When installing the ZED SDK, I chose to download the depth model and all models, but the installation was unsuccessful. The following error appeared:
/usr/local/zed/tools/ZED_Diagnostic: error while loading shared libraries: libcudart.so.12: cannot open shared object file: No such file or directory
I have included more detailed error information below. Could you please advise me on how to resolve this issue? Thank you very much!
ray@jetson:~/Downloads$ ./ZED_SDK_Tegra_L4T36.4_v5.0.3.zstd.run
Verifying archive integrity... 100% MD5 checksums are OK. All good.
Uncompressing 'ZED camera SDK by Stereolabs (Use 'sudo apt install zstd' if zstd is not found)' 100%
L4T version 36.4 detected. OK
To continue you have to accept the EULA. Accept [Y/n] ?y
Installing...
ZED SDK will be installed in: /usr/local/zed
[sudo] password for ray:
Sorry, try again.
[sudo] password for ray:
Checking CUDA version...
ERROR : the installer failed to detect the CUDA version (CUDA 12.6 required), make sure it's installed
Do you want to install CUDA 12.6 automatically [Y/n] ?n
The ZED SDK will NOT work without CUDA, Continue [Y/n] ?y
Installing...
Install samples (recommended) [Y/n] ?y
Installation path: /usr/local/zed/samples/
Dependencies installation complete
Do you want to install the Python API (recommended) [Y/n] ?y
Please specify your python executable: python3
Defaulting to user installation because normal site-packages is not writeable
Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
Requirement already satisfied: numpy in /home/ray/.local/lib/python3.10/site-packages (2.2.6)
Defaulting to user installation because normal site-packages is not writeable
Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
Requirement already satisfied: requests in /usr/lib/python3/dist-packages (2.25.1)
-> Downloading to '/tmp/selfgz12350'
Detected platform:
linux_aarch64
Python 3.10
ZED SDK 5.0
-> Checking if https://download.stereolabs.com/zedsdk/5.0/whl/linux_aarch64/pyzed-5.0-cp310-cp310-linux_aarch64.whl exists and is available
-> Found ! Downloading python package into /tmp/selfgz12350/pyzed-5.0-cp310-cp310-linux_aarch64.whl
-> Installing necessary dependencies
Defaulting to user installation because normal site-packages is not writeable
Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
Requirement already satisfied: wheel in /usr/lib/python3/dist-packages (0.37.1)
Defaulting to user installation because normal site-packages is not writeable
Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
Requirement already satisfied: cython in /home/ray/.local/lib/python3.10/site-packages (3.1.2)
Defaulting to user installation because normal site-packages is not writeable
Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
Requirement already satisfied: numpy in /home/ray/.local/lib/python3.10/site-packages (2.2.6)
Defaulting to user installation because normal site-packages is not writeable
Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
Processing ./pyzed-5.0-cp310-cp310-linux_aarch64.whl
Collecting cython>=3.0.0
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/23/3a/5b92bfff9c1cc1179a493684d0e6a893ee7cd69c4f1977813000ea76c5d7/cython-3.1.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (3.2 MB)
Collecting numpy<3.0,>=2.0
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/eb/17/96a3acd228cec142fcb8723bd3cc39c2a474f7dcf0a5d16731980bcafa95/numpy-2.2.6-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (14.3 MB)
Installing collected packages: numpy, cython, pyzed
Attempting uninstall: numpy
Found existing installation: numpy 2.2.6
Uninstalling numpy-2.2.6:
Successfully uninstalled numpy-2.2.6
Attempting uninstall: cython
Found existing installation: Cython 3.1.2
Uninstalling Cython-3.1.2:
Successfully uninstalled Cython-3.1.2
Attempting uninstall: pyzed
Found existing installation: pyzed 5.0
Uninstalling pyzed-5.0:
Successfully uninstalled pyzed-5.0
Successfully installed cython-3.1.2 numpy-2.2.6 pyzed-5.0
Done
To install it later or on a different environment run :
python -m pip install --ignore-installed /tmp/selfgz12350/pyzed-5.0-cp310-cp310-linux_aarch64.whl
The ZED Python API was installed for 'python3'
/sbin/ldconfig.real: /usr/lib/aarch64-linux-gnu/nvidia/libnvisppg.so is not a symbolic link
Do you want to download and optimize the NEURAL Depth models now? These will be required at runtime and will be processed then if not done now, which will extend startup time on first use. [Y/n] ?y
/usr/local/zed/tools/ZED_Diagnostic: error while loading shared libraries: libcudart.so.12: cannot open shared object file: No such file or directory
Do you want to run the ZED Diagnostic to download all AI models [Y/n] ?y
/usr/local/zed/tools/ZED_Diagnostic: error while loading shared libraries: libcudart.so.12: cannot open shared object file: No such file or directory
Do you want to run the ZED Diagnostic to optimize all AI models, it may take a very long time, up to multiple hours but will be done only once. Otherwise it will be optimized just in time when running the ZED SDK [Y/n] ?y
/usr/local/zed/tools/ZED_Diagnostic: error while loading shared libraries: libcudart.so.12: cannot open shared object file: No such file or directory
For GMSL support, please navigate to https://www.stereolabs.com/docs/get-started-with-zed-x/ where you will find compatible drivers and installation instructions.
Please note that installing the 'libv4l-dev' apt package at any point on jetson will break the hardware encoding/decoding support
ZED SDK installation complete, with 1 warning(s)
ray@jetson:~/Downloads$ apt list libv4l-dev
Listing... Done
ray@jetson:~/Downloads$ cat /etc/nv_tegra_release
# R36 (release), REVISION: 4.3, GCID: 38968081, BOARD: generic, EABI: aarch64, DATE: Wed Jan 8 01:49:37 UTC 2025
# KERNEL_VARIANT: oot
TARGET_USERSPACE_LIB_DIR=nvidia
TARGET_USERSPACE_LIB_DIR_PATH=usr/lib/aarch64-linux-gnu/nvidia
ray@jetson:~/Downloads$ nvidia-smi
Mon Jul 7 18:04:58 2025
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 540.4.0 Driver Version: 540.4.0 CUDA Version: 12.6 |
|-----------------------------------------+----------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 Orin (nvgpu) N/A | N/A N/A | N/A |
| N/A N/A N/A N/A / N/A | Not Supported | N/A N/A |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
+---------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=======================================================================================|
| No running processes found |
+---------------------------------------------------------------------------------------+