Running Deepstream_python_apps on deepstream 6.0.1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) Xavier nx
• DeepStream Version 6.0.1
• JetPack Version (valid for Jetson only) 4.6.1
• TensorRT Version 8.2.1-1+cuda10.2
• Issue Type( questions, new requirements, bugs) Questions

im trying to run deepstream_launchpad.ipynb from

im getting file not found errors

Creating Pipeline

Creating streammux

Creating source_bin 0

Creating source bin
source-bin-00
Creating source_bin 1

Creating source bin
source-bin-01
Creating source_bin 2

Creating source bin
source-bin-02
Creating source_bin 3

Creating source bin
source-bin-03
Creating nvinfer (PGIE)

WARNING: Overriding infer-config batch-size 30 with number of sources 4

Creating nvtracker

Creating nvinfer (SGIE1)

Creating nvinfer (SGIE2)

Creating tiler

Creating nvvidconv

Creating nvosd

Creating nvvidconv

Creating nvv4l2h264enc

Creating qtmux

Creating h264parse

Creating FileSink

Starting pipeline

Opening in BLOCKING MODE
ERROR: Deserialize engine failed because file path: /home/aaeon/deepstream_python_apps/notebooks/configs/…/…/…/…/samples/models/Secondary_VehicleTypes/resnet18_vehicletypenet.etlt_b16_gpu0_int8.engine open error
0:00:04.541544798 22501 0x217b1590 WARN nvinfer gstnvinfer.cpp:635:gst_nvinfer_logger: NvDsInferContext[UID 3]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1889> [UID = 3]: deserialize engine from file :/home/aaeon/deepstream_python_apps/notebooks/configs/…/…/…/…/samples/models/Secondary_VehicleTypes/resnet18_vehicletypenet.etlt_b16_gpu0_int8.engine failed
0:00:04.560121373 22501 0x217b1590 WARN nvinfer gstnvinfer.cpp:635:gst_nvinfer_logger: NvDsInferContext[UID 3]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1996> [UID = 3]: deserialize backend context from engine from file :/home/aaeon/deepstream_python_apps/notebooks/configs/…/…/…/…/samples/models/Secondary_VehicleTypes/resnet18_vehicletypenet.etlt_b16_gpu0_int8.engine failed, try rebuild
0:00:04.560225725 22501 0x217b1590 INFO nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger: NvDsInferContext[UID 3]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1914> [UID = 3]: Trying to create engine from model files
WARNING: INT8 calibration file not specified/accessible. INT8 calibration can be done through setDynamicRange API in ‘NvDsInferCreateNetwork’ implementation
NvDsInferCudaEngineGetFromTltModel: Failed to open TLT encoded model file /home/aaeon/deepstream_python_apps/notebooks/configs/…/…/…/…/samples/models/Secondary_VehicleTypes/resnet18_vehicletypenet.etlt
ERROR: Failed to create network using custom network creation function
ERROR: Failed to get cuda engine from custom library API
0:00:05.060526413 22501 0x217b1590 ERROR nvinfer gstnvinfer.cpp:632:gst_nvinfer_logger: NvDsInferContext[UID 3]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1934> [UID = 3]: build engine file failed
ERROR: [TRT]: 2: [logging.cpp::decRefCount::61] Error Code 2: Internal Error (Assertion mRefCount > 0 failed. )
corrupted size vs. prev_size

my question is , as my deepstream does not have the resnet18_trafficcamnet.etlt_b1_gpu0_int8.engine,resnet18_trafficcamnet.etlt, files

where do i get these files ?

these files are not present in
/opt/nvidia/deepstream/deepstream-6.0/samples/models/Secondary_VehicleTypes$ ls
cal_trt.bin labels.txt mean.ppm resnet18.caffemodel resnet18.prototxt

Did you install Deepstream 6.0.1 on your Xavier NX?
Please checkout tag v1.1.1 in the repo which is for DeepStream 6.0.1. deepstream_launchpad.ipynb was only added since DeepStream 6.3 (tag v1.1.8).

Two comments:

  1. Please clone the repo to /opt/nvidia/deepstream/deepstream-6.0/sources/deepstream_python_apps, refer the guide here: deepstream_python_apps/HOWTO.md at master · NVIDIA-AI-IOT/deepstream_python_apps · GitHub
  2. The model file should exist in directory /opt/nvidia/deepstream/deepstream-6.0/samples/models/Secondary_VehicleTypes if DeepStream is installed correctly.

hey @yingliu
Thank you for your response.
I am using a vendor product and deepstream 6.0.1 came preinstalled.
i did checkout the v1.1.1 tag and tried to run with
python3 deepstream_test_1.py …/…/…/…/samples/streams/sample_720p.h264

also had to install pyds from here DeepStream SDK FAQ - #22 by mchi

And it worked!

Thank you for the support.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.