Keras - 绘制训练、验证和测试集准确性

Question

我想绘制这个简单神经网络的输出:

model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
history = model.fit(x_test, y_test, nb_epoch=10, validation_split=0.2, shuffle=True)

model.test_on_batch(x_test, y_test)
model.metrics_names

我已经绘制了训练和验证的准确性和损失:

print(history.history.keys())
#  "Accuracy"
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('model accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'validation'], loc='upper left')
plt.show()
# "Loss"
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'validation'], loc='upper left')
plt.show()

现在我想从 model.test_on_batch(x_test, y_test) 添加和绘制测试集的准确性，但来自 model.metrics_names我获得了用于绘制训练数据准确性的相同值“acc” plt.plot(history.history['acc']) .我如何绘制测试集的准确性？

Answer 1

这是一样的，因为你是在测试集上训练，而不是在训练集上。不要那样做，只需在训练集上训练:

history = model.fit(x_test, y_test, nb_epoch=10, validation_split=0.2, shuffle=True)

变成:

history = model.fit(x_train, y_train, nb_epoch=10, validation_split=0.2, shuffle=True)