TrendBlock

class tfts.layers.nbeats_layer.TrendBlock(*args, **kwargs)

Bases: Layer

Trend block that learns trend patterns using polynomial basis functions.

This block uses polynomial basis functions to model trends in the time series data. It outputs both backcast (reconstruction of input) and forecast (prediction) components.

Parameters:

• train_sequence_length (int) – Length of the input sequence

• predict_sequence_length (int) – Length of the prediction sequence

• hidden_size (int) – Number of units in the hidden layers

• n_block_layers (int, optional) – Number of fully connected layers in the block, by default 4

• polynomial_term (int, optional) – Degree of the polynomial basis functions, by default 2

Inherited-members:

Methods

add_loss(loss)	Can be called inside of the call() method to add a scalar loss.
add_metric(*args, **kwargs)
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 the layer's weights.
build_from_config(config)	Builds the layer's states with the supplied config dict.
call(inputs)	Compute the output of the Trend Block.
compute_mask(inputs, previous_mask)
compute_output_shape(input_shape)
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[, type_check])
quantized_build(input_shape, mode)
quantized_call(*args, **kwargs)
rematerialized_call(layer_call, *args, **kwargs)	Enable rematerialization dynamically for layer's call method.
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.

build(input_shape: Tuple[int | None, ...])

Build the layer’s weights.

Parameters:

input_shape (Tuple[Optional[int], ...]) – Shape of the input tensor

call(inputs: Tensor) → Tuple[Tensor, Tensor]

Compute the output of the Trend Block.

Parameters:

inputs (tf.Tensor) – A tensor of shape (batch_size, train_sequence_length, input_size)

Returns:

A tuple of two tensors: - backcast: Shape (batch_size, train_sequence_length, output_size) - forecast: Shape (batch_size, predict_sequence_length, output_size)

Return type:

Tuple[tf.Tensor, tf.Tensor]