Losses tl.losses
#
Custom tf.Keras.losses.Loss
functions for specific use cases.
Supply these (or your own) to a tl.TaskConfig
to be able to use them for training.
|
Custom loss function that combines cosine similarity and mean squared error (MSE). |
|
Custom loss function combining logarithmic transformation, cosine similarity, and mean squared error (MSE). |
|
Custom Poisson loss for count data with optional log(x + 1) transformation. |
|
Poisson decomposition with multinomial specificity term for aggregated counts. |