Open JavierEscobarOrtiz opened 2 weeks ago
I think it is because of keras 3.0
Hi @AVPokrovsky. You are right.
The current version of skforecast is not compatible with keras3 (tensorflow>=2.13, <2.16). We are working to add keras3 compatibility in the next release.
@FernandoCarazoMelo
I got another one with RNN regressor (below). It also appears with you code examples on RNN. It was resolved when I downgraded Tensorflow from 2.16.1 to 2.15.1
Input shape of the regressor should be Input(shape=(lags, n_series))
Originally posted by @AVPokrovsky in https://github.com/JoaquinAmatRodrigo/skforecast/issues/714#issuecomment-2167824884