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

Source:`R/losses.R`

`loss_binary_focal_crossentropy.Rd`

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, there is no focal
effect on the binary crossentropy loss.

If `apply_class_balancing == TRUE`

, this function also takes into account a
weight balancing factor for the binary classes 0 and 1 as follows:

`weight = alpha`

for class 1 (`target == 1`

)
`weight = 1 - alpha`

for class 0
where `alpha`

is a float in the range of `[0, 1]`

.

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.

## Usage

```
loss_binary_focal_crossentropy(
y_true,
y_pred,
apply_class_balancing = FALSE,
alpha = 0.25,
gamma = 2,
from_logits = FALSE,
label_smoothing = 0,
axis = -1L,
...,
reduction = "sum_over_batch_size",
name = "binary_focal_crossentropy",
dtype = NULL
)
```

## Arguments

- y_true
Ground truth values, of shape

`(batch_size, d0, .. dN)`

.- y_pred
The predicted values, of shape

`(batch_size, d0, .. dN)`

.- 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`

.- ...
For forward/backward compatability.

- 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`NULL`

.- name
Optional name for the loss instance.

- 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()`

).

## Examples

```
y_true <- rbind(c(0, 1), c(0, 0))
y_pred <- rbind(c(0.6, 0.4), c(0.4, 0.6))
loss <- loss_binary_focal_crossentropy(y_true, y_pred, gamma = 2)
loss
```

With the `compile()`

API:

```
model %>% compile(
loss = loss_binary_focal_crossentropy(
gamma = 2.0, from_logits = TRUE),
...
)
```

As a standalone function:

```
# Example 1: (batch_size = 1, number of samples = 4)
y_true <- op_array(c(0, 1, 0, 0))
y_pred <- op_array(c(-18.6, 0.51, 2.94, -12.8))
loss <- loss_binary_focal_crossentropy(gamma = 2, from_logits = TRUE)
loss(y_true, y_pred)
```

```
# Apply class weight
loss <- loss_binary_focal_crossentropy(
apply_class_balancing = TRUE, gamma = 2, from_logits = TRUE)
loss(y_true, y_pred)
```

```
# Example 2: (batch_size = 2, number of samples = 4)
y_true <- rbind(c(0, 1), c(0, 0))
y_pred <- rbind(c(-18.6, 0.51), c(2.94, -12.8))
# Using default 'auto'/'sum_over_batch_size' reduction type.
loss <- loss_binary_focal_crossentropy(
gamma = 3, from_logits = TRUE)
loss(y_true, y_pred)
```

```
# Apply class weight
loss <- loss_binary_focal_crossentropy(
apply_class_balancing = TRUE, gamma = 3, from_logits = TRUE)
loss(y_true, y_pred)
```

```
# Using 'sample_weight' attribute with focal effect
loss <- loss_binary_focal_crossentropy(
gamma = 3, from_logits = TRUE)
loss(y_true, y_pred, sample_weight = c(0.8, 0.2))
```

```
# Apply class weight
loss <- loss_binary_focal_crossentropy(
apply_class_balancing = TRUE, gamma = 3, from_logits = TRUE)
loss(y_true, y_pred, sample_weight = c(0.8, 0.2))
```

```
# Using 'sum' reduction` type.
loss <- loss_binary_focal_crossentropy(
gamma = 4, from_logits = TRUE,
reduction = "sum")
loss(y_true, y_pred)
```

```
# Apply class weight
loss <- loss_binary_focal_crossentropy(
apply_class_balancing = TRUE, gamma = 4, from_logits = TRUE,
reduction = "sum")
loss(y_true, y_pred)
```

```
# Using 'none' reduction type.
loss <- loss_binary_focal_crossentropy(
gamma = 5, from_logits = TRUE,
reduction = NULL)
loss(y_true, y_pred)
```

```
# Apply class weight
loss <- loss_binary_focal_crossentropy(
apply_class_balancing = TRUE, gamma = 5, from_logits = TRUE,
reduction = NULL)
loss(y_true, y_pred)
```

## See also

Other losses: `Loss()`

`loss_binary_crossentropy()`

`loss_categorical_crossentropy()`

`loss_categorical_focal_crossentropy()`

`loss_categorical_hinge()`

`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()`

`loss_tversky()`

`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()`