Skip to content

Latest commit

 

History

History
22 lines (16 loc) · 824 Bytes

File metadata and controls

22 lines (16 loc) · 824 Bytes

Uncertainty Estimation with Infinitesimal Jackknife, Its Distribution and Mean-Field Approximation

This repository contains a PyTorch implementation of paper "Uncertainty Estimation with Infinitesimal Jackknife, Its Distribution and Mean-Field Approximation".

Code Structure

  • Utils/ common util functions for hessian computation, uncertainty metrics evaluation, and etc.
  • MNIST/ experiments on MNIST dataset.
  • ImageNet/ experiments on ImageNet dataset.

Prerequisites

The following packages are required to run the scripts: