modelzoo.transformers.pytorch.layers_api_demo.cb_transformer.TransformerModel

class modelzoo.transformers.pytorch.layers_api_demo.cb_transformer.TransformerModel

Bases: torch.nn.Module

Methods

forward	param src Tensor, shape [seq_len, batch_size]
init_weights

__call__(*args: Any, **kwargs: Any) → Any

Call self as a function.

__init__(ntoken: int, d_model: int, nhead: int, d_hid: int, nlayers: int, dropout: float = 0.5, activation: str = 'gelu', max_len: int = 10)

static __new__(cls, *args: Any, **kwargs: Any) → Any

forward(src: torch.Tensor, src_mask: torch.Tensor) → torch.Tensor

Parameters

• src – Tensor, shape [seq_len, batch_size]

• src_mask – Tensor, shape [seq_len, seq_len]

Returns

output Tensor of shape [seq_len, batch_size, ntoken]

previous

modelzoo.transformers.pytorch.layers_api_demo.cb_transformer

next

modelzoo.transformers.pytorch.layers_api_demo.data