teras.layers.TransformerFeedForward

class teras.layers.TransformerFeedForward(embedding_dim, hidden_dim=None, activation='relu', dropout=0.0, **kwargs)

Transformer Feed Forward layer as proposed in the original Transformers architecture, in the paper,”Attention is all you need”, with a slight addition of optional Dropout layer.

Reference(s):

https://arxiv.org/abs/1706.03762

Parameters:

• embedding_dim (int) – int, dimensionality of embeddings being used in the model

• hidden_dim (int) – int, hidden dimensionality to use. By default, it is four-times of the embedding_dim.

• activation (Union[str, Callable, Layer]) – str or callable, activation function to use for the inner linear layer. Defaults to “relu”,

• dropout (float) – float, dropout rate to use for the dropout layer that is applied in between the two linear layer. Defaults to 0., because the original transformer architecture doesn’t employ a Dropout layer.

__init__(embedding_dim, hidden_dim=None, activation='relu', dropout=0.0, **kwargs)

Methods

__init__(embedding_dim[, hidden_dim, ...])
add_loss(loss)	Can be called inside of the call() method to add a scalar loss.
add_metric()
add_variable(shape, initializer[, dtype, ...])	Add a weight variable to the layer.
add_weight([shape, initializer, dtype, ...])	Add a weight variable to the layer.
build(input_shape)
build_from_config(config)	Builds the layer's states with the supplied config dict.
call(inputs)
compute_mask(inputs, previous_mask)
compute_output_shape(*args, **kwargs)
compute_output_spec(*args, **kwargs)
count_params()	Count the total number of scalars composing the weights.
from_config(config)	Creates an operation from its config.
get_build_config()	Returns a dictionary with the layer's input shape.
get_config()	Returns the config of the object.
get_weights()	Return the values of layer.weights as a list of NumPy arrays.
load_own_variables(store)	Loads the state of the layer.
quantize(mode)
quantized_call(*args, **kwargs)
save_own_variables(store)	Saves the state of the layer.
set_weights(weights)	Sets the values of layer.weights from a list of NumPy arrays.
stateless_call(trainable_variables, ...[, ...])	Call the layer without any side effects.
symbolic_call(*args, **kwargs)

Attributes

compute_dtype	The dtype of the computations performed by the layer.
dtype	Alias of layer.variable_dtype.
dtype_policy
input	Retrieves the input tensor(s) of a symbolic operation.
input_dtype	The dtype layer inputs should be converted to.
input_spec
losses	List of scalar losses from add_loss, regularizers and sublayers.
metrics	List of all metrics.
metrics_variables	List of all metric variables.
non_trainable_variables	List of all non-trainable layer state.
non_trainable_weights	List of all non-trainable weight variables of the layer.
output	Retrieves the output tensor(s) of a layer.
path	The path of the layer.
quantization_mode	The quantization mode of this layer, None if not quantized.
supports_masking	Whether this layer supports computing a mask using compute_mask.
trainable	Settable boolean, whether this layer should be trainable or not.
trainable_variables	List of all trainable layer state.
trainable_weights	List of all trainable weight variables of the layer.
variable_dtype	The dtype of the state (weights) of the layer.
variables	List of all layer state, including random seeds.
weights	List of all weight variables of the layer.