在 keras 中保存最佳模型 [英] Saving best model in keras

问题描述

我在 keras 中训练模型时使用以下代码

I use the following code when training a model in keras

from keras.callbacks import EarlyStopping

model = Sequential()
model.add(Dense(100, activation='relu', input_shape = input_shape))
model.add(Dense(1))

model_2.compile(optimizer='adam', loss='mean_squared_error', metrics=['accuracy'])


model.fit(X, y, epochs=15, validation_split=0.4, callbacks=[early_stopping_monitor], verbose=False)

model.predict(X_test)

但最近我想保存最好的训练模型，因为我正在训练的数据在高 val_loss vs epochs"图中给出了很多峰值，我想使用模型中可能的最好的模型.

but recently I wanted to get the best trained model saved as the data I am training on gives a lot of peaks in "high val_loss vs epochs" graph and I want to use the best one possible yet from the model.

有什么方法或功能可以帮助解决这个问题吗?

Is there any method or function to help with that?

推荐答案

EarlyStopping 和 ModelCheckpoint 是您从 Keras 文档中需要的.

EarlyStopping and ModelCheckpoint is what you need from Keras documentation.

您应该在 ModelCheckpoint 中设置 save_best_only=True.如果需要任何其他调整，都是微不足道的.

You should set save_best_only=True in ModelCheckpoint. If any other adjustments needed, are trivial.

为了帮助你更多，你可以看到一个用法在 Kaggle 上.

Just to help you more you can see a usage here on Kaggle.

如果上面的 Kaggle 示例链接不可用，请在此处添加代码:

Adding the code here in case the above Kaggle example link is not available:

model = getModel()
model.summary()

batch_size = 32

earlyStopping = EarlyStopping(monitor='val_loss', patience=10, verbose=0, mode='min')
mcp_save = ModelCheckpoint('.mdl_wts.hdf5', save_best_only=True, monitor='val_loss', mode='min')
reduce_lr_loss = ReduceLROnPlateau(monitor='val_loss', factor=0.1, patience=7, verbose=1, epsilon=1e-4, mode='min')

model.fit(Xtr_more, Ytr_more, batch_size=batch_size, epochs=50, verbose=0, callbacks=[earlyStopping, mcp_save, reduce_lr_loss], validation_split=0.25)

这篇关于在 keras 中保存最佳模型的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！