Z,J Hu's repositories
Re-IDdataset
there is a script use to convert the Darklabel data to the Martket1501 datasets
UsefulPaper
Maybe useful to my work and may has great choices for else project
ImageProcessExample
Use for a templet process
360-Surround-View-CUDA-Project
10000 fps 🚀 for 360 Surround-View CUDA Solution
arm-gcc-inline-assembler
ARM GCC 内联汇编参考手册 - 中文版
Arm-neon-intrinsics
arm neon 相关文档和指令意义
bench_test
About the cpu or gpu test in different framework
lift-splat-shoot
Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D (ECCV 2020)
build-your-own-x
Master programming by recreating your favorite technologies from scratch.
classification-pytorch
这是各个主干网络分类模型的源码,可以用于训练自己的分类模型。
F0xZz.github.io
This is my own website for show the day and night
fq
翻墙工具收集,翻墙免费软件、免费ss账号、vps便宜网站
giantpandacv.com
www.giantpandacv.com
Image-processing-algorithm
paper implement
maskrcnn-benchmark
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
openpose
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
PLabel
半自动标注系统是基于BS架构,由鹏城实验室叶齐翔教授团队自主研发,集成视频抽帧,目标检测、视频跟踪、ReID分类、人脸检测等算法,实现了对图像,视频的自动标注,并可以对自动算法的结果进行人工标注,最终得到标注结果,同时也可以对视频、图片、医疗(包括dicom文件及病理图像)相关的数据进行人工标注,标注结果支持COCO及VOC格式。支持多人协同标注。 半自动标注系统主要功能有:用户管理,数据集管理,自动标注,人工标注,ReID标注,车流统计,视频标注,医疗CT标注,超大图像标注,模型管理与重训,报表管理。数据标注过程一个非常重要的因素是数据安全,在标注使用中防止数据泄露,采用基于web标注工具是有效避免数据泄露的措施之一。 半自动标注系统以保证性能的情况下最小化人工标注代价为目标,不断提升自动标注效率,减少人工标注和人工参与过程。
pnnx
PyTorch Neural Network eXchange
ppl.nn
A primitive library for neural network
pytorchx
Implement popular deep learning networks in pytorch, used by tensorrtx.
tensorrtx
Implementation of popular deep learning networks with TensorRT network definition API
yolov5
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
yolov5-rt-stack
yolort is a runtime stack for yolov5 on specialized accelerators such as libtorch, onnxruntime, tvm, tensorrt and ncnn.
YOLOX
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported.