0

I am using Keras with TF backend. I want to set up a neural network with keras using python, then save it, convert it to tensorflow and train it using TF's C++ API.

What I have found so far was already pretty helpful:

1) Run your Keras models in C++ Tensorflow

2) Convert Keras model to C++

Unfortunately both approaches use Keras to train the NN and convert it to TF afterwards. Basically, I just want to set up the architecture using Keras and then train the network using TF's C++ API. Is there a way to do so?

Thanks for help!

RolleRugu
  • 233
  • 2
  • 11
  • 1
    Why the downvote? I have the exact same problem. The reason to do so is because using Keras for the training is too slow, with the bottlenect being converting `Numpy` array to `Tensor` after doing Preprocessing in C++. – yuqli Jul 02 '20 at 22:51

1 Answers1

0

I guess the second link you noted, is just enough what you need. You may need to search on "Save and Load Your Keras Deep Learning Models" and then open it with the TF's C++ API.

prosti
  • 42,291
  • 14
  • 186
  • 151