Welcome to TorchCP!¶

TorchCP is a Python toolbox for conformal prediction research on deep learning models, using PyTorch with strong GPU acceleration. Comments, issues, contributions, and collaborations are all welcomed!

User Guide

  • Installation
    • Latest version (1.2.1)

API Reference

  • torchcp.classification
    • score function
    • predictor
    • loss function
    • trainer
    • metrics
    • utils
  • torchcp.regression
    • score function
    • predictor
    • loss
    • metrics
    • utils
  • torchcp.graph
    • score function
    • predictor
    • trainer
  • torchcp.llm
    • predictor
    • scoring
    • scaling
    • metrics
  • torchcp.utils
    • Tools
  • Changelog
    • 1.2.1 (2025-10-13)
    • 1.2.0 (2025-08-26)
    • 1.1.0 (2025-07-15)
    • 1.0.2 (2025-02-17)
    • 1.0.1 (2024-12-16)
    • 1.0.0 (2024-12-06)
    • 0.1.3 (2024-02-22)
    • 0.1.2 (2023-12-24)
    • 0.1.1 (2023-12-24)
    • 0.1.0 (2023-12-23)

Indices and tables¶

  • Index

  • Module Index

  • Search Page

Logo

TorchCP

Navigation

User Guide

  • Installation

API Reference

  • torchcp.classification
  • torchcp.regression
  • torchcp.graph
  • torchcp.llm
  • torchcp.utils
  • Changelog

Related Topics

  • Documentation overview
    • Next: Installation

Quick search

©2025, ml-stat-Sustech. | Powered by Sphinx 7.2.6 & Alabaster 0.7.16 | Page source