TransPose is a human pose estimation model based on a CNN feature extractor, a Transformer Encoder, and a prediction head. Given an image, the attention layers built in Transformer can efficiently capture long-range spatial relationships between keypoints and explain what dependencies the predicted keypoints locations highly rely on.
Features
- Try out the Web Demo
- Documentation available
- Load TransPose-R-A4 or TransPose-H-A4 models with pretrained weights
- Traing & Testing available
- Examples available
License
MIT LicenseFollow TransPose
You Might Also Like
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of TransPose!