I run JP 5.1.2 and all seems to install fine but deepstream-app complaints about deepstream-app: error while loading shared libraries: libyaml-cpp.so.0.7: cannot open shared object file: No such file or directory
I have tried building from source and install using apt, but apt does not recognize the library.
Any ideas?
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
• Hardware Platform (Jetson / GPU) Jetson AGX Orin 64
• DeepStream Version deepstream_sdk_v6.4.0_jetson.tbz2
• JetPack Version (valid for Jetson only) JP 5.1.2
• TensorRT Version ibnvinfer-bin 8.5.2-1+cuda11.4 arm64 TensorRT binaries
• NVIDIA GPU Driver Version (valid for GPU only) I dont know where to find that. Preinstalled from supplier, silicon highway
• Issue Type( questions, new requirements, bugs) I get the error as above. I want to run deepstream-app and also deepstream in python. deepstream-app: error while loading shared libraries: libyaml-cpp.so.0.7: cannot open shared object file: No such file or directory
• 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) I dont know. I follow the installation instructions from your website for deepstream SDK and it does not work.
• 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
No pipline, just trying to run deepstream-app without arguments.
Trying to run python sample app I get errors to.(good that you updated pyds to be installed with pip) python3 deepstream_test_1.py /opt/nvidia/deepstream/deepstream-6.4/samples/streams/sample_1080p_h264.h264
Creating Pipeline
Creating Source
Creating H264Parser
Creating Decoder
Unable to create NvStreamMux
Unable to create pgie
Unable to create nvvidconv
Unable to create nvosd
Creating nv3dsink
Playing file /opt/nvidia/deepstream/deepstream-6.4/samples/streams/sample_1080p_h264.h264
None
Traceback (most recent call last):
File “deepstream_test_1.py”, line 259, in
sys.exit(main(sys.argv))
File “deepstream_test_1.py”, line 197, in main
streammux.set_property(‘width’, 1920)
AttributeError: ‘NoneType’ object has no attribute 'set_property
Unable to create nvosd
I am reinstalling a third system to work with python deepstream. You are more than welcome to give me an official guide and I will let you know where it fails.
I have now a newly flashed Jetson AGX Orin 64 devkit using SDK Manager and have:
Ubuntu 20.04
Jetpack 5.1.2
Deepstream 6.3 (installed from SDK Manager)
I run deepstream-app and I get dependency missing. How do I proceed?
I give you the opportunity to give me a strep by step guide to follow. What I understand
is that deepstream should be installed and ready to be used. But that is not the case.
Hi,
I have now a newly flashed Jetson AGX Orin 64 devkit using SDK Manager and have:
Ubuntu 20.04
Jetpack 5.1.2
Deepstream 6.3 (installed from SDK Manager)
I run deepstream-app and I get dependency missing. How do I proceed?
I give you the opportunity to give me a strep by step guide to follow. What I understand
is that deepstream should be installed and ready to be used. But that is not the case.
I got the deepstream-app to work by installing these missing dependencies and compiling the source:
libgstrtspserver-1.0-0
libjansson4
The rest of the dependencies already exists, so they must come with SDK Manager, but why those two are not included beats me??? Please explain?
I get this warning running:
sudo ./deepstream-test1-app dstest1_config.yml
WARNING: [TRT]: Unknown embedded device detected. Using 59660MiB as the allocation cap for memory on embedded devices.
But after building the engine file it runs inference on the h264 file.
For the first setup I made and got it working I have never gotten ridden of the warnings and why it cant reuse the engine file. I have chmoded the location where I store the engine file since the deepstream-6.3 location is not accessable for the user.
WARNING: Deserialize engine failed because file path: /mnt/M2Disk/resnet10/resnet10.caffemodel_b1_gpu0_int8.engine open error
0:00:03.304068093 10172 0xaaaaf0c21780 WARN nvinfer gstnvinfer.cpp:679:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1976> [UID = 1]: deserialize engine from file :/mnt/M2Disk/resnet10/resnet10.caffemodel_b1_gpu0_int8.engine failed
0:00:03.480228165 10172 0xaaaaf0c21780 WARN nvinfer gstnvinfer.cpp:679:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2081> [UID = 1]: deserialize backend context from engine from file :/mnt/M2Disk/resnet10/resnet10.caffemodel_b1_gpu0_int8.engine failed, try rebuild
0:00:03.480277925 10172 0xaaaaf0c21780 INFO nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:2002> [UID = 1]: Trying to create engine from model files
WARNING: [TRT]: The implicit batch dimension mode has been deprecated. Please create the network with NetworkDefinitionCreationFlag::kEXPLICIT_BATCH flag whenever possible.
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 document you refer to is for DS-6.4, but you installed DS-6.3.DS-6.4 requires ubuntu 22.04, so some library versions are different.