy: 0.9441
89/157 [>…] - ETA: 0s - loss: 0.7783 - sparse_categorical_accuracy: 0.9473
110/157 [>…] - ETA: 0s - loss: 0.6985 - sparse_categorical_accuracy: 0.9540
141/157 [=>…] - ETA: 0s - loss: 0.5986 - sparse_categorical_accuracy: 0.9580
157/157 [================] - 0s 3ms/step - loss: 0.5758 - sparse_categorical_accuracy: 0.9590
[0.5758481910577826, 0.959]

使用tf.data.Dataset加载numpy数据相关推荐

Tensorflow2.* 加载和预处理数据之用 tf.data 加载 Numpy数据(2)
Tensorflow2.* 机器学习基础知识篇: 对服装图像进行分类使用Tensorflow Hub对未处理的电影评论数据集IMDB进行分类 Keras 机器学习基础知识之对预处理的电影评论文本分类 ...
tf.data.Dataset.from_tensor_slices 的用法
将python列表和numpy数组转换成tensorflow的dataset 只有dataset才能被model.fit函数训练 import tensorflow as tf import nump ...
TensorFlow数据读取机制：文件队列 tf.train.slice_input_producer和 tf.data.Dataset机制
TensorFlow数据读取机制:文件队列 tf.train.slice_input_producer和tf.data.Dataset机制之前写了一篇博客,关于<Tensorflow生成自己的 ...
TensorFlow 2.0 - tf.data.Dataset 数据预处理猫狗分类
文章目录 1 tf.data.Dataset.from_tensor_slices() 数据集建立 2. Dataset.map(f) 数据集预处理 3. Dataset.prefetch() 并行处 ...
轻轻松松使用StyleGAN2（六）：StyleGAN2 Encoder是怎样加载训练数据的？源代码+中文注释，dataset_tool.py和dataset.py
上一篇文章里,我们简单介绍了StyleGAN2 Encoder的一部分源代码,即:projector.py和project_images.py,内容请参考: 轻轻松松使用StyleGAN2(五):St ...
tensorflow的数据读取 tf.data.DataSet、tf.data.Iterator
tensorflow的工程有使用python的多进程读取数据,然后给feed给神经网络进行训练. 也有tensorflow中的 tf.data.DataSet的使用.并且由于是tensorflow框架 ...
tensorflow2数据读取P3: tf.data.Dataset.from_generator通过preprocessing.image.ImageDataGenerator构造Dataset
tf.data.Dataset.from_generator通过preprocessing.image.ImageDataGenerator构造Dataset 虽然自己定义生成器就可以构建datase ...
tf.data.Dataset与tfrecord学习笔记
目录 1.tf.data.Dataset 2.tfrecord 2.1 使用tfrecord的原因 2.2 tfrecord的写入 2.3 tfrecord的读取 3.两种方式的区别参考资料: 1. ...
cbitmap 从内存中加载jpg_Pytorch数据加载的分析
Pytorch数据加载的效率一直让人头痛,此前我介绍过两个方法,实际使用后数据加载的速度还是不够快,我陆续做了一些尝试,这里做个简单的总结和分析. 1.定位问题在优化数据加载前,应该先确定是否需要优 ...

使用tf.data.Dataset加载numpy数据

解析npz数据文件为numpy格式的数据

使用tf.data加载numpy数据

使用tf.data.Dataset加载numpy数据相关推荐

最新文章

热门文章