Struggling to detect classes with DeepStream-Yolo despite following YOLOv5 setup

Accelerated Computing Intelligent Video Analytics DeepStream SDK
, ,
1

Goodday

I am struggling to with https://github.com/marcoslucianops/DeepStream-Yolo/blob/master/docs/YOLOv5.md. I follow all the instructions but I am unable to infer/detect the classes when I run deepstream-app -c deepstream_app_config.txt. I have also made a post on the of the issue on the
DeepStream-Yolo repo here
[incorrect 0 INPUT kFLOAT input 3x640x640 1 OUTPUT kFLOAT output 25200x6 shape instead of WARNING: [TRT]: The getMaxBatchSize() function should not be used with an engine built from a network created with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag. This function will always return 1. INFO: [Implicit Engine Info]: layers num: 4 0 INPUT kFLOAT input 3x640x640 1 OUTPUT kFLOAT boxes 25200x4 2 OUTPUT kINT32 classes 25200x1 3 OUTPUT kFLOAT scores 25200x1 · Issue #595 · marcoslucianops/DeepStream-Yolo · GitHub](https://Issue post). But I am still unable to get the classes to infer/detect.

I would really be greatfull for any additional information or if anyone can point me in the right directio

2

Hi ,
Request you to raise thi son Deepstream Forum.

Thanks

4

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)

5

Gooday I have posted there issue. But I haven’t had any responses from the maintainers of the repo.

6

• Hardware Platform (Jetson / GPU) - NVIDIA Jetson AGX Xavier Developer Kit
• DeepStream Version - 6.2.0
• JetPack Version - 5.1.1
• TensorRT Version - 8.5
• NVIDIA GPU Driver Version (valid for GPU only) - N.A
• Issue Type - DeepStream-Yolo/docs/YOLOv5.md at master · marcoslucianops/DeepStream-Yolo · GitHub I was trying to run this app.
the command
deepstream-app -c deepstream_app_config.txt
• How to reproduce the issue - incorrect 0 INPUT kFLOAT input 3x640x640 1 OUTPUT kFLOAT output 25200x6 shape instead of WARNING: [TRT]: The getMaxBatchSize() function should not be used with an engine built from a network created with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag. This function will always return 1. INFO: [Implicit Engine Info]: layers num: 4 0 INPUT kFLOAT input 3x640x640 1 OUTPUT kFLOAT boxes 25200x4 2 OUTPUT kINT32 classes 25200x1 3 OUTPUT kFLOAT scores 25200x1 · Issue #595 · marcoslucianops/DeepStream-Yolo · GitHub

7

could you provide a summary? is there any DeepStream bug? Thanks!

8

in Summary when I follow https://github.com/marcoslucianops/DeepStream-Yolo/blob/master/docs/YOLOv5.md.Everything works but on the pipelines when the video/stream is pulled there is no inference/detection of the classes I have more then triple checked if I have the correct labels.txt file. It also seems to be something a few people are struggling with but our questions haven’t been fully addressed on the Deepstream repo.

9

In the link, seems the model has two layers, and you want four layers. it should be the issue of export_yoloV5.py. this issue would be outside of DeepStream. maybe the author can fix.