tf.nn.crelu( features, name=None, axis=-1 )
See the guide: Neural Network > Activation Functions
Computes Concatenated ReLU.
Concatenates a ReLU which selects only the positive part of the activation with a ReLU which selects only the negative part of the activation. Note that as a result this non-linearity doubles the depth of the activations. Source: Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units. W. Shang, et al.
name: A name for the operation (optional).
axis: The axis that the output values are concatenated along. Default is -1.
Tensor with the same type as