KellerJordan / REPAIRLinks
Code release for REPAIR: REnormalizing Permuted Activations for Interpolation Repair
☆52Updated 2 years ago
Alternatives and similar repositories for REPAIR
Users that are interested in REPAIR are comparing it to the libraries listed below
Sorting:
- Git Re-Basin: Merging Models modulo Permutation Symmetries in PyTorch☆78Updated 2 years ago
- ☆58Updated 2 years ago
- Towards Understanding Sharpness-Aware Minimization [ICML 2022]☆38Updated 3 years ago
- ☆23Updated 3 years ago
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Updated 2 years ago
- Model Fusion via Optimal Transport, NeurIPS 2020☆152Updated 3 years ago
- Data for "Datamodels: Predicting Predictions with Training Data"☆97Updated 2 years ago
- ModelDiff: A Framework for Comparing Learning Algorithms☆58Updated 2 years ago
- Model Zoos published at the NeurIPS 2022 Dataset & Benchmark track: "Model Zoos: A Dataset of Diverse Populations of Neural Network Model…☆57Updated 3 months ago
- Recycling diverse models☆46Updated 3 years ago
- Code for "Supermasks in Superposition"☆125Updated 2 years ago
- Train ImageNet *fast* in 500 lines of code with FFCV☆149Updated last year
- Python library for argument and configuration management☆56Updated 2 years ago
- Code for Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot☆42Updated 5 years ago
- ☆28Updated 2 years ago
- The official PyTorch implementation - Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from t…☆83Updated 3 years ago
- Deep Learning & Information Bottleneck☆63Updated 2 years ago
- ☆56Updated 5 years ago
- ☆47Updated 3 years ago
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆37Updated 3 years ago
- [NeurIPS 2021] A Geometric Analysis of Neural Collapse with Unconstrained Features☆60Updated 3 years ago
- Code for "Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?" [ICML 2023]☆38Updated last year
- Training vision models with full-batch gradient descent and regularization☆39Updated 2 years ago
- ☆18Updated 3 years ago
- Source code of "What can linearized neural networks actually say about generalization?☆20Updated 4 years ago
- ☆133Updated 4 years ago
- PyTorch repository for ICLR 2022 paper (GSAM) which improves generalization (e.g. +3.8% top-1 accuracy on ImageNet with ViT-B/32)☆145Updated 3 years ago
- Code for Active Learning at The ImageNet Scale. This repository implements many popular active learning algorithms and allows training wi…☆54Updated 4 years ago
- Code to reproduce experiments from 'Does Knowledge Distillation Really Work' a paper which appeared in the 2021 NeurIPS proceedings.☆33Updated 2 years ago
- PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures (CVPR 2022)☆110Updated 3 years ago