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

Project Samples

Project Activity

See All Activity >

License

MIT License

Follow TransPose

TransPose Web Site

Other Useful Business Software
Run Any Workload on Compute Engine VMs Icon
Run Any Workload on Compute Engine VMs

From dev environments to AI training, choose preset or custom VMs with 1–96 vCPUs and industry-leading 99.95% uptime SLA.

Compute Engine delivers high-performance virtual machines for web apps, databases, containers, and AI workloads. Choose from general-purpose, compute-optimized, or GPU/TPU-accelerated machine types—or build custom VMs to match your exact specs. With live migration and automatic failover, your workloads stay online. New customers get $300 in free credits.
Try Compute Engine
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of TransPose!

Additional Project Details

Operating Systems

Linux, Mac, Windows

Programming Language

Python

Related Categories

Python Localization (L10N) Software, Python Data Visualization Software

Registered

2024-07-12