Skip to contents

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

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

m$reset_state()
m$update_state(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)

# 1.6271976

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_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_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()