F0xZz

CUDA_Freshman

rust-raspberrypi-OS-tutorials

:books: Learn to write an embedded OS in Rust :crab:

libsvm

LIBSVM -- A Library for Support Vector Machines

PLCT-Open-Reports

PLCT实验室的公开演讲，或者决定公开的组内报告

data-competition-calendar

国内外数据竞赛资讯整理

ncnn_Android_MoveNet

Android MoveNet pose estimation by ncnn

DS

cpp deep_sort: C++ implementation of Simple Online Realtime Tracking with a Deep Association Metric

yolov3-point

Learning YOLOv3 from scratch 从零开始学习YOLOv3代码

MegFlow

Efficient ML solution for long-tailed demands.

yolov4-pytorch

这是一个YoloV4-pytorch的源码，可以用于训练自己的模型。

yolov5_annotations

annotations of yolov5-5.0

fe-necessary-book

:bowtie: A book and software collection about frontend

RepVGG

RepVGG: Making VGG-style ConvNets Great Again

threadpool

based on C++11 , a mini threadpool , accept variable number of parameters 基于C++11的线程池,简洁且可以带任意多的参数

yolox-opencv-dnn

使用OpenCV部署YOLOX，支持YOLOX-S、YOLOX-M、YOLOX-L、YOLOX-X、YOLOX-Darknet53五种结构，包含C++和Python两种版本的程序

ncnn_Android_RobustVideoMatting

Android human segmentation by ncnn

pynif3d

yolor

implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)

TensorRT

PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

awesome-productivity-cn

绝妙的个人生产力（Awesome Productivity - Chinese version）

YOLOP

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

PanopticFCN

Fully Convolutional Networks for Panoptic Segmentation (CVPR2021 Oral)

build-your-own-x

Master programming by recreating your favorite technologies from scratch.

Ultra-Fast-Lane-Detection

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

pnnx

PyTorch Neural Network eXchange

APN

Normal Learning in Videos with Attention Prototype Network

image-processing

zero-shot-object-tracking

Object tracking implemented with the Roboflow Inference API, DeepSort, and OpenAI CLIP.

fucking-algorithm

刷算法全靠套路，认准 labuladong 就够了！English version supported! Crack LeetCode, not only how, but also why.

d2l-zh

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。