/ViTPose_pytorch

An unofficial implementation of ViTPose [Y. Xu et al., 2022]

Primary LanguageJupyter NotebookApache License 2.0Apache-2.0

ViTPose (simple version w/o mmcv)

An unofficial implementation of ViTPose [Y. Xu et al., 2022]
result_image

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

  1. Download the trained model (.pth)
  2. Set the config. according to the trained model

Reference

All codes were written with reference to the official ViTPose repo.