💻深度学习实战：手写数字识别、Discuz验证码识别、垃圾分类、语义分割

使用OpenCV部署Yolo-FastestV2，包含C++和Python两种版本的程序

The minimal opencv for Android, iOS, ARM Linux, Windows, Linux, MacOS, WebAssembly

Unofficial implementation of "TTNet: Real-time temporal and spatial video analysis of table tennis" (CVPR 2020)

开发者边车，github打不开，github加速，git clone加速，git release下载加速，stackoverflow加速

[NeurIPS 2021] You Only Look at One Sequence

[ICCV 2021] Instances as Queries

Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers [CVPR 2021]

Guided Mesh Normal Filtering

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

Boundary IoU API (Beta version)

rotated bbox detection. inspired by https://github.com/hukaixuan19970627/YOLOv5_DOTA_OBB, thanks hukaixuan19970627.

rotation detection based on yolov5

yolov5 + csl_label.(Oriented Object Detection)（Rotation Detection）（Rotated BBox）基于yolov5的旋转目标检测

Label Rotated Rect On Images for training

做QT导出word报表，发现网上的资源不是很多，也浪费了很多时间，我自己做了一份demo,将会详细讲述如何做出需要样式的报表。在网上很容易查到java或者其他语言操作word的接口函数，但是QT能操作word的，不是很多，而且还不太好用。我把自己已经调试出来的代码，贡献出来，免得以后浪费时间。 写了一部分接口函数，可以满足大部分的word报表。

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

Pixel2Mesh-Tensorflow2

ncnn is a high-performance neural network inference framework optimized for the mobile platform

[ECCV 2020] Boundary-preserving Mask R-CNN

Official Implementation for "Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation" (CVPR 2021) presenting the pixel2style2pixel (pSp) framework

Annotate quickly images.

Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.

Lightweight Image Super-Resolution with Enhanced CNN (Knowledge-Based Systems,2020)

Open Source Computer Vision Library