Hello I'm trying to implement the "Tacotron Towards end to end" paper and in the
Encoder CBHG - a Conv1D bank of K=16, conv-k-128-ReLU
“conv-k-c-ReLU” - denotes 1-D convolution with width k and c output channels with ReLU activation.
And I wanted to ask how exactly I can implement it in Tensorflow 2.1? because in the documentation I haven't seen how to specify the output channels

Reference to the paper: https://arxiv.org/pdf/1703.10135.pdf

  • $\begingroup$ Hi. Could you add a reference and maybe polish your text to make it more readable? Thanks. $\endgroup$
    – oW_
    Mar 17 '20 at 2:56
  • $\begingroup$ Hi @oW_ I added a reference $\endgroup$
    – user200544
    Mar 17 '20 at 6:12

Refer to this: https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv1D

The parameter filter determines the output channel.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.