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")