I was trying to convert my own frozen model and it shows me that "ctc_beam_search_decoder" layer is not supported and I have it in my graph, Is there a pre-made custom implementation for this layer that I can use?
Thanks in advance.
Dear Medhat, Amr,
Here is the Supported Model Optimizer Tensorflow Layers doc. And you are correct, ctc_beam_search_decoder is not on the list for Tensorflow. However, all is not lost. You can make a custom layer to handle it.
Kindly peruse the below documents:
Also this IDZ Post which I wrote earlier this year is a bit dated since it has 2018 links but simply go to https://github.com/opencv/dldt and redirect to the 2019 R3 links.
Hope it helps,