Source info not found for source 2. Maybe the GST_NVEVENT_PAD_ADDED event was never generated for the source

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

0:01:08.378639504 23885 0x3148c980 WARN nvinfer gstnvinfer.cpp:1705:gst_nvinfer_process_objects: Source info not found for source 2. Maybe the GST_NVEVENT_PAD_ADDED event was never generated for the source.

0:01:08.394033843 23885 0x3148caa0 WARN nvinfer gstnvinfer.cpp:1705:gst_nvinfer_process_objects: Source info not found for source 1. Maybe the GST_NVEVENT_PAD_ADDED event was never generated for the source.
0:01:08.394058108 23885 0x3148c8c0 WARN nvinfer gstnvinfer.cpp:1705:gst_nvinfer_process_objects: Source info not found for source 1. Maybe the GST_NVEVENT_PAD_ADDED event was never generated for the source.
0:01:08.413693848 23885 0x22bc08c0 WARN nvinfer gstnvinfer.cpp:1705:gst_nvinfer_process_objects: Source info not found for source 2. Maybe the GST_NVEVENT_PAD_ADDED event was never generated for the source.
0:01:08.413718584 23885 0x22bc0800 WARN nvinfer gstnvinfer.cpp:1705:gst_nvinfer_process_objects: Source info not found for source 2. Maybe the GST_NVEVENT_PAD_ADDED event was never generated for the source.
0:01:08.420194007 23885 0x3148c980 WARN nvinfer gstnvinfer.cpp:1705:gst_nvinfer_process_objects: Source info not found for source 2. Maybe the GST_NVEVENT_PAD_ADDED event was never generated for the source.
0:01:08.421480022 23885 0x3148caa0 WARN nvinfer gstnvinfer.cpp:1705:gst_nvinfer_process_objects: Source info not found for source 1. Maybe the GST_NVEVENT_PAD_ADDED event was never generated for the source.
0:01:08.421515776 23885 0x3148c8c0 WARN nvinfer gstnvinfer.cpp:1705:gst_nvinfer_process_objects: Source info not found for source 1. Maybe the GST_NVEVENT_PAD_ADDED event was never generated for the source.

Hi, I am trying to run the deepstream parallel inference using python, but when I try to run three PGIE branches .
I am getting the above error.

2

Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• 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)
• The pipeline being used

4

• Hardware Platform GPU
• DeepStream Version -----> 6.2
• JetPack Version (valid for Jetson only)
• TensorRT Version 8.5
• NVIDIA GPU Driver Version 535
• 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)
• The pipeline being used

5

@yingliu, No reply from your side.

6

Sorry for the late reply.

Can you share your configuration files and sample python code ?

I will try to reproduce

7

I have a couple of configuration files!
I am trying to implement the deepstream-parallel-inference using python.

8

This warning usually means no objects added in the meta by upstream components.

Can you reproduce this problem if you use the deepstream-parallel-inference sample

I can’t confirm whether it is your configuration problem or the python code problem

9

Lets consider I have A, B, C, D PGIE’s.
when I try to use A, and B, I don’t encounter this. But when I use C, D I am getting this warning.
Okay, let me share my configs.

10

all_vehicle
all_vehicle1920×89 20.7 KB

This is my pipeline

11

Please find my config file in this zip and let me know if you able to fix this problem ASAP.

nvidia_forum_config.zip (8.3 KB)

12

@junshengy @yingliu Did you find any solution ? or Any update ?

13

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

I have tried modifying configuration file to run four-way parallel inferences using deepstream_parallel_infer_app as your description. It can work normal.

From the logs you provided, I guess the problem is that streammux is not successfully linked with nvinfer

I can help you if you share the sample code.

14

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