Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]

Deep learning operations reinvented (for pytorch, tensorflow, jax and others)

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 300 universities from 55 countries including Stanford, MIT, Harvard, and Cambridge.

Ultra Fast Structure-aware Deep Lane Detection (ECCV 2020)

Pytorch implementation of "Spatial As Deep: Spatial CNN for Traffic Scene Understanding"

Learning Sparse Neural Networks through L0 regularization

code for "Residual Flows for Invertible Generative Modeling".

Concolic Testing for Deep Neural Networks

Implementation of the paper "Adversarial Attacks on Neural Networks for Graph Data".

Good Semi-Supervised Learning That Requires a Bad GAN

Real-time image saliency 🌠 (NIPS 2017)

Code for the ISIC2018 Lesion Diagnosis Challenge

Code for Neural Motifs: Scene Graph Parsing with Global Context (CVPR 2018)

A faster pytorch implementation of faster r-cnn

An open-source NLP research library, built on PyTorch.

An adversarial example library for constructing attacks, building defenses, and benchmarking both

Spatially Transformed Adversarial Examples with TensorFlow

Most popular metrics used to evaluate object detection algorithms

Pytorch implementation of Real Time Image Saliency for Black Box Classifiers https://arxiv.org/abs/1705.07857

"Scene Graph Generation by Iterative Message Passing" code repository

A library for performing coverage guided fuzzing of neural networks

Benchmarking and Visualization Tool for Adversarial Machine Learning

Stochastic algorithms for computing Regularized Optimal Transport

Pytorch implementation of FactorVAE proposed in Disentangling by Factorising(http://arxiv.org/abs/1802.05983)

PyTorch implementation of "Weight Uncertainty in Neural Networks"