Module: tf.contrib.metrics

Ops for evaluation metrics and summary statistics.

See the Contrib Metrics guide.

Functions

accuracy(...): Computes the percentage of times that predictions matches labels.

aggregate_metric_map(...): Aggregates the metric names to tuple dictionary.

aggregate_metrics(...): Aggregates the metric value tensors and update ops into two lists.

auc_using_histogram(...): AUC computed by maintaining histograms.

auc_with_confidence_intervals(...): Computes the AUC and asymptotic normally distributed confidence interval.

cohen_kappa(...): Calculates Cohen's kappa.

confusion_matrix(...): Deprecated. Use tf.math.confusion_matrix instead.

count(...): Computes the number of examples, or sum of weights.

f1_score(...): Computes the approximately best F1-score across different thresholds.

precision_at_recall(...): Computes the precision at a given recall.

precision_recall_at_equal_thresholds(...): A helper method for creating metrics related to precision-recall curves.

recall_at_precision(...): Computes recall at precision.

set_difference(...): Compute set difference of elements in last dimension of a and b.

set_intersection(...): Compute set intersection of elements in last dimension of a and b.

set_size(...): Compute number of unique elements along last dimension of a.

set_union(...): Compute set union of elements in last dimension of a and b.

sparse_recall_at_top_k(...): Computes recall@k of top-k predictions with respect to sparse labels.

streaming_accuracy(...): Calculates how often predictions matches labels. (deprecated)

streaming_auc(...): Computes the approximate AUC via a Riemann sum. (deprecated)

streaming_concat(...): Concatenate values along an axis across batches.

streaming_covariance(...): Computes the unbiased sample covariance between predictions and labels.

streaming_curve_points(...): Computes curve (ROC or PR) values for a prespecified number of points.

streaming_dynamic_auc(...): Computes the apporixmate AUC by a Riemann sum with data-derived thresholds.

streaming_false_negative_rate(...): Computes the false negative rate of predictions with respect to labels.

streaming_false_negative_rate_at_thresholds(...): Computes various fnr values for different thresholds on predictions.

streaming_false_negatives(...): Computes the total number of false negatives. (deprecated)

streaming_false_negatives_at_thresholds(...)

streaming_false_positive_rate(...): Computes the false positive rate of predictions with respect to labels.

streaming_false_positive_rate_at_thresholds(...): Computes various fpr values for different thresholds on predictions.

streaming_false_positives(...): Sum the weights of false positives. (deprecated)

streaming_false_positives_at_thresholds(...)

streaming_mean(...): Computes the (weighted) mean of the given values. (deprecated)

streaming_mean_absolute_error(...): Computes the mean absolute error between the labels and predictions. (deprecated)

streaming_mean_cosine_distance(...): Computes the cosine distance between the labels and predictions.

streaming_mean_iou(...): Calculate per-step mean Intersection-Over-Union (mIOU).

streaming_mean_relative_error(...): Computes the mean relative error by normalizing with the given values.

streaming_mean_squared_error(...): Computes the mean squared error between the labels and predictions. (deprecated)

streaming_mean_tensor(...): Computes the element-wise (weighted) mean of the given tensors. (deprecated)

streaming_pearson_correlation(...): Computes Pearson correlation coefficient between predictions, labels.

streaming_percentage_less(...): Computes the percentage of values less than the given threshold.

streaming_precision(...): Computes the precision of the predictions with respect to the labels. (deprecated)

streaming_precision_at_thresholds(...): Computes precision values for different thresholds on predictions. (deprecated)

streaming_recall(...): Computes the recall of the predictions with respect to the labels. (deprecated)

streaming_recall_at_k(...): Computes the recall@k of the predictions with respect to dense labels. (deprecated)

streaming_recall_at_thresholds(...): Computes various recall values for different thresholds on predictions. (deprecated)

streaming_root_mean_squared_error(...): Computes the root mean squared error between the labels and predictions. (deprecated)

streaming_sensitivity_at_specificity(...): Computes the sensitivity at a given specificity.

streaming_sparse_average_precision_at_k(...): Computes average precision@k of predictions with respect to sparse labels.

streaming_sparse_average_precision_at_top_k(...): Computes average precision@k of predictions with respect to sparse labels.

streaming_sparse_precision_at_k(...): Computes precision@k of the predictions with respect to sparse labels.

streaming_sparse_precision_at_top_k(...): Computes precision@k of top-k predictions with respect to sparse labels.

streaming_sparse_recall_at_k(...): Computes recall@k of the predictions with respect to sparse labels.

streaming_specificity_at_sensitivity(...): Computes the specificity at a given sensitivity.

streaming_true_negatives(...): Sum the weights of true_negatives. (deprecated)

streaming_true_negatives_at_thresholds(...)

streaming_true_positives(...): Sum the weights of true_positives. (deprecated)

streaming_true_positives_at_thresholds(...)

© 2020 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/metrics