merlin.models.tf.EmbeddingFeatures

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

Bases: merlin.models.tf.blocks.core.tabular.TabularBlock

Input block for embedding-lookups for categorical features.

For multi-hot features, the embeddings will be aggregated into a single tensor using the mean.

Parameters

• feature_config (Dict[str, FeatureConfig]) – This specifies what TableConfig to use for each feature. For shared embeddings, the same TableConfig can be used for multiple features.

• item_id (str, optional) – The name of the feature that’s used for the item_id.

pre: Union[str, TabularTransformation, List[str], List[TabularTransformation]], optional

Transformations to apply on the inputs when the module is called (so before call).

post: Union[str, TabularTransformation, List[str], List[TabularTransformation]], optional

Transformations to apply on the inputs after the module is called (so after call).

aggregation: Union[str, TabularAggregation], optional

Aggregation to apply after processing the call-method to output a single Tensor.

Next to providing a class that extends TabularAggregation, it’s also possible to provide the name that the class is registered in the tabular_aggregation_registry. Out of the box this contains: “concat”, “stack”, “element-wise-sum” & “element-wise-sum-item-multi”.

schema: Optional[DatasetSchema]

DatasetSchema containing the columns used in this block.

name: Optional[str]

Name of the layer.

__init__(feature_config: Dict[str, tensorflow.python.tpu.tpu_embedding_v2_utils.FeatureConfig], 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, aggregation: Optional[Union[str, merlin.models.tf.blocks.core.tabular.TabularAggregation]] = None, schema: Optional[merlin.schema.schema.Schema] = None, name=None, add_default_pre=True, l2_reg: Optional[float] = 0.0, **kwargs)

Methods

__init__(feature_config[, 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.
apply_to_all(inputs[, columns_to_filter])
as_tabular([name])
build(input_shapes)
calculate_batch_size_from_input_shapes(…)
call(inputs, **kwargs)
call_outputs(outputs[, training])
check_schema([schema])
compute_call_output_shape(input_shapes)
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.
embedding_table_dataset(table_name[, …])	Creates a Dataset for the embedding table
embedding_table_df(table_name[, …])	Retrieves a dataframe with the embedding table
export_embedding_table(table_name, export_path)	Exports the embedding table to parquet file
finalize_state()	Finalizes the layers state after updating layer weights.
from_config(config)
from_features(features[, pre, post, …])	Initializes a TabularLayer instance where the contents of features will be filtered out
from_layer(layer)
from_schema(schema[, embedding_options, …])	Instantiates embedding features from the schema
get_config()
get_embedding_table(table_name[, …])
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_weights()	Returns the current weights of the layer, as NumPy arrays.
lookup_feature(name, val[, output_sequence])
parse(*block)
parse_block(input)
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()
select_by_name(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()
table_config(feature_name)
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	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.
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, embedding_options: merlin.models.tf.inputs.embedding.EmbeddingOptions = EmbeddingOptions(embedding_dims=None, embedding_dim_default=64, infer_embedding_sizes=False, infer_embedding_sizes_multiplier=2.0, infer_embeddings_ensure_dim_multiple_of_8=False, embeddings_initializers=None, embeddings_l2_reg=0.0, combiner='mean'), tags: Optional[Union[merlin.schema.tags.TagSet, List[str], List[merlin.schema.tags.Tags], List[Union[str, merlin.schema.tags.Tags]]]] = None, max_sequence_length: Optional[int] = None, **kwargs) → Optional[merlin.models.tf.inputs.embedding.EmbeddingFeatures]

Instantiates embedding features from the schema

Parameters

• schema (Schema) – The features chema

• embedding_options (EmbeddingOptions, optional) – An EmbeddingOptions instance, which allows for a number of options for the embedding table, by default EmbeddingOptions()

• tags (Optional[TagsType], optional) – If provided, keeps only features from those tags, by default None

• max_sequence_length (Optional[int], optional) – Maximum sequence length of sparse features (if any), by default None

Returns

An instance of EmbeddingFeatures block, with the embedding layers created under-the-hood

Return type

EmbeddingFeatures

build(input_shapes)

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

compute_call_output_shape(input_shapes)

lookup_feature(name, val, output_sequence=False)

table_config(feature_name: str)

get_embedding_table(table_name: Union[str, merlin.schema.tags.Tags], l2_normalization: bool = False)

embedding_table_df(table_name: Union[str, merlin.schema.tags.Tags], l2_normalization: bool = False, gpu: bool = True)

Retrieves a dataframe with the embedding table

Parameters

• table_name (Union[str, Tags]) – Tag or name of the embedding table

• l2_normalization (bool, optional) – Whether the L2-normalization should be applied to embeddings (common approach for Matrix Factorization and Retrieval models in general), by default False

• gpu (bool, optional) – Whether or not should use GPU, by default True

Returns

Returns a dataframe (cudf or pandas), depending on the gpu

Return type

Union[pd.DataFrame, cudf.DataFrame]

embedding_table_dataset(table_name: Union[str, merlin.schema.tags.Tags], l2_normalization: bool = False, gpu=True) → merlin.io.dataset.Dataset

Creates a Dataset for the embedding table

Parameters

• table_name (Union[str, Tags]) – Tag or name of the embedding table

• l2_normalization (bool, optional) – Whether the L2-normalization should be applied to embeddings (common approach for Matrix Factorization and Retrieval models in general), by default False

• gpu (bool, optional) – Whether or not should use GPU, by default True

Returns

Returns a Dataset with the embeddings

Return type

merlin.io.Dataset

export_embedding_table(table_name: Union[str, merlin.schema.tags.Tags], export_path: str, l2_normalization: bool = False, gpu=True)

Exports the embedding table to parquet file

Parameters

• table_name (Union[str, Tags]) – Tag or name of the embedding table

• export_path (str) – Path for the generated parquet file

• l2_normalization (bool, optional) – Whether the L2-normalization should be applied to embeddings (common approach for Matrix Factorization and Retrieval models in general), by default False

• gpu (bool, optional) – Whether or not should use GPU, by default True

get_config()

classmethod from_config(config)