transformers4rec.tf.block package

Submodules

transformers4rec.tf.block.base module

class transformers4rec.tf.block.base.Block(*args, **kwargs)

Bases: transformers4rec.config.schema.SchemaMixin, keras.engine.base_layer.Layer

to_model(prediction_task_or_head, inputs=None, **kwargs)

as_tabular(name=None)

class transformers4rec.tf.block.base.SequentialBlock(*args, **kwargs)

Bases: transformers4rec.tf.block.base.Block

The SequentialLayer represents a sequence of Keras layers. It is a Keras Layer that can be used instead of tf.keras.layers.Sequential, which is actually a Keras Model. In contrast to keras Sequential, this layer can be used as a pure Layer in tf.functions and when exporting SavedModels, without having to pre-declare input and output shapes. In turn, this layer is usable as a preprocessing layer for TF Agents Networks, and can be exported via PolicySaver. Usage:

c = SequentialLayer([layer1, layer2, layer3])
output = c(inputs)    # Equivalent to: output = layer3(layer2(layer1(inputs)))

compute_output_shape(input_shape)

compute_output_signature(input_signature)

build(input_shape=None)

set_schema(schema=None)

property inputs

property trainable_weights

property non_trainable_weights

property trainable

property losses

property regularizers

call(inputs, **kwargs)

get_config()

classmethod from_config(config, custom_objects=None)

transformers4rec.tf.block.base.right_shift_layer(self, other)

transformers4rec.tf.block.dlrm module

class transformers4rec.tf.block.dlrm.ExpandDimsAndToTabular(*args, **kwargs)

Bases: keras.layers.core.lambda_layer.Lambda

class transformers4rec.tf.block.dlrm.DLRMBlock(*args, **kwargs)

Bases: transformers4rec.tf.block.base.Block

classmethod from_schema(schema: merlin_standard_lib.schema.schema.Schema, bottom_mlp: Union[keras.engine.base_layer.Layer, transformers4rec.tf.block.base.Block], top_mlp: Optional[Union[keras.engine.base_layer.Layer, transformers4rec.tf.block.base.Block]] = None, **kwargs)

call(inputs, **kwargs)

transformers4rec.tf.block.mlp module

class transformers4rec.tf.block.mlp.MLPBlock(*args, **kwargs)

Bases: transformers4rec.tf.block.base.SequentialBlock

transformers4rec.tf.block.transformer module

class transformers4rec.tf.block.transformer.TransformerPrepare(*args, **kwargs)

Bases: keras.engine.base_layer.Layer

call(inputs_embeds, **kwargs) → Dict[str, Any]

class transformers4rec.tf.block.transformer.TransformerBlock(*args, **kwargs)

Bases: transformers4rec.tf.block.base.Block

Class to support HF Transformers for session-based and sequential-based recommendation models.

Parameters

• transformer (TransformerBody) – The T4RecConfig, The pre-trained HF model or the custom keras layer TF*MainLayer, related to specific transformer architecture.

• masking – Needed when masking is applied on the inputs.

TRANSFORMER_TO_PREPARE: Dict[Type[transformers.modeling_tf_utils.TFPreTrainedModel], Type[transformers4rec.tf.block.transformer.TransformerPrepare]] = {}

transformer: transformers.modeling_tf_utils.TFPreTrainedModel

prepare_module: Optional[transformers4rec.tf.block.transformer.TransformerPrepare]

get_config()

classmethod from_config(config)

classmethod from_registry(transformer: str, d_model: int, n_head: int, n_layer: int, total_seq_length: int, masking: Optional[transformers4rec.tf.masking.MaskSequence] = None)

Load the HF transformer architecture based on its name

Parameters

• transformer (str) – Name of the Transformer to use. Possible values are : [“reformer”, “gtp2”, “longformer”, “electra”, “albert”, “xlnet”]

• d_model (int) – size of hidden states for Transformers

• n_head – Number of attention heads for Transformers

• n_layer (int) – Number of layers for RNNs and Transformers”

• total_seq_length (int) – The maximum sequence length

call(inputs_embeds: tensorflow.python.framework.ops.Tensor, **kwargs)

Parameters

• tf.Tensor of shape ({0} (inputs_embeds) – An embedded representation of a sequence.

• hidden_size)` – An embedded representation of a sequence.

Returns

Return type

tf.Tensor

Module contents