Skip to contents

Computes the cross-entropy loss between true labels and predicted labels.

Source: R/losses.R
loss_binary_crossentropy.Rd

Use this cross-entropy loss for binary (0 or 1) classification applications. 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).

Usage

loss_binary_crossentropy(
  y_true,
  y_pred,
  from_logits = FALSE,
  label_smoothing = 0,
  axis = -1L,
  ...,
  reduction = "sum_over_batch_size",
  name = "binary_crossentropy",
  dtype = NULL
)

Arguments

y_true

Ground truth values. shape = [batch_size, d0, .. dN].

y_pred

The predicted values. shape = [batch_size, d0, .. dN].

from_logits

Whether to interpret y_pred as a tensor of logit values. By default, we assume that y_pred is probabilities (i.e., values in [0, 1)).

label_smoothing

Float in range [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()). If a keras$DTypePolicy is provided, then the compute_dtype will be utilized.

Value

Binary crossentropy loss value. shape = [batch_size, d0, .. dN-1].

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_crossentropy(y_true, y_pred)
loss

## tf.Tensor([0.91629073 0.71355818], shape=(2), dtype=float64)

Recommended Usage: (set from_logits=TRUE)

With compile() API:

model %>% compile(
    loss = loss_binary_crossentropy(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))
bce <- loss_binary_crossentropy(from_logits = TRUE)
bce(y_true, y_pred)

## tf.Tensor(0.865458, shape=(), dtype=float32)


# 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.
bce <- loss_binary_crossentropy(from_logits = TRUE)
bce(y_true, y_pred)

## tf.Tensor(0.865458, shape=(), dtype=float32)


# Using 'sample_weight' attribute
bce(y_true, y_pred, sample_weight = c(0.8, 0.2))

## tf.Tensor(0.2436386, shape=(), dtype=float32)


# 0.243
# Using 'sum' reduction` type.
bce <- loss_binary_crossentropy(from_logits = TRUE, reduction = "sum")
bce(y_true, y_pred)

## tf.Tensor(1.730916, shape=(), dtype=float32)


# Using 'none' reduction type.
bce <- loss_binary_crossentropy(from_logits = TRUE, reduction = NULL)
bce(y_true, y_pred)

## tf.Tensor([0.23515666 1.4957594 ], shape=(2), dtype=float32)

Default Usage: (set from_logits=FALSE)

# Make the following updates to the above "Recommended Usage" section
# 1. Set `from_logits=FALSE`
loss_binary_crossentropy() # OR ...('from_logits=FALSE')

## <keras.src.losses.losses.BinaryCrossentropy object>
##  signature: (y_true, y_pred, sample_weight=None)


# 2. Update `y_pred` to use probabilities instead of logits
y_pred <- c(0.6, 0.3, 0.2, 0.8) # OR [[0.6, 0.3], [0.2, 0.8]]

See also

Other losses:
Loss()
loss_binary_focal_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()