How to know which yolo variant has used in sample

Autonomous Vehicles DRIVE AGX Orin DRIVE AGX Orin General
1

Please provide the following info (tick the boxes after creating this topic):
Software Version
DRIVE OS 6.0.10.0
[1] DRIVE OS 6.0.8.1
DRIVE OS 6.0.6
DRIVE OS 6.0.5
DRIVE OS 6.0.4 (rev. 1)
DRIVE OS 6.0.4 SDK
other

Target Operating System
[1] Linux
QNX
other

Hardware Platform
DRIVE AGX Orin Developer Kit (940-63710-0010-300)
DRIVE AGX Orin Developer Kit (940-63710-0010-200)
DRIVE AGX Orin Developer Kit (940-63710-0010-100)
DRIVE AGX Orin Developer Kit (940-63710-0010-D00)
DRIVE AGX Orin Developer Kit (940-63710-0010-C00)
[1] DRIVE AGX Orin Developer Kit (not sure its number)
other

SDK Manager Version
2.1.0
[1] other

Host Machine Version
native Ubuntu Linux 20.04 Host installed with SDK Manager
native Ubuntu Linux 20.04 Host installed with DRIVE OS Docker Containers
native Ubuntu Linux 18.04 Host installed with DRIVE OS Docker Containers
other

Issue Description
Hi team, there is a sample named “sample object detector tracker”. I went through the code. I could see yolo has been used but I want to know which version or variant of yolo has been used in object detection.
TensorRT is used as an accelerator???

3

Dear @akshay.tupkar,
Updated the topic as per Announcement from NVIDIA: Guidelines to create a new topic . Please follow the same for future topics.

Please find the model at /usr/local/driveworks/data/samples/detector/yolo.onnx

Yes. The sample uses TensorRT optimzed model.

4

Dear @SivaRamaKrishnaNV
Yolo is a dnn based model and tensorRT is optimising the yolo model. So yolo is responsible for detecting objects or tensorRT is detection objects. It is creating a confusion

5

Dear @akshay.tupkar,
TensorRT is an SDK used to optimize your DNN model to improve inference performance. The optimization process involves fusion of DNN layers and picking up optimal GPU kernels for the layers on that HW. This allows you get good inference speed up when using TRT model compared to ONNX DNN model in your application.
Note that, DW allows the models generated using DriveWorks SDK Reference: TensorRT Optimizer Tool .

6

Thanks for sharing this information @SivaRamaKrishnaNV
Is there any tool to view the yolo.onnx file to see its content, I could open it using vi editor but it is not fully understandable. I want to know the yolo varient used

7

You could check with tools like netron.

8

Thanks dear @SivaRamaKrishnaNV

10

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