Stars
Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
PyTorch code for FLD (Feature Likelihood Divergence), FID, KID, Precision, Recall, etc. using DINOv2, InceptionV3, CLIP, etc.
Codebase for evaluation of deep generative models as presented in Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
Pytorch implementation of convolutional neural network visualization techniques
VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.
Code for the paper "Generalizing to Unseen Domains via Adversarial Data Augmentation", NeurIPS 2018
A collection of AWESOME things about domian adaptation
Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.
Train Scene Graph Generation for Visual Genome and GQA in PyTorch >= 1.2 with improved zero and few-shot generalization.
Visual localization made easy with hloc
Back to the Feature: Learning Robust Camera Localization from Pixels to Pose (CVPR 2021)
This repository contains the code for our papers "Learning Condition Invariant Features for Retrieval-Based Localization from 1M Images" and "Geometrically Mappable Image Features".
minimal example with native build instructions
Unscented Kalman Filter library for state and parameter estimation
SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)
A simple Multi-Robot SLAM solution that communicates efficiently. The result of my M.Sc. work.
Karabiner (KeyRemap4MacBook) is a powerful utility for keyboard customization.
PyTorch deep learning projects made easy.