Files
FastDeploy/model_zoo/vision/nanodet_plus/api.md
DefTruth e248781784 Add NanoDet-Plus Model support (#32)
* update .gitignore

* Added checking for cmake include dir

* fixed missing trt_backend option bug when init from trt

* remove un-need data layout and add pre-check for dtype

* changed RGB2BRG to BGR2RGB in ppcls model

* add model_zoo yolov6 c++/python demo

* fixed CMakeLists.txt typos

* update yolov6 cpp/README.md

* add yolox c++/pybind and model_zoo demo

* move some helpers to private

* fixed CMakeLists.txt typos

* add normalize with alpha and beta

* add version notes for yolov5/yolov6/yolox

* add copyright to yolov5.cc

* revert normalize

* fixed some bugs in yolox

* Add NanoDet-Plus Model support

Co-authored-by: Jason <jiangjiajun@baidu.com>
2022-07-22 09:49:55 +08:00

2.5 KiB
Raw Blame History

NanoDetPlus API说明

Python API

NanoDetPlus类

fastdeploy.vision.rangilyu.NanoDetPlus(model_file, params_file=None, runtime_option=None, model_format=fd.Frontend.ONNX)

NanoDetPlus模型加载和初始化当model_format为fd.Frontend.ONNX只需提供model_filenanodet-plus-m_320.onnx当model_format为fd.Frontend.PADDLE则需同时提供model_file和params_file。

参数

  • model_file(str): 模型文件路径
  • params_file(str): 参数文件路径
  • runtime_option(RuntimeOption): 后端推理配置默认为None即采用默认配置
  • model_format(Frontend): 模型格式

predict函数

NanoDetPlus.predict(image_data, conf_threshold=0.35, nms_iou_threshold=0.5)

模型预测结口,输入图像直接输出检测结果。

参数

  • image_data(np.ndarray): 输入数据注意需为HWCBGR格式
  • conf_threshold(float): 检测框置信度过滤阈值
  • nms_iou_threshold(float): NMS处理过程中iou阈值

示例代码参考nanodet_plus.py

C++ API

NanoDetPlus类

fastdeploy::vision::rangilyu::NanoDetPlus(
        const string& model_file,
        const string& params_file = "",
        const RuntimeOption& runtime_option = RuntimeOption(),
        const Frontend& model_format = Frontend::ONNX)

NanoDetPlus模型加载和初始化当model_format为Frontend::ONNX只需提供model_filenanodet-plus-m_320.onnx当model_format为Frontend::PADDLE则需同时提供model_file和params_file。

参数

  • model_file(str): 模型文件路径
  • params_file(str): 参数文件路径
  • runtime_option(RuntimeOption): 后端推理配置默认为None即采用默认配置
  • model_format(Frontend): 模型格式

Predict函数

NanoDetPlus::Predict(cv::Mat* im, DetectionResult* result,
                     float conf_threshold = 0.35,
                     float nms_iou_threshold = 0.5)

模型预测接口,输入图像直接输出检测结果。

参数

  • im: 输入图像注意需为HWCBGR格式
  • result: 检测结果,包括检测框,各个框的置信度
  • conf_threshold: 检测框置信度过滤阈值
  • nms_iou_threshold: NMS处理过程中iou阈值

示例代码参考cpp/nanodet_plus.cc

其它API使用