Deepstream GstElement pgie using the nvinfer config file, how to understand parse-bbox-func-name and custom-lib-path?

I use yolo4 in deepstrem_test3, use the code
* Configure the nvinfer element using the nvinfer config file. */ g_object_set (G_OBJECT (pgie), "config-file-path", "dstest3_pgie_config.txt", NULL);
the para file:

[property]
gpu-id=0
net-scale-factor=0.0039215697906911373
#yolo4
#0=RGB, 1=BGR
model-color-format=0
model-engine-file=yolov4-uniform-dynamic-max8.engine
labelfile-path=labels.txt
batch-size=1
## 0=FP32, 1=INT8, 2=FP16 mode
network-mode=1
num-detected-classes=80
gie-unique-id=1
network-type=0
is-classifier=0
## 0=Group Rectangles, 1=DBSCAN, 2=NMS, 3= DBSCAN+NMS Hybrid, 4 = None(No clustering)
cluster-mode=2
maintain-aspect-ratio=1
parse-bbox-func-name=NvDsInferParseCustomYoloV4
custom-lib-path=libnvdsinfer_custom_impl_Yolo.so

Why do I have to use the .so library file? Why can’t I use the library in this code to show the yolo detecting info? If so, what should I do, please help !!

Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) Jetson
• DeepStream Version 6.1
• JetPack Version (valid for Jetson only) 5.1
• TensorRT Version 11.4
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

By default the bonding box parse is for resnet, as different detection model may have output format, thus need to be updated if Yolov4 is used.

different detection model may have output format, thus need to be updated if Yolov4 is used.

I know ,I want to process the detection box in the main program, but can I not implement it in the so library,
How can i do?

nvinfer low level lib is opensource, you can implement function m_CustomBBoxParseFunc of DetectPostprocessor::fillDetectionOutput, the code path is \opt\nvidia\deepstream\deepstream\sources\libs\nvdsinfer\nvdsinfer_context_impl_output_parsing.cpp

There is no update from you for a period, assuming this is not an issue any more.
Hence we are closing this topic. If need further support, please open a new one.
Thanks

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.