res2net-plus

res2net-plus copied to clipboard

pretrained model

4

Hello,The url of the pretrained model can't find

ivylinden

关于代码问题

1

if self.scale > 1: if self.first_block: out = torch.cat((out, self.pool(xs[len(self.convs)])), 1)你好，请问这一步到底是什么意思，为什么要对最后一块做池化呢， nb_branches = max(scale, 2) - 1----还有文章不是说分成4块吗，为什么代码只有3块呢

swjtulinxi

I'm trying to implement the res2net in a different way, following how fastai wrote their xresnet. The res2block I have is ``` def no_op(x): return x # no operations done...

maxmatical

Thanks for your repo, I tried to use your implementation but I keep getting this error when trying to train the model using learn.fit_one_cycle(20, max_lr=1e-2, callbacks=stage1_callbacks). this is the trace...

armheb