RBERT (version 0.1.11)

layer_norm_and_dropout: Run layer normalization followed by dropout

Description

Run layer normalization followed by dropout

Usage

layer_norm_and_dropout(input_tensor, dropout_prob = NULL, name = NULL)

Arguments

input_tensor

Float Tensor to perform layer_norm and dropout on.

dropout_prob

A double describing the probability of dropping out a value (NOT of KEEPING a dimension as in `tf.nn.dropout`).

name

Optional variable_scope for layer_norm.

Value

Tensor resulting from applying layer_norm and dropout to input_tensor.

Examples

# NOT RUN {
tfx <- tensorflow::tf$get_variable("example2", tensorflow::shape(10L))
layer_norm_and_dropout(tfx, dropout_prob = 0.5)
# }