root@dell:/opt/nvidia/deepstream/deepstream-8.0/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream# python3 deepstream_imagedata-multistream.py rtsp://127.0.0.1/video1 rtsp://127.0.0.1/video2 frames4
Frames will be saved in frames4
Creating Pipeline
Creating streamux
Creating source_bin 0
Creating source bin
source-bin-00
Creating source_bin 1
Creating source bin
source-bin-01
Creating Pgie
Creating nvvidconv1
Creating filter1
Creating tiler
Creating nvvidconv
Creating nvosd
ERROR: Getting cuda device property failed: 35
Creating EGLSink
Atleast one of the sources is live
WARNING: Overriding infer-config batch-size 1 with number of sources 2
ERROR: Getting cuda device property failed: 35
Traceback (most recent call last):
File "/opt/nvidia/deepstream/deepstream-8.0/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream/deepstream_imagedata-multistream.py", line 459, in <module>
sys.exit(main(sys.argv))
^^^^^^^^^^^^^^
File "/opt/nvidia/deepstream/deepstream-8.0/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream/deepstream_imagedata-multistream.py", line 393, in main
mem_type = int(pyds.NVBUF_MEM_CUDA_UNIFIED)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
AttributeError: module 'pyds' has no attribute 'NVBUF_MEM_CUDA_UNIFIED'
Additional Information:
My NVIDIA driver 535.274.02 worked fine with DeepStream 7.1, but it seems incompatible with DeepStream 8.0.
I also tried to install NVIDIA driver 570.133.20 to match DeepStream 8.0 requirements, but I was unable to install it successfully.
How to Solve failed (35) CUDA Error and Fix Missing NVBUF_MEM_CUDA_UNIFIED in pyds in DeepStream 8.0?
However, when I run the multi-stream Python sample (deepstream_imagedata-multistream.py), I encounter errors:
Frames will be saved in frames4
Creating Pipeline
Creating streamux
Creating source_bin 0
Creating source bin
source-bin-00
Creating source_bin 1
Creating source bin
source-bin-01
Creating Pgie
Creating nvvidconv1
Creating filter1
Creating tiler
Creating nvvidconv
Creating nvosd
ERROR: Getting cuda device property failed: 35
Creating EGLSink
Atleast one of the sources is live
WARNING: Overriding infer-config batch-size 1 with number of sources 2
ERROR: Getting cuda device property failed: 35
Adding elements to Pipeline
Linking elements in the Pipeline
Now playing...
1 : rtsp://127.0.0.1/video1
2 : rtsp://127.0.0.1/video2
Starting pipeline
WARNING: ../nvdsinfer/nvdsinfer_model_builder.cpp:1261 Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-8.0/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream/../../../../samples/models/Primary_Detector/resnet18_trafficcamnet_pruned.onnx_b1_gpu0_fp16.engine open error
0:00:00.301037719 649 0xb7fe850 WARN nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:2097> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-8.0/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream/../../../../samples/models/Primary_Detector/resnet18_trafficcamnet_pruned.onnx_b1_gpu0_fp16.engine failed
0:00:00.301052316 649 0xb7fe850 WARN nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2202> [UID = 1]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-8.0/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream/../../../../samples/models/Primary_Detector/resnet18_trafficcamnet_pruned.onnx_b1_gpu0_fp16.engine failed, try rebuild
0:00:00.301059179 649 0xb7fe850 INFO nvinfer gstnvinfer.cpp:685:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:2123> [UID = 1]: Trying to create engine from model files
0:00:27.132126717 649 0xb7fe850 INFO nvinfer gstnvinfer.cpp:685:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:2155> [UID = 1]: serialize cuda engine to file: /opt/nvidia/deepstream/deepstream-8.0/samples/models/Primary_Detector/resnet18_trafficcamnet_pruned.onnx_b2_gpu0_fp16.engine successfully
INFO: ../nvdsinfer/nvdsinfer_model_builder.cpp:363 [FullDims Engine Info]: layers num: 3
0 INPUT kFLOAT input_1:0 3x544x960 min: 1x3x544x960 opt: 2x3x544x960 Max: 2x3x544x960
1 OUTPUT kFLOAT output_cov/Sigmoid:0 4x34x60 min: 0 opt: 0 Max: 0
2 OUTPUT kFLOAT output_bbox/BiasAdd:0 16x34x60 min: 0 opt: 0 Max: 0
0:00:27.240286391 649 0xb7fe850 INFO nvinfer gstnvinfer_impl.cpp:343:notifyLoadModelStatus:<primary-inference> [UID 1]: Load new model:dstest_imagedata_config.txt sucessfully
Decodebin child added: source
ERROR: Getting cuda device property failed: 35
Decodebin child added: source
ERROR: Getting cuda device property failed: 35
**PERF: {'stream0': 0.0, 'stream1': 0.0}
Error: gst-resource-error-quark: Could not open resource for reading and writing. (7): ../gst/rtsp/gstrtspsrc.c(8442): gst_rtspsrc_retrieve_sdp (): /GstPipeline:pipeline0/GstBin:source-bin-00/GstURIDecodeBin:uri-decode-bin/GstRTSPSrc:source:
Failed to connect. (Generic error)
Exiting app
ERROR: Getting cuda device property failed: 35
Error: gst-resource-error-quark: Could not open resource for reading and writing. (7): ../gst/rtsp/gstrtspsrc.c(8442): gst_rtspsrc_retrieve_sdp (): /GstPipeline:pipeline0/GstBin:source-bin-00/GstURIDecodeBin:uri-decode-bin/GstRTSPSrc:source: Failed to connect. (Generic error) Exiting app
Refer to this topic. you can try to update CUDA toolkit. Use docker is a better choice, the corresponding CUDA toolkit is already installed in the Docker image.
Make sure your RTSP source is working; you can test it using a local file first.
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.
