An extension of the PyTorch library containing various tools for performing deep learning in hyperbolic space.

Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV 2023)

Code for the paper "ViperGPT: Visual Inference via Python Execution for Reasoning"

Code for the paper Real-Time Neural Voice Camouflage

Code for the paper Learning the Predictability of the Future (CVPR 2021)

Shapley values for assessing the importance of each frame in a video

Code for the Globetrotter project

When can you tell whether an image has been cropped or not?

Code for Learning to Learn Language from Narrated Video

Code for Oops! Predicting Unintentional Action in Video

Pytorch implementation of convolutional neural network visualization techniques

Self-supervised Learning for Video Correspondence Flow (BMVC 2019)

Codebase for ECCV18 "The Sound of Pixels"

Architected for speed. Automated for easy. Monitoring and troubleshooting, transformed!

StyleGAN - Official TensorFlow Implementation

PyTorch implementation of PNASNet-5 on ImageNet

Fast sparse video decode

Code for the paper: Fighting Fake News: Image Splice Detection via Learned Self-Consistency

The implementation of an algorithm presented in the CVPR18 paper: "Detect-and-Track: Efficient Pose Estimation in Videos"

A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.

Code for the paper: Audio-Visual Scene Analysis with Self-Supervised Multisensory Features

Deep Reinforcement Learning for Keras.

Open-source simulator for autonomous driving research.

A library that uses hardware acceleration to load sequences of video frames to facilitate machine learning training

The AVA dataset densely annotates 80 atomic visual actions in 351k movie clips with actions localized in space and time, resulting in 1.65M action labels with multiple labels per human occurring fr…

The pretrained models trained on Moments in Time Dataset

A simplified implemention of Faster R-CNN that replicate performance from origin paper

Various tutorials given for welcoming new students at MILA.