TransformerEncoderLayer

class paddle.nn. TransformerEncoderLayer ( d_model, nhead, dim_feedforward, dropout=0.1, activation='relu', attn_dropout=None, act_dropout=None, normalize_before=False, weight_attr=None, bias_attr=None, layer_norm_eps=1e-05 ) [source]

TransformerEncoderLayer is composed of two sub-layers which are self (multi-head) attention and feedforward network. Before and after each sub-layer, pre-process and post-precess would be applied on the input and output accordingly. If normalize_before is True, pre-process is layer normalization and post-precess includes dropout, residual connection. Otherwise, no pre-process and post-precess includes dropout, residual connection, layer normalization.

Parameters
  • d_model (int) – The expected feature size in the input and output.

  • nhead (int) – The number of heads in multi-head attention(MHA).

  • dim_feedforward (int) – The hidden layer size in the feedforward network(FFN).

  • dropout (float, optional) – The dropout probability used in pre-process and post-precess of MHA and FFN sub-layer. Default 0.1

  • activation (str, optional) – The activation function in the feedforward network. Default relu.

  • attn_dropout (float, optional) – The dropout probability used in MHA to drop some attention target. If None, use the value of dropout. Default None

  • act_dropout (float, optional) – The dropout probability used after FFN activation. If None, use the value of dropout. Default None

  • normalize_before (bool, optional) – Indicate whether to put layer normalization into preprocessing of MHA and FFN sub-layers. If True, pre-process is layer normalization and post-precess includes dropout, residual connection. Otherwise, no pre-process and post-precess includes dropout, residual connection, layer normalization. Default False

  • weight_attr (ParamAttr|list|tuple, optional) – To specify the weight parameter property. If it is a list/tuple, weight_attr[0] would be used as weight_attr for MHA, and weight_attr[1] would be used as weight_attr for linear in FFN. Otherwise, MHA and FFN both use it as weight_attr to create parameters. Default: None, which means the default weight parameter property is used. See usage for details in ParamAttr .

  • bias_attr (ParamAttr|list|tuple|bool, optional) – To specify the bias parameter property. If it is a list/tuple, bias_attr[0] would be used as bias_attr for MHA, and bias_attr[1] would be used as bias_attr for linear in FFN. Otherwise, MHA and FFN both use it as bias_attr to create parameters. The False value means the corresponding layer would not have trainable bias parameter. See usage for details in ParamAttr . Default: None, which means the default bias parameter property is used.

  • layer_norm_eps – the eps value in layer normalization components. Default=1e-5.

Examples

>>> import paddle
>>> from paddle.nn import TransformerEncoderLayer

>>> # encoder input: [batch_size, src_len, d_model]
>>> enc_input = paddle.rand((2, 4, 128))
>>> # self attention mask: [batch_size, n_head, src_len, src_len]
>>> attn_mask = paddle.rand((2, 2, 4, 4))
>>> encoder_layer = TransformerEncoderLayer(128, 2, 512)
>>> enc_output = encoder_layer(enc_input, attn_mask)
>>> print(enc_output.shape)
[2, 4, 128]
forward ( src, src_mask=None, cache=None )

forward

Applies a Transformer encoder layer on the input.

Parameters
  • src (Tensor) – The input of Transformer encoder layer. It is a tensor with shape [batch_size, sequence_length, d_model]. The data type should be float32 or float64.

  • src_mask (Tensor, optional) – A tensor used in multi-head attention to prevents attention to some unwanted positions, usually the paddings or the subsequent positions. It is a tensor with shape broadcasted to [batch_size, n_head, sequence_length, sequence_length]. When the data type is bool, the unwanted positions have False values and the others have True values. When the data type is int, the unwanted positions have 0 values and the others have 1 values. When the data type is float, the unwanted positions have -INF values and the others have 0 values. It can be None when nothing wanted or needed to be prevented attention to. Default None.

  • cache (Tensor, optional) – It is an instance of MultiHeadAttention.Cache. See TransformerEncoderLayer.gen_cache for more details. It is only used for inference and should be None for training. Default None.

Returns

It is a tensor that has the same shape and data type

as enc_input, representing the output of Transformer encoder layer. Or a tuple if cache is not None, except for encoder layer output, the tuple includes the new cache which is same as input cache argument but incremental_cache has an incremental length. See MultiHeadAttention.gen_cache and MultiHeadAttention.forward for more details.

Return type

Tensor|tuple

gen_cache ( src )

gen_cache

Generates cache for forward usage. The generated cache is an instance of MultiHeadAttention.Cache.

Parameters

src (Tensor) – The input of Transformer encoder. It is a tensor with shape [batch_size, source_length, d_model]. The data type should be float32 or float64.

Returns

It is an instance of MultiHeadAttention.Cache

produced by self_attn.gen_cache, it reserves two tensors shaped [batch_size, nhead, 0, d_model // nhead]. See MultiHeadAttention.gen_cache and MultiHeadAttention.forward for more details.

Return type

incremental_cache