ZHEQIUSHUI / CLIP-ONNX-AX650-CPP
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 4 months ago
Alternatives and similar repositories for CLIP-ONNX-AX650-CPP
Users that are interested in CLIP-ONNX-AX650-CPP are comparing it to the libraries listed below
Sorting:
- 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。☆47Updated last year
- ☆10Updated 9 months ago
- ☆25Updated 4 months ago
- 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 last year
- 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☆19Updated 10 months ago
- ☆22Updated last year
- Python scripts performing Open Vocabulary Object Detection using the YOLO-World model in ONNX. And Export the ONNX model for AXera's NPU☆12Updated 7 months ago
- an example of segment-anything infer by ncnn☆121Updated 2 years ago
- ☆64Updated 2 years ago
- ppstructure deploy by ncnn☆32Updated 9 months ago
- rknn inference☆45Updated 3 years ago
- a plugin-oriented framework for video structured. 国产程序员请加微信zhzhi78拉群交流。☆20Updated 11 months ago
- 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
- ffmpeg+cuvid+tensorrt+multicamera☆12Updated 4 months ago
- 对 tensorRT_Pro 开源项目理解☆20Updated 2 years ago
- 使用ONNXRuntime部署PP-YOLOE目标检测,支持PP-YOLOE-s、PP-YOLOE-m、PP-YOLOE-l、PP-YOLOE-x四种结构,包含C++和Python两个版本的程序☆20Updated 2 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
- ncnn demo of (文档矫正)DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction☆43Updated 3 years ago
- ncnn 实现一些项目例子☆25Updated 2 years ago
- Learning to See in the Dark running in Android by ncnn with Raw Camera☆25Updated 3 years ago
- 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☆22Updated last year
- a simple lightweight large language model pipeline framework.☆25Updated 2 weeks ago
- segment-anything based mnn☆35Updated last year
- ☆19Updated last year
- ☆23Updated last year
- 使用ONNXRuntime部署百度PaddleSeg发布的实时人像抠图模型PP-MattingV2,一共包含18个onnx模型,依然是包含C++和Python两个版本的程序☆30Updated 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☆26Updated 11 months ago
- some ncnn demos of FunASR☆25Updated 7 months ago
- The rknn2 API uses the secondary encapsulation of the process, which is easy for everyone to call. It is applicable to rk356x rk3588☆45Updated 2 years ago
- HunyuanDiT with TensorRT and libtorch☆17Updated 11 months ago