What is the correct way to specify a loss? This will be relevant for streamlining the process of defining new losses.
losses.dice as seen in
or
losses.Dice() as seen in
|
model.compile('sgd', loss=nobrainer.losses.Dice()) |
Check how using either impact saving/loading the model.
What is the correct way to specify a loss? This will be relevant for streamlining the process of defining new losses.
losses.diceas seen innobrainer/nobrainer/processing/segmentation.py
Line 54 in 976691d
losses.Dice()as seen innobrainer/nobrainer/losses.py
Line 35 in 976691d
Check how using either impact saving/loading the model.