Open d12306 opened 3 years ago
We just copy-paste from our previous codebase. I have not tried the torchvision dataset of SVHN, it should make no difference from my point. Please let me know if you find any significantly different results using torchvision.
Hi, @gmh14 , thanks for our implementation, I notice that you re-implement the SVHN dataset in the dataset.py, kindly want to know what is the point of rewriting the dataset rather than using the torchvision datasets?
Thanks,