Update results.csv files with cait, mlp-mixer, resnetrs, miil imagenet21k pretrained, and my latest efficientnet v2s/b4 weights.

Update results csv, includes latest transformer models, swin, pit, tnt... run on pytorch 1.8.1 cuda 10.2 (11.x rel crashes).

Update results csvs, run with PyTorch 1.7.1 cuda 10.2, some differences from prev run with older PT ver.

Update results csv files with latest models, incl 101D, 152D, 200D, SE152D ResNets and yet to be merged BiT and ViT-R50 models.

Add synset/label indices for results generation. Add 'valid labels' to validation script to support imagenet-a/r label subsets properly.

Update results README to include robustness and real labels tests. Include labels files used in results gen.

Fix relative paths (I think)

Add update results on ImageNet validation, ImageNetV2, ImageNet-A, and ImageNet-Sketch for all models

Finish with HRNet, weights and models updated. Improve consistency in model classifier/global pool treatment.