Stars
FastAPI framework, high performance, easy to learn, fast to code, ready for production
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Super Resolution for images using deep learning.
A logical, reasonably standardized, but flexible project structure for doing and sharing data science work.
Bayesian Modeling and Probabilistic Programming in Python
Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.
Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.
Simple, elegant, Pythonic functional programming.
A highly efficient implementation of Gaussian Processes in PyTorch
📊 Save matplotlib figures as TikZ/PGFplots for smooth integration into LaTeX.
Speedy Wavenet generation using dynamic programming ⚡
Differentiable SDE solvers with GPU support and efficient sensitivity analysis.
Dream to Control: Learning Behaviors by Latent Imagination
Geometric loss functions between point clouds, images and volumes
High Fidelity Simulator for Reinforcement Learning and Robotics Research.
Training deep learning models on AWS and GCP instances
A probabilistic programming system for simulators and high-performance computing (HPC), based on PyTorch
The first public PyTorch implementation of Attentive Recurrent Comparators
A strongly-typed genetic programming framework for Python
PyTorch implementation of Variational Diffusion Models.
Deep Generative Models with Stick-Breaking Priors
Ladder Variational Autoencoders (LVAE) in PyTorch
Official PyTorch BIVA implementation (BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling)
Code for "Probabilistic Neural Programmed Networks for Scene Generation.", Deng et al, NIPS 2018
Simulation for the Real Robot Challenge (https://real-robot-challenge.com)
Code for NeurIPS 2019 paper: "Symmetry-Based Disentangled Representation Learning requires Interaction with Environments" by H. Caselles-Dupré, M. Garcia-Ortiz and D. Filliat.