ERROR: Batch-size in network-input-shape should be atleast Sum Total of ROIs

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Hi all, I recently ran into a problem related to nvdspreprocess.

I have a pipeline in my code as follows:
uridecodebin->nvstreammux->preprocess->nvinfer->osd->sink

I try to create that pipeline and destroy the pipeline after a period of time and then repeat the operation several times.

The nth time I do it, the creation of the pipeline reports the above error
(where n is equal to the batch-size in network-input-shape，e.g. if N is equal to 8, I can only perform the above operation 8 times)
image

How can I troubleshoot the above issue?

• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 6.0
• JetPack Version (valid for Jetson only)
• TensorRT Version 8.5
• NVIDIA GPU Driver Version (valid for GPU only) 530
• 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)

3

How did you destroy and re-create the pipeline?

4

Something like this.

create:

gst_element_factory_make...
gst_bin_add...
gst_element_link...
gst_set_state_playing...

destroy:

gst_set_state_null...
gst_object_unref...

and call create and destroy in a for loop in the main function.

5

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

Can you upgrade to the latest DeepStream 6.3 to test the case? Can you provide your code and configurations which can run in our platform?

6

Sorry, my current system does not support deepstream-6.3, I may verify it later!

7

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