3D convolution/deconvolution support in TensorRT 3.0 ?


We want to use TensorRT in 3D medical data analysis.

Our data is MRI and dimension is [width, height, depth, channel]. Is it possible to use TensorRT?

I have the same question.

looks UFF has no support for Conv3D layer (correct me if wrong)

Checked inside TensorRT container 18.03-py2 by adding Tensorflow 3D convolution in lenet example,

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:

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.


I’m pretty interested in this too