merlin.models.tf.ParallelPredictionBlock

class merlin.models.tf.ParallelPredictionBlock(*args, **kwargs)

Bases: merlin.models.tf.blocks.core.combinators.ParallelBlock, merlin.models.tf.utils.mixins.LossMixin, merlin.models.tf.utils.mixins.MetricsMixin

Multi-task prediction block.

Parameters

• prediction_tasks (*PredictionTask) – List of tasks to be used for prediction.

• task_blocks (Optional[Union[Layer, Dict[str, Layer]]]) – Task blocks to be used for prediction.

• task_weights (Optional[List[float]]) – Weights for each task.

• bias_block (Optional[Layer]) – Bias block to be used for prediction.

• loss_reduction (Callable) – Reduction function for loss.

__init__(*prediction_tasks: merlin.models.tf.prediction_tasks.base.PredictionTask, task_blocks: Optional[Union[keras.engine.base_layer.Layer, Dict[str, keras.engine.base_layer.Layer]]] = None, task_weights: Optional[List[float]] = None, bias_block: Optional[keras.engine.base_layer.Layer] = None, loss_reduction=<function reduce_mean>, pre: Optional[Union[merlin.models.tf.blocks.core.base.Block, str, Sequence[str]]] = None, post: Optional[Union[merlin.models.tf.blocks.core.base.Block, str, Sequence[str]]] = None, **kwargs)

Methods

__init__(*prediction_tasks[, task_blocks, …])
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_task(task[, task_weight])
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)
calculate_batch_size_from_input_shapes(…)
calculate_metrics(outputs[, mode, forward, …])	Calculate metrics on a batch of data, each metric is stateful and this updates the state.
call(inputs[, training, bias_outputs])
call_outputs(outputs[, training])
check_schema([schema])
compute_call_output_shape(input_shape)
compute_loss(inputs, targets[, training])
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, **kwargs)
from_features(features[, pre, post, …])	Initializes a TabularLayer instance where the contents of features will be filtered out
from_layer(layer)
from_schema(schema[, task_blocks, …])	Built Multi-task prediction Block from schema
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_tasks_from_schema(schema[, task_weight_dict])
get_weights()	Returns the current weights of the layer, as NumPy arrays.
metric_result_dict([mode])
metric_results([mode])
parse(*block)
parse_block(input)
parse_config(config[, custom_objects])
pop_labels(inputs)
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()
reset_metrics()
select_by_name(name)	Select a parallel block by name
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()
task_names_from_schema(schema)
to_model(schema[, input_block, prediction_tasks])	Wrap the block between inputs & outputs to create a model.
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	returns: :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.
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
losses	List of losses added using the add_loss() API.
metrics
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	returns: :rtype: SequentialTabularTransformations, optional
pre	returns: :rtype: SequentialTabularTransformations, optional
registry
schema
stateful
submodules	Sequence of all sub-modules.
supports_masking	Whether this layer supports computing a mask using compute_mask.
task_blocks
task_names
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.

classmethod get_tasks_from_schema(schema, task_weight_dict=None)

classmethod from_schema(schema: merlin.schema.schema.Schema, task_blocks: Optional[Union[keras.engine.base_layer.Layer, Dict[str, keras.engine.base_layer.Layer]]] = None, task_weight_dict: Optional[Dict[str, float]] = None, bias_block: Optional[keras.engine.base_layer.Layer] = None, loss_reduction=<function reduce_mean>, **kwargs) → merlin.models.tf.prediction_tasks.base.ParallelPredictionBlock

Built Multi-task prediction Block from schema

Parameters

• schema (Schema) – The Schema with the input features

• task_blocks (Optional[Union[Layer, Dict[str, Layer]]], optional) – Task blocks to be used for prediction, by default None

• task_weight_dict (Optional[Dict[str, float]], optional) – Weights for each task, by default None

• bias_block (Optional[Layer], optional) – Bias block to be used for prediction, by default None

• loss_reduction (_type_, optional) – Reduction function for loss, by default tf.reduce_mean

classmethod task_names_from_schema(schema: merlin.schema.schema.Schema) → List[str]

add_task(task: merlin.models.tf.prediction_tasks.base.PredictionTask, task_weight=1)

pop_labels(inputs: Dict[str, tensorflow.python.framework.ops.Tensor])

call(inputs: Union[Dict[str, tensorflow.python.framework.ops.Tensor], tensorflow.python.framework.ops.Tensor], training: bool = False, bias_outputs=None, **kwargs)

compute_call_output_shape(input_shape)

compute_loss(inputs: Union[tensorflow.python.framework.ops.Tensor, Dict[str, tensorflow.python.framework.ops.Tensor]], targets, training=False, **kwargs) → tensorflow.python.framework.ops.Tensor

metric_results(mode=None)

metric_result_dict(mode=None)

reset_metrics()

property task_blocks

property task_names

property metrics

repr_ignore() → List[str]

classmethod from_config(config, **kwargs)

get_config()

parallel_layers: Union[List[TabularBlock], Dict[str, TabularBlock]]