How to train the model used in sample object detector tracker on new dataset?

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, Yolo v3 is used in sample object detector tracker. What if I want to train this model on new dataset? What are the steps to do so? Any recommendations would be very helpful.

3

Dear @akshay.tupkar,
You need to train yolo v3 darknet model with new dataset and convert the final model to ONNX model.
Then use tensorRT_optimization tool to generate DW integrated model from ONNX.

4

Yes, but what are the steps to train the model? How can I do this?

5

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