Computes how often integer targets are in the top K predictions.

Computes how often integer targets are in the top K predictions.

By default, the arguments expected by update_state() are:

• y_true: a tensor of shape (batch_size) representing indices of true categories.

• y_pred: a tensor of shape (batch_size, num_categories) containing the scores for each sample for all possible categories.

With from_sorted_ids=TRUE, the arguments expected by update_state are:

• y_true: a tensor of shape (batch_size) representing indices or IDs of true categories.

• y_pred: a tensor of shape (batch_size, N) containing the indices or IDs of the top N categories sorted in order from highest score to lowest score. N must be greater or equal to k.

The from_sorted_ids=TRUE option can be more efficient when the set of categories is very large and the model has an optimized way to retrieve the top ones either without scoring or without maintaining the scores for all the possible categories.

Usage

metric_sparse_top_k_categorical_accuracy(
  y_true,
  y_pred,
  k = 5L,
  ...,
  name = "sparse_top_k_categorical_accuracy",
  dtype = NULL,
  from_sorted_ids = FALSE
)

Arguments

y_true

Tensor of true targets.

y_pred

Tensor of predicted targets.

k

(Optional) Number of top elements to look at for computing accuracy. Defaults to 5.

...

For forward/backward compatability.

name

(Optional) string name of the metric instance.

dtype

(Optional) data type of the metric result.

from_sorted_ids

(Optional) When FALSE, the default, the tensor passed in y_pred contains the unsorted scores of all possible categories. When TRUE, y_pred contains the indices or IDs for the top categories.

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_sparse_top_k_categorical_accuracy(k = 1L)
m$update_state(
  rbind(2, 1),
  op_array(rbind(c(0.1, 0.9, 0.8), c(0.05, 0.95, 0)), dtype = "float32")
)
m$result()

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

m$reset_state()
m$update_state(
  rbind(2, 1),
  op_array(rbind(c(0.1, 0.9, 0.8), c(0.05, 0.95, 0)), dtype = "float32"),
  sample_weight = c(0.7, 0.3)
)
m$result()

## tf.Tensor(0.3, shape=(), dtype=float32)

m <- metric_sparse_top_k_categorical_accuracy(k = 1, from_sorted_ids = TRUE)
m$update_state(array(c(2, 1)), rbind(c(1, 0, 3),
                                     c(1, 2, 3)))
m$result()

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

Usage with compile() API:

model %>% compile(optimizer = 'sgd',
                  loss = 'sparse_categorical_crossentropy',
                  metrics = list(metric_sparse_top_k_categorical_accuracy()))

See also

• https://keras.io/api/metrics/accuracy_metrics#sparsetopkcategoricalaccuracy-class

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

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_concordance_correlation()
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_pearson_correlation()
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_specificity_at_sensitivity()
metric_squared_hinge()
metric_sum()
metric_top_k_categorical_accuracy()
metric_true_negatives()
metric_true_positives()