mxpi_objectpostprocessor

Function	Inherits the image postprocessing base class, which is used to postprocess the inference output tensor of an object detection model.
Constraints	Currently, the upstream of the plugin can only be connected to the mxpi_tensorinfer inference plugin, and only MxpiTensorPackageList can be used as the metadata input. This plugin calls the object detection base class Process API of the mxBase repository to communicate and receive the return value of the ObjectInfo data type.
Plugin Base Class (Factory)	mxpi_objectpostprocessor
Input/Output	Input: buffer (data type: MxpiBuffer), metadata (data type: MxpiTensorPackageList) Output: buffer (data type: MxpiBuffer), metadata (data type: MxpiObjectList)
Port Format (Caps)	Static input: {"metadata/tensor"} Static output: {"metadata/object"}
Property	For details, see Table 1 and Table 2.

Sample pipeline of the Python postprocessing plugin:

"mxpi_objectpostprocessor0": {
            "props": {
                "funcLanguage":"python",
                "postProcessConfigPath": "../models/yolov3/yolov3_tf_bs1_fp16.cfg",
                "labelPath": "../models/yolov3/yolov3.names",
                "postProcessLibPath": "../../../python",
                "className":"Yolov3PostProcess",
                "pythonModule":"postprocess.post"
            },
            "factory": "mxpi_objectpostprocessor",
            "next": "mxpi_dataserialize0"
        },

Sample pipeline of the C++ postprocessing plugin:

"mxpi_objectpostprocessor0": {
 "props": {
                "dataSource": "mxpi_tensorinfer0",
                "funcLanguage":"c++",
                "postProcessConfigPath": "../models/yolov3/yolov3_tf_bs1_fp16.cfg",
                "labelPath": "../models/yolov3/yolov3.names",
                "postProcessLibPath": "../../../lib/modelpostprocessors/libyolov3postprocess.so"
        },
        "factory": "mxpi_objectpostprocessor",
        "next": "mxpi_dataserialize0"
},

Parent topic: Model Postprocessing Plugins