I’m trying to install nvidia-tensorrt.But I am getting these errors .Please help ı need solve this.
pip3 install nvidia-tensorrt
Defaulting to user installation because normal site-packages is not writeable
Looking in indexes: Simple index, https://pypi.ngc.nvidia.com
Collecting nvidia-tensorrt
Downloading nvidia-tensorrt-0.0.1.dev5.tar.gz (7.9 kB)
Preparing metadata (setup.py) … error
error: subprocess-exited-with-error
× python setup.py egg_info did not run successfully.
│ exit code: 1
╰─> [17 lines of output]
Traceback (most recent call last):
File “”, line 2, in
File “”, line 34, in
File “/tmp/pip-install-yt2_vwld/nvidia-tensorrt_4a7786637417410d941eec9fc35a411b/setup.py”, line 150, in
raise RuntimeError(open(“ERROR.txt”, “r”).read())
RuntimeError:
###########################################################################################
The package you are trying to install is only a placeholder project on PyPI.org repository.
This package is hosted on NVIDIA Python Package Index.
This package can be installed as:
```
$ pip install nvidia-pyindex
$ pip install nvidia-tensorrt
```
###########################################################################################
[end of output]
note: This error originates from a subprocess, and is likely not a problem with pip.
error: metadata-generation-failed
× Encountered error while generating package metadata.
╰─> See above for output.
note: This is an issue with the package mentioned above, not pip.
hint: See above for details.
I know nothing of that particular package. However, you posted in the Nano forum. Is this the older Nano, or is this the Orin Nano? There is an extreme difference. What L4T release do you have? See “head -n 1 /etc/nv_tegra_release”.
My reason for asking is that Ubuntu 20.04 is not available on an ordinary Nano (it is available on an Orin, but this is not the Orin forum). Nor is CUDA 11 available on ordinary Nano (but it is available on Orin). Anyone answering will need to know if this is Orin, or if it is instead the older Nano.
I already did this.But it doesn’T work still.I downloaded tensorrt in nvidia website and I did all installation.When I tried this command I m taking this output.
$sudo apt install python3-libnvinfer*
Reading package lists… Done
Building dependency tree
Reading state information… Done
Note, selecting ‘python3-libnvinfer’ for glob ‘python3-libnvinfer*’
Note, selecting ‘python3-libnvinfer-dev’ for glob ‘python3-libnvinfer*’
python3-libnvinfer is already the newest version (8.5.2-1+cuda11.4).
python3-libnvinfer-dev is already the newest version (8.5.2-1+cuda11.4).
0 upgraded, 0 newly installed, 0 to remove and 0 not upgraded.
Here, the tensorrt version looks correct as I installed it last, but when I look at it with the jtop command, the tensorrt version appears to be 5.1.1 unrelatedly, I don’t understand why. I did the tensorrt setup and key definition, everything looked fine, but it still doesn’t see nvidia-tensorrt in my code and therefore my code doesn’t work.