更新时间:2023-12-02 15:44:10
我认为您可以通过如下所示在model.compile
中启用run_eagerly=True
来做到这一点.
I think you can do this by enabling run_eagerly=True
in model.compile
as shown below.
model.compile(loss=custom_loss(weight_building, weight_space),optimizer=keras.optimizers.Adam(), metrics=['accuracy'],run_eagerly=True)
我认为您还需要更新custom_loss
,如下所示.
I think you also need to update custom_loss
as shown below.
def custom_loss(weight_building, weight_space):
def loss(y_true, y_pred):
truth = backend.get_value(y_true)
error = backend.square((y_pred - y_true))
mse_error = backend.mean(error, axis=-1)
return mse_error
return loss
我用一个简单的mnist
数据演示了这个想法.请在此处查看代码.
I am demonstrating the idea with a simple mnist
data. Please take a look at the code here.