zdl's repositories
cuda-image-enhancement
An implementation of parallel version of gamma correction, histogram equalization, gaussian filter and sobel filter algorithms written in CUDA C++.OpenCV is used for including image into main program and saving output image.
360-Surround-View-CUDA-Project
10000 fps 🚀 for 360 Surround-View CUDA Solution
awesome-yolo-object-detection
🚀🚀🚀 A collection of some awesome public YOLO object detection series projects.
C_plus_plus
:cow: C++ 记录 :tm: CPP :airplane:
Chinese_MobileBert_on_SNPE
Run Chinese MobileBert model on SNPE.
crnn_plate_recognition
crnn chinese_plate_recognition
CV-CUDA
CV-CUDA™ is an open-source, graphics processing unit (GPU)-accelerated library for cloud-scale image processing and computer vision.
deepstream-yolo-pose
Use Deepstream python API to extract the model output tensor and customize the post-processing of YOLO-Pose
objectdetection_script
一些关于目标检测的脚本的改进思路代码,详细请看readme.md
onnx-modifier
A tool to modify onnx models in a visualization fashion, based on Netron and Flask.
cuda-image-preprocess
Speed up image preprocess with cuda when handle image or tensorrt inference
cuda-learn-note
CUDA 笔记 / 高频面试题汇总 / C++笔记,个人笔记,更新随缘: sgemm、sgemv、warp reduce、block reduce、dot、elementwise、softmax、layernorm、rmsnorm、hist etc.
DIP-OpenCV
Digital Image Processing OpenCV_Cpp learning code
export_llama_to_onnx
export llama to onnx
FaceAlgorithm
包含人脸检测(Retinaface,yolov5face,yolov7face,yolov8face),人脸检测跟踪(ByteTracker),人脸角度计算(Face_Angle)人脸矫正(Face_Aligner),人脸识别(Arcface),口罩检测(MaskRecognitiion),年龄性别检测(Gender_age),静默活体检测(Silent_Face_Anti_Spoofing),FaceAlignment(106keypoints)
my_trt_plugin
实现自己的tensorrt算子
onnx_matcher
Using pattern matcher in onnx model to match and replace subgraphs.
rknn-cpp-Multithreading
rk3588/rk3588s使用c++多线程异步等进行优化,yolov5s运行速度可达135帧
SF_TRT_62
支持yolov5,yolov7,yolov8,yolox 的tensorrt项目
SiLU_to_ReLU_ONNX
The python script to convert ONNX models SiLU activation layers in YOLOv5 or YOLOv8 to ReLU or LeakyReLU.
StableDiffusionOnDevice
本项目是一个通过文字生成图片的项目,基于开源模型Stable Diffusion V1.5生成可以在手机的CPU和NPU上运行的模型,包括其配套的模型运行框架。
surround-view-system-introduction
A full Python implementation for real car surround view system
Torch-Pruning
[CVPR-2023] Towards Any Structural Pruning; LLMs / Diffusion / YOLOv8 / CNNs / Transformers
trt_yolov8_infer_example
基于手写AI的infer模块,使用ffmpeg拉流解码送入trt_yolov8进行目标检测,渲染后推流输出画面,支持cuda硬件编解码
YOLOv6_pro
Make it easier for yolov6 to change the network structure
yolov8_tensorrt
pt-->wts-->engine