Deepstream-app sample app use multiple PGIEs

**• Hardware Platform (GPU) RTX 3060
**• DeepStream Version 6.3
• TensorRT Version
**• NVIDIA GPU Driver Version (valid for GPU only) CUDA12.0
• Issue Type (questions)

If I want to modify the deepstream-app sample app to use multiple PGIEs, where should I start with the modification?

Can you describe your specific use case?

Continuing from the previous topic,
I want to modify the deepstream-app sample app to enable the use of multiple PGIEs.
I’m not sure where to make the modifications.

For the previous topic, if you want to use pgie, you need to set the process-mode to 1, not 0.
If you want to change the deepstream source code, you can try to change the create_secondary_gie in the deepstream_secondary_gie_bin.c.

  g_object_set (G_OBJECT (subbin->secondary_gie),
      "config-file-path", GET_FILE_PATH (config->config_file_path),
      "process-mode", 2, NULL);
1 Like

I would like to ask, what is the difference between this method and the following?

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

The example you posted is parallel, the above method is serial.

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