Add additional dataloaders

[mach-12]

There are multiple baselines used in the paper.

1. ImageNet
2. CIFAR-100
3. Oxford-IIIT
4. Pets-Oxford
5. Flowers-102
6. VTAB

• Create a dataset loaders similar to load_cifar10
• Make the traning script dynamic such that the argparse takes <model_name> as an additional argument
• Note that the img_size in ViT model initialization at train.py is statically set as 32. You need to infer the dimensions at the data loader init. time.