Device : jetson nano 2gb
Jetpack: 4.5.1
Deepstream: 5.1
SOC : tegra 210
Error:
0:02:53.891197209 3908 0x30a53de0 WARN nvinfer gstnvinfer.cpp:1812:gst_nvinfer_submit_input_buffer: error: streaming stopped, reason error (-5)
Error: gst-stream-error-quark: Internal data stream error. (1): /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(1812): gst_nvinfer_submit_input_buffer (): /GstPipeline:pipeline0/GstNvInfer:secondary3-nvinference-engine:
streaming stopped, reason error (-5)
Command: root@jetson2gb:/opt/nvidia/deepstream/deepstream-5.1/samples/deepstream_python_apps/apps/deepstream-test2# python3 deepstream_test_2.py …/…/…/streams/sample_720p.h264
I have followed all the prerequisits and installed all the deendent modules, yet the python app is giving this error while running the test apps. The same error is present for test_1.py file.
Need help to fix this error and any hints would be wonderful for me to try out.
I had cloned the github repo for this python files to run.
Thanks in advance.
Can you post the whole log?
root@jetson2gb:/opt/nvidia/deepstream/deepstream-5.1/samples/deepstream_python_apps/apps/deepstream-test1# python3 deepstream_test_1.py …/…/…/streams/sample_720p.h264
Creating Pipeline
Creating Source
Creating H264Parser
Creating Decoder
Creating EGLSink
Playing file …/…/…/streams/sample_720p.h264
Adding elements to Pipeline
Linking elements in the Pipeline
Starting pipeline
Using winsys: x11
Opening in BLOCKING MODE
Opening in BLOCKING MODE
ERROR: Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-5.1/samples/deepstream_python_apps/apps/deepstream-test1/…/…/…/…/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine open error
0:00:05.151360970 7812 0x15be1c40 WARN nvinfer gstnvinfer.cpp:616:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1691> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-5.1/samples/deepstream_python_apps/apps/deepstream-test1/…/…/…/…/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine failed
0:00:05.151465266 7812 0x15be1c40 WARN nvinfer gstnvinfer.cpp:616:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1798> [UID = 1]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-5.1/samples/deepstream_python_apps/apps/deepstream-test1/…/…/…/…/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine failed, try rebuild
0:00:05.151503035 7812 0x15be1c40 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1716> [UID = 1]: Trying to create engine from model files
WARNING: INT8 not supported by platform. Trying FP16 mode.
INFO: [TRT]: Some tactics do not have sufficient workspace memory to run. Increasing workspace size may increase performance, please check verbose output.
INFO: [TRT]: Detected 1 inputs and 2 output network tensors.
0:00:40.400924195 7812 0x15be1c40 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1749> [UID = 1]: serialize cuda engine to file: /opt/nvidia/deepstream/deepstream-5.1/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_fp16.engine successfully
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
0:00:41.075795664 7812 0x15be1c40 INFO nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus: [UID 1]: Load new model:dstest1_pgie_config.txt sucessfully
NvMMLiteOpen : Block : BlockType = 261
NVMEDIA: Reading vendor.tegra.display-size : status: 6
NvMMLiteBlockCreate : Block : BlockType = 261
Frame Number=0 Number of Objects=5 Vehicle_count=3 Person_count=2
0:00:41.658635876 7812 0x15559d40 WARN nvinfer gstnvinfer.cpp:1984:gst_nvinfer_output_loop: error: Internal data stream error.
0:00:41.658685518 7812 0x15559d40 WARN nvinfer gstnvinfer.cpp:1984:gst_nvinfer_output_loop: error: streaming stopped, reason error (-5)
Error: gst-stream-error-quark: Internal data stream error. (1): /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(1984): gst_nvinfer_output_loop (): /GstPipeline:pipeline0/GstNvInfer:primary-inference:
streaming stopped, reason error (-5)
would anyone let me know the path where the gst-python package must be present?
Nano is poor. You need to modify dstest1_pgie_config.txt file, change the following lines:
model-file=…/…/…/…/samples/models/Primary_Detector/resnet10.caffemodel
proto-file=…/…/…/…/samples/models/Primary_Detector/resnet10.prototxt
model-engine-file=…/…/…/…/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine
labelfile-path=…/…/…/…/samples/models/Primary_Detector/labels.txt
int8-calib-file=…/…/…/…/samples/models/Primary_Detector/cal_trt.bin
to the lines:
model-file=…/…/…/…/samples/models/Primary_Detector_Nano/resnet10.caffemodel
proto-file=…/…/…/…/samples/models/Primary_Detector_Nano/resnet10.prototxt
model-engine-file=…/…/…/…/samples/models/Primary_Detector_Nano/resnet10.caffemodel_b1_gpu0_int8.engine
labelfile-path=…/…/…/…/samples/models/Primary_Detector_Nano/labels.txt
Some cases may not work with Nano.
I don’t believe its the problem of Nano being poor in performance, the C test apps will give almost 30 fps for 4 batches of video processing, while th python test apps only process 1 batch of video. I think the mistake is somewhere else, maybe when installing the gstreamer python plugin or with the py-bindings.
It generated the same error.
Do you mean C deepstream-test1 app can work?
yes, all the c test apps works without any issues.
Yes, I have the latest code form GitHub from master branch. May I know the exact path where Gst Python v1.14.5 must be installed?
Got the fix, Reinstalled the OS and then just downloaded the .deb deepstream package and installed the 2 dependencies required for that .deb package and then cloned the GitHub python programs and it executed without error. By not installing other prerequisits or dependencies again fixed this issue because all the necessary ones already come with the JetPack.