如何在 Keras 中计算精度和召回率

How to calculate precision and recall in Keras

我正在使用 Keras 2.02(带有 Tensorflow 后端)构建一个 multi-class classifier,我不知道如何在 Keras 中计算精度和召回率。请帮助我。

从 Keras 2.0 开始,精度和召回率已从 master 分支中删除。您必须自己实施它们。按照本指南创建自定义指标:Here.

可以找到精度和召回方程Here

或者重新使用 keras 中删除之前的代码 Here

删除了一些指标,因为它们是按批处理的,因此值可能正确也可能不正确。

为此使用 Scikit Learn 框架。

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 很有用。

Python 包 keras-metrics 可能对此有用(我是包的作者)。

import keras
import keras_metrics

model = models.Sequential()
model.add(keras.layers.Dense(1, activation="sigmoid", input_dim=2))
model.add(keras.layers.Dense(1, activation="softmax"))

model.compile(optimizer="sgd",
              loss="binary_crossentropy",
              metrics=[keras_metrics.precision(), keras_metrics.recall()])

更新:从Keras版本2.3.0开始,库分发包中提供了精确度、召回率等指标。

用法如下:

model.compile(optimizer="sgd",
              loss="binary_crossentropy",
              metrics=[keras.metrics.Precision(), keras.metrics.Recall()])

我的回答是基于 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 以了解如何使用 keras.backend 功能来完成。

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()

这个线程有点陈旧,但以防万一它会帮助某人登陆这里。如果您愿意升级到 Keras v2.1.6,虽然似乎还有更多工作要做 (https://github.com/keras-team/keras/pull/9446)。

已经有很多工作让有状态指标发挥作用。

无论如何,我发现集成 precision/recall 的最佳方法是使用子类 Layer 的自定义指标,如 BinaryTruePositives.

中的示例所示

回想一下,这看起来像:

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