merlin.models.tf.MultiClassClassificationTask

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

Bases: merlin.models.tf.prediction_tasks.base.PredictionTask

Prediction task for multi-class classification.

Parameters

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

• task_name (str, optional) – The name of the task.

• task_block (Block, optional) – The block to use for the task.

• loss (LossType, optional) – The loss to use for the task. Defaults to “sparse_categorical_crossentropy”.

• metrics (MetricOrMetrics, optional) – The metrics to use for the task. Defaults to [accuracy].

__init__(target_name: Optional[str] = None, task_name: Optional[str] = None, task_block: Optional[keras.engine.base_layer.Layer] = None, loss: Optional[Union[str, keras.losses.Loss]] = 'sparse_categorical_crossentropy', metrics: Optional[Union[Sequence[Union[keras.metrics.base_metric.Metric, Type[keras.metrics.base_metric.Metric]]], keras.metrics.base_metric.Metric, Type[keras.metrics.base_metric.Metric]]] = (<class 'keras.metrics.metrics.Accuracy'>,), pre: Optional[merlin.models.tf.blocks.core.base.Block] = None, **kwargs)

Methods

__init__([target_name, task_name, …])
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.
attach_metrics_calculation_to_loss(outputs, …)
build(input_shape)	Creates the variables of the layer (optional, for subclass implementers).
build_task(input_shape, schema, body, **kwargs)
calculate_metrics(outputs[, sample_weight, …])	Method to compute the metrics.
call(inputs[, training])
child_name(name)
compute_loss(predictions, targets[, …])	Method to compute the loss and metrics during training/evaluation.
compute_mask(inputs[, mask])	Computes an output mask tensor.
compute_output_shape(input_shape)	Computes the output shape of the layer.
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)
from_schema(schema[, feature_name, loss, …])	Create 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_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.
metric_result_dict([mode])
metric_results([mode])
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.
repr_add()
reset_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

DEFAULT_LOSS
DEFAULT_METRICS
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.

DEFAULT_LOSS = 'sparse_categorical_crossentropy'

DEFAULT_METRICS: Union[Sequence[Union[keras.metrics.base_metric.Metric, Type[keras.metrics.base_metric.Metric]]], keras.metrics.base_metric.Metric, Type[keras.metrics.base_metric.Metric]] = (<class 'keras.metrics.metrics.Accuracy'>,)

classmethod from_schema(schema: merlin.schema.schema.Schema, feature_name: str = <Tags.ITEM_ID: 'item_id'>, loss='sparse_categorical_crossentropy', bias_initializer='zeros', kernel_initializer='random_normal', extra_pre: Optional[merlin.models.tf.blocks.core.base.Block] = None, **kwargs) → merlin.models.tf.prediction_tasks.classification.MultiClassClassificationTask

Create from Schema.

call(inputs, training=False, **kwargs)

metric_results(mode: str = 'val')

get_config()

classmethod from_config(config)