ZHEQIUSHUI / SAM-ONNX-AX650-CPPLinks
SAM and lama inpaint,包含QT的GUI交互界面,实现了交互式可实时显示结果的画点、画框进行SAM,然后通过进行Inpaint,具体操作看readme里的视频。
☆51Updated last year
Alternatives and similar repositories for SAM-ONNX-AX650-CPP
Users that are interested in SAM-ONNX-AX650-CPP are comparing it to the libraries listed below
Sorting:
- an example of segment-anything infer by ncnn☆125Updated 2 years ago
- c++实现的clip推理,模型有一点点改动,但是不大,改动和导出模型的代码可以在readme里找到,模型文件都在Releases里,包括AX650的模型。新增支持ChineseCLIP☆30Updated 5 months ago
- segment-anything based mnn☆36Updated last year
- DragGan in NCNN with c++☆52Updated 2 years ago
- ppstructure deploy by ncnn☆33Updated last year
- ☆16Updated last year
- ☆23Updated last year
- 使用onnxruntime部署LYT-Net轻量级低光图像增强,包含C++和Python两个版本的程序☆28Updated last year
- mnn yolo demos.☆86Updated last year
- 使用ONNXRuntime部署DeDoDe:"局部特征匹配:检测,不要描述——描述,不要检测"。依然是C++和Python两个版本的程序☆23Updated last year
- ncnn version of CodeFormer☆109Updated 2 years ago
- 使用ONNXRuntime部署Informative-Drawings生成素描画,包含C++和Python两个版本的程序☆14Updated 2 years ago
- Implementation of yolo v10 in c++ std 17 over opencv and onnxruntime☆90Updated last year
- ☆20Updated last year
- 使用ONNXRuntime部署Detic检测2万1千种类别的物体,包含C++和Python两个版本的程序☆17Updated 2 years ago
- Learning to See in the Dark running in Android by ncnn with Raw Camera☆26Updated 3 years ago
- ☆24Updated 2 years ago
- 使用onnxruntime部署MOWA:多合一图像扭曲模型,能处理6种图像扭曲任务,依然是包含C++和Python两个版本的程序☆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.☆49Updated 3 years ago
- NeRF in NCNN with c++ & vulkan☆68Updated 2 years ago
- a Android demo of depth_anything_v1 and depth_anything_v2☆68Updated last year
- 高效部署:YOLO X, V3, V4, V5, V6, V7, V8, EdgeYOLO TRT推理 ™️ ,前后处理均由CUDA核函数实现 CPP/CUDA🚀☆52Updated 2 years ago
- stable diffusion using mnn☆67Updated 2 years ago
- ☆67Updated 3 years ago
- segment anything(SAM) for CPP Inference☆30Updated last year
- naive c++ version of Mask2Former with ncnn☆23Updated 3 years ago
- 这是一个使用opencv读取视频并使用socket进行传输视频画面的脚本文件,相较于调用ffmpeg传输节约了90%的数据量☆11Updated last year
- 分别使用OpenCV、ONNXRuntime部署FreeYOLO目标检测,总共包含143个onnx模型,有COCO目标检测,人脸检测,密集行人检测的三种检测功能,依然是包含C++和Python两个版本的程序☆32Updated 2 years ago
- 使用OpenCV部署CoupledTPS,包 含了肖像矫正,不规则边界的图像矩形化,旋转图像矫正,三个模型。依然是包含C++和Python两个版本的程序☆20Updated last year
- 高性能 高精度 大陆车牌、港澳车牌、台湾车牌 韩国车牌(South Korea LPR)识别 代码开源(ncnn移植)☆38Updated last month