How does the pre-cluster-threshold parameter work for the detection problem?

[lehuyhoang30122000]

I have file config as follows:

• Hardware Platform: GPU
• DeepStream Version: 6.3
• TensorRT Version: 8.5.3-1+cuda11.8
• NVIDIA GPU Driver Version: 525.89.02

[property]
gpu-id=0
net-scale-factor=1.0
offsets=103.939;116.779;123.68
onnx-file=/deepstream/weights/primary/night_vision_detection/yolov4_cspdarknet_tiny_epoch_015_fp16.onnx
labelfile-path=/deepstream/weights/primary/night_vision_detection/labels_nightvision.txt
#int8-calib-file=/deepstream/weights/primary/night_vision_detection/cal_obd_det.bin
model-engine-file=/deepstream/weights/primary/night_vision_detection/yolov4_cspdarknet_tiny_epoch_015_fp16.onnx_b1_gpu0_fp16.engine
infer-dims=3;384;640
batch-size=1
process-mode=1
## 0=FP32, 1=INT8, 2=FP16 mode
network-mode=2
num-detected-classes=7
interval=0
gie-unique-id=1
cluster-mode=2
#roi-top-offset=0
#roi-bottom-offset=0
model-color-format=1
maintain-aspect-ratio=0
output-tensor-meta=0
output-blob-names=BatchedNMS
parse-bbox-func-name=NvDsInferParseCustomYoloV4TLT
custom-lib-path=/deepstream/nvdsinfer_custom_impl_Yolo/libnvdsinfer_custom_impl_Yolo.so

[class-attrs-all]
topk=200
nms-iou-threshold=0.5
pre-cluster-threshold=0.4

I need to know exactly what is the purpose of pre-cluster-threshold parameter and why cluster is needed when confidence_threshold and nms_iou_threshold are enough

[fanzh]

Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

[lehuyhoang30122000]

I have provided a deepstream running version

[fanzh]

Warn: ‘threshold’ parameter has been deprecated."
" Use ‘pre-cluster-threshold’ instead.\n"
nvinfer plugin is opensource. as the log in \opt\nvidia\deepstream\deepstream\sources\gst-plugins\gst-nvinfer\gstnvinfer_property_parser.cpp shown, pre-cluster-threshold means threshold.