CLASS torch.nn.TransformerEncoder(encoder_layer, num_layers, norm=None)
TransformerEncoder is a stack of N encoder layers
参数 | 描述 |
---|---|
encoder_layer | an instance of the TransformerEncoderLayer() class (required). |
num_layers | the number of sub-encoder-layers in the encoder (required). |
norm | the layer normalization component (optional). |
encoder_layer = nn.TransformerEncoderLayer(d_model=512, nhead=8)
transformer_encoder = nn.TransformerEncoder(encoder_layer, num_layers=6)
src = torch.rand(10, 32, 512)
out = transformer_encoder(src)
参考:
https://pytorch.org/docs/master/generated/torch.nn.TransformerEncoder.html#torch.nn.TransformerEncoder