Confused on tensor splitting

[koyakuwe]

In line here, you split the input tensor based on the number of width, but I am expecting it should be based on scale. Am I missing something? Also, you process 1st split/group with conv and bn while your paper said that "To reduce the number of parameters, we omit the convolution for the first split, which can also be regarded as a form of feature reuse.". Could you enlighten me?

EDIT: for first question, I get it now (I was confused about "the number" vs "the size" in torch.split)
EDIT2: got it, turns out conv is not applied in last input

Thanks!

[drcege]

For the first question, how do you get 26 as the baseWidth?