Top AI Repos — open-source AI, indexed and scored

Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.

Star history, last 90 days
Date	Stars
2026-07-24	1584
2026-07-25	1584
2026-07-28	1584
2026-07-30	1584
2026-08-06	1584

Star history, last 90 days

Date

Stars

2026-07-24

1584

2026-07-25

1584

2026-07-28

1584

2026-07-30

1584

2026-08-06

1584

# Uncertainty Baselines [![Tests](https://github.com/google/uncertainty-baselines/actions/workflows/ci.yml/badge.svg)](https://github.com/google/uncertainty-baselines/actions/workflows/ci.yml) The goal of Uncertainty Baselines is to provide a template for researchers to build on. The baselines can be a starting point for any new ideas, applications, and/or for communicating with other uncertainty and robustness researchers. This is done in three ways: 1. Provide high-quality implementations of standard and state-of-the-art methods on standard tasks. 2. Have minimal dependencies on other files in the codebase. Baselines should be easily forkable without relying on other baselines and generic modules. 3. Prescribe best practices for uncertainty and robustness benchmarking. __Motivation.__ There are many uncertainty and robustness implementations across GitHub. However, they are typically one-off experiments for a specific paper (many papers don't even have code). There are no clear examples that uncertainty researchers can build on to quickly prototype their work. Everyone must implement their own baseline. In fact, even on standard tasks, every project differs slightly in their experiment setup, whether it be architectures, hyperparameters, or data preprocessing. This makes it difficult to compare properly against baselines. ## Installation To install the latest development version, run ```sh pip install "git+https://github.com/google/uncertainty-baselines.git#egg=uncertainty_baselines" ``` There is not yet a stable version (nor an official release of this library). All APIs are subject to change. Installing `uncertainty_baselines` does not automatically install any backend. For TensorFlow, you will need to install TensorFlow ( `tensorflow` or `tf-nightly`), TensorFlow Addons (`tensorflow- addons` or `tfa-nightly`), and TensorBoard (`tensorboard` or `tb-nightly`). See the extra dependencies one can install in `setup.py`. ## Usage ### Baselines The [`baselines/`](https://github.com/google/uncertainty-baselines/tree/main/baselines) directory includes all the baselines, organized by their training dataset. For example, [`baselines/cifar/determinstic.py`](https://github.com/google/uncertainty-baselines/tree/main/baselines/cifar/deterministic.py) is a Wide ResNet 28-10 obtaining 96.0% test accuracy on CIFAR-10. __Launching with TPUs.__ You often need TPUs to reproduce baselines. There are three options: 1. __Colab.__ [Colab offers free TPUs](https://colab.research.google.com/notebooks/tpu.ipynb). This is the most convenient and budget-friendly option. You can experiment with a baseline by copying its script and running it from scratch. This works well for simple experimentation. However, be careful relying on Colab long-term: TPU access isn't guaranteed, and Colab can only go so far for managing multiple long experiments. 2. __Google Cloud.__ This is the most flexible option. First, you'll need to create a virtual machine instance (details [here](https://cloud.google.com/compute/docs/instances/create-start-instance)). Here's an example to launch the BatchEnsemble baseline on CIFAR-10. We assume a few environment variables which are set up with the cloud TPU (details [here](https://cloud.google.com/tpu/docs/quickstart)). ```sh export BUCKET=gs://bucket-name export TPU_NAME=ub-cifar-batchensemble export DATA_DIR=$BUCKET/tensorflow_datasets export OUTPUT_DIR=$BUCKET/model python baselines/cifar/batchensemble.py \ --tpu=$TPU_NAME \ --data_dir=$DATA_DIR \ --output_dir=$OUTPUT_DIR ``` Note the TPU's accelerator type must align with the number of cores for the baseline (`num_cores` flag). In this example, BatchEnsemble uses a default of `num_cores=8`. So the TPU must be set up with `accelerator_type=v3-8`. 3. __Change the flags.__ For example, go from 8 TPU cores to 8 GPUs, or reduce the number of cores to train the baseline. ```sh