Flax is a neural network library for JAX that is designed for flexibility.

Google Brain AutoML

Probabilistic reasoning and statistical analysis in TensorFlow

[ICCV 2019] Monocular depth estimation from a single image

YoloV3 Implemented in Tensorflow 2.0

A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.

High Quality Monocular Depth Estimation via Transfer Learning

A smaller subset of 10 easily classified classes from Imagenet, and a little more French

Tooling for GANs in TensorFlow

Code for the TCAV ML interpretability project

CLU lets you write beautiful training loops in JAX.

Reduce end to end training time from days to hours (or hours to minutes), and energy requirements/costs by an order of magnitude using coresets and data selection.

Named tensors with first-class dimensions for PyTorch

🎄 Virtual DOM for Python

A 1D analogue of the MNIST dataset for measuring spatial biases and answering Science of Deep Learning questions.

A Collection of GitHub Actions That Facilitate MLOps

Source code for our open-source EDU website

This project contains additional material for the textbook Deep Learning for Physics Research by Martin Erdmann, Jonas Glombitza, Gregor Kasieczka, and Uwe Klemradt.

Cost function builder. For fitting distributions.

Jupyter libraries for Rust

Code for the paper "Training Binary Neural Networks with Bayesian Learning Rule

🍭 Dali in Python

A binary-weight-binary-input YOLOv2 implementation based on Larq's QuickNet as the backbone

Experimenting with jp-kernel

Small toy example: Air-shower Reconstruction using Deep Learning