How to calculate precision and recall in Keras

As of Keras 2.0, precision and recall were removed from the master branch. You will have to implement them yourself. Follow this guide to create custom metrics : Here.

Precision and recall equation can be found Here

Or reuse the code from keras before it was removed Here.

There metrics were remove because they were batch-wise so the value may or may not be correct.

Use Scikit Learn framework for this.

from sklearn.metrics import classification_report

history = model.fit(x_train, y_train, batch_size=32, epochs=10, verbose=1, validation_data=(x_test, y_test), shuffle=True)
pred = model.predict(x_test, batch_size=32, verbose=1)
predicted = np.argmax(pred, axis=1)
report = classification_report(np.argmax(y_test, axis=1), predicted)
print(report)

This blog is very useful.

My answer is based on the comment of Keras GH issue. It calculates validation precision and recall at every epoch for a onehot-encoded classification task. Also please look at this SO answer to see how it can be done with keras.backend functionality.

import keras as keras
import numpy as np
from keras.optimizers import SGD
from sklearn.metrics import precision_score, recall_score

model = keras.models.Sequential()
# ...
sgd = SGD(lr=0.001, momentum=0.9)
model.compile(optimizer=sgd, loss='categorical_crossentropy', metrics=['accuracy'])


class Metrics(keras.callbacks.Callback):
    def on_train_begin(self, logs={}):
        self._data = []

    def on_epoch_end(self, batch, logs={}):
        X_val, y_val = self.validation_data[0], self.validation_data[1]
        y_predict = np.asarray(model.predict(X_val))

        y_val = np.argmax(y_val, axis=1)
        y_predict = np.argmax(y_predict, axis=1)

        self._data.append({
            'val_recall': recall_score(y_val, y_predict),
            'val_precision': precision_score(y_val, y_predict),
        })
        return

    def get_data(self):
        return self._data


metrics = Metrics()
history = model.fit(X_train, y_train, epochs=100, validation_data=(X_val, y_val), callbacks=[metrics])
metrics.get_data()

This thread is a little stale, but just in case it’ll help someone landing here. If you are willing to upgrade to Keras v2.1.6, there has been a lot of work on getting stateful metrics to work though there seems to be more work that is being done (https://github.com/keras-team/keras/pull/9446).

Anyway, I found the best way to integrate precision/recall was using the custom metric that subclasses Layer, shown by example in BinaryTruePositives.

For recall, this would look like:

class Recall(keras.layers.Layer):
    """Stateful Metric to count the total recall over all batches.

    Assumes predictions and targets of shape `(samples, 1)`.

    # Arguments
        name: String, name for the metric.
    """

    def __init__(self, name='recall', **kwargs):
        super(Recall, self).__init__(name=name, **kwargs)
        self.stateful = True

        self.recall = K.variable(value=0.0, dtype='float32')
        self.true_positives = K.variable(value=0, dtype='int32')
        self.false_negatives = K.variable(value=0, dtype='int32')
    def reset_states(self):
        K.set_value(self.recall, 0.0)
        K.set_value(self.true_positives, 0)
        K.set_value(self.false_negatives, 0)

    def __call__(self, y_true, y_pred):
        """Computes the number of true positives in a batch.

        # Arguments
            y_true: Tensor, batch_wise labels
            y_pred: Tensor, batch_wise predictions

        # Returns
            The total number of true positives seen this epoch at the
                completion of the batch.
        """
        y_true = K.cast(y_true, 'int32')
        y_pred = K.cast(K.round(y_pred), 'int32')

        # False negative calculations
        y_true = K.cast(y_true, 'int32')
        y_pred = K.cast(K.round(y_pred), 'int32')
        false_neg = K.cast(K.sum(K.cast(K.greater(y_pred, y_true), 'int32')), 'int32')
        current_false_neg = self.false_negatives * 1
        self.add_update(K.update_add(self.false_negatives,
                                     false_neg),
                        inputs=[y_true, y_pred])
        # True positive  calculations
        correct_preds = K.cast(K.equal(y_pred, y_true), 'int32')
        true_pos = K.cast(K.sum(correct_preds * y_true), 'int32')
        current_true_pos = self.true_positives * 1
        self.add_update(K.update_add(self.true_positives,
                                     true_pos),
                        inputs=[y_true, y_pred])
        # Combine
        recall = (K.cast(self.true_positives, 'float32') / (K.cast(self.true_positives, 'float32') + K.cast(self.false_negatives, 'float32') + K.cast(K.epsilon(), 'float32')))
        self.add_update(K.update(self.recall,
                                     recall),
                        inputs=[y_true, y_pred])

        return recall