AXERA-TECH / ONNX-YOLO-World-Open-Vocabulary-Object-DetectionLinks
Python scripts performing Open Vocabulary Object Detection using the YOLO-World model in ONNX. And Export the ONNX model for AXera's NPU
☆12Updated 4 months ago
Alternatives and similar repositories for ONNX-YOLO-World-Open-Vocabulary-Object-Detection
Users that are interested in ONNX-YOLO-World-Open-Vocabulary-Object-Detection are comparing it to the libraries listed below
Sorting:
- FastSAM 部署版本,便于移植不同平,部署简单、运行速度快。☆24Updated last year
- DETR tensor去除推理过程无用辅助头+fp16部署再次加速+解决转tensorrt 输出 全为0问题的新方法。☆12Updated last year
- 使用NCNN推理框架和ByteTrack目标跟踪框架,对网络、文件流URL进行实时性视频推理,而UI界面则由Qt框架实现☆22Updated last year
- 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 6 months ago
- Quantize yolov5 using pytorch_quantization.🚀🚀🚀☆14Updated 2 years ago
- ☆27Updated 5 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☆47Updated 3 years ago
- ffmpeg+cuvid+tensorrt+multicamera☆12Updated 11 months ago
- ☆23Updated last year
- A unified and extensible pipeline for deep learning model inference with C++. Now support yolov8, yolov9, clip, and nanosam. More models …☆12Updated 4 months ago
- ☆29Updated 3 years ago
- ☆17Updated 2 years ago
- ☆17Updated last year
- Quantize yolov7 using pytorch_quantization.🚀🚀🚀☆11Updated 2 years ago
- ☆24Updated 2 years ago
- 基于rknn的yolov5的cpp实现,包含各种依赖库,是一个完整工程,可直接编译运行☆21Updated 3 years ago
- Nanodet with mosaic and mixup☆13Updated 4 years ago
- ncnn 实现一些项目例子☆26Updated 2 years ago
- YOLOv12 TensorRT 端到端模型加速推理和INT8量化实现☆13Updated 9 months ago
- 对 tensorRT_Pro 开源项目理解☆21Updated 2 years ago
- ppstructure deploy by ncnn☆34Updated last year
- 基于NCNN框架实现车道线检测(C/C++)☆24Updated 8 months ago
- yolov8 旋转目标检测部署,瑞芯微RKNN芯片部署、地平线Horizon芯片部署、TensorRT部署☆28Updated last year
- naive c++ version of Mask2Former with ncnn☆23Updated 3 years ago
- 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)☆40Updated last month
- ☆67Updated 3 years ago
- ☆16Updated 2 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☆23Updated 2 years ago
- 车道线检测Lanenet TensorRT加速C++实现☆23Updated 3 years ago
- yolov8seg 瑞芯微 rknn 板端 C++部署,使用平台 rk3588。☆29Updated last year