brade31919

system-design-primer

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

reverse-interview-zh

技术面试最后反问面试官的话

triton

Development repository for the Triton language and compiler

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

awesome-NeRF

A curated list of awesome neural radiance fields papers

slambook2

edition 2 of the slambook

Machine-Learning-Interviews

This repo is meant to serve as a guide for Machine Learning/AI technical interviews.

vissl

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

deepmask

Torch implementation of DeepMask and SharpMask

torchgeo

TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data

Tela-icon-theme

A flat colorful Design icon theme

slambook-en

The English version of 14 lectures on visual SLAM.

rpg_svo_pro_open

pixel-perfect-sfm

Pixel-Perfect Structure-from-Motion with Featuremetric Refinement (ICCV 2021, Best Student Paper Award)

convmixer

Implementation of ConvMixer for "Patches Are All You Need? 🤷"

google-landmark

Dataset with 5 million images depicting human-made and natural landmarks spanning 200 thousand classes.

pixloc

Back to the Feature: Learning Robust Camera Localization from Pixels to Pose (CVPR 2021)

bitsandbytes

Library for 8-bit optimizers and quantization routines.

Tela-circle-icon-theme

Tela-circle-icon-theme

bts

From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation

local-feature-refinement

Multi-View Optimization of Local Feature Geometry

visloc-iccv2021

ETH-Microsoft dataset for the ICCV 2021 visual localization challenge

editable-humans

[CVPR 2023] Learning Locally Editable Virtual Humans

VulkanSift

SIFT detection and matching on (almost) any GPU with Vulkan

kV-Margin

NeurIPS 2021, Code for Measuring Generalization with Optimal Transport

Render-In-Between

Official implementation for BMVC 2021 paper Render In-between: Motion Guided Video Synthesis for Action Interpolation

DanceReID

Official dataset for the paper "Learning from Dances: Pose-Invariant Re-Identification for Multi-Person Tracking" (ICASSP '20)

SMnet

Spatiotemporal Multimodal Network for Dynamic Gesture Recognition

basic-react-web

React & Redux