merlin.models.tf.AverageEmbeddingsByWeightFeature#

class merlin.models.tf.AverageEmbeddingsByWeightFeature(*args, **kwargs)[source]#

Bases: keras.engine.base_layer.Layer

__init__(weight_feature_name: str, axis=1, **kwargs)[source]#

Computes the weighted average of a Tensor based on one of the input features. Typically used as a combiner for EmbeddingTable for aggregating sequential embedding features

Parameters

weight_feature_name (str) – Name of the feature to be used as weight for average
axis (int, optional) – Axis for reduction, by default 1 (assuming the 2nd dim is the sequence length)

Methods

`__init__`(weight_feature_name[, axis])	Computes the weighted average of a Tensor based on one of the input features.
`add_loss`(losses, **kwargs)	Add loss tensor(s), potentially dependent on layer inputs.
`add_metric`(value[, name])	Adds metric tensor to the layer.
`add_update`(updates)	Add update op(s), potentially dependent on layer inputs.
`add_variable`(args, *kwargs)	Deprecated, do NOT use! Alias for add_weight.
`add_weight`([name, shape, dtype, ...])	Adds a new variable to the layer.
`build`(input_shape)	Creates the variables of the layer (for subclass implementers).
`build_from_config`(config)
`call`(inputs, features)	Performs the weighted average calculation.
`compute_mask`(inputs[, mask])	Computes an output mask tensor.
`compute_output_shape`(input_shape)	Computes the output shape.
`compute_output_signature`(input_signature)	Compute the output tensor signature of the layer based on the inputs.
`count_params`()	Count the total number of scalars composing the weights.
`finalize_state`()	Finalizes the layers state after updating layer weights.
`from_config`(config)	Creates a layer from its config.
`from_schema_convention`(schema[, ...])	Infers the weight features corresponding to sequential embedding features based on the feature name suffix.
`get_build_config`()
`get_config`()	Returns the configuration of the layer.
`get_input_at`(node_index)	Retrieves the input tensor(s) of a layer at a given node.
`get_input_mask_at`(node_index)	Retrieves the input mask tensor(s) of a layer at a given node.
`get_input_shape_at`(node_index)	Retrieves the input shape(s) of a layer at a given node.
`get_output_at`(node_index)	Retrieves the output tensor(s) of a layer at a given node.
`get_output_mask_at`(node_index)	Retrieves the output mask tensor(s) of a layer at a given node.
`get_output_shape_at`(node_index)	Retrieves the output shape(s) of a layer at a given node.
`get_weights`()	Returns the current weights of the layer, as NumPy arrays.
`set_weights`(weights)	Sets the weights of the layer, from NumPy arrays.
`with_name_scope`(method)	Decorator to automatically enter the module name scope.

Attributes

`activity_regularizer`	Optional regularizer function for the output of this layer.
`compute_dtype`	The dtype of the layer's computations.
`dtype`	The dtype of the layer weights.
`dtype_policy`	The dtype policy associated with this layer.
`dynamic`	Whether the layer is dynamic (eager-only); set in the constructor.
`inbound_nodes`	Return Functional API nodes upstream of this layer.
`input`	Retrieves the input tensor(s) of a layer.
`input_mask`	Retrieves the input mask tensor(s) of a layer.
`input_shape`	Retrieves the input shape(s) of a layer.
`input_spec`	InputSpec instance(s) describing the input format for this layer.
`losses`	List of losses added using the add_loss() API.
`metrics`	List of metrics added using the add_metric() API.
`name`	Name of the layer (string), set in the constructor.
`name_scope`	Returns a tf.name_scope instance for this class.
`non_trainable_variables`
`non_trainable_weights`	List of all non-trainable weights tracked by this layer.
`outbound_nodes`	Return Functional API nodes downstream of this layer.
`output`	Retrieves the output tensor(s) of a layer.
`output_mask`	Retrieves the output mask tensor(s) of a layer.
`output_shape`	Retrieves the output shape(s) of a layer.
`stateful`
`submodules`	Sequence of all sub-modules.
`supports_masking`	Whether this layer supports computing a mask using compute_mask.
`trainable`
`trainable_variables`
`trainable_weights`	List of all trainable weights tracked by this layer.
`updates`
`variable_dtype`	Alias of Layer.dtype, the dtype of the weights.
`variables`	Returns the list of all layer variables/weights.
`weights`	Returns the list of all layer variables/weights.

call(inputs, features)[source]#

Performs the weighted average calculation.

Parameters

inputs (tf.Tensor) – Input tensor.
features (dict) – Dictionary of features, must include the weight feature.

Returns

Output tensor after applying the weighted average calculation.

Return type

Tensor

Raises

ValueError – If the inputs is a tf.RaggedTensor, the weight feature should also be a tf.RaggedTensor.

compute_output_shape(input_shape)[source]#

Computes the output shape.

Parameters: input_shape (tf.TensorShape) – Shape of the input.
Returns: Shape of the output, which is the same as the input shape in this case.
Return type: tf.TensorShape

static from_schema_convention(schema: merlin.schema.schema.Schema, weight_features_name_suffix: str = '_weight')[source]#

Infers the weight features corresponding to sequential embedding features based on the feature name suffix. For example, if a sequential categorical feature is called item_id_seq, if there is another feature in the schema called item_id_seq_weight, then it will be used for weighted average. If a weight feature cannot be found for a given seq cat. feature then standard mean is used as combiner

Parameters

schema (Schema) – The feature schema
weight_features_name_suffix (str) – Suffix to look for a corresponding weight feature

Returns

A dict where the key is the sequential categorical feature name and the value is an instance of WeightedAverageByFeature with the corresponding weight feature name

Return type

Dict[str, WeightedAverageByFeature]

get_config()[source]#

Returns the configuration of the layer.

Returns: A dictionary containing the configuration of the layer.
Return type: dict