[英]How to calculate precision and recall in Keras
我正在用Keras 2.02(带有Tensorflow后端)构建一个多类分类器,我不知道如何计算Keras中的精度和召回率。 请帮我。
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()])
我的回答是基于Keras GH问题的评论 。 它计算验证精度并在每个时期调用单一编码的分类任务。 另外,请查看此SO答案 ,了解如何使用keras.backend
功能完成此操作。
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,但万一它会帮助有人登陆这里。 如果你愿意升级到Keras v2.1.6,那么有很多工作要让有状态的指标工作,尽管似乎还有更多工作要做( https://github.com/keras-team/keras / pull / 9446 )。
无论如何,我发现集成精度/召回的最佳方法是使用子类Layer
的自定义度量,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
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)
这个博客非常有用。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.