LBQ-0829

YOLOv8_Tensorrt

A simple implementation of Tensorrt YOLOv8

ZCU102-VitisAI-Resnet50-DoE

DPU benchmarking on Xilinx's ZCU 102 using Vitis-AI and Resnet50

Vitis-AI

Vitis AI is Xilinx’s development stack for AI inference on Xilinx hardware platforms, including both edge devices and Alveo cards.

Vitis-ai-zcu104-yolov5

Use Vitis AI to deploy yolov5 on ZCU104

A-White-Paper-on-Neural-Network-Deployment

模型部署白皮书(CUDA|ONNX|TensorRT|C++)🚀🚀🚀

progressive_cnn_filter

RDO-free approach to coordinate the CNNbased in-loop filters to work seamlessly with video encoders

OVQE

[IEEE TBC] PyTorch Implementation for "OVQE: Omniscient Network for Compressed Video Quality Enhancement"

xeve

eXtra-fast Essential Video Encoder, MPEG-5 EVC (Essential Video Coding)

powervqe

Empower the quality enhancement approaches for compressed videos.

VToonify

[SIGGRAPH Asia 2022] VToonify: Controllable High-Resolution Portrait Video Style Transfer

changeable_region_detection

A changeable region detection method based on yolov5

SOLOv2

SOLOv2: Dynamic, Faster and Stronger, achives 39.5mAP on coco test-dev (36 epochs result)

YOLO-Streaming

Push-pull streaming and Web display of YOLO series

YOLOv5_NCNN

🍅 Deploy ncnn on mobile phones. Support Android and iOS. 移动端ncnn部署，支持Android与iOS。

YOLOP-opencv-dnn

使用OpenCV部署全景驾驶感知网络YOLOP，可同时处理交通目标检测、可驾驶区域分割、车道线检测，三项视觉感知任务，包含C++和Python两种版本的程序实现。本套程序只依赖opencv库就可以运行， 从而彻底摆脱对任何深度学习框架的依赖。

Smart_Construction

Base on YOLOv5 Head Person Helmet Detection on Construction Sites，基于目标检测工地安全帽和禁入危险区域识别系统，🚀😆附 YOLOv5 训练自己的数据集超详细教程🚀😆2021.3新增可视化界面❗❗

awesome-ncnn

😎 A Collection of Awesome NCNN-based Projects

RLFN

Winner of runtime track in NTIRE 2022 challenge on Efficient Super-Resolution

Deformable-Convolution-V2-PyTorch

Deformable ConvNets V2 (DCNv2) in PyTorch

Face-Forgery-Generation-and-Detection-Overview

AdversarialDeepFakes

TSAN

Transcoded Video Restoration by Temporal Spatial Auxiliary Network-AAAI2022

ai20projects

DAT

Repository of Vision Transformer with Deformable Attention (CVPR2022) and DAT++: Spatially Dynamic Vision Transformerwith Deformable Attention

yolov5-face

YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931) ECCV Workshops 2022)

QGCN

Learning a Single Model With a Wide Range of Quality Factors for JPEG Image Artifacts Removal (TIP 2020)