ViTPose (simple version w/o mmcv) An unofficial implementation of ViTPose [Y. Xu et al., 2022] Usage | Inference python inference.py --image-path './examples/img1.jpg' | Training python train.py --config-path config.yaml --model-name 'b' model_name must be in ( b , l , h ) Note Download the trained model (.pth) ViTPose-B-Multi-COCO.pth ViTPose-L-Multi-COCO.pth ViTPose-H-Multi-COCO.pth Set the config. according to the trained model ViTPose-B-COCO-256x192 ViTPose-L-COCO-256x192 ViTPose-H-COCO-256x192 Reference All codes were written with reference to the official ViTPose repo.