You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Currently, the model is designed for a single band. It can be extended to multiband in a simple way, by changing the number of input channels in the first convolution (line 108 in model.py).
Notice that this is not necessarily the best way of creating a multiband model. We are going to work on that in the future.
Is it possible to expand the model to train on multi-band (RGBNIR) images instead of just the RED/NIR band?
The text was updated successfully, but these errors were encountered: