n_in and n_out
carbocation opened this issue · comments
James Pirruccello commented
In the fastai v2 unet_learner
function call, n_in can be specified in order to reshape the learner to accept inputs that don't have 3 channels. Is this something that can be specified in SemTorch? Asking because I don't see it as a parameter in the README, though perhaps it will passthrough as a kwarg.