hollance / reliability-diagrams
Reliability diagrams visualize whether a classifier model needs calibration
☆150Updated 3 years ago
Alternatives and similar repositories for reliability-diagrams:
Users that are interested in reliability-diagrams are comparing it to the libraries listed below
- NumPy library for calibration metrics☆72Updated 2 months ago
- Calibration library and code for the paper: Verified Uncertainty Calibration. Ananya Kumar, Percy Liang, Tengyu Ma. NeurIPS 2019 (Spotlig…☆149Updated 2 years ago
- Code for the paper "Calibrating Deep Neural Networks using Focal Loss"☆161Updated last year
- Code for Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty☆139Updated last year
- Wrapper for a PyTorch classifier which allows it to output prediction sets. The sets are theoretically guaranteed to contain the true cla…☆239Updated 2 years ago
- Code for "Uncertainty Estimation Using a Single Deep Deterministic Neural Network"☆272Updated 3 years ago
- Calibration of Convolutional Neural Networks☆162Updated 2 years ago
- Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning, ICLR 2020☆235Updated 2 years ago
- Code for "On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertainty".☆112Updated 2 years ago
- Wasserstein Adversarial Active Learning☆29Updated 4 years ago
- ☆66Updated 5 years ago
- Code to accompany the paper 'Improving model calibration with accuracy versus uncertainty optimization'.☆55Updated 2 years ago
- Last-layer Laplace approximation code examples☆83Updated 3 years ago
- Reusable BatchBALD implementation☆79Updated last year
- The net:cal calibration framework is a Python 3 library for measuring and mitigating miscalibration of uncertainty estimates, e.g., by a …☆360Updated 8 months ago
- Model-agnostic posthoc calibration without distributional assumptions☆42Updated last year
- Bayesianize: A Bayesian neural network wrapper in pytorch☆88Updated 11 months ago
- ☆106Updated 3 years ago
- [ICML 2023] Change is Hard: A Closer Look at Subpopulation Shift☆108Updated last year
- DISTIL: Deep dIverSified inTeractIve Learning. An active/inter-active learning library built on py-torch for reducing labeling costs.☆149Updated 2 years ago
- ☆40Updated 5 years ago
- A machine learning benchmark of in-the-wild distribution shifts, with data loaders, evaluators, and default models.☆564Updated last year
- An implementation of the BADGE batch active learning algorithm.☆206Updated 11 months ago
- ☆109Updated 2 years ago
- ☆236Updated 4 years ago
- ☆120Updated 3 years ago
- ☆35Updated 4 years ago
- An implementation of the state-of-the-art Deep Active Learning algorithms☆103Updated last year
- 👽 Out-of-Distribution Detection with PyTorch☆289Updated this week
- Addressing Failure Prediction by Learning Model Confidence☆171Updated 2 years ago