class torch.nn.Transformer(d_model=512, nhead=8, num_encoder_layers=6, num_decoder_layers=6, dim_feedforward=2048, dropout=0.1, activation=<function relu>, custom_encoder=None, custom_decoder=None, layer_norm_eps=1e-05, batch_first=False, norm_first=False, device=None, dtype=None)[source]

A transformer model. User is able to modify the attributes as needed. The architecture 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.

  • d_model (int) – the number of expected features in the encoder/decoder inputs (default=512).

  • nhead (int) – the number of heads in the multiheadattention models (default=8).

  • num_encoder_layers (int) – the number of sub-encoder-layers in the encoder (default=6).

  • num_decoder_layers (int) – the number of sub-decoder-layers in the decoder (default=6).

  • 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 encoder/decoder intermediate layer, can be a string (“relu” or “gelu”) or a unary callable. Default: relu

  • custom_encoder (Optional[Any]) – custom encoder (default=None).

  • custom_decoder (Optional[Any]) – custom decoder (default=None).

  • 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, encoder and decoder layers will perform LayerNorms before other attention and feedforward operations, otherwise after. Default: False (after).

>>> transformer_model = nn.Transformer(nhead=16, num_encoder_layers=12)
>>> src = torch.rand((10, 32, 512))
>>> tgt = torch.rand((20, 32, 512))
>>> out = transformer_model(src, tgt)

Note: A full example to apply nn.Transformer module for the word language model is available in

forward(src, tgt, src_mask=None, tgt_mask=None, memory_mask=None, src_key_padding_mask=None, tgt_key_padding_mask=None, memory_key_padding_mask=None)[source]

Take in and process masked source/target sequences.

  • src (Tensor) – the sequence to the encoder (required).

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

  • src_mask (Optional[Tensor]) – the additive mask for the src sequence (optional).

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

  • memory_mask (Optional[Tensor]) – the additive mask for the encoder output (optional).

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

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

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

Return type:


  • src: (S,E)(S, E) for unbatched input, (S,N,E)(S, N, E) if batch_first=False or (N, S, E) if batch_first=True.

  • tgt: (T,E)(T, E) for unbatched input, (T,N,E)(T, N, E) if batch_first=False or (N, T, E) if batch_first=True.

  • src_mask: (S,S)(S, S) or (Nnum_heads,S,S)(N\cdot\text{num\_heads}, S, S).

  • tgt_mask: (T,T)(T, T) or (Nnum_heads,T,T)(N\cdot\text{num\_heads}, T, T).

  • memory_mask: (T,S)(T, S).

  • src_key_padding_mask: (S)(S) for unbatched input otherwise (N,S)(N, S).

  • tgt_key_padding_mask: (T)(T) for unbatched input otherwise (N,T)(N, T).

  • memory_key_padding_mask: (S)(S) for unbatched input otherwise (N,S)(N, S).

Note: [src/tgt/memory]_mask ensures that position i is allowed to attend the unmasked positions. If a BoolTensor is provided, positions with True are not allowed to attend while False values will be unchanged. If a FloatTensor is provided, it will be added to the attention weight. [src/tgt/memory]_key_padding_mask provides specified elements in the key to be ignored by the attention. If a BoolTensor is provided, the positions with the value of True will be ignored while the position with the value of False will be unchanged.

  • output: (T,E)(T, E) for unbatched input, (T,N,E)(T, N, E) if batch_first=False or (N, T, E) if batch_first=True.

Note: Due to the multi-head attention architecture in the transformer model, the output sequence length of a transformer is same as the input sequence (i.e. target) length of the decoder.

where S is the source sequence length, T is the target sequence length, N is the batch size, E is the feature number


>>> output = transformer_model(src, tgt, src_mask=src_mask, tgt_mask=tgt_mask)
static generate_square_subsequent_mask(sz, device='cpu')[source]

Generate a square mask for the sequence. The masked positions are filled with float(‘-inf’). Unmasked positions are filled with float(0.0).

Return type:



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