Function for categorical focal loss

Source: R/customMetrics.R

The categorical focal loss discussed in this paper:

categorical_focal_loss(y_true, y_pred, gamma = 2, alpha = 0.25)

Arguments

y_true

True labels (Tensor)
y_pred

Predictions (Tensor of the same shape as y_true)
gamma

focusing parameter for modulating factor (1-p). Default = 2.0.
alpha

weighing factor in balanced cross entropy. Default = 0.25.

Value

function value

Details

https://arxiv.org/pdf/1708.02002.pdf

and ported from this implementation:

https://github.com/umbertogriffo/focal-loss-keras/blob/master/losses.py

Used to handle imbalanced classes .

Author

Tustison NJ

Examples


library( ANTsRNet )
library( keras )

model <- createUnetModel2D( c( 64, 64, 1 ) )

#> Error in py_discover_config(required_module, use_environment): Python specified in RETICULATE_PYTHON (/Users/ntustison/anaconda3/envs/antsx/bin/python3) does not exist

metric_categorical_focal_gain <-
  custom_metric( "categorical_focal_gain",
    categorical_focal_gain( alpha = 0.25, gamma = 2.0 ) )

#> Error in value[[3L]](cond): The R function's signature must not contains esoteric Python-incompatible constructs. Detailed traceback: 
#> Python specified in RETICULATE_PYTHON (/Users/ntustison/anaconda3/envs/antsx/bin/python3) does not exist

model %>% compile( loss = categorical_focal_loss( alpha = 0.25, gamma = 2.0 ),
 optimizer = optimizer_adam( lr = 0.0001 ),
   metrics = c( metric_categorical_focal_gain ) )

#> Error in compile(., loss = categorical_focal_loss(alpha = 0.25, gamma = 2),     optimizer = optimizer_adam(lr = 1e-04), metrics = c(metric_categorical_focal_gain)): object 'model' not found