Koala comments

Repositories
Issues
Comments

Results 2 comments of


                                            Koala

Why the loss become NaN?

I have trained TNT on ImageNet. With the hyper-parameters in paper (https://arxiv.org/pdf/2103.00112.pdf) and DeiT training code (https://github.com/facebookresearch/deit), I reproduced the result: Top-1 acc=81.3 of TNT-S. Have you tried the default...

Apply FReLU to MobileNetV3

Thanks for your quick reply. I'll try your suggestions.