Francisco Santos

Currently the base structure is refactored from a previous implementation. Next steps are: - validation/revision of the train method logic comparing to the article

@fabclmnt I believe this should be ready to merge, wdyt?

Hello @pbezz1! You are interested in retrieving a _single_ record for each of the learned time series but with an arbitrary length x, is this correct? This is the implemented...

The sample shape that you are trying to retrieve (x, 20) is basically a single record of length x and the 20 time series. The slice operation is required since...

Hey Patrick! For this you would need either an RNN synthesizer ran in a stateful manner or a conditional generator. WGAN_GP does not meet any of these! See this synthesizer...

Hello @INSACY98! Can you please provide information on the system and the versions of ydata_synthetic and tensorflow libraries in the environment that you are using? Thanks in advance