p-lambda / wilds
A machine learning benchmark of in-the-wild distribution shifts, with data loaders, evaluators, and default models.
☆558Updated 11 months ago
Alternatives and similar repositories for wilds:
Users that are interested in wilds are comparing it to the libraries listed below
- ☆468Updated 5 months ago
- Project site for "Your Classifier is Secretly an Energy-Based Model and You Should Treat it Like One"☆418Updated 2 years ago
- PyTorch code to run synthetic experiments.☆415Updated 3 years ago
- An implementation of the BADGE batch active learning algorithm.☆202Updated 7 months ago
- A simple way to calibrate your neural network.☆1,124Updated 3 years ago
- Implementation of Estimating Training Data Influence by Tracing Gradient Descent (NeurIPS 2020)☆224Updated 2 years ago
- The net:cal calibration framework is a Python 3 library for measuring and mitigating miscalibration of uncertainty estimates, e.g., by a …☆352Updated 5 months ago
- A clean and simple data loading library for Continual Learning☆423Updated last year
- Reduce end to end training time from days to hours (or hours to minutes), and energy requirements/costs by an order of magnitude using co…☆328Updated last year
- Optimal Transport Dataset Distance☆159Updated 2 years ago
- Distributionally robust neural networks for group shifts☆253Updated 2 years ago
- Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)☆339Updated 5 months ago
- Code for the paper "Calibrating Deep Neural Networks using Focal Loss"☆158Updated last year
- Domain adaptation made easy. Fully featured, modular, and customizable.☆361Updated last year
- Understanding Training Dynamics of Deep ReLU Networks☆284Updated 2 months ago
- Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning, ICLR 2020☆235Updated 2 years ago
- Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorch☆313Updated last year
- ☆314Updated 9 months ago
- Wrapper for a PyTorch classifier which allows it to output prediction sets. The sets are theoretically guaranteed to contain the true cla…☆235Updated last year
- Reliability diagrams visualize whether a classifier model needs calibration☆144Updated 2 years ago
- Concept Bottleneck Models, ICML 2020☆185Updated last year
- Self-labelling via simultaneous clustering and representation learning. (ICLR 2020)☆538Updated 5 months ago
- BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.☆568Updated 2 weeks ago
- Toolkit for building machine learning models that generalize to unseen domains and are robust to privacy and other attacks.☆175Updated last year
- Evaluate three types of task shifting with popular continual learning algorithms.☆517Updated 3 years ago
- Official repository for CMU Machine Learning Department's 10732: Robustness and Adaptivity in Shifting Environments☆73Updated 2 years ago
- This is a PyTorch reimplementation of Influence Functions from the ICML2017 best paper: Understanding Black-box Predictions via Influence…☆325Updated last year
- 👽 Out-of-Distribution Detection with PyTorch☆270Updated this week
- Original dataset release for CIFAR-10H☆82Updated 4 years ago
- Awesome coreset/core-set/subset/sample selection works.☆168Updated 6 months ago