class torch.nn.TransformerDecoderLayer(d_model, nhead, dim_feedforward=2048, dropout=0.1, activation='relu')[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 – the number of expected features in the input (required).

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

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

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

  • activation – the activation function of intermediate layer, relu or gelu (default=relu).

>>> 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)
forward(tgt, memory, tgt_mask=None, memory_mask=None, tgt_key_padding_mask=None, memory_key_padding_mask=None)[source]

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

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

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

  • tgt_mask – the mask for the tgt sequence (optional).

  • memory_mask – the mask for the memory sequence (optional).

  • tgt_key_padding_mask – the mask for the tgt keys per batch (optional).

  • memory_key_padding_mask – the mask for the memory keys per batch (optional).


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