tf.ActivationLayer module

tf.ActivationLayer module

class tf.ActivationLayer.ActivationLayer(*args: Any, **kwargs: Any)

Bases: modelzoo.common.layers.tf.BaseLayer.BaseLayer

Wrapper around the Keras activation layer.

Also supports activation="GeLU", which is currently missing in keras.layers.ActivationLayer.

Parameters

  • activation (Union[str, Callable]) – The function to be applied. This can either be callable string name of a Tensorflow built-in activation, or one of "gelu" or "lrelu" (lrelu denotes LeakyReLU).

  • boundary_casting (bool) – If True, outputs the values in half precision and casts the input values up to full precision.

  • tf_summary (bool) – If True, saves the activations with the summary_layer.

call(inputs, **kwargs)

Apply the activation layer.

Parameters

inputs – Arbitrary tensor.

Returns

A tensor of the same shape as the input.

Return type

Tensor

static gelu(x)

previous

tf package

next

tf.AddLayer module