Model not working after upgrading to Deepstream 7.1

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) Jetson Orin AGX
• DeepStream Version 7.1
• JetPack Version (valid for Jetson only) 6.2
• TensorRT Version 10.3.0
• 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)

Hi,
I was running a person detect YOLOv8 model as PGIE and person attribute model as SGIE in deepstream 7.0, jetpack 6.0 and tensorRT 8.6. Now I have upgraded it as per configuration mentioned above. I have build the new engine files for both models using deepstream7.1. I found that YOLOV8 model is working properly, however the person attribute model is not able to recognize any attribute.
To debug I print confidence in custom parser and found that all the values are less than 0.2 while earlier with 7.0 I was getting values higher then 0.55.
If needed I can provide you both the engine file created with 7.0 and 7.1. Below is the configuration I am using.

[property]
gpu-id=0
onnx-file=solider_model.onnx
model-engine-file=solider_model.onnx_b1_gpu0_fp32.engine
batch-size=1
net-scale-factor=0.00392156862745098
offsets=123.675;116.28;103.53
model-color-format=0
network-mode=0
process-mode=2
network-type=1
labelfile-path=labels.txt
interval=0
infer-dims=3;256;192
maintain-aspect-ratio=1
symmetric-padding=0
custom-lib-path=parser/libnvdsinfer_custom_impl.so
parse-classifier-func-name=NvDsInferParseSolider
classifier-threshold=0.55

Thanks

3

I have checked the onnx model and it was created with opset 11. I have gone through the tensorRT 10.3 release notes and found that it is recommending to use opset 18 or 19. So I have created the model again, still the confidence score is too low. The onnx model created today or the previous one are still giving accurate result.

I am not using container. While converting to fp32 engine by deepstream there were no errors. I tried fp16 as well but the problem didn’t resolve. Please help.

4

Please refer to the sample deepstream_tools/yolo_deepstream at main · NVIDIA-AI-IOT/deepstream_tools for how to handle the Yolo model.

5

My question is for person atrribute model Solider used as SGIE and not for Yolo model. Please resolve.

6

The only change is TensorRT version upgrading. For the ONNX model TensorRT accuracy issue, please consult in TensorRT forum. Latest Deep Learning (Training & Inference)/TensorRT topics - NVIDIA Developer Forums

7

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