Keras layer that only adds a bias to the input.
tf_agents.keras_layers.BiasLayer(
bias_initializer='zeros', **kwargs
)
BiasLayer implements the operation:
output = input + bias
Args |
|---|
bias_initializer
|
Initializer for the bias vector.
|
|
|---|
nD tensor with shape: (batch_size, ..., input_dim). The most common
situation would be a 2D input with shape (batch_size, input_dim). Note
a rank of at least 2 is required.
|
Output shape |
|---|
nD tensor with shape: (batch_size, ..., input_dim). For instance, for a
2D input with shape (batch_size, input_dim), the output would have
shape (batch_size, input_dim).
|
View source on GitHub