numalogic icon indicating copy to clipboard operation
numalogic copied to clipboard

Support same sequence shape for all architectures

Open ab93 opened this issue 2 years ago • 0 comments

Summary

Currently LSTM and Vanilla/Conv1d based models require a different shape of input. This creates a bit of confusion and can be simplified.

What change needs making? Support same input shape for all autoencoder based architectures. Will need to change the view in one of the types of variants.

ab93 avatar Sep 22 '22 00:09 ab93