您可以在训练期间保存一个 keras 模型，然后再次加载它。要保存模型，您可以使用 json 格式执行此操作，然后要保存权重，您可以使用回调执行此操作，如下所示：

让我们做一些随机模型，

model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
                 activation='relu',
                 input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))

model.compile(loss=keras.losses.categorical_crossentropy,
              optimizer=keras.optimizers.Adadelta(),
              metrics=['accuracy'])

然后我们可以保存我们自己创建的模型

# Save the model
model_json = model.to_json()
with open("weights/model.json", "w") as json_file:
    json_file.write(model_json)

我们可以使用回调来保存某个给定检查点的权重。在此示例中，每次我们获得更好的模型性能时都会保存它们。

# Save the weights using a checkpoint.
filepath="weights/weights-improvement-{epoch:02d}-{val_acc:.2f}.hdf5"
checkpoint = ModelCheckpoint(filepath, monitor='val_acc', verbose=1, save_best_only=True, mode='max')
callbacks_list = [checkpoint]

epochs = 4
batch_size = 128
# Fit the model weights.
model.fit(x_train_reshaped, y_train_binary,
          batch_size=batch_size,
          epochs=epochs,
          verbose=1,
          callbacks=callbacks_list,
          validation_data=(x_test_reshaped, y_test_binary))

然后我们可以在未来使用加载模型和权重

# load model saved as a json and create model
json_file = open('weights/model.json', 'r')
loaded_model_json = json_file.read()
json_file.close()
loaded_model = model_from_json(loaded_model_json)

# load weights into new model
loaded_model.load_weights("weights/weights-improvement-04-0.99.hdf5")
print("Loaded model from disk")

# evaluate loaded model on test data
#loaded_model.compile(loss='binary_crossentropy', optimizer='rmsprop', metrics=['accuracy'])
predictions = loaded_model.predict_classes(x_test_reshaped[0:10], verbose=0)
show_imgs(x_test[0:10])
print('Predicted classes: ', predictions)

一旦你加载了权重，你就可以通过再次调用 fit 函数来恢复训练

epochs = 4
batch_size = 128
# Fit the model weights.
loaded_model.fit(x_train_reshaped, y_train_binary,
          batch_size=batch_size,
          epochs=epochs,
          verbose=1,
          callbacks=callbacks_list,
          validation_data=(x_test_reshaped, y_test_binary))

这将再进行 4 次训练。