tensorflow.contrib.tensorrt problems

Robotics & Edge Computing Jetson & Embedded Systems Jetson TX2
1

I wanna know that I have installed tensorflow gpu 1.9 nv18.8 on TX2.
I found that I can use tensorRT as follow:
import tensorflow.contrib.tensorrt as trt
When I want to use some ways such as :
G_LOGGER = trt.infer.ConsoleLogger(trt.infer.LogSeverity.ERROR)
It shows that no module here.
That means there are some difference between TX2 tensorrt and X86 tensorrt.
And how can I know what ways or what module I can use in tx2 with tensorrt.

By the way, how can I know what the version of tensorrt in TX2 is?
It confuse me a long time…

2

Hi,

tensorflow.contrib.tensorrt is a TensorRT wrapper.
You will need to install TensorRT library with JetPack first or the wrapper cannot find the corresponding modules.

You can find TensorRT version with this command:

$ dpkg -l | grep TensorRT

ii graphsurgeon-tf 5.1.2-1+cuda10.1 amd64 GraphSurgeon for TensorRT package
ii libnvinfer-dev 5.1.2-1+cuda10.1 amd64 TensorRT development libraries and headers
ii libnvinfer-samples 5.1.2-1+cuda10.1 amd64 TensorRT samples and documentation
ii libnvinfer5 5.1.2-1+cuda10.1 amd64 TensorRT runtime libraries
ii python-libnvinfer 5.1.2-1+cuda10.1 amd64 Python bindings for TensorRT
ii python-libnvinfer-dev 5.1.2-1+cuda10.1 amd64 Python development package for TensorRT
…

Thanks.

3
4

Hi, 794836749

Is everything okay on your side?
Thanks.