Hands-On Generative Adversarial Networks with Keras

Precision, Recall, and the F1 Score

Precision, recall, and the F1 Score are metrics related to classification. Precision is the ratio of true positives to true positives plus false positives; in other words, given the items that the model identified as positives, the number of these that are correctly positive. Recall is the ratio of true positives to true positives plus false negatives. In other words, given the items that the model has recognized and not recognized, the number that are recognized. The F1 score is the harmonic average of Precision and recall:

• Precision: TP / TP + FP
• Pecall: TP / TP + FN
• F1 scores: 2 (Precision * Recall) / Precision + Recall

A famous image used to illustrate Precision and recall. Source: Wikipedia (https://en.wikipedia.org/wiki/Precision_and_recall ...