source8_1080p_dec_infer-resnet_tracker_tiled_display_fp16_tx1.txt doesn’t work.
I tried to run the deepstream-app sample, but an error occurred.
(I tried running the app with sudo, but I ran into a same error.)
**nvidia@nvidia-desktop** : **/opt/nvidia/deepstream/deepstream-4.0/samples/configs/deepstream-app** $ deepstream-app -c source8_1080p_dec_infer-resnet_tracker_tiled_display_fp16_tx1.txt
Creating LL OSD context new
gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream-4.0/lib/libnvds_mot_klt.so
gstnvtracker: Failed to open low-level lib at /opt/nvidia/deepstream/deepstream-4.0/lib/libnvds_mot_klt.so
dlopen error: libvisionworks.so: cannot open shared object file: No such file or directory
gstnvtracker: Failed to initilaize low level lib.
** ERROR: <main:651>: Failed to set pipeline to PAUSED
Quitting
App run failed
I checked /opt/nvidia/deepstream/deepstream-4.0/lib/libnvds_mot_klt.so is exist and its permission is
$ ls -la /opt/nvidia/deepstream/deepstream-4.0/lib/libnvds_mot_klt.so
-rwxrwxrwx 1 root root 2809832 7月 19 2019 **/opt/nvidia/deepstream/deepstream-4.0/lib/libnvds_mot_klt.so**
Incidentally, source30_1080p_dec_infer-resnet_tiled_display_int8.txt works fine.
nvidia@nvidia-desktop:/opt/nvidia/deepstream/deepstream-4.0/samples/configs/deepstream-app$ deepstream-app -c source30_1080p_dec_infer-resnet_tiled_display_int8.txt
Using winsys: x11
Creating LL OSD context new
0:00:01.192300431 2128 0x5e6f990 WARN nvinfer gstnvinfer.cpp:515:gst_nvinfer_logger:<primary_gie_classifier> NvDsInferContext[UID 1]:useEngineFile(): Failed to read from model engine file
0:00:01.192418830 2128 0x5e6f990 INFO nvinfer gstnvinfer.cpp:519:gst_nvinfer_logger:<primary_gie_classifier> NvDsInferContext[UID 1]:initialize(): Trying to create engine from model files
0:00:01.192750061 2128 0x5e6f990 WARN nvinfer gstnvinfer.cpp:515:gst_nvinfer_logger:<primary_gie_classifier> NvDsInferContext[UID 1]:generateTRTModel(): INT8 not supported by platform. Trying FP16 mode.
0:00:54.235784590 2128 0x5e6f990 INFO nvinfer gstnvinfer.cpp:519:gst_nvinfer_logger:<primary_gie_classifier> NvDsInferContext[UID 1]:generateTRTModel(): Storing the serialized cuda engine to file at /opt/nvidia/deepstream/deepstream-4.0/samples/models/Primary_Detector/resnet10.caffemodel_b30_fp16.engine
...
**PERF: 0.00 (0.59) 0.00 (2.48) 0.00 (0.78) 0.00 (0.72) 0.00 (0.53) 0.00 (2.48) 0.00 (0.56) 0.00 (0.78) 0.00 (2.48) 0.00 (1.84) 0.00 (0.90) 0.00 (1.82) 0.00 (0.59) 0.00 (0.72) 0.00 (1.95) 0.00 (1.95) 0.00 (1.82) 0.00 (0.57) 0.00 (1.95) 0.00 (0.53) 0.00 (0.83) 0.00 (0.53) 0.00 (0.53) 0.00 (0.57) 0.00 (0.78) 0.00 (2.38) 0.00 (1.84) 0.00 (1.95) 0.00 (0.56) 0.00 (0.96)
** INFO: <bus_callback:186>: Received EOS. Exiting ...
Quitting
App run successful
information
• Hardware Platform (Jetson / GPU): Jetson TX2
• DeepStream Version: DeepStream 4.0
• JetPack Version (valid for Jetson only): 4.2.1
• TensorRT Version: 5.1.6.1-1+cuda10.0