Skip to contents

Computes the Tversky loss value between y_true and y_pred.

Source: R/losses.R
loss_tversky.Rd

This loss function is weighted by the alpha and beta coefficients that penalize false positives and false negatives.

With alpha=0.5 and beta=0.5, the loss value becomes equivalent to Dice Loss.

This loss function is weighted by the alpha and beta coefficients that penalize false positives and false negatives.

With alpha=0.5 and beta=0.5, the loss value becomes equivalent to Dice Loss.

Usage

loss_tversky(
  y_true,
  y_pred,
  ...,
  alpha = 0.5,
  beta = 0.5,
  reduction = "sum_over_batch_size",
  name = "tversky",
  axis = NULL,
  dtype = NULL
)

Arguments

y_true

tensor of true targets.

y_pred

tensor of predicted targets.

...

For forward/backward compatability.

alpha

The coefficient controlling incidence of false positives. Defaults to 0.5.

beta

The coefficient controlling incidence of false negatives. Defaults to 0.5.

reduction

Type of reduction to apply to the loss. In almost all cases this should be "sum_over_batch_size". Supported options are "sum", "sum_over_batch_size", "mean", "mean_with_sample_weight" or NULL. "sum" sums the loss, "sum_over_batch_size" and "mean" sum the loss and divide by the sample size, and "mean_with_sample_weight" sums the loss and divides by the sum of the sample weights. "none" and NULL perform no aggregation. Defaults to "sum_over_batch_size".

name

Optional name for the loss instance. (string)

axis

Axis (1-based)

dtype

The dtype of the loss's computations. Defaults to NULL, which means using config_floatx(). config_floatx() is a "float32" unless set to different value (via config_set_floatx()). If a keras$DTypePolicy is provided, then the compute_dtype will be utilized.

Value

Tversky loss value.

Reference

See also

Other losses:
Loss()
loss_binary_crossentropy()
loss_binary_focal_crossentropy()
loss_categorical_crossentropy()
loss_categorical_focal_crossentropy()
loss_categorical_generalized_cross_entropy()
loss_categorical_hinge()
loss_circle()
loss_cosine_similarity()
loss_ctc()
loss_dice()
loss_hinge()
loss_huber()
loss_kl_divergence()
loss_log_cosh()
loss_mean_absolute_error()
loss_mean_absolute_percentage_error()
loss_mean_squared_error()
loss_mean_squared_logarithmic_error()
loss_poisson()
loss_sparse_categorical_crossentropy()
loss_squared_hinge()
metric_binary_crossentropy()
metric_binary_focal_crossentropy()
metric_categorical_crossentropy()
metric_categorical_focal_crossentropy()
metric_categorical_hinge()
metric_hinge()
metric_huber()
metric_kl_divergence()
metric_log_cosh()
metric_mean_absolute_error()
metric_mean_absolute_percentage_error()
metric_mean_squared_error()
metric_mean_squared_logarithmic_error()
metric_poisson()
metric_sparse_categorical_crossentropy()
metric_squared_hinge()