WANGXIXI

Apex doesn’t work

1

I still got banned after using this tools for apex, could u recheck if Apex got update on their anti-cheat? If so, could u update the spoofer? Thanks

In networks, WeightGenerator. Why *100000.0?

大数据集训练前疯狂使用内存

2

你好我在训练一个20倍imagenet大小数据集，我使用torch dist，4卡，在训练前执行`logger.info(f'Start training from epoch: {start_epoch}, iter: {current_iter}')` 这行之前，内存就疯狂使用（超过300G内存占用），按理来说不是应该只使用当前batch size部分的数据进入内存吗，为什么会使用如此多，求解答

无法定位程序输入点DAXPY手动连接库neural_color_transfer.exe上

2

I wonder the environmnet requirements for running the exe, I really love this amazing project, please tell me the potential issues, thanks!

Pretrained model have problems

4

def resume_eval(self, trained_generator): # 在test的时候都要用什么。。 state_dict = torch.load(trained_generator) self.model.load_state_dict(state_dict['a']) # error here self.decoder.load_state_dict(state_dict['b']) return 0 Exception has occurred: RuntimeError Error(s) in loading state_dict for DataParallel: size mismatch for module.coeffs.local_features.0.conv.weight: copying...