shmann

@Aakanksha-Rana thanks, that makes sense. I was expecting the dice metric would be more in line with something like tf.keras.metrics.BinaryAccuracy, where y_pred is thresholded at 0.5 (unless otherwise defined) before...

I was thinking the encoder part could be used to encode MRI images to then use for downstream tasks

@dhritimandas -- Right. Specifically, I'm playing with a similar type of segmentation as in the AMS paper--in other words, segmentation that is inconsistent spatially (as opposed to a particular brain...

@kaczmarj I tried fine tuning the brainy model (up to 200 epochs), but it's still putting out a decent amount of noise. I might try incorporating the 'largest-label' concept (as...