i tried to run deepstream-app -c source4_720p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt this demo and found it could not work well.
debug information like blow:
root@hite-All-Series:/home/DeepStream_Release/samples/configs/deepstream-app# deepstream-app -c source4_720p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt
** ERROR: <create_primary_gie_bin:96>: Failed to create ‘primary_gie_classifier’
** ERROR: <create_primary_gie_bin:150>: create_primary_gie_bin failed
** ERROR: <create_pipeline:957>: create_pipeline failed
** ERROR: main:544: Failed to create pipeline
Quitting
App run failed
i have checked my tensorRT
root@hite-All-Series:/opt# dpkg -l | grep TensorRT
ii libnvinfer-dev 5.0.2-1+cuda10.0 amd64 TensorRT development libraries and headers
ii libnvinfer-samples 5.0.2-1+cuda10.0 all TensorRT samples and documentation
ii libnvinfer5 5.0.2-1+cuda10.0 amd64 TensorRT runtime libraries
ii python-libnvinfer 5.0.2-1+cuda10.0 amd64 Python bindings for TensorRT
ii python-libnvinfer-dev 5.0.2-1+cuda10.0 amd64 Python development package for TensorRT
ii tensorrt 5.0.2.6-1+cuda10.0 amd64 Meta package of TensorRT
it’s there any reason for this problem? thanks for help
hi amycao
log as blow:
root@hite-All-Series:/home/DeepStream_Release/samples/configs/deepstream-app# deepstream-app -c source4_720p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt
Warning. Could not open model engine file /home/DeepStream_Release/samples/configs/deepstream-app/…/…/models/Secondary_CarMake/resnet18.caffemodel_b16_int8.engine
Generating new TRT model engine
Using INT8 data type.
Warning: Flatten layer ignored. TensorRT implicitly flattens input to FullyConnected layers, but in other circumstances this will result in undefined behavior.
Warning. Could not open model engine file /home/DeepStream_Release/samples/configs/deepstream-app/…/…/models/Secondary_CarColor/resnet18.caffemodel_b16_int8.engine
Generating new TRT model engine
Using INT8 data type.
Warning: Flatten layer ignored. TensorRT implicitly flattens input to FullyConnected layers, but in other circumstances this will result in undefined behavior.
Warning. Could not open model engine file /home/DeepStream_Release/samples/configs/deepstream-app/…/…/models/Secondary_VehicleTypes/resnet18.caffemodel_b16_int8.engine
Generating new TRT model engine
Using INT8 data type.
Warning: Flatten layer ignored. TensorRT implicitly flattens input to FullyConnected layers, but in other circumstances this will result in undefined behavior.
Warning. Could not open model engine file /home/DeepStream_Release/samples/configs/deepstream-app/…/…/models/Primary_Detector/resnet10.caffemodel_b4_int8.engine
Generating new TRT model engine
Using INT8 data type.
^C** ERROR: <_intr_handler:133>: User Interrupted…
NOTE: To expand a source in the 2D tiled display and view object details, left-click on the source.
To go back to the tiled display, right-click anywhere on the window.
linux - What does .cache do? It consumes a huge disk space - Super User,
the link may help you, when your system environments have some changes, something like if you have some
new binaries updated, then you should remove the cache for gstreamer, ~/.cache/gstreamer-1.0/, reload
everything needed for app run.