我有一个模型,我想用学习率=0.8来训练它几个时期,然后设置学习率=0.4&;继续训练。 但由于在编译模型时设定了学习率。。。那么,如果我在几个时代之后重新编译模型/权重,会发生什么呢
下面是我的代码:p.S(我的学习率是动态的)
lr = 0.04
adam = Adam(lr=lr)
weight_factor = 10
models.compile(
optimizer=adam,
"kullback_leibler_divergence"
loss = {'W1':kl_divergence,'age':mae},
metrics={"age": mae,"W1":'accuracy'},
loss_weights={'W1':weight_factor, 'age': 1}
)
动态学习率回调
callbacks = [
ReduceLROnPlateau(monitor='val_age_mean_absolute_error',
factor = 0.5,
patience = 7,
min_delta = 0.01,
cooldown = 2,
min_lr = 0.0001,
mode = 'min')
]
训练
epochs=35
history = models.fit(train_gen, steps_per_epoch=len(trainset) / batch_size, epochs=epochs, callbacks=callbacks, validation_data=validation_gen, validation_steps=len(testset) / batch_size * 3)
重新编译模型时,权重将重置为“随机”
所以您应该使用
model.save_weights('weights.h5')
保存权重,然后编译模型,然后加载权重model.load_weights('weights.h5')
相关问题 更多 >
编程相关推荐