TransformerEncoderLayer

class torch.nn.TransformerEncoderLayer(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)

TransformerEncoderLayer is made up of self-attn and feedforward network. This standard encoder 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.

Parameters

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

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

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

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

Examples::

>>> encoder_layer = nn.TransformerEncoderLayer(d_model=512, nhead=8)
>>> src = torch.rand(10, 32, 512)
>>> out = encoder_layer(src)

Alternatively, when batch_first is True:

>>> encoder_layer = nn.TransformerEncoderLayer(d_model=512, nhead=8, batch_first=True)
>>> src = torch.rand(32, 10, 512)
>>> out = encoder_layer(src)

Fast path:

forward() will use a special optimized implementation if all of the following conditions are met:

• Either autograd is disabled (using torch.inference_mode or torch.no_grad) or no tensor argument requires_grad

• training is disabled (using .eval())

• batch_first is True and the input is batched (i.e., src.dim() == 3)

• norm_first is False (this restriction may be loosened in the future)

• activation is one of: "relu", "gelu", torch.functional.relu, or torch.functional.gelu

• at most one of src_mask and src_key_padding_mask is passed

• if src is a NestedTensor, neither src_mask nor src_key_padding_mask is passed

• the two LayerNorm instances have a consistent eps value (this will naturally be the case unless the caller has manually modified one without modifying the other)

If the optimized implementation is in use, a NestedTensor can be passed for src to represent padding more efficiently than using a padding mask. In this case, a NestedTensor will be returned, and an additional speedup proportional to the fraction of the input that is padding can be expected.

forward(src, src_mask=None, src_key_padding_mask=None)

Pass the input through the encoder layer.

Parameters

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

• src_mask – the mask for the src sequence (optional).

• src_key_padding_mask – the mask for the src keys per batch (optional).

Shape:

see the docs in Transformer class.