How to use nvtracker with sub-batches?

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

**• Hardware Platform ------> GPU
**• DeepStream Version ----------> 6.4
• TensorRT Version -------> 8.5
**• NVIDIA GPU Driver Version ------> 545
• Issue Type( questions, new requirements, bugs)

I want know How can I use sub-batches , tracker.txt and how to make property

if key == ‘ll-config-file’ :
tracker_ll_config_file = config.get(‘tracker’, key)
new_model_element.set_property(‘ll-config-file’, tracker_ll_config_file)

and I am using NVDCF tracker, tracker.yml if I need to change ?

3

Please upgrade to latest DeepStream 7.0. Please refer here for sub-batching: Gst-nvtracker — DeepStream documentation 6.4 documentation

4

I already went through the documentation trying to implement here no example with sample app and how can I set property for “sub-batches” , if you can give a example !

5

You can refer: /opt/nvidia/deepstream/deepstream-7.0/sources/apps/apps-common/src/deepstream_tracker_bin.c
Above set all the nvtracker properties.

6

One more question I have, So tracker ID will be go till 32bit INT, is there is a way to reduce it, let’s say 50,000 and when it(tracker-ID) will reach 50K automatically it will start from 0 again ?

7

No. Not sure why you need it. Maybe you can calculate it in your application based on the object id.

8

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

9

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