Error Importing tensorrt

gustavvz · January 9, 2018, 10:35am

I want to use tensorrt to convert a tf model to uff.

I got CUDA 9 and cuDNN 7 installed on my x86 Host Machine, i installed TensorRT and pyCuda according to the official installation guide using the debian: http://developer2.download.nvidia.com/compute/machine-learning/tensorrt/secure/3.0/ga/TensorRT-Installation-Guide.pdf?EjPPsmXia1_6e64BqMgr4lvVg5x5wxt4rRsF0xY80vveGy6Vr7Ds6cXBjzwGzTO74mxnw-mXs6LoZpq_1T3cZnlmjXRZuIBRxTtqmS2CN54S6L8lE_LBVOZW2fhnoyaoh-IIgK-vQqoQk8HdehJuFBvTsEZsI_CayclUDD4UmAjLsg2H7yFRKYUDgowx3A

But when i run the Python API i get following Error:

File "/home/gustav/workspace/TensorRT/tf_to_trt.py", line 10, in <module>
    import tensorrt as trt

  File "/usr/lib/python2.7/dist-packages/tensorrt/__init__.py", line 53, in <module>
    from tensorrt import __versions__

ImportError: cannot import name __versions__

Any Solutions to that? Inside the versions file stands following:

'''
Version information for the TensorRT Python API
'''
package_version = '3.0.1'
infer_lib_version = 301
so_version = '4.0.1'
cudnn_version = '7.0'

dusty_nv · January 9, 2018, 4:36pm

Hi gustavvz, are you still experiencing the issue, since you more recently posted this topic about using the UFF converter?

[url]Converting TF Model to TensorRT UFF Format - Jetson TX2 - NVIDIA Developer Forums

If you did something to resolve your environment of the ImportError, can you post it to this thread? Thanks!

gustavvz · January 10, 2018, 8:20am

Hey dusty_nv, yes i found a very simple solution as it is written in your TensorRT Release Notes (maybe this usefull file should be highlighted a little bit more :) )

You have to import uff and tensorflow before you import tensorrrt (even if you dont use tensorflow in the code)

The reason is said to be:

“When using the TensorRT APIs from Python, import the tensorflow and uff
modules before importing the tensorrt module. This is required to avoid a
potential namespace conflict with the protobuf library as well as the cuDNN
version. In a future update, the modules will be fixed to allow the loading of these
Python modules to be in an arbitrary order.”

Pratosha · January 30, 2018, 10:13am

Hi,
I have imported uff and tensorflow as mentioned above, yet I am facing this error:

import tensorflow as tf
import uff
import tensorrt
Traceback (most recent call last):
File “”, line 1, in
ImportError: No module named tensorrt

kindly help.
Thanks

gustavvz · January 30, 2018, 3:10pm

Did you already install tensorRT?

Pratosha · January 30, 2018, 3:17pm

Hi gustavvz,
Yes I have installed tensorRT from the link.
https://developer.nvidia.com/nvidia-tensorrt-download

yan.pang · January 31, 2018, 7:01pm

Yes, I met the same issue with gustavvz.

AastaLLL · February 1, 2018, 9:43am

Hi,

TensorRT python API doesn’t support Jetson platform:
[url]Developer Guide :: NVIDIA Deep Learning TensorRT Documentation

Do you meet this error on a x86 Linux environment?

Thanks.

Nejla · February 21, 2018, 11:12pm

I’m getting ‘ModuleNotFoundError’ error. I’ve ubuntu 16.04 and my GPU is TitanX (Pascal). I tried what pratosha suggested by first importing tesnorflow and uff. But, I can’t even import uff. I installed nv-tensorrt-repo-ubuntu1604-ga-cuda9.0-trt3.0.4-20180208_1-1_amd64.deb and folllowed instructions provided by NVIDIA (Debian Installation): [url]Installation Guide :: NVIDIA Deep Learning TensorRT Documentation and I verify that it’s been installed.

Other information that might help:

Python 3.6.4
Cuda 9.0
cuDNN 7.0.5

Thanks

AastaLLL · February 23, 2018, 7:16am

Hi,

For python API and UFF parser, please install with this command:

$ sudo apt-get install python3-libnvinfer-doc
$ sudo apt-get install uff-converter-tf

You can find more information in our installation guide:
http://docs.nvidia.com/deeplearning/sdk/tensorrt-install-guide/index.html#installing-debian

Thanks.

Nejla · February 24, 2018, 5:48am

Hi AastaLLL,

Thank you for your reply. I ran those commands and when I run dpkg -l | grep TensorRT I see the output that is provided at section 2 of the installation guide. But, it’s not working! My NVidia driver version is 384.111. Do you think that’s causing problem?! Do I need to set a specific environment variable? My environment variables are:

[i]# added by Anaconda3 installer
export PATH=“/home/administrator/anaconda3/bin:$PATH”

added by Nejla

export CUDA_ROOT=/usr/local/cuda-9.0
export PATH=/usr/local/cuda-9.0/bin${PATH:+:${PATH}}
export LD_LIBRARY_PATH=/usr/local/cuda-9.0/lib64${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}
export CUDA_HOME=/usr/local/cuda-9.0
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/cuda/extras/CUPTI/lib64 [/i]

More information:

NVidia driver version: 384.111
Anaconda Python 3.6.4
Cuda 9.0
cuDNN 7.0.5
gcc 4.8
swig installed
“import pycuda” works

Nejla · February 26, 2018, 4:29am

Thank you. I finally got it working. I’d three python installations: python 2.7 coming with ubuntu, python 3.5 coming with ubuntu and anaconda python 3.5 that I’d installed myself. Got rid of Anaconda 3.5 as I couldn’t control where tensorrt is installed and made 3.5 the default one and reinstalled tensorrt, python packages as well as pycuda. Now, it’s working.

AastaLLL · February 26, 2018, 8:12am

Hi,

Good to know this : )

Thanks to update status with us.

dhingratul · April 4, 2018, 8:38pm

Any alternative to the solution, I do not want to remove Anaconda.

AastaLLL · April 10, 2018, 6:12am

Hi,

Guess the simplest way to achieve this is to use Anacona Python 2.7.
[url]https://conda.io/docs/user-guide/install/download.html[/url]

Thanks.

dhingratul · April 10, 2018, 3:55pm

Tried it, doesn’t work.

Nejla · April 10, 2018, 11:37pm

hi atul,

Unfortunately, you can’t use anaconda with TensorRT but you can still have anaconda on your system. To make tensorRT work I think it’s better to figure out what version of Python the tensorRT has been installed under and then make that version your default version and install other libraries under that version (tensorflow, …). You don’t have control where to install tensorRT but you’ve control on everything else.

Hope that helps!

plain_junior · June 26, 2018, 7:21am

Hi,

I met the same problem when import tensorrt in a python interpreter。

I updated the numpy using： pip install -U numpy
then imported tf and uff before tensorrt.
it works.

versions:
python 2.7.12
updated numpy 1.14.5 / pre version 1.13.3
linux Ubuntu 16.04.3
tensorrt 4
cuda 8.0

AastaLLL · June 29, 2018, 6:30am

Hi,

Please remember that TensorRT python API is only available on x86 environment. It also requires PyCUDA installed first.

You can follow this page to install PyCUDA.
[url]https://docs.nvidia.com/deeplearning/sdk/tensorrt-install-guide/index.html#installing-pycuda[/url]

After that, please follow this page to install TensorRT.
[url]https://docs.nvidia.com/deeplearning/sdk/tensorrt-install-guide/index.html#installing[/url]

Thanks.

bpinaya · August 3, 2018, 9:15am

Hi there AastaLLL,
I’m having sort of the same issue, but with CUDA 9.2 and TensorRT 4.
I have numpy version 1.11 on Ubuntu 16.04 x86
When trying to import tensorrt with:

import tensorrt as trt

I get:

ImportError: numpy.core.multiarray failed to import

Then I import numpy.core.multiarray and try again and this time I get:

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/usr/lib/python2.7/dist-packages/tensorrt/__init__.py", line 53, in <module>
    from tensorrt import __versions__
ImportError: cannot import name __versions__

As I’ve seen in this thread I have to import tensorflow and uff first. I had tensorflow for CUDA 9.0 so I gave it a try but can’t import uff or tensorflow due to:

ImportError: libcublas.so.9.0: cannot open shared object file: No such file or directory

Should I reinstall tensorflow with CUDA 9.2 support? I think for that I’ll have to build from source, as shown here: http://www.python36.com/how-to-install-tensorflow-gpu-with-cuda-9-2-for-python-on-ubuntu

Or is there other way to import tensorrt without having to install tensorflow.
Also, I installed TensorRT with Cuda9.2 support.
Thanks for your time!

Topic		Replies	Views
how to import uff model from a UFF File Jetson TX2	15	3409	October 18, 2021
TF-TRT issue Jetson TX2	26	3822	October 18, 2021
TensorRT 3.0 RC now available with support for TensorFlow Jetson TX2	83	23205	May 21, 2018
TF-TRT Error on Jetson Nano TensorRT tensorrt , nano	2	2117	August 26, 2021
Converting Tensorflow .pb models to TensorRT Models to run on the Nano Jetson Nano tensorrt , tensorflow	9	905	October 18, 2021
TensorRT-5.0.2.6 \| ImportError: /usr/local/lib/python3.5/dist-packages/tensorrt/tensorrt.so: cannot ... Jetson TX2	9	2717	October 18, 2021
Failed to Convert frozen graph to TensorRT engine Jetson TX2	9	2186	October 18, 2021
How to convert to uff from frozen graph pb Jetson AGX Xavier tensorrt	10	2340	October 18, 2021
Tensorflow RNN UFF conversion not yet supported? TensorRT	8	1264	October 12, 2021
TensorRT and UFF support for NVIDIA DRIVE PX 2 [cross-post from TensorRT forum] General	4	638	December 12, 2018

Error Importing tensorrt

added by Nejla

Related topics