C++ use of Eigen in tensorflow

Question

What is the relation between tensorflow and Eigen, particularly regarding the tensor datastructures?

There are some older quotations (e.g. here) which state that tensorflow is using Eigen extensively (afaik a tensorflow guy has extended the Eigen code). More recent tensorflow documentation, however, seems to not explicitly refer to Eigen.

Are the two tensor structures identical? Are they being updated concurrently? Is there any (possibly future) disadvantage in using the Eigen::tensor over the tensorflow::tensor?

Answer 1

tensorflow::tensor is just a thin wrapper around Eigen::Tensor with limited high-level features only. You can access to the underlying Eigen::Tensor of a tensorflow::tensor using the tensor() method. I guess that this information also solve your last two questions.