ConvTemp#

class tfts.layers.cnn_layer.ConvTemp(*args, **kwargs)[source]#

Bases: Layer

Temporal convolutional layer for time series processing.

This layer implements a 1D convolutional layer with optional causal padding, which is commonly used in time series models like WaveNet. The layer can be configured to use dilated convolutions and causal padding to ensure temporal dependencies are properly captured.

Parameters:

  • filters (int) – The number of output filters in the convolution.

  • kernel_size (int) – The length of the 1D convolution window.

  • strides (int, optional) – The stride length of the convolution. Defaults to 1.

  • dilation_rate (int, optional) – The dilation rate to use for dilated convolution. Defaults to 1.

  • activation (str, optional) – Activation function to use. Defaults to “relu”.

  • causal (bool, optional) – Whether to use causal padding. If True, ensures no information leakage from future timesteps. Defaults to True.

  • kernel_initializer (str, optional) – Initializer for the kernel weights matrix. Defaults to “glorot_uniform”.

  • name (str, optional) – Name of the layer. Defaults to None.

  • shape (Output) –

    • 3D tensor with shape (batch_size, sequence_length, features)

  • shape –

    • 3D tensor with shape (batch_size, new_sequence_length, filters)

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 by creating the convolutional layer.

build_from_config(config)

Builds the layer's states with the supplied config dict.

call(inputs)

Forward pass of the layer.

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()

Get the configuration of the layer.

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[source]#

Build the layer by creating the convolutional layer.

Parameters:

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

call(inputs)[source]#

Forward pass of the layer.

Parameters:

inputs (tf.Tensor) – Input tensor with shape (batch_size, sequence_length, features)

Returns:

Output tensor after applying temporal convolution

Return type:

tf.Tensor

get_config()[source]#

Get the configuration of the layer.

Returns:

Configuration dictionary containing layer parameters

Return type:

dict