biggzlar/plausible-uncertainties
Methods used in the paper "Plausible Uncertainties for Human Pose Regression".
This project helps researchers and engineers working on computer vision tasks, specifically human pose estimation. It provides tools to assess the confidence in predictions when estimating 3D human body positions from images or video, giving you not just a pose, but also how 'certain' the system is about each joint's location. This is useful for anyone developing or evaluating AI models that need to understand human movement accurately and reliably.
No commits in the last 6 months.
Use this if you are developing or evaluating computer vision models for human pose estimation and need to quantify the uncertainty of your predictions.
Not ideal if you are looking for a pre-trained, ready-to-use human pose estimation model without needing to analyze or improve its uncertainty quantification.
Stars
14
Forks
—
Language
Python
License
MIT
Last pushed
Aug 13, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/biggzlar/plausible-uncertainties"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
EmuKit/emukit
A Python-based toolbox of various methods in decision making, uncertainty quantification and...
google/uncertainty-baselines
High-quality implementations of standard and SOTA methods on a variety of tasks.
nielstron/quantulum3
Library for unit extraction - fork of quantulum for python3
IBM/UQ360
Uncertainty Quantification 360 (UQ360) is an extensible open-source toolkit that can help you...
aamini/evidential-deep-learning
Learn fast, scalable, and calibrated measures of uncertainty using neural networks!