Skip to contents

Calculates how often predictions match binary labels.

Source: R/metrics.R
metric_binary_accuracy.Rd

This metric creates two local variables, total and count that are used to compute the frequency with which y_pred matches y_true. This frequency is ultimately returned as binary accuracy: an idempotent operation that simply divides total by count.

If sample_weight is NULL, weights default to 1. Use sample_weight of 0 to mask values.

Usage

metric_binary_accuracy(
  y_true,
  y_pred,
  threshold = 0.5,
  ...,
  name = "binary_accuracy",
  dtype = NULL
)

Arguments

y_true

Tensor of true targets.

y_pred

Tensor of predicted targets.

threshold

(Optional) Float representing the threshold for deciding whether prediction values are 1 or 0.

...

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.

Usage

Standalone usage:

m <- metric_binary_accuracy()
m$update_state(rbind(1, 1, 0, 0), rbind(0.98, 1, 0, 0.6))
m$result()

## tf.Tensor(0.75, shape=(), dtype=float32)


# 0.75

m$reset_state()
m$update_state(rbind(1, 1, 0, 0), rbind(0.98, 1, 0, 0.6),
               sample_weight = c(1, 0, 0, 1))
m$result()

## tf.Tensor(0.5, shape=(), dtype=float32)


# 0.5

Usage with compile() API:

model %>% compile(optimizer='sgd',
                  loss='binary_crossentropy',
                  metrics=list(metric_binary_accuracy()))

See also

Other accuracy metrics:
metric_categorical_accuracy()
metric_sparse_categorical_accuracy()
metric_sparse_top_k_categorical_accuracy()
metric_top_k_categorical_accuracy()

Other metrics:
Metric()
custom_metric()
metric_auc()
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_categorical_crossentropy()
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()