merlin.models.tf.ParallelPredictionBlock
-
class
merlin.models.tf.
ParallelPredictionBlock
(*args, **kwargs)[source] 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)[source]
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_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
()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.
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.
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
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[source] 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
-
call
(inputs: Union[Dict[str, tensorflow.python.framework.ops.Tensor], tensorflow.python.framework.ops.Tensor], training: bool = False, bias_outputs=None, **kwargs)[source]
-
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[source]
-
property
task_blocks
-
property
task_names
-
property
metrics
-
parallel_layers
: Union[List[TabularBlock], Dict[str, TabularBlock]]