hongson23

cpp_new_features

2021年最新整理， C++ 学习资料，含C++ 11 / 14 / 17 / 20 / 23 新特性、入门教程、推荐书籍、优质文章、学习笔记、教学视频等

DAMO-YOLO

DAMO-YOLO: a fast and accurate object detection method with some new techs, including NAS backbones, efficient RepGFPN, ZeroHead, AlignedOTA, and distillation enhancement.

mmyolo

OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.

papers

Summaries of machine learning papers

vdp

💧 Instill VDP (Versatile Data Pipeline) is an open-source tool to seamlessly integrate AI to process unstructured data in the modern data stack

Stable-Diffusion-NCNN

Stable Diffusion in NCNN with c++, supported txt2img and img2img

sherpa-ncnn

Real-time speech recognition using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Raspberry Pi, VisionFive2, LicheePi4A etc.

ffmpeg-cpp

A clean, easy-to-use C++ wrapper around the ffmpeg libraries

PyMuPDF-Utilities

Demos, examples and utilities using PyMuPDF

lcnn

LCNN: End-to-End Wireframe Parsing

Calibration-ZhangZhengyou-Method

Calibrate the camera with ZhangZhengyou method (in both distortion case and no distortion case)

insight3d

Deep-Hough-Transform-Line-Priors

Official implementation for Deep-Hough-Transform-Line-Priors (ECCV 2020)

Blur-and-Clear-Classification

Classifying the Blur and Clear Images

Yolov7-training

A clean, modular implementation of the Yolov7 model family, which uses the official pretrained weights, with utilities for training the model on custom (non-COCO) tasks.

deepstream_parallel_inference_app

A project demonstrating how to use nvmetamux to run multiple models in parallel.

YOLOX-OBB

YOLOX in DOTA with KLD loss. (Oriented Object Detection)（Rotated BBox）基于YOLOX的旋转目标检测

toxic_spans

Detect toxic spans in toxic texts

GFPGANv1.3-to-ncnn

The GFPGAN network consists of two networks. Actually GFPGAN and StyleGAN2

ncnn-swift

An example on using ncnn with Swift.

yolov5_deepsort_ncnn_qt

ShakaLakaBoomBoom

Unity application to convert 2D sketches to 3D models which could be maneuvered around using hand gestures (to a position and orientation of choice) in a 3D scene.

SMS-Spam-Detection

A spam filter for detecting spam sms messages using ML

yolo-series

YOLO算法的实现

Datasets-ReaChOcc-and-SynChOcc

tracking_evaluation

Reimplementation of TRA measure

vispamdetection

Blur_Detection

Detect blurred images

3Dorfi

3D object model generation from a set of images.

SMS-Spam-Detector-NLP

Natural Language Processing using Tensorflow, the model is trained on >5000 SMS text messages to identify spam messages with an validation accuracy of over 98%.