python - 在keras中创建自定义激活函数

Question

我正在尝试在 keras 中创建自己的自定义激活函数，如果 x < 0，则返回 0；如果 x >= 0，则返回 1

 from keras.layers import Dense
 from keras.models import Sequential
 from keras.layers import Activation
 import tensorflow as tf


def hard_lim(x):

     zero = tf.convert_to_tensor(0., x.dtype.base_dtype)

     one = tf.convert_to_tensor(1., x.dtype.base_dtype)

     sess = tf.Session()

     if sess.run(tf.greater_equal(x, zero)):
         return one
     else:
         return zero

     model = Sequential()

     model.add(Dense(4, input_dim=2, activation=Activation(hard_lim))
     model.add(Dense(2, activation=Activation(hard_lim))
     model.add(Dense(1, activation=Activation(hard_lim))

它给了我这个错误

 InvalidArgumentError (see above for traceback): You must feed a value           
 for placeholder tensor '1_input' with dtype float and shape [?,2]

如何修复它？

Answer 1

Warning: this operation you want has no gradients and will not allow any weights before it to be trainable. You will see error messages like "an operation has None for gradient" or something like "None type not supported".

As a workaround for your activation, I believe the 'relu' activation would be the closest and best option, with the advantage of being very popular and used in most models.

在 Keras 中，您通常不运行 session 。对于自定义操作，您可以使用 backend 创建一个函数功能。

因此，您可以使用 Lambda 层:

import keras.backend as K

def hardlim(x):
   return K.cast(K.greater_equal(x,0), K.floatx())

然后您可以在层中使用activation=hardlim。