akaniklaus
akaniklaus
Thank you very much for sharing this impressive work. I am somehow receiving the following error: ``` for group, base_lr in zip(self.param_groups, self.base_lrs): AttributeError: 'AdaBound' object has no attribute 'base_lrs'...
First of all, thank you for such a great work. In the below repository, they used VAT for regression and also proposed another method called SSDKL, which they claim to...
Hello, I have tried your meProp implementation with the output of nn.Conv1d(s) in my existing network. simplified_topk hanged for some reason. topk worked but didn't make any speed improvement. I...
Thank you for the code. This seems to me nicer than author's original PyTorch implementation. Can you please extend it with the meSimp method which was also introduced by same...
Thanks a lot for sharing your work! I would very much appreciate if you can also include a 1d version.
Hello, can you please provide PyTorch implementation of the best performing block you have? (Just the code of the relevant block / module would be sufficient, rather than a whole...
Hello, Do you have any comparison with BAM / CBAM attention modules? They claim to perform better than SE: https://github.com/Jongchan/attention-module/
Hello, can you please let me know the advantages and disadvantages of this library over Hyperopt? Also, it would be great if you can add support for PyTorch. Thank you...
Thank you very much. I would welcome if you can share the 1d version of OctConv as well.
Thank you very much. I would welcome if you can share the 1d version of OctConv as well.