modelzoo.transformers.pytorch.layers_api_demo.pytorch_transformer.PositionalEncoding#

class modelzoo.transformers.pytorch.layers_api_demo.pytorch_transformer.PositionalEncoding[source]#

Bases: torch.nn.Module

Methods

forward

param x

Tensor, shape [seq_len, batch_size, embedding_dim]
__call__(*args: Any, **kwargs: Any) → Any#

Call self as a function.

__init__(d_model: int, dropout: float = 0.1, max_len: int = 5000)[source]#
static __new__(cls, *args: Any, **kwargs: Any) → Any#
forward(x: torch.Tensor) → torch.Tensor[source]#
Parameters

x – Tensor, shape [seq_len, batch_size, embedding_dim]

previous

modelzoo.transformers.pytorch.layers_api_demo.pytorch_transformer.generate_square_subsequent_mask

next

modelzoo.transformers.pytorch.layers_api_demo.pytorch_transformer.TransformerModel