Keras allows one to specify padding='causal' to achieve autoregressive connections in Conv1D layers. However, in deconvolution with Conv1DTranspose, padding is limited to same and valid.

How can one achieve causal deconvolution then?

Is there something I am missing?


Your Answer

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

Browse other questions tagged or ask your own question.