Skip to contents

Computes the crossentropy metric between the labels and predictions.

Source: R/metrics.R
metric_sparse_categorical_crossentropy.Rd

Use this crossentropy metric when there are two or more label classes. It expects labels to be provided as integers. If you want to provide labels that are one-hot encoded, please use the metric_categorical_crossentropy() metric instead.

There should be num_classes floating point values per feature for y_pred and a single floating point value per feature for y_true.

Usage

metric_sparse_categorical_crossentropy(
  y_true,
  y_pred,
  from_logits = FALSE,
  ignore_class = NULL,
  axis = -1L,
  ...,
  name = "sparse_categorical_crossentropy",
  dtype = NULL
)

Arguments

y_true

Ground truth values.

y_pred

The predicted values.

from_logits

(Optional) Whether output is expected to be a logits tensor. By default, we consider that output encodes a probability distribution.

ignore_class

Optional integer. The ID of a class to be ignored during loss computation. This is useful, for example, in segmentation problems featuring a "void" class (commonly -1 or 255) in segmentation maps. By default (ignore_class=NULL), all classes are considered.

axis

(Optional) Defaults to -1. The dimension along which entropy is computed.

...

For forward/backward compatability.

name

(Optional) string name of the metric instance.

dtype

(Optional) data type of the metric result.

Value

If y_true and y_pred are missing, a Metric instance is returned. The Metric instance that can be passed directly to compile(metrics = ), or used as a standalone object. See ?Metric for example usage. If y_true and y_pred are provided, then a tensor with the computed value is returned.

Examples

Standalone usage:

m <- metric_sparse_categorical_crossentropy()
m$update_state(array(c(1, 2)),
               rbind(c(0.05, 0.95, 0), c(0.1, 0.8, 0.1)))
m$result()

## tf.Tensor(1.1769392, shape=(), dtype=float32)


m$reset_state()
m$update_state(array(c(1, 2)),
               rbind(c(0.05, 0.95, 0), c(0.1, 0.8, 0.1)),
               sample_weight = c(0.3, 0.7))
m$result()

## tf.Tensor(1.6271976, shape=(), dtype=float32)

Usage with compile() API:

model |> compile(
  optimizer = 'sgd',
  loss = 'mse',
  metrics = list(metric_sparse_categorical_crossentropy())
)

See also

Other losses:
Loss()
loss_binary_crossentropy()
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_squared_hinge()

Other metrics:
Metric()
custom_metric()
metric_auc()
metric_binary_accuracy()
metric_binary_crossentropy()
metric_binary_focal_crossentropy()
metric_binary_iou()
metric_categorical_accuracy()
metric_categorical_crossentropy()
metric_categorical_focal_crossentropy()
metric_categorical_hinge()
metric_cosine_similarity()
metric_f1_score()
metric_false_negatives()
metric_false_positives()
metric_fbeta_score()
metric_hinge()
metric_huber()
metric_iou()
metric_kl_divergence()
metric_log_cosh()
metric_log_cosh_error()
metric_mean()
metric_mean_absolute_error()
metric_mean_absolute_percentage_error()
metric_mean_iou()
metric_mean_squared_error()
metric_mean_squared_logarithmic_error()
metric_mean_wrapper()
metric_one_hot_iou()
metric_one_hot_mean_iou()
metric_poisson()
metric_precision()
metric_precision_at_recall()
metric_r2_score()
metric_recall()
metric_recall_at_precision()
metric_root_mean_squared_error()
metric_sensitivity_at_specificity()
metric_sparse_categorical_accuracy()
metric_sparse_top_k_categorical_accuracy()
metric_specificity_at_sensitivity()
metric_squared_hinge()
metric_sum()
metric_top_k_categorical_accuracy()
metric_true_negatives()
metric_true_positives()

Other probabilistic metrics:
metric_binary_crossentropy()
metric_categorical_crossentropy()
metric_kl_divergence()
metric_poisson()