please install cuda 10.1 and try again.
Ok. I am using this CUDA 10.2 with OpenCV and CuDNN combination for development. I can’t remove CUDA 10.02, but I think I can install another CUDA version 10.1 and use it in virtual environment for DeepStream Python setup.
@Amycao, I have downloaded the docker image DeepStream | NVIDIA NGC and tried to run the C samples. Now this docker image have all required Cuda and TensorRT versions for Deepstream 4.0.2. Still the C samples are not working.
$ deepstream-app -c ~/deepstream_sdk_v4.0.2_x86_64/samples/configs/deepstream-app/config_infer_primary.txt ** ERROR: <create_multi_source_bin:714>: Failed to create element 'src_bin_muxer' ** ERROR: <create_multi_source_bin:777>: create_multi_source_bin failed ** ERROR: <create_pipeline:1045>: create_pipeline failed ** ERROR: <main:632>: Failed to create pipeline Quitting App run failed
And when tried to run Python samples, got below error:
$ python3 deepstream_test_1.py ~/deepstream_sdk_v4.0.2_x86_64/samples/streams/sample_720p.h264
Creating Pipeline Creating Source Creating H264Parser Creating Decoder Unable to create Nvv4l2 Decoder Unable to create NvStreamMux Unable to create pgie Unable to create nvvidconv Creating EGLSink Playing file /root/deepstream_sdk_v4.0.2_x86_64/samples/streams/sample_720p.h264 Traceback (most recent call last): File "deepstream_test_1.py", line 263, in <module> sys.exit(main(sys.argv)) File "deepstream_test_1.py", line 196, in main streammux.set_property('width', 1920) AttributeError: 'NoneType' object has no attribute 'set_property'
When I downloaded the docker, install.sh was missing from deepstream sdk folder and I already tried to clear the cache sudo rm ${HOME}/.cache/gstreamer-1.0/registry.x86_64.bin
Please help me to setup deepstream setup at least in this docker image on my Ubuntu 18.04 Desktop.
Thanks,
Archana
config_infer_primary.txt is for nvinfer, you should use config source***
Ho @Amycao,
I tried below source*** configs, but all have the same output:
deepstream-app -c ~/deepstream_sdk_v4.0.2_x86_64/samples/configs/deepstream-app/source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8_gpu1.txt deepstream-app -c ~/deepstream_sdk_v4.0.2_x86_64/samples/configs/deepstream-app/source30_1080p_dec_infer-resnet_tiled_display_int8.txt deepstream-app -c ~/deepstream_sdk_v4.0.2_x86_64/samples/configs/deepstream-app/source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt No protocol specified No protocol specified No protocol specified No protocol specified No protocol specified No protocol specified ** ERROR: <main:651>: Failed to set pipeline to PAUSED Quitting App run failed
If you not change the config, the output will be onto display, if you not set display environments, the error like this, you can change sink type to 1 Fakesink or 3 File.
[sink0]
enable=1
#Type - 1=FakeSink 2=EglSink 3=File
type=1
or
[sink1]
enable=1
type=3
Hi @Amycao,
Changing below lines, worked for me.
[sink0]
enable=1
#Type - 1=FakeSink 2=EglSink 3=File
type=1
Thanks,
Archana