Hello friends,
I am an intern at NVIDIA in Santa Clara, CA.
I received the same error message every time when trying to run the sample application included in the DeepStream SDK 2.0 for Tesla:
** ERROR: <parse_config_file:1320>: parse_config_file failed
** ERROR: <main:456>: Failed to parse config file './configs/deepstream-app/source4_720p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt'
Quitting
(deepstream-app:2345): GStreamer-CRITICAL **: gst_element_get_static_pad: assertion 'GST_IS_ELEMENT (element)' failed
(deepstream-app:2345): GStreamer-CRITICAL **: gst_pad_send_event: assertion 'GST_IS_PAD (pad)' failed
(deepstream-app:2345): GStreamer-CRITICAL **: gst_element_set_state: assertion 'GST_IS_ELEMENT (element)' failed
(deepstream-app:2345): GStreamer-CRITICAL **: gst_element_get_bus: assertion 'GST_IS_ELEMENT (element)' failed
(deepstream-app:2345): GStreamer-CRITICAL **: gst_bus_remove_watch: assertion 'GST_IS_BUS (bus)' failed
(deepstream-app:2345): GStreamer-CRITICAL **: gst_object_unref: assertion 'object != NULL' failed
(deepstream-app:2345): GStreamer-CRITICAL **: gst_object_unref: assertion 'object != NULL' failed
App run failed
I am using a Titan X (Pascal) (Could that be an issue?) in Ubuntu 16.04 LTS environment. Following the instruction given by the user guide of DeepStream 2.0, I installed CUDA-9.2 (w/ cuDNN 7.1.4, NCCL 2.2.13 and GPU driver 396.26), TensorRT 4.0.1.6, OpenCV-3.4.0 (using exactly the same commands in the user guide) and all other necessary packages. I created the symlink for libnvcuvide.so as well.
I re-installed my system multiple times to make sure that I followed the instruction in the user guide perfectly.
The command window output for “nvidia-smi”, “nvcc --version”, “dpkg -l | grep TensorRT” and “pkg-config --modversion opencv” are all given as follows.
Thu Jul 5 16:36:00 2018
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 396.26 Driver Version: 396.26 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 TITAN X (Pascal) Off | 00000000:65:00.0 On | N/A |
| 23% 31C P8 18W / 250W | 357MiB / 12192MiB | 8% Default |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Type Process name Usage |
|=============================================================================|
| 0 1128 G /usr/lib/xorg/Xorg 220MiB |
| 0 1789 G /opt/teamviewer/tv_bin/TeamViewer 2MiB |
| 0 1986 G compiz 76MiB |
| 0 2443 G ...-token=4DD2B2A558A8B22E96B9A4C707E64416 55MiB |
+-----------------------------------------------------------------------------+
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2018 NVIDIA Corporation
Built on Wed_Apr_11_23:16:29_CDT_2018
Cuda compilation tools, release 9.2, V9.2.88
ii graphsurgeon-tf 4.1.2-1+cuda9.2 amd64 GraphSurgeon for TensorRT package
ii libnvinfer-dev 4.1.2-1+cuda9.2 amd64 TensorRT development libraries and headers
ii libnvinfer-samples 4.1.2-1+cuda9.2 amd64 TensorRT samples and documentation
ii libnvinfer4 4.1.2-1+cuda9.2 amd64 TensorRT runtime libraries
ii python-libnvinfer 4.1.2-1+cuda9.2 amd64 Python bindings for TensorRT
ii python-libnvinfer-dev 4.1.2-1+cuda9.2 amd64 Python development package for TensorRT
ii python-libnvinfer-doc 4.1.2-1+cuda9.2 amd64 Documention and samples of python bindings for TensorRT
ii python3-libnvinfer 4.1.2-1+cuda9.2 amd64 Python 3 bindings for TensorRT
ii python3-libnvinfer-dev 4.1.2-1+cuda9.2 amd64 Python 3 development package for TensorRT
ii python3-libnvinfer-doc 4.1.2-1+cuda9.2 amd64 Documention and samples of python bindings for TensorRT
ii tensorrt 4.0.1.6-1+cuda9.2 amd64 Meta package of TensorRT
ii uff-converter-tf 4.1.2-1+cuda9.2 amd64 UFF converter for TensorRT package
3.4.0