Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
GPU
• DeepStream Version
5.0.1
• 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)
Hello everyone.
I have a problem getting the confidence value from obj_meta->confidence.
I configured a tiny yolo primary detector following this steps.
Visually, I have a prety good deepstream-app, it runs smoothly and I can see on screen that objects are detected quite accurately, furthermore, the tracker can follow the objects correctly and recognice them if they dissapear for one second.
The problem is that every object, from any class or frame, I get obj_meta->confidence= -0.10000.
This is my config-file
[property]
gpu-id=0
#0=RGB, 1=BGR
model-color-format=0
onnx-file=…/tiny_yolov2.onnx
#custom-network-config=yolov2.cfg
#model-file=yolov2.weights
#model-engine-file=…/tiny_yolov2.onnx_b1_fp16.engine
model-engine-file=…/tiny_yolov2.onnx_b1_gpu0_fp32.engine
labelfile-path=…/labels.txt
network-mode=0
num-detected-classes=7
gie-unique-id=1
is-classifier=0
maintain-aspect-ratio=1
output-blob-names=grid
parse-bbox-func-name=NvDsInferParseCustomYoloV2Tiny
custom-lib-path=…/custom_bbox_parser/libnvdsinfer_custom_bbox_tiny_yolo.so
I don’t know where the error could be, any help will be appreciated.
thank you!