CeiT-pytorch
CeiT-pytorch copied to clipboard
Training on new datasets.
Are there any instructions to help me train the model on other datasets mentioned in the paper, e.g., Oxford pets? As I understood, as of now, it is just possible to train on CIFAR10 or CIFAR100. I would appreciate any clues that point me in the right direction. Thanks a lot.
Hi , I am going throught the same question I was wondering if you figured it out ?
Hello, I have managed to train the model with a dataset from a folder I have. I did that by changing the code of the data_utils.py. Check It and use the torchvision.datasets to load the specific dataset. don't forget to change this in the config