Please provide complete information as applicable to your setup.
**• Hardware Platform : GPU
**• DeepStream Version : 6.2
**• TensorRT Version : 8.5.3.1
**• NVIDIA GPU Driver Version : 525.85.12
**• Issue Type :bug
**• Graph Composer Version : 2.5.0
Hi, i want to use my own custom models in graph composer. But there are only 5 sample models in component list. When i set the config file and model engine textboxes (in engine field i write etlt models path) i receive this error message:
2023-02-13 06:35:30 [Error] [omni.kit.app._impl] [py stderr]: 0:00:00.174270403 e[334m45567e[00m 0x7f0948806160 e[36mINFO e[00m e[00m nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger:<nvinfer_bin_nvinfer>e[00m NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1923> [UID = 1]: Trying to create engine from model files
2023-02-13 06:35:30 [Error] [omni.kit.app._impl] [py stderr]:
2023-02-13 06:35:30 [Error] [omni.kit.app._impl]
2023-02-13 06:35:32 [Error] [omni.kit.app._impl] [py stderr]: ERROR: [TRT]: 3: [builder.cpp::~Builder::307] Error Code 3: API Usage Error (Parameter check failed at: optimizer/api/builder.cpp::~Builder::307, condition: mObjectCounter.use_count() == 1. Destroying a builder object before destroying objects it created leads to undefined behavior.
2023-02-13 06:35:32 [Error] [omni.kit.app._impl] [py stderr]:
2023-02-13 06:35:32 [Error] [omni.kit.app._impl]
2023-02-13 06:35:32 [Error] [omni.kit.app._impl] [py stderr]: )
2023-02-13 06:35:32 [Error] [omni.kit.app._impl] [py stderr]:
2023-02-13 06:35:32 [Error] [omni.kit.app._impl]
2023-02-13 06:35:49 [Error] [omni.kit.app._impl] [py stderr]: 0:00:19.593475164 e[334m45567e[00m 0x7f0948806160 e[36mINFO e[00m e[00m nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger:<nvinfer_bin_nvinfer>e[00m NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1955> [UID = 1]: serialize cuda engine to file: /home/ali-desktop/Desktop/sifirdan-imagedata-sgieli-yedek/emotionmodel.etlt_b30_gpu0_fp32.engine successfully
2023-02-13 06:35:49 [Error] [omni.kit.app._impl] [py stderr]:
2023-02-13 06:35:49 [Error] [omni.kit.app._impl]
2023-02-13 06:35:49 [Error] [omni.kit.app._impl] [py stderr]: 0:00:19.693043645 e[334m45567e[00m 0x7f0948806160 e[36mINFO e[00m e[00m nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus:<nvinfer_bin_nvinfer>e[00m [UID 1]: Load new model:/home/ali-desktop/Desktop/sifirdan-imagedata-sgieli-yedek/sgie1-config.txt sucessfully
2023-02-13 06:35:49 [Error] [omni.kit.app._impl] [py stderr]:
2023-02-13 06:35:49 [Error] [omni.kit.app._impl]
2023-02-13 06:35:49 [Error] [omni.kit.app._impl] [py stderr]: e[1;31m2023-02-13 09:35:49.755 ERROR extensions/nvdsbase/nvds_scheduler.cpp@184: Failed to set GStreamer pipeline to PLAYINGe[0m
2023-02-13 06:35:49 [Error] [omni.kit.app._impl] [py stderr]:
2023-02-13 06:35:49 [Error] [omni.kit.app._impl]
this is my workflow’s screenshots
first part
second part(Video inference 1 object is the same object, they are all linearly connected)
how can i add my own custom models to video inference object?
Thanks.