AXERA-TECH / CLIP-ONNX-AX650-CPP
☆25Updated 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
- HunyuanDiT with TensorRT and libtorch☆17Updated 11 months 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☆18Updated 2 years ago
- ☆24Updated 2 years ago
- ☆22Updated last year
- Tengine 管子是用来快速生产 demo 的辅助工具☆13Updated 3 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 4 months ago
- the C++ version of thundernet with ncnn☆14Updated 4 years ago
- Wanwu models release, code will be released soon☆24Updated 2 years ago
- 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
- NVIDIA TensorRT Hackathon 2023复赛选题:通义千问Qwen-7B用TensorRT-LLM模型搭建及优化☆42Updated last year
- FSANet: 1 Mb!! Head Pose Estimation with MNN、TNN and ONNXRuntime C++.☆17Updated 3 years ago
- ☆24Updated 3 years ago
- Whisper in TensorRT-LLM☆15Updated 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
- ☆18Updated 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☆19Updated 10 months ago
- ffmpeg+cuvid+tensorrt+multicamera☆12Updated 4 months ago
- segment-anything based mnn☆35Updated last year
- A Special YOLOv5s-6.0 Deploy TensorRT☆8Updated 2 years ago
- ☆64Updated 2 years 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
- ☆16Updated last month
- 手摸手 美团 YOLOv6模型训练和TensorRT端到端部署方案教程☆30Updated 2 years ago
- SCRFD face detection based on MNN inference framework☆17Updated 3 years ago
- yolov5s_ncnn_inference pipeline☆21Updated 4 years ago
- ☆10Updated 9 months ago
- caffe train face licenseplate reID action ocr centernet☆23Updated 4 years ago
- 天池 NVIDIA TensorRT Hackathon 2023 —— 生成式AI模型优化赛 初赛第三名方案☆49Updated last year
- 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☆19Updated 3 years ago
- A fully cuda implementation of DCNv2(deformable convolution) forward. Without dependent of cuTorch(THC).☆10Updated 5 years ago