Implementation of the Aurora model for Earth system forecasting

JS library for creating high-performance grid-based applications

An easy to customize, strong type library with built in support for unit-like behavior

Compiler for LightGBM gradient-boosted trees, based on LLVM. Speeds up prediction by ≥10x.

Label Studio is a multi-type data labeling and annotation tool with standardized output format

Power-Grid Frequency

Python library to easily setup basic logging functionality

Lagrangian VAE

Tensors and Dynamic neural networks in Python with strong GPU acceleration

categorical variational autoencoder using the Gumbel-Softmax estimator

Code for the paper "Improved Techniques for Training GANs"

A probabilistic programming language in TensorFlow. Deep generative models, variational inference.

Variational and semi-supervised neural network toppings for Lasagne

Code to train Importance Weighted Autoencoders on MNIST and OMNIGLOT

Computation Graph Toolkit

A flexible framework of neural networks for deep learning

Lightweight library to build and train neural networks in Theano