Closed DanielCoelho112 closed 2 years ago
Hi @DanielCoelho112 , thanks for flagging it. Changing it in the code will break the models trained. It is probably a mistake in the visualization or in the code. Let's not change it for now.
If you want tho, feel free to fork, fix it and publish the new models!
Hi @hazirbas,
congrats for this implementation. Great job.
According to the architecture of the network:
I believe that the lstm_hidden_size should be 128 and not 256 as it currently is. What do you say? Do you want me to do a pull request to fix it, or there is some reason that I'm not seeing for the 256?