https://github.com/aangelopoulos/conformal_classification

Wrapper for a PyTorch classifier which allows it to output prediction sets. The sets are theoretically guaranteed to contain the true class with high probability (via conformal prediction).
https://github.com/aangelopoulos/conformal_classification

artificial-intelligence classification classifier computer-vision conformal conformal-prediction deep-neural-networks distribution-free imagenet machine-learning neural-networks nonparametric nonparametric-statistics prediction-sets pytorch statistics uncertainty uncertainty-quantification vision

Last synced: about 4 hours ago
JSON representation

Wrapper for a PyTorch classifier which allows it to output prediction sets. The sets are theoretically guaranteed to contain the true class with high probability (via conformal prediction).

• Host: GitHub
• URL: https://github.com/aangelopoulos/conformal_classification
• Owner: aangelopoulos
• License: mit
• Created: 2020-09-04T19:07:51.000Z (about 4 years ago)
• Default Branch: master
• Last Pushed: 2023-01-23T09:25:27.000Z (almost 2 years ago)
• Last Synced: 2024-08-02T15:18:45.809Z (3 months ago)
• Topics: artificial-intelligence, classification, classifier, computer-vision, conformal, conformal-prediction, deep-neural-networks, distribution-free, imagenet, machine-learning, neural-networks, nonparametric, nonparametric-statistics, prediction-sets, pytorch, statistics, uncertainty, uncertainty-quantification, vision
• Language: Jupyter Notebook
• Homepage:
• Size: 4.26 MB
• Stars: 218
• Watchers: 8
• Forks: 37
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project