tf.keras.losses.BinaryFocalCrossentropy

Computes focal cross-entropy loss between true labels and predictions.

Inherits From: Loss

tf.keras.losses.BinaryFocalCrossentropy(
    apply_class_balancing=False,
    alpha=0.25,
    gamma=2.0,
    from_logits=False,
    label_smoothing=0.0,
    axis=-1,
    reduction='sum_over_batch_size',
    name='binary_focal_crossentropy'
)

Binary cross-entropy loss is often used for binary (0 or 1) classification tasks. The loss function requires the following inputs:

  • y_true (true label): This is either 0 or 1.
  • y_pred (predicted value): This is the model's prediction, i.e, a single floating-point value which either represents a logit, (i.e, value in [-inf, inf] when from_logits=True) or a probability (i.e, value in [0., 1.] when from_logits=False).

According to Lin et al., 2018, it helps to apply a "focal factor" to down-weight easy examples and focus more on hard examples. By default, the focal tensor is computed as follows:

focal_factor = (1 - output) ** gamma for class 1 focal_factor = output ** gamma for class 0 where gamma is a focusing parameter. When gamma=0, this function is equivalent to the binary crossentropy loss.

apply_class_balancing A bool, whether to apply weight balancing on the binary classes 0 and 1.
alpha A weight balancing factor for class 1, default is 0.25 as mentioned in reference Lin et al., 2018. The weight for class 0 is 1.0 - alpha.
gamma A focusing parameter used to compute the focal factor, default is 2.0 as mentioned in the reference Lin et al., 2018.
from_logits Whether to interpret y_pred as a tensor of logit values. By default, we assume that y_pred are probabilities (i.e., values in [0, 1]).
label_smoothing Float in [0, 1]. When 0, no smoothing occurs. When > 0, we compute the loss between the predicted labels and a smoothed version of the true labels, where the smoothing squeezes the labels towards 0.5. Larger values of label_smoothing correspond to heavier smoothing.
axis The axis along which to compute crossentropy (the features axis). Defaults to -1.
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" or None.
name Optional name for the loss instance.

Examples:

With the compile() API:

model.compile(
    loss=keras.losses.BinaryFocalCrossentropy(
        gamma=2.0, from_logits=True),
    ...
)

As a standalone function:

# Example 1: (batch_size = 1, number of samples = 4)
y_true = [0, 1, 0, 0]
y_pred = [-18.6, 0.51, 2.94, -12.8]
loss = keras.losses.BinaryFocalCrossentropy(
   gamma=2, from_logits=True)
loss(y_true, y_pred)
0.691
 
# Apply class weight
loss = keras.losses.BinaryFocalCrossentropy(
    apply_class_balancing=True, gamma=2, from_logits=True)
loss(y_true, y_pred)
0.51
 
# Example 2: (batch_size = 2, number of samples = 4)
y_true = [[0, 1], [0, 0]]
y_pred = [[-18.6, 0.51], [2.94, -12.8]]
# Using default 'auto'/'sum_over_batch_size' reduction type.
loss = keras.losses.BinaryFocalCrossentropy(
    gamma=3, from_logits=True)
loss(y_true, y_pred)
0.647
 
# Apply class weight
loss = keras.losses.BinaryFocalCrossentropy(
     apply_class_balancing=True, gamma=3, from_logits=True)
loss(y_true, y_pred)
0.482
 
# Using 'sample_weight' attribute with focal effect
loss = keras.losses.BinaryFocalCrossentropy(
    gamma=3, from_logits=True)
loss(y_true, y_pred, sample_weight=[0.8, 0.2])
0.133
 
# Apply class weight
loss = keras.losses.BinaryFocalCrossentropy(
     apply_class_balancing=True, gamma=3, from_logits=True)
loss(y_true, y_pred, sample_weight=[0.8, 0.2])
0.097
 
# Using 'sum' reduction` type.
loss = keras.losses.BinaryFocalCrossentropy(
    gamma=4, from_logits=True,
    reduction="sum")
loss(y_true, y_pred)
1.222
 
# Apply class weight
loss = keras.losses.BinaryFocalCrossentropy(
    apply_class_balancing=True, gamma=4, from_logits=True,
    reduction="sum")
loss(y_true, y_pred)
0.914
 
# Using 'none' reduction type.
loss = keras.losses.BinaryFocalCrossentropy(
    gamma=5, from_logits=True,
    reduction=None)
loss(y_true, y_pred)
array([0.0017 1.1561], dtype=float32)
 
# Apply class weight
loss = keras.losses.BinaryFocalCrossentropy(
    apply_class_balancing=True, gamma=5, from_logits=True,
    reduction=None)
loss(y_true, y_pred)
array([0.0004 0.8670], dtype=float32)

Methods

call

View source

call(
    y_true, y_pred
)

from_config

View source

@classmethod
from_config(
    config
)

get_config

View source

get_config()

__call__

View source

__call__(
    y_true, y_pred, sample_weight=None
)

Call self as a function.