Transformer_Time_Series

Transformer_Time_Series copied to clipboard

Convolutional self-attention

3

Dear mlpotter, your code is perfect！ I found you just deal with the initial input by causal convolutions, however, the K and Q were still calculated by 'torch.nn.TransformerEncoderLayer'. Thus, this...

Yanruoqin

wrong conv, no spare, no likehood train

2

Thanks for your code. But I think your code is very different from the method which the paper mentioned.

ddz16

Thank you for your code, it's very useful. I found that the current version of the code only has one-dimensional time characteristics, ``in_ Channels`` is 1. If my data has...

GISWLH