Error trying running pretrained models from tlt_pretrained_models using deepstream

[sarvatmak]

HI,

I’m using Jetson Xavier NX Developer Kit and trying to test TrafficCamNet.
I’ve installed the latest DeepStream 5.1 on Jetpack 4.5.1.
I navigated to:-
/opt/nvidia/deepstream/deepstream-5.1/samples/configs/tlt_pretrained_models

From there While running the deepstream-app, I’m getting the following error output:

I ran the code using command:-
deepstream-app -c deepstream_app_source1_trafficcamnet.txt

Warning: ‘input-dims’ parameter has been deprecated. Use ‘infer-dims’ instead.

Using winsys: x11
gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream-5.1/lib/libnvds_mot_klt.so
gstnvtracker: Optional NvMOT_RemoveStreams not implemented
gstnvtracker: Batch processing is OFF
gstnvtracker: Past frame output is OFF
ERROR: Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-5.1/samples/configs/tlt_pretrained_models/…/…/models/tlt_pretrained_models/trafficcamnet/resnet18_trafficcamnet_pruned.etlt_b1_gpu0_int8.engine open error
0:00:01.308713876 10488 0x8088d50 WARN nvinfer gstnvinfer.cpp:616:gst_nvinfer_logger:<primary_gie> 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/configs/tlt_pretrained_models/…/…/models/tlt_pretrained_models/trafficcamnet/resnet18_trafficcamnet_pruned.etlt_b1_gpu0_int8.engine failed
0:00:01.308823413 10488 0x8088d50 WARN nvinfer gstnvinfer.cpp:616:gst_nvinfer_logger:<primary_gie> 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/configs/tlt_pretrained_models/…/…/models/tlt_pretrained_models/trafficcamnet/resnet18_trafficcamnet_pruned.etlt_b1_gpu0_int8.engine failed, try rebuild
0:00:01.308858294 10488 0x8088d50 INFO nvinfer gstnvinfer.cpp:619:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1716> [UID = 1]: 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
parseModel: Failed to open TLT encoded model file /opt/nvidia/deepstream/deepstream-5.1/samples/configs/tlt_pretrained_models/…/…/models/tlt_pretrained_models/trafficcamnet/resnet18_trafficcamnet_pruned.etlt
ERROR: failed to build network since parsing model errors.
ERROR: Failed to create network using custom network creation function
ERROR: Failed to get cuda engine from custom library API
0:00:01.309345678 10488 0x8088d50 ERROR nvinfer gstnvinfer.cpp:613:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1736> [UID = 1]: build engine file failed
Segmentation fault (core dumped)

And other models such as PeopleNet are also not running.
models from configs/deepstream-app run properly.

i have also boosted the clocks using
sudo nvpmodel -m 0
sudo jetson_clocks

ALSO NOTE THAT I HAVE NOT YET CONNECTED ANY CAMERA OR GIVEN ANY VIDEO SOURCE.

Thanks.

[AastaLLL]

Hi,

Deepstream doesn’t contain the model by default to save space.
Please download the model manually before running the pipeline.

You can find the corresponding command in the below file:

/opt/nvidia/deepstream/deepstream-5.1/samples/configs/tlt_pretrained_models/README

For example:

mkdir -p ../../models/tlt_pretrained_models/trafficcamnet && \
    wget https://api.ngc.nvidia.com/v2/models/nvidia/tlt_trafficcamnet/versions/pruned_v1.0/files/resnet18_trafficcamnet_pruned.etlt \
    -O ../../models/tlt_pretrained_models/trafficcamnet/resnet18_trafficcamnet_pruned.etlt && \
    wget https://api.ngc.nvidia.com/v2/models/nvidia/tlt_trafficcamnet/versions/pruned_v1.0/files/trafficnet_int8.txt \
    -O ../../models/tlt_pretrained_models/trafficcamnet/trafficnet_int8.txt

Thanks.

[sarvatmak]

Thanks the issue got resolved i had not downloaded the model just like you said.