zhg-SZPT / FastSAM_Awsome_Openvino
"FastSAM_Awsome_Openvino" 项目展示了如何通过 OpenVINO 框架高效部署 FastSAM 模型,实现了令人瞩目的实例分割功能。该项目提供了 C++ 版本和 Python 版本两种实现,为开发者提供了在不同语言环境下使用 FastSAM 模型的选择。
☆35Updated last year
Alternatives and similar repositories for FastSAM_Awsome_Openvino:
Users that are interested in FastSAM_Awsome_Openvino are comparing it to the libraries listed below
- 用OpenVINO对yolov8导出的onnx模型进行C++的推理, 任务包括图像分类, 目标识别和语义分割, 步骤包括图片前处理, 推理, NMS等☆62Updated 11 months ago
- tensorrt sahi yolo 目标检测☆40Updated this week
- This is the code to implement Segment Anything (SAM) using TensorRT(C++).☆39Updated last year
- YOLOv8 Inference C++ sample code based on OpenVINO C++ API☆43Updated last year
- 在Jetson AGX Xavier上部署yolov8-seg检测分割模型(带自适应低光照补偿)☆45Updated last month
- YOLOv8 C++ DET、SEG、POSE TENSORRT 推理库,便于学习开发拓展与工作中实际部署☆18Updated last year
- yolov11 的tensorRT C++ 部署,后处理使用cuda实现比较耗时的操作。☆32Updated 3 months ago
- 使用TensorRT加速YOLOv8-Seg,完整的后端框架,包括Http服务器,Mysql数据库,ffmpeg视频推流等。☆81Updated last year
- based on the yolov8,provide pt-onnx-tensorrt transcode and infer code by c++☆59Updated 2 years ago
- Using OnnxRuntime to inference yolov10,yolov10+SAM ,yolov10+bytetrack and SAM2 by c++ .☆94Updated 6 months ago
- deploy the YOLO model on C++ with Opencv4.8 or onnxruntime☆42Updated 2 months ago
- SPEED SAM C++ TENSORRT: A high-performance C++ implementation using TensorRT and CUDA☆28Updated 4 months ago
- ☆77Updated last year
- simplest yolov8 segment onnx model infer in cpp using onnxruntime and opencv dnn net☆34Updated last year
- This project provides simple code and demonstrates how to use the TensorRT C++ API and ONNX to deploy PaddleOCR text recognition model.☆41Updated 2 years ago
- Based on tensorrt v8.0+, deploy detect, pose, segment, tracking of YOLOv8 with C++ and python api.☆95Updated last month
- yolov8seg 瑞芯微 rknn 板端 C++部署,使用平台 rk3588。☆24Updated 11 months ago
- 11111☆28Updated 2 years ago
- yolov11(yolov8)尝试了7种不同的部署方法,并对每种方法的优势进行了简单总结。不同的平台、不同的时耗或CPU占用需求,总有一种方法是适用的。针对想入门部署的也是一个很好的参考学习资料。☆18Updated 2 months ago
- C++ application to perform computer vision tasks using Nvidia Triton Server for model inference☆23Updated last month
- yolov8n 部署版,基于官方的导出onnx脚本导出onnx模型,在不同平台上进行部署测试,便于移植不同平台(onnx、tensorRT、rknn、Horizon)。☆38Updated last year
- 使用onnxruntime部署GroundingDINO开放世界目标检测,包含C++和Python两个版本的程序☆55Updated last year
- 对 tensorRT_Pro 开源项目理解☆20Updated 2 years ago
- yolov8obb 旋转目标检测部署rknn的C++代码☆17Updated 9 months ago
- This project showcases the deployment of the RT-DETR model using ONNXRUNTIME in C++ and Python.☆52Updated last year
- Example of using ultralytics YOLOv5 with Openvino in C++ and Python.☆67Updated 2 years ago
- RT-DETRv2 tensorrt C++ 部署☆15Updated 5 months ago
- 基于yolov8_obb的芯片引脚缺陷检测,使用tensorrt进行加速。☆23Updated 8 months ago
- segmentation algorithm yolact use tensorrt deploy☆14Updated 2 years ago
- fish-kong/Yolov5-Instance-Seg-Tensorrt-CPP☆58Updated 2 years ago