Deepstream_python get_prediction int casting problem

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 6.2
• 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)

I applied output-tensor-meta=1 to pgie using deepstream-python. However, I am curious as to whether the KINT32 type is not properly parsed in pyds during the process of parsing the model output. However, even though det_classes is kint32 type, it is parsed as 0.0 (float), and I am curious why Num_dets returns the value 4.203895392974451e-45.

0   INPUT  kFLOAT images          3x704x1280      min: 1x3x704x1280    opt: 2x3x704x1280    Max: 2x3x704x1280    
1   OUTPUT kINT32 num_dets        1               min: 0               opt: 0               Max: 0               
2   OUTPUT kFLOAT det_boxes       100x4           min: 0               opt: 0               Max: 0               
3   OUTPUT kFLOAT det_scores      100             min: 0               opt: 0               Max: 0               
4   OUTPUT kINT32 det_classes     100             min: 0               opt: 0               Max: 0               
5   OUTPUT kFLOAT det_lmks        100x10          min: 0               opt: 0               Max: 0               
6   OUTPUT kFLOAT det_lmks_mask   100x5           min: 0               opt: 0               Max: 0 

num_detection_layer = layer_finder(layers_info, "num_dets")

num_dets = pyds.get_detections(num_detection_layer.buffer, 0) # 4.203895392974451e-45

# Parsing fine...
box_layer = layer_finder(layers_info, "det_boxes")
score_layer = layer_finder(layers_info, "det_scores")
class_layer = layer_finder(layers_info, "det_classes")

The pyds.get_detections() only support float pointer. You may add new bindings to get int data.

deepstream_python_apps/bindings/src/bindfunctions.cpp at master · NVIDIA-AI-IOT/deepstream_python_apps (