merlin.models.tf.ParallelBlock#

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

Bases: merlin.models.tf.core.tabular.TabularBlock

Merge multiple layers or TabularModule’s into a single output of TabularData.

Parameters

inputs (Union[tf.keras.layers.Layer, Dict[str, tf.keras.layers.Layer]]) – keras layers to merge into, this can also be one or multiple layers keyed by the name the module should have.
pre (Union[str, TabularTransformation, List[str], List[TabularTransformation]], optional) – Transformations to apply on the inputs when the module is called (so before call).
post (Union[str, TabularTransformation, List[str], List[TabularTransformation]], optional) – Transformations to apply on the inputs after the module is called (so after call).
aggregation (Union[str, TabularAggregation], optional) –
Aggregation to apply after processing the call-method to output a single Tensor.

Next to providing a class that extends TabularAggregation, it’s also possible to provide the name that the class is registered in the tabular_aggregation_registry. Out of the box this contains: “concat”, “stack”, “element-wise-sum” & “element-wise-sum-item-multi”.
schema (Optional[DatasetSchema]) – DatasetSchema containing the columns used in this block.
name (Optional[str]) – Name of the layer.
use_layer_name (use the original name of layers provided in inputs as key-index of the) – parallel branches.
strict – If true, inputs must be a dictionary. Otherwise, an error will be raised.
automatic_pruning – If true, branches with no output will automatically be pruned.
**kwargs – Extra arguments to pass to TabularBlock.

__init__(*inputs: Union[keras.engine.base_layer.Layer, Dict[str, keras.engine.base_layer.Layer]], pre: Optional[Union[merlin.models.tf.core.base.Block, str, Sequence[str]]] = None, post: Optional[Union[merlin.models.tf.core.base.Block, str, Sequence[str]]] = None, aggregation: Optional[Union[str, merlin.models.tf.core.tabular.TabularAggregation]] = None, schema: Optional[merlin.schema.schema.Schema] = None, name: Optional[str] = None, strict: bool = False, automatic_pruning: bool = True, use_layer_name: bool = True, **kwargs)[source]#

Methods

`__init__`(*inputs[, pre, post, aggregation, ...])
`add_branch`(name, block)
`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.
`apply_to_all`(inputs[, columns_to_filter])
`apply_to_branch`(branch_name, *block)
`as_tabular`([name])
`build`(input_shape)
`build_from_config`(config)
`calculate_batch_size_from_input_shapes`(...)
`call`(inputs, **kwargs)	The call method for ParallelBlock
`call_outputs`(outputs[, training])
`check_schema`([schema])
`compute_call_output_shape`(input_shape)
`compute_mask`(inputs[, mask])	Computes an output mask tensor.
`compute_output_shape`(input_shapes)
`compute_output_signature`(input_signature)	Compute the output tensor signature of the layer based on the inputs.
`connect`(*block[, block_name, context])	Connect the block to other blocks sequentially.
`connect_branch`(*branches[, add_rest, post, ...])	Connect the block to one or multiple branches.
`connect_debug_block`([append])	Connect the block to a debug block.
`connect_with_residual`(block[, activation])	Connect the block to other blocks sequentially with a residual connection.
`connect_with_shortcut`(block[, ...])	Connect the block to other blocks sequentially with a shortcut connection.
`copy`()
`count_params`()	Count the total number of scalars composing the weights.
`finalize_state`()	Finalizes the layers state after updating layer weights.
`from_config`(config[, custom_objects])
`from_features`(features[, pre, post, ...])	Initializes a TabularLayer instance where the contents of features will be filtered out
`from_layer`(layer)
`from_schema`(schema[, tags, allow_none])	Instantiate a TabularLayer instance from a DatasetSchema.
`get_build_config`()
`get_config`()
`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_item_ids_from_inputs`(inputs)
`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_padding_mask_from_item_id`(inputs[, ...])
`get_weights`()	Returns the current weights of the layer, as NumPy arrays.
`parse`(*block)
`parse_block`(input)
`parse_config`(config[, custom_objects])
`post_call`(inputs[, transformations, ...])	Method that's typically called after the forward method for post-processing.
`pre_call`(inputs[, transformations])	Method that's typically called before the forward method for pre-processing.
`prepare`([block, post, aggregation])	Transform the inputs of this block.
`register_features`(feature_shapes)
`repeat`([num])	Repeat the block num times.
`repeat_in_parallel`([num, prefix, names, ...])	Repeat the block num times in parallel.
`repr_add`()
`repr_extra`()
`repr_ignore`()
`select_by_name`(name)	Select a parallel block by name
`select_by_names`(names)	Select a list of parallel blocks by names
`select_by_tag`(tags)	Select layers of parallel blocks by tags.
`set_aggregation`(value)	param value
`set_post`(value)
`set_pre`(value)
`set_schema`([schema])
`set_weights`(weights)	Sets the weights of the layer, from NumPy arrays.
`super`()
`with_name_scope`(method)	Decorator to automatically enter the module name scope.

Attributes

`REQUIRES_SCHEMA`
`activity_regularizer`	Optional regularizer function for the output of this layer.
`aggregation`	rtype: TabularAggregation, optional
`compute_dtype`	The dtype of the layer's computations.
`context`
`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.
`first`
`has_schema`
`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.
`is_input`
`is_tabular`
`layers`
`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.
`parallel_dict`
`parallel_values`
`post`	rtype: SequentialTabularTransformations, optional
`pre`	rtype: SequentialTabularTransformations, optional
`registry`
`schema`
`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.

property schema#

property parallel_values: List[keras.engine.base_layer.Layer]#

property parallel_dict: Dict[Union[str, int], keras.engine.base_layer.Layer]#

property layers: List[keras.engine.base_layer.Layer]#

select_by_name(name: str) → Optional[merlin.models.tf.core.base.Block][source]#

Select a parallel block by name

Returns: The block corresponding to the name
Return type: Block

select_by_names(names: List[str]) → Optional[List[merlin.models.tf.core.base.Block]][source]#

Select a list of parallel blocks by names

Returns: The blocks corresponding to the names
Return type: List[Block]

select_by_tag(tags: Union[str, merlin.schema.tags.Tags, List[Union[str, merlin.schema.tags.Tags]]]) → Optional[merlin.models.tf.core.combinators.ParallelBlock][source]#

Select layers of parallel blocks by tags.

This method will return a ParallelBlock instance with all the branches that have at least one feature that matches any of the tags provided.

For example, this method can be useful when a ParallelBlock has both item and user features in a two-tower model or DLRM, and we want to select only the item or user features.

>>> all_inputs = InputBlockV2(schema)  # InputBlock is also a ParallelBlock
>>> item_inputs = all_inputs.select_by_tag(Tags.ITEM)
['continuous', 'embeddings']
>>> item_inputs.schema["continuous"].column_names
['item_recency']
>>> item_inputs.schema["embeddings"].column_names
['item_id', 'item_category', 'item_genres']

Parameters: tags (str or Tags or List[Union[str, Tags]]) – List of tags that describe which blocks to match
Return type: ParallelBlock

property first: merlin.models.tf.core.base.Block#

add_branch(name: str, block: merlin.models.tf.core.base.Block) → merlin.models.tf.core.combinators.ParallelBlock[source]#

apply_to_branch(branch_name: str, *block: merlin.models.tf.core.base.Block)[source]#

call(inputs, **kwargs)[source]#

The call method for ParallelBlock

Parameters: inputs (TabularData) – The inputs for the Parallel Block
Returns: Outputs of the ParallelBlock
Return type: TabularData

compute_call_output_shape(input_shape)[source]#

build(input_shape)[source]#

get_config()[source]#

classmethod parse_config(config, custom_objects=None)[source]#

classmethod from_config(config, custom_objects=None)[source]#