Deepstream 6 Error: GXF_FACTORY_UNKNOWN_CLASS_NAME

Accelerated Computing Intelligent Video Analytics DeepStream SDK
,
1

Please provide complete information as applicable to your setup.

• Hardware Platform: GPU
• DeepStream Version: 6.0 (devel Docker)
• TensorRT Version
• NVIDIA GPU Driver Version: 510.39.01
• Issue Type(bugs)

I’m able to run deepstream-app3 with 4 rtsp streams and I tried to rebuild the same graph but I got this error:

2022-02-19 06:32:36 [799,577ms] [Error] [carb.python] [py stderr]: 2022-02-19 06:32:36.583 ERROR gxf/std/type_registry.cpp@48: Unknown type: nvidia::deepstream::NvDsResnet10_4ClassDetectorModel
2022-02-19 06:32:36.583 ERROR gxf/std/type_registry.cpp@48: Unknown type: nvidia::deepstream::NvDsResnet10_4ClassDetectorModel2022-02-19 06:32:36 [799,578ms] [Error] [carb.python] [py stderr]: 


2022-02-19 06:32:36 [799,578ms] [Error] [carb.python] [py stderr]: 2022-02-19 06:32:36.583 ERROR gxf/std/yaml_file_loader.cpp@125: Could not add component of type 'nvidia::deepstream::NvDsResnet10_4ClassDetectorModel' to entity.
2022-02-19 06:32:36.583 ERROR gxf/std/yaml_file_loader.cpp@125: Could not add component of type 'nvidia::deepstream::NvDsResnet10_4ClassDetectorModel' to entity.2022-02-19 06:32:36 [799,578ms] [Error] [carb.python] [py stderr]: 


2022-02-19 06:32:36 [799,578ms] [Error] [carb.python] [py stderr]: 2022-02-19 06:32:36.583 ERROR gxf/gxe/gxe.cpp@149: LoadApplication Error: GXF_FACTORY_UNKNOWN_CLASS_NAME
2022-02-19 06:32:36.583 ERROR gxf/gxe/gxe.cpp@149: LoadApplication Error: GXF_FACTORY_UNKNOWN_CLASS_NAME2022-02-19 06:32:36 [799,578ms] [Error] [carb.python] [py stderr]:

Platform config file: /opt/nvidia/graph-composer/config/target_x86_64_cuda_11_4.yaml
Config file:
simple_infer_stream (copy).yaml (6.5 KB)

3

Sorry for the late response, is this still an issue to support? Thanks

4

Yes. I don’t want to duplicate the sample/test app for each new project

5

Usually, when that happens for me I have to remove the gst cache like so:

rm -rf ~/.cache/gstreamer-1.0/

Could you try that?

6

Still no luck

7

Why don’t you set “uri-list” of NvDsMultiSrcInput? There is no input of the pipeline.

8

I remove the sources in the file. The sources are from rtsp streams

9

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

Sorry for the late response, is this still an issue to support? Thanks

11

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