Hi,
I am getting the following error when I am trying to launch ./ZED_Depth_Viewer:
usr/local/zed/tools$ ./ZED_Depth_Viewer
CUDA error at /builds/sl/ZEDKit/lib/src/sl_core/utils/util.cu:422 code=1(cudaErrorInvalidValue) “cudaCreateTextureObject(tex, &resDesc, &texDesc, NULL)”
CUDA error at /builds/sl/ZEDKit/lib/src/sl_core/utils/util.cu:422 code=1(cudaErrorInvalidValue) “cudaCreateTextureObject(tex, &resDesc, &texDesc, NULL)”
This is the result of installing the zed related jetson orin:
nvidia@ubuntu:~/Downloads$ ./ZED_SDK_Tegra_L4T34.1_v3.7.5.run
Verifying archive integrity… 100% MD5 checksums are OK. All good.
Uncompressing ‘ZED camera SDK by Stereolabs’ 100%
L4T version 34.1 detected. OK
To continue you have to accept the EULA. Accept [Y/n] ?y
Installing…
Installation path: /usr/local/zed
Checking CUDA version…
OK: Found CUDA 11.4
Do you want to also install the static version of the ZED SDK (AI module will still require libsl_ai.so) [Y/n] ?y
Do you want to install the AI module (required for Object detection and Neural Depth, recommended) [Y/n] ?y
Do you want to enable maximum performance mode (recommended)? It provides optimal performance but increases power draw. [Y/n] ?y
NVIDIA Orin Jetson-Small Developer Kit detected
NV Power Mode: MAXN
0
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
Requirement already satisfied: numpy in /home/nvidia/.local/lib/python3.8/site-packages (1.23.1)
→ Downloading to ‘/tmp/selfgz5129’
L4T 34.1
Detected platform:
jetsons
Python 3.8
ZED SDK 3.7
→ Checking if https://download.stereolabs.com/zedsdk/3.7/jetsons/l4t34/py38 exists and is available
→ Found ! Downloading python package into /tmp/selfgz5129/pyzed-3.7-cp38-cp38-linux_aarch64.whl
→ Installing necessary dependencies
Requirement already satisfied: wheel in /usr/lib/python3/dist-packages (0.34.2)
Requirement already satisfied: cython in /home/nvidia/.local/lib/python3.8/site-packages (0.29.30)
Requirement already satisfied: numpy in /home/nvidia/.local/lib/python3.8/site-packages (1.23.1)
Processing ./pyzed-3.7-cp38-cp38-linux_aarch64.whl
Collecting cython>=0.28
Using cached Cython-0.29.30-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl (1.8 MB)
Collecting numpy>=1.13
Using cached numpy-1.23.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (14.0 MB)
Installing collected packages: numpy, cython, pyzed
Successfully installed cython-0.29.30 numpy-1.23.1 pyzed-3.7
Done
To install it later or on a different environment run :
python -m pip install --ignore-installed /tmp/selfgz5129/pyzed-3.7-cp38-cp38-linux_aarch64.whl
The ZED Python API was installed for ‘python3’, when using conda environement or virtualenv, the ZED Python API may need to be resetup to be available (using ‘python /usr/local/zed/get_python_api.py’)
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 !
Can you please help with that?
Thank you,