Using TensorFlow with TensorRT on Windows

Hello Devs,

I am using TensorFlow on Python. I want to use TensorRT to import my TF model + weights.

Would like to deploy on 1050 Ti card running on Windows 7. (Is it possible?)

Please help me with Tensor RT download for Windows.
An example on how to import TF model + weights

Thanks,
Uday

also wanna know is there any plan for windows?

The TensorRT Developer Guide contains a list of supported features on different plateforms. The platefomrs mentionned are Linux x86, Linux aarch64, Android aarch64, and QNX aarch64. So windows seems not supported at all, despite the fact that windows IS mentioned in the following blog post : https://blogs.nvidia.com/blog/2017/05/10/nvidia-sdk-update/ :

“TensorRT…
Developers can optimize models trained in TensorFlow or Caffe deep learning frameworks and deploy fast AI services to platforms running Linux, Microsoft Windows, BlackBerry QNX or Android operating systems.”

So I guess that a windows version has been considered …?..
I also really would like a running windows version.

We created a new “Deep Learning Training and Inference” section in Devtalk to improve the experience for deep learning and accelerated computing, and HPC users:
https://devtalk.nvidia.com/default/board/301/deep-learning-training-and-inference-/

We are moving active deep learning threads to the new section.

URLs for topics will not change with the re-categorization. So your bookmarks and links will continue to work as earlier.

-Siddharth