(train_input, train_target), (test_input, test_target) = imdb.load_data(num_words=500)
train_input, val_input, train_target, val_target = train_test_split(train_input, train_target,
test_size=0.2, random_state=42)
2021-10-15 15:45:34.095087: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
embedding (Embedding) (None, 100, 16) 8000
_________________________________________________________________
lstm (LSTM) (None, 8) 800
_________________________________________________________________
dense (Dense) (None, 1) 9
=================================================================
Total params: 8,809
Trainable params: 8,809
Non-trainable params: 0
_________________________________________________________________
rmsprop = keras.optimizers.RMSprop(learning_rate=1e-4)
model.compile(optimizer=rmsprop, loss='binary_crossentropy',
metrics=['accuracy'])
checkpoint_cb = keras.callbacks.ModelCheckpoint('best-lstm-model.h5',
save_best_only=True)
early_stopping_cb = keras.callbacks.EarlyStopping(patience=3,
restore_best_weights=True)
history = model.fit(train_seq, train_target, epochs=100, batch_size=64,
validation_data=(val_seq, val_target),
callbacks=[checkpoint_cb, early_stopping_cb])
2021-10-15 15:45:34.498346: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:185] None of the MLIR Optimization Passes are enabled (registered 2)
Epoch 1/100
313/313 [==============================] - 10s 26ms/step - loss: 0.6927 - accuracy: 0.5314 - val_loss: 0.6920 - val_accuracy: 0.5662
Epoch 2/100
313/313 [==============================] - 7s 24ms/step - loss: 0.6906 - accuracy: 0.6061 - val_loss: 0.6893 - val_accuracy: 0.6270
Epoch 3/100
313/313 [==============================] - 7s 24ms/step - loss: 0.6858 - accuracy: 0.6496 - val_loss: 0.6828 - val_accuracy: 0.6524
Epoch 4/100
313/313 [==============================] - 8s 24ms/step - loss: 0.6737 - accuracy: 0.6758 - val_loss: 0.6631 - val_accuracy: 0.6828
Epoch 5/100
313/313 [==============================] - 7s 24ms/step - loss: 0.6189 - accuracy: 0.7182 - val_loss: 0.5647 - val_accuracy: 0.7258
Epoch 6/100
313/313 [==============================] - 7s 24ms/step - loss: 0.5455 - accuracy: 0.7382 - val_loss: 0.5359 - val_accuracy: 0.7490
Epoch 7/100
313/313 [==============================] - 7s 24ms/step - loss: 0.5219 - accuracy: 0.7558 - val_loss: 0.5165 - val_accuracy: 0.7640
Epoch 8/100
313/313 [==============================] - 7s 24ms/step - loss: 0.5035 - accuracy: 0.7688 - val_loss: 0.5023 - val_accuracy: 0.7690
Epoch 9/100
313/313 [==============================] - 7s 24ms/step - loss: 0.4888 - accuracy: 0.7774 - val_loss: 0.4891 - val_accuracy: 0.7768
Epoch 10/100
313/313 [==============================] - 8s 24ms/step - loss: 0.4758 - accuracy: 0.7850 - val_loss: 0.4792 - val_accuracy: 0.7838
Epoch 11/100
313/313 [==============================] - 7s 24ms/step - loss: 0.4651 - accuracy: 0.7919 - val_loss: 0.4702 - val_accuracy: 0.7868
Epoch 12/100
313/313 [==============================] - 7s 24ms/step - loss: 0.4560 - accuracy: 0.7965 - val_loss: 0.4634 - val_accuracy: 0.7888
Epoch 13/100
313/313 [==============================] - 7s 24ms/step - loss: 0.4485 - accuracy: 0.7985 - val_loss: 0.4588 - val_accuracy: 0.7934
Epoch 14/100
313/313 [==============================] - 7s 24ms/step - loss: 0.4421 - accuracy: 0.8038 - val_loss: 0.4531 - val_accuracy: 0.7930
Epoch 15/100
313/313 [==============================] - 7s 24ms/step - loss: 0.4367 - accuracy: 0.8051 - val_loss: 0.4485 - val_accuracy: 0.7954
Epoch 16/100
313/313 [==============================] - 7s 24ms/step - loss: 0.4323 - accuracy: 0.8073 - val_loss: 0.4456 - val_accuracy: 0.7964
Epoch 17/100
313/313 [==============================] - 7s 24ms/step - loss: 0.4285 - accuracy: 0.8080 - val_loss: 0.4423 - val_accuracy: 0.7990
Epoch 18/100
313/313 [==============================] - 7s 24ms/step - loss: 0.4253 - accuracy: 0.8091 - val_loss: 0.4414 - val_accuracy: 0.7948
Epoch 19/100
313/313 [==============================] - 7s 24ms/step - loss: 0.4228 - accuracy: 0.8103 - val_loss: 0.4392 - val_accuracy: 0.7970
Epoch 20/100
313/313 [==============================] - 7s 24ms/step - loss: 0.4207 - accuracy: 0.8109 - val_loss: 0.4380 - val_accuracy: 0.7990
Epoch 21/100
313/313 [==============================] - 7s 24ms/step - loss: 0.4184 - accuracy: 0.8102 - val_loss: 0.4361 - val_accuracy: 0.8010
Epoch 22/100
313/313 [==============================] - 7s 24ms/step - loss: 0.4168 - accuracy: 0.8119 - val_loss: 0.4367 - val_accuracy: 0.7996
Epoch 23/100
313/313 [==============================] - 7s 24ms/step - loss: 0.4155 - accuracy: 0.8111 - val_loss: 0.4344 - val_accuracy: 0.7988
Epoch 24/100
313/313 [==============================] - 7s 24ms/step - loss: 0.4145 - accuracy: 0.8116 - val_loss: 0.4339 - val_accuracy: 0.7976
Epoch 25/100
313/313 [==============================] - 7s 24ms/step - loss: 0.4135 - accuracy: 0.8124 - val_loss: 0.4355 - val_accuracy: 0.7956
Epoch 26/100
313/313 [==============================] - 7s 24ms/step - loss: 0.4123 - accuracy: 0.8135 - val_loss: 0.4329 - val_accuracy: 0.7988
Epoch 27/100
313/313 [==============================] - 7s 24ms/step - loss: 0.4119 - accuracy: 0.8134 - val_loss: 0.4330 - val_accuracy: 0.7976
Epoch 28/100
313/313 [==============================] - 7s 24ms/step - loss: 0.4112 - accuracy: 0.8127 - val_loss: 0.4325 - val_accuracy: 0.7986
Epoch 29/100
313/313 [==============================] - 7s 23ms/step - loss: 0.4103 - accuracy: 0.8124 - val_loss: 0.4319 - val_accuracy: 0.7996
Epoch 30/100
313/313 [==============================] - 7s 24ms/step - loss: 0.4098 - accuracy: 0.8126 - val_loss: 0.4330 - val_accuracy: 0.8038
Epoch 31/100
313/313 [==============================] - 7s 24ms/step - loss: 0.4092 - accuracy: 0.8145 - val_loss: 0.4347 - val_accuracy: 0.7958
Epoch 32/100
313/313 [==============================] - 8s 24ms/step - loss: 0.4083 - accuracy: 0.8138 - val_loss: 0.4325 - val_accuracy: 0.8014
Model: "sequential_1"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
embedding_1 (Embedding) (None, 100, 16) 8000
_________________________________________________________________
lstm_1 (LSTM) (None, 8) 800
_________________________________________________________________
dense_1 (Dense) (None, 1) 9
=================================================================
Total params: 8,809
Trainable params: 8,809
Non-trainable params: 0
_________________________________________________________________
rmsprop = keras.optimizers.RMSprop(learning_rate=1e-4)
model2.compile(optimizer=rmsprop, loss='binary_crossentropy',
metrics=['accuracy'])
checkpoint_cb = keras.callbacks.ModelCheckpoint('best-dropout-model.h5',
save_best_only=True)
early_stopping_cb = keras.callbacks.EarlyStopping(patience=3,
restore_best_weights=True)
history = model2.fit(train_seq, train_target, epochs=100, batch_size=64,
validation_data=(val_seq, val_target),
callbacks=[checkpoint_cb, early_stopping_cb])
Epoch 1/100
313/313 [==============================] - 9s 25ms/step - loss: 0.6924 - accuracy: 0.5368 - val_loss: 0.6915 - val_accuracy: 0.5540
Epoch 2/100
313/313 [==============================] - 8s 24ms/step - loss: 0.6882 - accuracy: 0.6065 - val_loss: 0.6835 - val_accuracy: 0.6858
Epoch 3/100
313/313 [==============================] - 8s 24ms/step - loss: 0.6516 - accuracy: 0.6911 - val_loss: 0.6115 - val_accuracy: 0.6950
Epoch 4/100
313/313 [==============================] - 8s 25ms/step - loss: 0.6008 - accuracy: 0.6999 - val_loss: 0.5880 - val_accuracy: 0.7170
Epoch 5/100
313/313 [==============================] - 8s 25ms/step - loss: 0.5796 - accuracy: 0.7225 - val_loss: 0.5699 - val_accuracy: 0.7296
Epoch 6/100
313/313 [==============================] - 8s 24ms/step - loss: 0.5616 - accuracy: 0.7375 - val_loss: 0.5516 - val_accuracy: 0.7470
Epoch 7/100
313/313 [==============================] - 8s 24ms/step - loss: 0.5459 - accuracy: 0.7483 - val_loss: 0.5390 - val_accuracy: 0.7600
Epoch 8/100
313/313 [==============================] - 8s 24ms/step - loss: 0.5296 - accuracy: 0.7576 - val_loss: 0.5232 - val_accuracy: 0.7580
Epoch 9/100
313/313 [==============================] - 8s 24ms/step - loss: 0.5159 - accuracy: 0.7653 - val_loss: 0.5123 - val_accuracy: 0.7708
Epoch 10/100
313/313 [==============================] - 8s 24ms/step - loss: 0.5027 - accuracy: 0.7730 - val_loss: 0.4996 - val_accuracy: 0.7718
Epoch 11/100
313/313 [==============================] - 8s 24ms/step - loss: 0.4910 - accuracy: 0.7807 - val_loss: 0.4894 - val_accuracy: 0.7776
Epoch 12/100
313/313 [==============================] - 8s 24ms/step - loss: 0.4808 - accuracy: 0.7840 - val_loss: 0.4806 - val_accuracy: 0.7836
Epoch 13/100
313/313 [==============================] - 8s 25ms/step - loss: 0.4705 - accuracy: 0.7886 - val_loss: 0.4736 - val_accuracy: 0.7842
Epoch 14/100
313/313 [==============================] - 8s 25ms/step - loss: 0.4652 - accuracy: 0.7908 - val_loss: 0.4732 - val_accuracy: 0.7822
Epoch 15/100
313/313 [==============================] - 8s 25ms/step - loss: 0.4581 - accuracy: 0.7958 - val_loss: 0.4607 - val_accuracy: 0.7902
Epoch 16/100
313/313 [==============================] - 8s 25ms/step - loss: 0.4504 - accuracy: 0.7976 - val_loss: 0.4554 - val_accuracy: 0.7962
Epoch 17/100
313/313 [==============================] - 8s 25ms/step - loss: 0.4457 - accuracy: 0.7997 - val_loss: 0.4512 - val_accuracy: 0.7990
Epoch 18/100
313/313 [==============================] - 8s 24ms/step - loss: 0.4403 - accuracy: 0.8020 - val_loss: 0.4473 - val_accuracy: 0.7990
Epoch 19/100
313/313 [==============================] - 8s 24ms/step - loss: 0.4361 - accuracy: 0.8031 - val_loss: 0.4443 - val_accuracy: 0.8000
Epoch 20/100
313/313 [==============================] - 8s 24ms/step - loss: 0.4344 - accuracy: 0.8052 - val_loss: 0.4449 - val_accuracy: 0.7954
Epoch 21/100
313/313 [==============================] - 8s 24ms/step - loss: 0.4325 - accuracy: 0.8024 - val_loss: 0.4425 - val_accuracy: 0.7968
Epoch 22/100
313/313 [==============================] - 8s 24ms/step - loss: 0.4289 - accuracy: 0.8061 - val_loss: 0.4410 - val_accuracy: 0.8008
Epoch 23/100
313/313 [==============================] - 8s 24ms/step - loss: 0.4268 - accuracy: 0.8067 - val_loss: 0.4371 - val_accuracy: 0.7988
Epoch 24/100
313/313 [==============================] - 8s 24ms/step - loss: 0.4245 - accuracy: 0.8067 - val_loss: 0.4352 - val_accuracy: 0.7978
Epoch 25/100
313/313 [==============================] - 8s 24ms/step - loss: 0.4229 - accuracy: 0.8070 - val_loss: 0.4333 - val_accuracy: 0.8006
Epoch 26/100
313/313 [==============================] - 8s 24ms/step - loss: 0.4206 - accuracy: 0.8076 - val_loss: 0.4369 - val_accuracy: 0.7976
Epoch 27/100
313/313 [==============================] - 8s 24ms/step - loss: 0.4198 - accuracy: 0.8082 - val_loss: 0.4324 - val_accuracy: 0.8006
Epoch 28/100
313/313 [==============================] - 8s 25ms/step - loss: 0.4195 - accuracy: 0.8106 - val_loss: 0.4319 - val_accuracy: 0.8010
Epoch 29/100
313/313 [==============================] - 8s 24ms/step - loss: 0.4177 - accuracy: 0.8101 - val_loss: 0.4313 - val_accuracy: 0.8006
Epoch 30/100
313/313 [==============================] - 8s 24ms/step - loss: 0.4167 - accuracy: 0.8086 - val_loss: 0.4326 - val_accuracy: 0.7956
Epoch 31/100
313/313 [==============================] - 8s 24ms/step - loss: 0.4166 - accuracy: 0.8093 - val_loss: 0.4318 - val_accuracy: 0.7948
Epoch 32/100
313/313 [==============================] - 8s 24ms/step - loss: 0.4141 - accuracy: 0.8108 - val_loss: 0.4301 - val_accuracy: 0.7990
Epoch 33/100
313/313 [==============================] - 8s 24ms/step - loss: 0.4160 - accuracy: 0.8087 - val_loss: 0.4304 - val_accuracy: 0.8048
Epoch 34/100
313/313 [==============================] - 8s 24ms/step - loss: 0.4139 - accuracy: 0.8081 - val_loss: 0.4313 - val_accuracy: 0.8058
Epoch 35/100
313/313 [==============================] - 8s 24ms/step - loss: 0.4136 - accuracy: 0.8113 - val_loss: 0.4321 - val_accuracy: 0.8052
model3 = keras.Sequential()
model3.add(keras.layers.Embedding(500, 16, input_length=100))
model3.add(keras.layers.LSTM(8, dropout=0.3, return_sequences=True))
model3.add(keras.layers.LSTM(8, dropout=0.3))
model3.add(keras.layers.Dense(1, activation='sigmoid'))
Model: "sequential_2"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
embedding_2 (Embedding) (None, 100, 16) 8000
_________________________________________________________________
lstm_2 (LSTM) (None, 100, 8) 800
_________________________________________________________________
lstm_3 (LSTM) (None, 8) 544
_________________________________________________________________
dense_2 (Dense) (None, 1) 9
=================================================================
Total params: 9,353
Trainable params: 9,353
Non-trainable params: 0
_________________________________________________________________
rmsprop = keras.optimizers.RMSprop(learning_rate=1e-4)
model3.compile(optimizer=rmsprop, loss='binary_crossentropy',
metrics=['accuracy'])
checkpoint_cb = keras.callbacks.ModelCheckpoint('best-dual-model.h5',
save_best_only=True)
early_stopping_cb = keras.callbacks.EarlyStopping(patience=3,
restore_best_weights=True)
history = model3.fit(train_seq, train_target, epochs=100, batch_size=64,
validation_data=(val_seq, val_target),
callbacks=[checkpoint_cb, early_stopping_cb])
Epoch 1/100
313/313 [==============================] - 18s 48ms/step - loss: 0.4864 - accuracy: 0.7742 - val_loss: 0.4853 - val_accuracy: 0.7736
Epoch 2/100
313/313 [==============================] - 15s 47ms/step - loss: 0.4750 - accuracy: 0.7836 - val_loss: 0.4699 - val_accuracy: 0.7858
Epoch 3/100
313/313 [==============================] - 15s 47ms/step - loss: 0.4668 - accuracy: 0.7833 - val_loss: 0.4622 - val_accuracy: 0.7858
Epoch 4/100
313/313 [==============================] - 15s 46ms/step - loss: 0.4610 - accuracy: 0.7894 - val_loss: 0.4597 - val_accuracy: 0.7896
Epoch 5/100
313/313 [==============================] - 14s 46ms/step - loss: 0.4569 - accuracy: 0.7904 - val_loss: 0.4586 - val_accuracy: 0.7896
Epoch 6/100
313/313 [==============================] - 14s 46ms/step - loss: 0.4526 - accuracy: 0.7934 - val_loss: 0.4535 - val_accuracy: 0.7934
Epoch 7/100
313/313 [==============================] - 14s 46ms/step - loss: 0.4501 - accuracy: 0.7928 - val_loss: 0.4518 - val_accuracy: 0.7886
Epoch 8/100
313/313 [==============================] - 15s 46ms/step - loss: 0.4446 - accuracy: 0.7968 - val_loss: 0.4472 - val_accuracy: 0.7954
Epoch 9/100
313/313 [==============================] - 14s 46ms/step - loss: 0.4423 - accuracy: 0.7966 - val_loss: 0.4484 - val_accuracy: 0.7880
Epoch 10/100
313/313 [==============================] - 14s 46ms/step - loss: 0.4406 - accuracy: 0.7964 - val_loss: 0.4477 - val_accuracy: 0.7880
Epoch 11/100
313/313 [==============================] - 14s 46ms/step - loss: 0.4401 - accuracy: 0.8005 - val_loss: 0.4437 - val_accuracy: 0.7922
Epoch 12/100
313/313 [==============================] - 14s 46ms/step - loss: 0.4392 - accuracy: 0.8004 - val_loss: 0.4414 - val_accuracy: 0.7946
Epoch 13/100
313/313 [==============================] - 14s 46ms/step - loss: 0.4373 - accuracy: 0.7989 - val_loss: 0.4457 - val_accuracy: 0.7884
Epoch 14/100
313/313 [==============================] - 14s 46ms/step - loss: 0.4323 - accuracy: 0.8019 - val_loss: 0.4431 - val_accuracy: 0.7988
Epoch 15/100
313/313 [==============================] - 14s 46ms/step - loss: 0.4334 - accuracy: 0.8023 - val_loss: 0.4390 - val_accuracy: 0.7988
Epoch 16/100
313/313 [==============================] - 14s 46ms/step - loss: 0.4316 - accuracy: 0.8034 - val_loss: 0.4385 - val_accuracy: 0.7972
Epoch 17/100
313/313 [==============================] - 14s 46ms/step - loss: 0.4297 - accuracy: 0.8018 - val_loss: 0.4377 - val_accuracy: 0.7952
Epoch 18/100
313/313 [==============================] - 14s 46ms/step - loss: 0.4294 - accuracy: 0.8012 - val_loss: 0.4387 - val_accuracy: 0.7984
Epoch 19/100
313/313 [==============================] - 14s 46ms/step - loss: 0.4288 - accuracy: 0.8009 - val_loss: 0.4399 - val_accuracy: 0.8000
Epoch 20/100
313/313 [==============================] - 15s 46ms/step - loss: 0.4261 - accuracy: 0.8055 - val_loss: 0.4356 - val_accuracy: 0.7994
Epoch 21/100
313/313 [==============================] - 15s 47ms/step - loss: 0.4275 - accuracy: 0.8056 - val_loss: 0.4368 - val_accuracy: 0.8014
Epoch 22/100
313/313 [==============================] - 15s 47ms/step - loss: 0.4258 - accuracy: 0.8039 - val_loss: 0.4348 - val_accuracy: 0.7990
Epoch 23/100
313/313 [==============================] - 15s 47ms/step - loss: 0.4230 - accuracy: 0.8063 - val_loss: 0.4341 - val_accuracy: 0.7994
Epoch 24/100
313/313 [==============================] - 15s 49ms/step - loss: 0.4239 - accuracy: 0.8062 - val_loss: 0.4364 - val_accuracy: 0.8030
Epoch 25/100
313/313 [==============================] - 15s 49ms/step - loss: 0.4219 - accuracy: 0.8065 - val_loss: 0.4338 - val_accuracy: 0.7994
Epoch 26/100
313/313 [==============================] - 17s 54ms/step - loss: 0.4229 - accuracy: 0.8048 - val_loss: 0.4331 - val_accuracy: 0.8004
Epoch 27/100
313/313 [==============================] - 16s 52ms/step - loss: 0.4215 - accuracy: 0.8084 - val_loss: 0.4349 - val_accuracy: 0.7974
Epoch 28/100
313/313 [==============================] - 15s 48ms/step - loss: 0.4206 - accuracy: 0.8070 - val_loss: 0.4341 - val_accuracy: 0.7970
Epoch 29/100
313/313 [==============================] - 15s 47ms/step - loss: 0.4238 - accuracy: 0.8043 - val_loss: 0.4330 - val_accuracy: 0.8000
Epoch 30/100
313/313 [==============================] - 15s 47ms/step - loss: 0.4207 - accuracy: 0.8084 - val_loss: 0.4330 - val_accuracy: 0.8032
Epoch 31/100
313/313 [==============================] - 15s 47ms/step - loss: 0.4191 - accuracy: 0.8076 - val_loss: 0.4345 - val_accuracy: 0.8054
Epoch 32/100
313/313 [==============================] - 15s 48ms/step - loss: 0.4194 - accuracy: 0.8089 - val_loss: 0.4307 - val_accuracy: 0.8024
Epoch 33/100
313/313 [==============================] - 17s 55ms/step - loss: 0.4165 - accuracy: 0.8105 - val_loss: 0.4319 - val_accuracy: 0.8032
Epoch 34/100
313/313 [==============================] - 18s 56ms/step - loss: 0.4173 - accuracy: 0.8082 - val_loss: 0.4360 - val_accuracy: 0.8034
Epoch 35/100
313/313 [==============================] - 17s 54ms/step - loss: 0.4156 - accuracy: 0.8114 - val_loss: 0.4315 - val_accuracy: 0.8030
Model: "sequential_3"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
embedding_3 (Embedding) (None, 100, 16) 8000
_________________________________________________________________
gru (GRU) (None, 8) 624
_________________________________________________________________
dense_3 (Dense) (None, 1) 9
=================================================================
Total params: 8,633
Trainable params: 8,633
Non-trainable params: 0
_________________________________________________________________
rmsprop = keras.optimizers.RMSprop(learning_rate=1e-4)
model4.compile(optimizer=rmsprop, loss='binary_crossentropy',
metrics=['accuracy'])
checkpoint_cb = keras.callbacks.ModelCheckpoint('best-GRU-model.h5',
save_best_only=True)
early_stopping_cb = keras.callbacks.EarlyStopping(patience=3,
restore_best_weights=True)
history = model4.fit(train_seq, train_target, epochs=100, batch_size=64,
validation_data=(val_seq, val_target),
callbacks=[checkpoint_cb, early_stopping_cb])
Epoch 1/100
313/313 [==============================] - 11s 30ms/step - loss: 0.6923 - accuracy: 0.5411 - val_loss: 0.6915 - val_accuracy: 0.5782
Epoch 2/100
313/313 [==============================] - 9s 28ms/step - loss: 0.6898 - accuracy: 0.5865 - val_loss: 0.6885 - val_accuracy: 0.6008
Epoch 3/100
313/313 [==============================] - 9s 28ms/step - loss: 0.6852 - accuracy: 0.6145 - val_loss: 0.6828 - val_accuracy: 0.6140
Epoch 4/100
313/313 [==============================] - 9s 28ms/step - loss: 0.6770 - accuracy: 0.6335 - val_loss: 0.6732 - val_accuracy: 0.6314
Epoch 5/100
313/313 [==============================] - 9s 28ms/step - loss: 0.6631 - accuracy: 0.6528 - val_loss: 0.6564 - val_accuracy: 0.6460
Epoch 6/100
313/313 [==============================] - 9s 28ms/step - loss: 0.6365 - accuracy: 0.6719 - val_loss: 0.6188 - val_accuracy: 0.6824
Epoch 7/100
313/313 [==============================] - 9s 28ms/step - loss: 0.5781 - accuracy: 0.7107 - val_loss: 0.5600 - val_accuracy: 0.7328
Epoch 8/100
313/313 [==============================] - 9s 29ms/step - loss: 0.5374 - accuracy: 0.7455 - val_loss: 0.5380 - val_accuracy: 0.7476
Epoch 9/100
313/313 [==============================] - 9s 28ms/step - loss: 0.5193 - accuracy: 0.7566 - val_loss: 0.5235 - val_accuracy: 0.7530
Epoch 10/100
313/313 [==============================] - 9s 28ms/step - loss: 0.5051 - accuracy: 0.7645 - val_loss: 0.5120 - val_accuracy: 0.7610
Epoch 11/100
313/313 [==============================] - 9s 30ms/step - loss: 0.4940 - accuracy: 0.7717 - val_loss: 0.5029 - val_accuracy: 0.7626
Epoch 12/100
313/313 [==============================] - 9s 30ms/step - loss: 0.4841 - accuracy: 0.7773 - val_loss: 0.4944 - val_accuracy: 0.7696
Epoch 13/100
313/313 [==============================] - 9s 30ms/step - loss: 0.4761 - accuracy: 0.7822 - val_loss: 0.4871 - val_accuracy: 0.7742
Epoch 14/100
313/313 [==============================] - 10s 31ms/step - loss: 0.4694 - accuracy: 0.7872 - val_loss: 0.4809 - val_accuracy: 0.7752
Epoch 15/100
313/313 [==============================] - 10s 31ms/step - loss: 0.4635 - accuracy: 0.7882 - val_loss: 0.4782 - val_accuracy: 0.7740
Epoch 16/100
313/313 [==============================] - 9s 29ms/step - loss: 0.4582 - accuracy: 0.7921 - val_loss: 0.4715 - val_accuracy: 0.7838
Epoch 17/100
313/313 [==============================] - 9s 29ms/step - loss: 0.4539 - accuracy: 0.7948 - val_loss: 0.4689 - val_accuracy: 0.7794
Epoch 18/100
313/313 [==============================] - 10s 31ms/step - loss: 0.4491 - accuracy: 0.7963 - val_loss: 0.4673 - val_accuracy: 0.7760
Epoch 19/100
313/313 [==============================] - 10s 31ms/step - loss: 0.4455 - accuracy: 0.7994 - val_loss: 0.4659 - val_accuracy: 0.7766
Epoch 20/100
313/313 [==============================] - 9s 30ms/step - loss: 0.4422 - accuracy: 0.8002 - val_loss: 0.4595 - val_accuracy: 0.7852
Epoch 21/100
313/313 [==============================] - 10s 31ms/step - loss: 0.4388 - accuracy: 0.8019 - val_loss: 0.4574 - val_accuracy: 0.7878
Epoch 22/100
313/313 [==============================] - 9s 30ms/step - loss: 0.4359 - accuracy: 0.8042 - val_loss: 0.4561 - val_accuracy: 0.7902
Epoch 23/100
313/313 [==============================] - 10s 31ms/step - loss: 0.4339 - accuracy: 0.8049 - val_loss: 0.4572 - val_accuracy: 0.7898
Epoch 24/100
313/313 [==============================] - 10s 32ms/step - loss: 0.4318 - accuracy: 0.8076 - val_loss: 0.4541 - val_accuracy: 0.7872
Epoch 25/100
313/313 [==============================] - 10s 30ms/step - loss: 0.4302 - accuracy: 0.8073 - val_loss: 0.4536 - val_accuracy: 0.7916
Epoch 26/100
313/313 [==============================] - 10s 31ms/step - loss: 0.4278 - accuracy: 0.8098 - val_loss: 0.4538 - val_accuracy: 0.7848
Epoch 27/100
313/313 [==============================] - 9s 29ms/step - loss: 0.4271 - accuracy: 0.8080 - val_loss: 0.4499 - val_accuracy: 0.7916
Epoch 28/100
313/313 [==============================] - 10s 31ms/step - loss: 0.4255 - accuracy: 0.8112 - val_loss: 0.4493 - val_accuracy: 0.7920
Epoch 29/100
313/313 [==============================] - 9s 29ms/step - loss: 0.4240 - accuracy: 0.8108 - val_loss: 0.4507 - val_accuracy: 0.7918
Epoch 30/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4225 - accuracy: 0.8117 - val_loss: 0.4488 - val_accuracy: 0.7916
Epoch 31/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4215 - accuracy: 0.8132 - val_loss: 0.4484 - val_accuracy: 0.7920
Epoch 32/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4204 - accuracy: 0.8133 - val_loss: 0.4471 - val_accuracy: 0.7940
Epoch 33/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4197 - accuracy: 0.8138 - val_loss: 0.4463 - val_accuracy: 0.7950
Epoch 34/100
313/313 [==============================] - 9s 27ms/step - loss: 0.4192 - accuracy: 0.8136 - val_loss: 0.4463 - val_accuracy: 0.7946
Epoch 35/100
313/313 [==============================] - 9s 27ms/step - loss: 0.4180 - accuracy: 0.8136 - val_loss: 0.4452 - val_accuracy: 0.7948
Epoch 36/100
313/313 [==============================] - 9s 27ms/step - loss: 0.4171 - accuracy: 0.8156 - val_loss: 0.4457 - val_accuracy: 0.7922
Epoch 37/100
313/313 [==============================] - 9s 27ms/step - loss: 0.4163 - accuracy: 0.8156 - val_loss: 0.4439 - val_accuracy: 0.7958
Epoch 38/100
313/313 [==============================] - 9s 27ms/step - loss: 0.4157 - accuracy: 0.8140 - val_loss: 0.4495 - val_accuracy: 0.7950
Epoch 39/100
313/313 [==============================] - 9s 27ms/step - loss: 0.4152 - accuracy: 0.8140 - val_loss: 0.4431 - val_accuracy: 0.7966
Epoch 40/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4146 - accuracy: 0.8163 - val_loss: 0.4447 - val_accuracy: 0.7930
Epoch 41/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4141 - accuracy: 0.8166 - val_loss: 0.4424 - val_accuracy: 0.7952
Epoch 42/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4135 - accuracy: 0.8159 - val_loss: 0.4428 - val_accuracy: 0.7938
Epoch 43/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4130 - accuracy: 0.8152 - val_loss: 0.4435 - val_accuracy: 0.7922
Epoch 44/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4123 - accuracy: 0.8170 - val_loss: 0.4408 - val_accuracy: 0.7956
Epoch 45/100
313/313 [==============================] - 9s 29ms/step - loss: 0.4121 - accuracy: 0.8166 - val_loss: 0.4412 - val_accuracy: 0.7988
Epoch 46/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4110 - accuracy: 0.8179 - val_loss: 0.4437 - val_accuracy: 0.7956
Epoch 47/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4109 - accuracy: 0.8171 - val_loss: 0.4400 - val_accuracy: 0.7962
Epoch 48/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4103 - accuracy: 0.8185 - val_loss: 0.4393 - val_accuracy: 0.7964
Epoch 49/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4098 - accuracy: 0.8184 - val_loss: 0.4393 - val_accuracy: 0.7982
Epoch 50/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4096 - accuracy: 0.8175 - val_loss: 0.4383 - val_accuracy: 0.7986
Epoch 51/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4093 - accuracy: 0.8173 - val_loss: 0.4379 - val_accuracy: 0.7998
Epoch 52/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4089 - accuracy: 0.8181 - val_loss: 0.4375 - val_accuracy: 0.7992
Epoch 53/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4084 - accuracy: 0.8172 - val_loss: 0.4366 - val_accuracy: 0.7988
Epoch 54/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4074 - accuracy: 0.8184 - val_loss: 0.4368 - val_accuracy: 0.8000
Epoch 55/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4073 - accuracy: 0.8194 - val_loss: 0.4421 - val_accuracy: 0.7932
Epoch 56/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4073 - accuracy: 0.8166 - val_loss: 0.4358 - val_accuracy: 0.7984
Epoch 57/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4067 - accuracy: 0.8194 - val_loss: 0.4351 - val_accuracy: 0.7996
Epoch 58/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4065 - accuracy: 0.8194 - val_loss: 0.4362 - val_accuracy: 0.7996
Epoch 59/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4061 - accuracy: 0.8196 - val_loss: 0.4362 - val_accuracy: 0.8008
Epoch 60/100
313/313 [==============================] - 9s 28ms/step - loss: 0.4058 - accuracy: 0.8169 - val_loss: 0.4383 - val_accuracy: 0.7992
Leave a comment