KellerJordan / REPAIR
Code release for REPAIR: REnormalizing Permuted Activations for Interpolation Repair
☆43Updated 7 months ago
Related projects: ⓘ
- Git Re-Basin: Merging Models modulo Permutation Symmetries in PyTorch☆69Updated last year
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆42Updated last year
- Training vision models with full-batch gradient descent and regularization☆37Updated last year
- Towards Understanding Sharpness-Aware Minimization [ICML 2022]☆34Updated 2 years ago
- Code for the ICLR 2022 paper. Salient Imagenet: How to discover spurious features in deep learning?☆35Updated 2 years ago
- ☆55Updated 4 years ago
- ☆57Updated last year
- ☆23Updated last year
- [NeurIPS 2021] A Geometric Analysis of Neural Collapse with Unconstrained Features☆50Updated 2 years ago
- Python library for argument and configuration management☆53Updated last year
- The official PyTorch implementation - Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from t…☆74Updated 2 years ago
- Sharpness-Aware Minimization Leads to Low-Rank Features [NeurIPS 2023]☆24Updated 11 months ago
- ☆102Updated 11 months ago
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆36Updated 2 years ago
- Model Zoos published at the NeurIPS 2022 Dataset & Benchmark track: "Model Zoos: A Dataset of Diverse Populations of Neural Network Model…☆51Updated last year
- Recycling diverse models☆42Updated last year
- Data for "Datamodels: Predicting Predictions with Training Data"☆87Updated last year
- Code for Active Learning at The ImageNet Scale. This repository implements many popular active learning algorithms and allows training wi…☆53Updated 2 years ago
- Gradient Starvation: A Learning Proclivity in Neural Networks☆59Updated 3 years ago
- ☆31Updated 7 months ago
- ☆40Updated last year
- Deep Learning & Information Bottleneck☆45Updated last year
- ImageNet Testbed, associated with the paper "Measuring Robustness to Natural Distribution Shifts in Image Classification."☆114Updated last year
- Source code of "What can linearized neural networks actually say about generalization?☆17Updated 2 years ago
- Official implementation for Equivariant Architectures for Learning in Deep Weight Spaces [ICML 2023]☆81Updated last year
- A centralized place for deep thinking code and experiments☆73Updated last year
- Distilling Model Failures as Directions in Latent Space☆45Updated last year
- Code for the paper "A Light Recipe to Train Robust Vision Transformers" [SaTML 2023]☆52Updated last year
- Pytorch code for "Improving Self-Supervised Learning by Characterizing Idealized Representations"☆40Updated last year
- Train ImageNet *fast* in 500 lines of code with FFCV☆135Updated 4 months ago