[英]Saving best model in keras
I use the following code when training a model in keras我在 keras 中训练模型时使用以下代码
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)
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.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,我想使用模型中最好的一个。
Is there any method or function to help with that?有什么方法或功能可以帮助解决这个问题吗?
EarlyStopping and ModelCheckpoint is what you need from Keras documentation. EarlyStopping和ModelCheckpoint是您从 Keras 文档中需要的。
You should set save_best_only=True
in ModelCheckpoint.您应该在 ModelCheckpoint 中设置
save_best_only=True
。 If any other adjustments needed, are trivial.如果需要任何其他调整,都是微不足道的。
Just to help you more you can see a usage here on Kaggle .为了帮助你更多,你可以在 Kaggle 上看到一个用法。
Adding the code here in case the above Kaggle example link is not available:如果上面的 Kaggle 示例链接不可用,请在此处添加代码:
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)
EarlyStopping
's restore_best_weights
argument will do the trick: EarlyStopping
的restore_best_weights
参数可以解决问题:
restore_best_weights: whether to restore model weights from the epoch with the best value of the monitored quantity.
restore_best_weights:是否从监测数量的最佳值的epoch恢复模型权重。 If False, the model weights obtained at the last step of training are used.
如果为 False,则使用在训练的最后一步获得的模型权重。
So not sure how your early_stopping_monitor
is defined, but going with all the default settings and seeing you already imported EarlyStopping
you could do this:所以不确定你的
early_stopping_monitor
是如何定义的,但是使用所有默认设置并看到你已经导入了EarlyStopping
你可以这样做:
early_stopping_monitor = EarlyStopping(
monitor='val_loss',
min_delta=0,
patience=0,
verbose=0,
mode='auto',
baseline=None,
restore_best_weights=True
)
And then just call model.fit()
with callbacks=[early_stopping_monitor]
like you already do.然后就像你已经做的那样,用
callbacks=[early_stopping_monitor]
调用model.fit()
。
I guess model_2.compile
was a typo.我猜
model_2.compile
是一个错字。 This should help if you want to save the best model wrt to the val_losses -如果您想将最佳模型 wrt 保存到 val_losses,这应该会有所帮助 -
checkpoint = ModelCheckpoint('model-{epoch:03d}-{acc:03f}-{val_acc:03f}.h5', verbose=1, monitor='val_loss',save_best_only=True, mode='auto')
model.compile(optimizer='adam', loss='mean_squared_error', metrics=['accuracy'])
model.fit(X, y, epochs=15, validation_split=0.4, callbacks=[checkpoint], verbose=False)
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.