你如何在 Python 中使用 Keras LeakyReLU？
声明：本页面是StackOverFlow热门问题的中英对照翻译，遵循CC BY-SA 4.0协议，如果您需要使用它，必须同样遵循CC BY-SA许可，注明原文地址和作者信息，同时你必须将它归于原作者（不是我）：StackOverFlow
原文地址: http://stackoverflow.com/questions/48828478/
Warning: these are provided under cc-by-sa 4.0 license. You are free to use/share it, But you must attribute it to the original authors (not me):
StackOverFlow
How do you use Keras LeakyReLU in Python?
提问by Hyman Trute
I am trying to produce a CNN using Keras, and wrote the following code:
我正在尝试使用 Keras 生成 CNN，并编写了以下代码：
batch_size = 64
epochs = 20
num_classes = 5
cnn_model = Sequential()
cnn_model.add(Conv2D(32, kernel_size=(3, 3), activation='linear',
input_shape=(380, 380, 1), padding='same'))
cnn_model.add(Activation('relu'))
cnn_model.add(MaxPooling2D((2, 2), padding='same'))
cnn_model.add(Conv2D(64, (3, 3), activation='linear', padding='same'))
cnn_model.add(Activation('relu'))
cnn_model.add(MaxPooling2D(pool_size=(2, 2), padding='same'))
cnn_model.add(Conv2D(128, (3, 3), activation='linear', padding='same'))
cnn_model.add(Activation('relu'))
cnn_model.add(MaxPooling2D(pool_size=(2, 2), padding='same'))
cnn_model.add(Flatten())
cnn_model.add(Dense(128, activation='linear'))
cnn_model.add(Activation('relu'))
cnn_model.add(Dense(num_classes, activation='softmax'))
cnn_model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.Adam(), metrics=['accuracy'])
I want to use Keras's LeakyReLUactivation layer instead of using Activation('relu'). However, I tried using LeakyReLU(alpha=0.1)in place, but this is an activation layer in Keras, and I get an error about using an activation layer and not an activation function.
我想使用Keras的LeakyReLU激活层而不是使用Activation('relu'). 但是，我尝试LeakyReLU(alpha=0.1)就地使用，但这是 Keras 中的激活层，我收到关于使用激活层而不是激活函数的错误。
How can I use LeakyReLUin this example?
在这个例子中如何使用LeakyReLU？
回答by desertnaut
All advanced activations in Keras, including LeakyReLU, are available as layers, and not as activations; therefore, you should use it as such:
Keras 中的所有高级激活，包括LeakyReLU，都可以作为layer 使用，而不是作为激活；因此，您应该这样使用它：
from keras.layers import LeakyReLU
# instead of cnn_model.add(Activation('relu'))
# use
cnn_model.add(LeakyReLU(alpha=0.1))
回答by P-Gn
Sometimes you just want a drop-in replacement for a built-in activation layer, and not having to add extra activation layers just for this purpose.
有时您只想直接替换内置激活层，而不必为此目的添加额外的激活层。
For that, you can use the fact that the activationargument can be a callable object.
为此，您可以使用activation参数可以是可调用对象这一事实。
lrelu = lambda x: tf.keras.activations.relu(x, alpha=0.1)
model.add(Conv2D(..., activation=lrelu, ...)
Since a Layeris also a callable object, you could also simply use
由于 aLayer也是一个可调用对象，您也可以简单地使用
model.add(Conv2D(..., activation=tf.keras.layers.LeakyReLU(alpha=0.1), ...)
which now works in TF2. This is a better solution as this avoids the need to use a custom_objectduring loading as @ChristophorusReyhan mentionned.
现在可以在 TF2 中使用。这是一个更好的解决方案，因为这避免了custom_object在加载过程中需要使用@ChristophorusReyhan 提到的。
