kumar-shridhar/PyTorch-BayesianCNN
PyTorch library implementing Bayesian CNNs with variational inference (Bayes by Backprop) for estimating uncertainty in model weights.
Not currently ranked — collecting fresh signals.
star history
This repository provides a PyTorch implementation of Bayesian convolutional neural networks where intractable posterior probability distributions over weights are inferred using variational inference. The approach replaces point estimates with learned distributions, enabling uncertainty quantification in deep learning models. It demonstrates performance equivalent to frequentist inference on standard image classification benchmarks including MNIST, CIFAR-10, and CIFAR-100. The implementation includes both standard Bayes by Backprop and flipout variants for computational efficiency.
Frequently asked
- What is kumar-shridhar/PyTorch-BayesianCNN?
- PyTorch library implementing Bayesian CNNs with variational inference (Bayes by Backprop) for estimating uncertainty in model weights.
- Is PyTorch-BayesianCNN open source?
- Yes — kumar-shridhar/PyTorch-BayesianCNN is open source, released under the MIT license.
- What language is PyTorch-BayesianCNN written in?
- kumar-shridhar/PyTorch-BayesianCNN is primarily written in Python.
- How popular is PyTorch-BayesianCNN?
- kumar-shridhar/PyTorch-BayesianCNN has 1.6k stars on GitHub.
- Where can I find PyTorch-BayesianCNN?
- kumar-shridhar/PyTorch-BayesianCNN is on GitHub at https://github.com/kumar-shridhar/PyTorch-BayesianCNN.