BCE Loss

neuralpy.loss_functions.BCELoss(weight=None, reduction='mean', pos_weight=None)
info

BCE Loss is mostly stable and can be used for any project. In the future, any chance of breaking changes is very low.

Applies a BCE Loss function to the model.

BCE Loss automatically applies a Sigmoid Layer at the end of the model, so there is no need to add a Sigmoid layer.

For more information, check this page.

Supported Arguments

  • weight=None : (Numpy Array | List) Manual rescaling of classes
  • reduction='mean' : (String) Specifies the reduction that is to be applied to the output.
  • post_weight=None : (Numpy Array | List) A weight of positive examples

Code Example

from neuralpy.models import Sequential
from neuralpy.optimizer import Adam
from neuralpy.loss_functions import BCELoss
...
# Rest of the imports
...
model = Sequential()
...
# Rest of the architecture
...
model.compile(optimizer=Adam(), loss_function=BCELoss(weight=None, reduction='mean', pos_weight=None))
Edit this page