merlin.models.tf.PredictionTask

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

Bases: keras.engine.base_layer.Layer, merlin.models.tf.core.base.ContextMixin

Base-class for prediction tasks.

Parameters

• target_name (Optional[str], optional) – Label name, by default None

• task_name (Optional[str], optional) – Task name, by default None

• metrics (Optional[MetricOrMetrics], optional) – List of Keras metrics to be evaluated, by default None

• pre (Optional[Block], optional) – Optional block to transform predictions before computing loss and metrics, by default None

• pre_eval_topk (Optional[Block], optional) – Optional block to apply additional transform predictions before computing top-k evaluation loss and metrics, by default None

• task_block (Optional[Layer], optional) – Optional block to apply to inputs before computing predictions, by default None

• prediction_metrics (Optional[List[tf.keras.metrics.Metric]], optional) – List of Keras metrics used to summarize the predictions, by default None

• label_metrics (Optional[List[tf.keras.metrics.Metric]], optional) – List of Keras metrics used to summarize the labels, by default None

• compute_train_metrics (Optional[bool], optional) – Enable computing metrics during training, by default True

• name (Optional[Text], optional) – Task name, by default None

__init__(target_name: Optional[str] = None, task_name: Optional[str] = None, pre: Optional[merlin.models.tf.core.base.Block] = None, pre_eval_topk: Optional[merlin.models.tf.core.base.Block] = None, task_block: Optional[keras.engine.base_layer.Layer] = None, name: Optional[str] = None, **kwargs) → None

Methods

__init__([target_name, task_name, pre, ...])
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[, features_shape])
build_from_config(config)
build_task(input_shape, schema, body, **kwargs)
call(inputs, *args, **kwargs)	This is where the layer's logic lives.
child_name(name)
compute_mask(inputs[, mask])	Computes an output mask tensor.
compute_output_shape(input_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.
create_default_metrics()
finalize_state()	Finalizes the layers state after updating layer weights.
from_config(config)
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_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.
pre_call(inputs, **kwargs)	Apply PredictionTask to inputs to get predictions scores
pre_loss(outputs, **kwargs)	Apply call_outputs method of pre block to transform predictions and targets before computing loss and metrics.
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.
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.
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.
pre_eval_topk
stateful
submodules	Sequence of all sub-modules.
supports_masking	Whether this layer supports computing a mask using compute_mask.
task_name
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 pre_eval_topk

pre_call(inputs: Union[tensorflow.python.framework.ops.Tensor, Dict[str, tensorflow.python.framework.ops.Tensor]], **kwargs) → tensorflow.python.framework.ops.Tensor

Apply PredictionTask to inputs to get predictions scores

Parameters

inputs (TensorOrTabularData) – inputs of the prediction task

Return type

tf.Tensor

pre_loss(outputs: merlin.models.tf.core.base.PredictionOutput, **kwargs) → merlin.models.tf.core.base.PredictionOutput

Apply call_outputs method of pre block to transform predictions and targets before computing loss and metrics.

Parameters

outputs (PredictionOutput) – The named tuple containing predictions and targets tensors

Returns

The named tuple containing transformed predictions and targets tensors

Return type

PredictionOutput

build(input_shape, features_shape=None)

build_task(input_shape, schema: merlin.schema.schema.Schema, body: merlin.models.tf.core.base.Block, **kwargs)

property task_name

child_name(name)

classmethod from_config(config)

get_config()

create_default_metrics()

compute_output_shape(input_shape)