class torch.nn.TransformerDecoderLayer(d_model, nhead, dim_feedforward=2048, dropout=0.1, activation=<function relu>, layer_norm_eps=1e-05, batch_first=False, norm_first=False, device=None, dtype=None)[source]

TransformerDecoderLayer is made up of self-attn, multi-head-attn and feedforward network. This standard decoder layer is based on the paper “Attention Is All You Need”. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems, pages 6000-6010. Users may modify or implement in a different way during application.

  • d_model (int) – the number of expected features in the input (required).

  • nhead (int) – the number of heads in the multiheadattention models (required).

  • dim_feedforward (int) – the dimension of the feedforward network model (default=2048).

  • dropout (float) – the dropout value (default=0.1).

  • activation (Union[str, Callable[[Tensor], Tensor]]) – the activation function of the intermediate layer, can be a string (“relu” or “gelu”) or a unary callable. Default: relu

  • layer_norm_eps (float) – the eps value in layer normalization components (default=1e-5).

  • batch_first (bool) – If True, then the input and output tensors are provided as (batch, seq, feature). Default: False (seq, batch, feature).

  • norm_first (bool) – if True, layer norm is done prior to self attention, multihead attention and feedforward operations, respectively. Otherwise it’s done after. Default: False (after).

>>> decoder_layer = nn.TransformerDecoderLayer(d_model=512, nhead=8)
>>> memory = torch.rand(10, 32, 512)
>>> tgt = torch.rand(20, 32, 512)
>>> out = decoder_layer(tgt, memory)
Alternatively, when batch_first is True:
>>> decoder_layer = nn.TransformerDecoderLayer(d_model=512, nhead=8, batch_first=True)
>>> memory = torch.rand(32, 10, 512)
>>> tgt = torch.rand(32, 20, 512)
>>> out = decoder_layer(tgt, memory)
forward(tgt, memory, tgt_mask=None, memory_mask=None, tgt_key_padding_mask=None, memory_key_padding_mask=None, tgt_is_causal=False, memory_is_causal=False)[source]

Pass the inputs (and mask) through the decoder layer.

  • tgt (Tensor) – the sequence to the decoder layer (required).

  • memory (Tensor) – the sequence from the last layer of the encoder (required).

  • tgt_mask (Optional[Tensor]) – the mask for the tgt sequence (optional).

  • memory_mask (Optional[Tensor]) – the mask for the memory sequence (optional).

  • tgt_key_padding_mask (Optional[Tensor]) – the mask for the tgt keys per batch (optional).

  • memory_key_padding_mask (Optional[Tensor]) – the mask for the memory keys per batch (optional).

  • tgt_is_causal (bool) – If specified, applies a causal mask as tgt mask. Mutually exclusive with providing tgt_mask. Default: False.

  • memory_is_causal (bool) – If specified, applies a causal mask as tgt mask. Mutually exclusive with providing memory_mask. Default: False.

Return type:



see the docs in Transformer class.


Access comprehensive developer documentation for PyTorch

View Docs


Get in-depth tutorials for beginners and advanced developers

View Tutorials


Find development resources and get your questions answered

View Resources