merlin.models.tf.CategoricalOutput#

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

Bases: merlin.models.tf.outputs.base.ModelOutput

Categorical output

Parameters
  • prediction (Union[Schema, ColumnSchema,) –

    EmbeddingTable, ‘CategoricalTarget’,

    ’EmbeddingTablePrediction’]

    The target feature to predict. To perform weight-tying [1] technique, you should provide the EmbeddingTable or EmbeddingTablePrediction related to the target feature.

  • negative_samplers (ItemSamplersType, optional) – List of samplers for negative sampling, by default None

  • pre (Optional[Block], optional) – Optional block to transform predictions before computing the binary logits, by default None

  • post (Optional[Block], optional) – Optional block to transform the binary logits, by default None

  • logits_temperature (float, optional) – Parameter used to reduce model overconfidence, so that logits / T. by default 1

  • name (str, optional) – The name of the task, by default None

  • default_loss (Union[str, tf.keras.losses.Loss], optional) – Default loss to use for categorical-classification by default ‘categorical_crossentropy’

  • get_default_metrics (Callable, optional) – A function returning the list of default metrics to use for categorical-classification

  • References

  • ----------

  • Inan ([1] Hakan) –

  • Khosravi (Khashayar) –

  • vectors (and Richard Socher. 2016. Tying word) –

  • classifiers (and word) –

  • arXiv (1611.01462 (2016).) –

__init__(to_call: typing.Union[merlin.schema.schema.Schema, merlin.schema.schema.ColumnSchema, merlin.models.tf.inputs.embedding.EmbeddingTable, merlin.models.tf.outputs.classification.CategoricalTarget, merlin.models.tf.outputs.classification.EmbeddingTablePrediction], target_name: typing.Optional[str] = None, pre: typing.Optional[keras.engine.base_layer.Layer] = None, post: typing.Optional[keras.engine.base_layer.Layer] = None, logits_temperature: float = 1.0, name: typing.Optional[str] = None, default_loss: typing.Union[str, keras.losses.Loss] = 'categorical_crossentropy', default_metrics_fn: typing.Callable[[], typing.Sequence[keras.metrics.base_metric.Metric]] = <function default_categorical_prediction_metrics>, **kwargs)[source]#

Methods

__init__(to_call[, target_name, pre, post, ...])

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])

Builds the PredictionBlock.

build_from_config(config)

call(inputs[, training, testing])

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_task_name(target_name)

Returns the name of the task :param target_name: Name of the target :type target_name: str

get_weights()

Returns the current weights of the layer, as NumPy arrays.

set_weights(weights)

Sets the weights of the layer, from NumPy arrays.

to_dataset([gpu])

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.

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.

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.

to_dataset(gpu=True) merlin.io.dataset.Dataset[source]#
get_config()[source]#