memoiry

DINO

[ICLR 2023] Official implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection"

openmlsys-zh

《Machine Learning Systems: Design and Implementation》- Chinese Version

DenseCL

Dense Contrastive Learning (DenseCL) for self-supervised representation learning, CVPR 2021 Oral.

jit-tutorial

How to write a very simple JIT compiler

amh-code

Complete implementations from "Algorithms for Modern Hardware"

Knowledge-Distillation-Zoo

Pytorch implementation of various Knowledge Distillation (KD) methods.

head2head

PyTorch implementation for Head2Head and Head2Head++. It can be used to fully transfer the head pose, facial expression and eye movements from a source video to a target identity.

VRT

VRT: A Video Restoration Transformer (official repository)

K-Net

[NeurIPS2021] Code Release of K-Net: Towards Unified Image Segmentation

instant-ngp

Instant neural graphics primitives: lightning fast NeRF and more

SimpleTrack

T3DP

Code repository for the paper "Tracking People with 3D Representations". NeurIPS 2021

hack-SysML

The road to hack SysML and become an system expert

hacker-laws-zh

💻📖对开发人员有用的定律、理论、原则和模式。(Laws, Theories, Principles and Patterns that developers will find useful.)

BlenderProc

A procedural Blender pipeline for photorealistic training image generation

koila

Prevent PyTorch's `CUDA error: out of memory` in just 1 line of code.

CUDA-PointPillars

A project demonstrating how to use CUDA-PointPillars to deal with cloud points data from lidar.

Advances-in-Label-Noise-Learning

A curated (most recent) list of resources for Learning with Noisy Labels

MaskTheFace

Convert face dataset to masked dataset

bitsandbytes

Library for 8-bit optimizers and quantization routines.

Lichee

一个多模态内容理解算法框架，其中包含数据处理、预训练模型、常见模型以及模型加速等模块。

Beijing-House

面向北京码农同胞的从0开始的买房踩盘实录，目标只有一个: 每一分钱都花的明白(持续补充和完善ing…)

SRDet

A simple, fast, efficient and end-to-end 3D object detector without NMS.

flow1d

[ICCV'21 Oral] High-Resolution Optical Flow from 1D Attention and Correlation

YOLOP

You Only Look Once for Panopitic Driving Perception.（MIR2022）

TOOD

TOOD: Task-aligned One-stage Object Detection, ICCV2021 Oral

OBBDetection

OBBDetection is an oriented object detection library, which is based on MMdetection.

res-loglikelihood-regression

Code for "Human Pose Regression with Residual Log-likelihood Estimation", ICCV 2021 Oral

YOLOX

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

HTML4Vision

A simple HTML visualization tool for computer vision research :hammer_and_wrench: