Closed NeroArcher closed 4 years ago
It's hard to say with this little information. Probably best to build your own Pytorch Dataset , then change places in the code where the data size is hardcoded. After that hopefully it works.
It's hard to say with this little information. Probably best to build your own Pytorch Dataset , then change places in the code where the data size is hardcoded. After that hopefully it works.
Thank you! I will learn from there!
Thank you for your advice last time, I can run the trainning process properly after that. My next goal is to train it with my own dataset(probably hundreds of images) instead of Mnist or Cifar. I have read something about the dataloader part but I am still a little confused about where and how I should do the adjusting in the code. May I get any more advice from you?