wangxun

@Zhongdao I have some question about the detail of your softmax training process，Can I have your telephone Number or we-chat?

yes, please give me your wechat account.

Please send your wechat account to me, I will add you.

No such assumption is needed. Weight loss is based on th idea of hard mining : to focus on harder samples, no matter positive or negative pairs.

I have not repreduced the result of proxy-nca and n-pairs

Good result. When I write the paper, the code is not with all tricks and the optimal optimizer. So the result is a bit worse than the code. If you...

> This should fix it: > > ```python > for _, module in self.fc.named_modules(): > if isinstance(module, nn.Linear): > module.weight.data = F.normalize(module.weight, p=2, dim=1) > ``` thanks

Thanks very much for your great work. I have successfully used the pretrained model in my research. But I have found a problem, though this model can be successfully loaded...

@yjxiong So, I want to ask you the version of python, torchvision and pytorch you used in tranferring the model from caffe.

PS: Both version of pytorch can successfully load your model, I have see into the value fo the weight. Both are same, and the forward output is the same.