python - 如何使用 Keras 创建自定义激活函数？

Question

有时默认 standard activations像 ReLU、tanh、softmax... 和 advanced activations像 LeakyReLU 是不够的。它也可能不在 keras-contrib 中.

如何创建自己的激活函数？

Answer 1

致this Github issue comment by Ritchie Ng .

# Creating a model
from keras.models import Sequential
from keras.layers import Dense

# Custom activation function
from keras.layers import Activation
from keras import backend as K
from keras.utils.generic_utils import get_custom_objects


def custom_activation(x):
    return (K.sigmoid(x) * 5) - 1

get_custom_objects().update({'custom_activation': Activation(custom_activation)})

# Usage
model = Sequential()
model.add(Dense(32, input_dim=784))
model.add(Activation(custom_activation, name='SpecialActivation'))
print(model.summary())

请记住，您必须在保存和恢复模型时导入此功能。见 the note of keras-contrib .