Question about the summation of all outputs from 1-D Conv Block.

[TuZehai]

Hi,

According to the network structure from the paper, all outputs from 1-D Conv Blocks are added together. However, I did not find this operation from the code. I am new to pytorch, so I may miss something. Could you help explain this a bit?

Thanks

[lihao0214]

Hi,

According to the network structure from the paper, all outputs from 1-D Conv Blocks are added together. However, I did not find this operation from the code. I am new to pytorch, so I may miss something. Could you help explain this a bit?

Thanks

I think you are right. I did not find the skip coneection layer too.

[YiyuLuo]

I'm so confused about that, too

[boriq]

Seems like the version of the paper at which the skip connection was added(v3 at least according to arxiv) was released months after the last commit to the model. May 19 vs Jan 19.