Failed to run sample deepstream_python_apps in Deepstream SDK 5.0 on Jetson Nano

Hi

I have taken the DLI course and after that I reflashed my sd card with deepstream 5.0 to build my own apps.

Today when I am trying to run sample apps in deepstreram_python_apps I got this error:
“Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-5.0/sources/deepstream_python_apps/apps/deepstream-test1-rtsp-out/…/…/…/…/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine open error”

I know jetson nano should run in fp16 mode, but how can I find the right engine? I didn’t find any fp16 engine in the “…/samples/models/Primary_Detector/” directory. I know in DLI course there is one there but I can’t find it in deepstream 5.0 now. Does this mean that the new sample apps currently do not support jetson nano?

The following is my log.

`Creating Pipeline

Creating Source

Creating H264Parser

Creating Decoder

Creating H264 Encoder
Creating H264 rtppay
Playing file /home/maxister/backup/CSI-Camera/my_prj/videos/traffic_day.mp4
Adding elements to Pipeline

Linking elements in the Pipeline

*** DeepStream: Launched RTSP Streaming at rtsp://localhost:8554/ds-test ***

Starting pipeline

Opening in BLOCKING MODE
Opening in BLOCKING MODE
ERROR: Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-5.0/sources/deepstream_python_apps/apps/deepstream-test1-rtsp-out/…/…/…/…/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine open error
0:00:04.514949997 30973 0x3b362070 WARN nvinfer gstnvinfer.cpp:616:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1690> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-5.0/sources/deepstream_python_apps/apps/deepstream-test1-rtsp-out/…/…/…/…/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine failed
0:00:04.515024426 30973 0x3b362070 WARN nvinfer gstnvinfer.cpp:616:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1797> [UID = 1]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-5.0/sources/deepstream_python_apps/apps/deepstream-test1-rtsp-out/…/…/…/…/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine failed, try rebuild
0:00:04.515057447 30973 0x3b362070 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1715> [UID = 1]: Trying to create engine from model files
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.
ERROR: Serialize engine failed because of file path: /opt/nvidia/deepstream/deepstream-5.0/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_fp16.engine opened error
0:00:37.653768266 30973 0x3b362070 WARN nvinfer gstnvinfer.cpp:616:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1743> [UID = 1]: failed to serialize cude engine to file: /opt/nvidia/deepstream/deepstream-5.0/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

0:00:38.063726840 30973 0x3b362070 INFO nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus: [UID 1]: Load new model:dstest1_pgie_config.txt sucessfully
Error: gst-stream-error-quark: No valid frames found before end of stream (5): gstbaseparse.c(3603): gst_base_parse_loop (): /GstPipeline:pipeline0/GstH264Parse:h264-parser`

Thanks!

after model build, you will find the engine file saved in place samples/models/Primary_Detector/
you could run using super power, add sudo before the command.
python test1 sample only accept h264 elementary stream, you may use test3 sample which accept any type of input (e.g. RTSP/File), any GStreamer
supported container format, and any codec can be used as input.