runnig by testing both as sudo and user:
python3 deepstream_test_1.py /opt/nvidia/deepstream/deepstream/samples/streams/sample_1080p_h264.mp4
ERROR:
Opening in BLOCKING MODE
0:00:00.310888790 11235 0xa036190 WARN nvinfer gstnvinfer.cpp:677:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1170> [UID = 1]: Warning, OpenCV has been deprecated. Using NMS for clustering instead of cv::groupRectangles with topK = 20 and NMS Threshold = 0.5
WARNING: Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-6.2/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine open error
0:00:03.491444604 11235 0xa036190 WARN nvinfer gstnvinfer.cpp:677:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1897> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-6.2/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine failed
0:00:03.696750652 11235 0xa036190 WARN nvinfer gstnvinfer.cpp:677:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2002> [UID = 1]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-6.2/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine failed, try rebuild
0:00:03.696811516 11235 0xa036190 INFO nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1923> [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.
WARNING: INT8 calibration file not specified. Trying FP16 mode.
WARNING: [TRT]: TensorRT encountered issues when converting weights between types and that could affect accuracy.
WARNING: [TRT]: If this is not the desired behavior, please modify the weights or retrain with regularization to adjust the magnitude of the weights.
WARNING: [TRT]: Check verbose logs for the list of affected weights.
WARNING: [TRT]: - 16 weights are affected by this issue: Detected subnormal FP16 values.
WARNING: [TRT]: - 13 weights are affected by this issue: Detected values less than smallest positive FP16 subnormal value and converted them to the FP16 minimum subnormalized value.
WARNING: Serialize engine failed because of file path: /opt/nvidia/deepstream/deepstream-6.2/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_fp16.engine opened error
0:00:46.629952180 11235 0xa036190 WARN nvinfer gstnvinfer.cpp:677:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1950> [UID = 1]: failed to serialize cude engine to file: /opt/nvidia/deepstream/deepstream-6.2/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_fp16.engine
INFO: [Implicit Engine Info]: layers num: 3
0 INPUT kFLOAT input_1 3x368x640
1 OUTPUT kFLOAT conv2d_bbox 16x23x40
2 OUTPUT kFLOAT conv2d_cov/Sigmoid 4x23x40
0:00:46.889340544 11235 0xa036190 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus: [UID 1]: Load new model:dstest1_pgie_config.txt sucessfully
Error: gst-stream-error-quark: Internal data stream error. (1): gstbaseparse.c(3666): gst_base_parse_loop (): /GstPipeline:pipeline0/GstH264Parse:h264-parser:
streaming stopped, reason not-negotiated (-4)
nvstreammux: Successfully handled EOS for source_id=0
I have tried a config-file with the deepstream-app and that work. The video I use is the particular file is used in the deepstream-app test and works. I see the cars and people. I also tried another source by adding my v4l2 camera and it works. Running the test app with the same configuration and files/camera in python app does not work. I have built the pyds from the 6.2 (Verision 1.1.8).
h264 file is pure h264 stream, while mp4 is a container which mux other information, a demux is needed to get the h264 stream in it.
Can you try this？just use the file with postfix “h264”.
Thank you! now it works but with the warnings. It should then work just fine with gstreamer as long as I fix the pipeline. Thanks!
How can I fix this open engine error?
Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-6.2/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine open error
0:00:00.264654822 3462 0x385c3590 WARN nvinfer gstnvinfer.cpp:677:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1170> [UID = 1]: Warning, OpenCV has been deprecated. Using NMS for clustering instead of cv::groupRectangles with topK = 20 and NMS Threshold = 0.5
WARNING: Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-6.2/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine open error
0:00:04.167325593 3462 0x385c3590 WARN nvinfer gstnvinfer.cpp:677:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1897> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-6.2/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine failed
0:00:04.366508454 3462 0x385c3590 WARN nvinfer gstnvinfer.cpp:677:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2002> [UID = 1]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-6.2/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine failed, try rebuild
0:00:04.366579652 3462 0x385c3590 INFO nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1923> [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.
WARNING: INT8 calibration file not specified. Trying FP16 mode.
WARNING: [TRT]: TensorRT encountered issues when converting weights between types and that could affect accuracy.
WARNING: [TRT]: If this is not the desired behavior, please modify the weights or retrain with regularization to adjust the magnitude of the weights.
WARNING: [TRT]: Check verbose logs for the list of affected weights.
WARNING: [TRT]: - 16 weights are affected by this issue: Detected subnormal FP16 values.
WARNING: [TRT]: - 13 weights are affected by this issue: Detected values less than smallest positive FP16 subnormal value and converted them to the FP16 minimum subnormalized value.
WARNING: Serialize engine failed because of file path: /opt/nvidia/deepstream/deepstream-6.2/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_fp16.engine opened error
0:00:52.728890919 3462 0x385c3590 WARN nvinfer gstnvinfer.cpp:677:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1950> [UID = 1]: failed to serialize cude engine to file: /opt/nvidia/deepstream/deepstream-6.2/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_fp16.engine
INFO: [Implicit Engine Info]: layers num: 3
0 INPUT kFLOAT input_1 3x368x640
1 OUTPUT kFLOAT conv2d_bbox 16x23x40
2 OUTPUT kFLOAT conv2d_cov/Sigmoid 4x23x40
0:00:53.005558631 3462 0x385c3590 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus: [UID 1]: Load new model:dstest1_pgie_config.txt sucessfully
NvMMLiteOpen : Block : BlockType = 261
This is by default the engine file config is set model-engine-file=../../../../samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine, but it doesn’t exist until it is created dring the first run. You can find this file after the sample program runs correctly, and if you run this program again, it can deserialize the engine file correctly without this warning.
It’s not an error, it’s just that the engine files cannot be found. Since deepstream is installed in /opt, only the root user has write access to this folder.
Hi, I tried to sudo it and it did not change the outcome. Still the warnings.
Blockquote
Opening in BLOCKING MODE
0:00:00.294466952 6382 0x3ea6f590 WARN nvinfer gstnvinfer.cpp:677:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1170> [UID = 1]: Warning, OpenCV has been deprecated. Using NMS for clustering instead of cv::groupRectangles with topK = 20 and NMS Threshold = 0.5
WARNING: Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-6.2/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine open error
0:00:03.610929666 6382 0x3ea6f590 WARN nvinfer gstnvinfer.cpp:677:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1897> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-6.2/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine failed
0:00:03.811346240 6382 0x3ea6f590 WARN nvinfer gstnvinfer.cpp:677:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2002> [UID = 1]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-6.2/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine failed, try rebuild
0:00:03.811418912 6382 0x3ea6f590 INFO nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1923> [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.
WARNING: INT8 calibration file not specified. Trying FP16 mode.
^C^CWARNING: [TRT]: TensorRT encountered issues when converting weights between types and that could affect accuracy.
WARNING: [TRT]: If this is not the desired behavior, please modify the weights or retrain with regularization to adjust the magnitude of the weights.
WARNING: [TRT]: Check verbose logs for the list of affected weights.
WARNING: [TRT]: - 16 weights are affected by this issue: Detected subnormal FP16 values.
WARNING: [TRT]: - 13 weights are affected by this issue: Detected values less than smallest positive FP16 subnormal value and converted them to the FP16 minimum subnormalized value.
0:00:49.135104401 6382 0x3ea6f590 INFO nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1955> [UID = 1]: serialize cuda engine to file: /opt/nvidia/deepstream/deepstream-6.2/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_fp16.engine successfully
I set the access rights to the folder and it does not work. BUT it does run, it just takes a while and I can live with that for now. Thanks for the support. please engage in my more problematic topic of gst pipline :D