martinengelcke

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

apex

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

dino

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

dm-haiku

JAX-based neural network library

releasing-research-code

Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)

py-motmetrics

:bar_chart: Benchmark multiple object trackers (MOT) in Python

robosuite

robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

torchsparse

[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

NVAE

The Official PyTorch Implementation of "NVAE: A Deep Hierarchical Variational Autoencoder" (NeurIPS 2020 spotlight paper)

awesome-equivariant-network

Paper list for equivariant neural network

pytorch-normalizing-flows

Normalizing flows in PyTorch. Current intended use is education not production.

nflows

Normalizing flows in PyTorch

what-is

Important concepts in numerical linear algebra and related areas

octnet

OctNet: Learning Deep 3D Representations at High Resolutions

vdvae

Repository for the paper "Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images"

apc-vision-toolbox

MIT-Princeton Vision Toolbox for the Amazon Picking Challenge 2016 - RGB-D ConvNet-based object segmentation and 6D object pose estimation.

survae_flows

Code for paper "SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows"

machine-learning-flashcards

Machine learning flashcards

visual_foresight

Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control

PSGNets

Neural Networks that convert input movies into Physical Scene Graphs (PSGs)

BlockGAN

fspool

[ICLR 2020] FSPool: Learning Set Representations with Featurewise Sort Pooling

object-centric-representation-benchmark

Code, data and benchmark from the paper "Unmasking the Inductive Biases of Unsupervised Object Representations for Video Sequences".

GNM

Official Release of NeurIPS 2020 Spotlight paper "Generative Neurosymbolic Machines"

G-SWM

Official PyTorch implementation of "Improving Generative Imagination in Object-Centric World Models"

relate

Official PyTorch implementation of 'RELATE: Physically Plausible Multi-Object SceneSynthesis Using Structured Latent Spaces'.

EfficientMORL

EfficientMORL (ICML'21)

SMORL

Learning-to-manipulate-individual-objects-in-an-image-Implementation

xmen