search

ViTAE-Transformer / ViTPose

The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [TPAMI'23] "ViTPose++: Vision Transformer for Generic Body Pose Estimation"
Apache License 2.0
1.27k stars 171 forks source link

Model in video demo #29

Open gsrujana opened 1 year ago

gsrujana commented 1 year ago

Hello, I was wondering, what is the model which is on Web Demo for video in HuggingFace? I would like to test that using scripts. Are weights provided for that particular model? Thanks

gsrujana commented 1 year ago

Also, is the model's accuracy on OCHuman coming from the VIT architecture or the fact that it has been trained on combination of MPII + Crowdpose +COCo datasets?