Keras

Question

我正在使用 keras 中的 CNN 解决多分类问题。我的准确率和召回率分数总是超过 1，这根本没有任何意义。下面附上我的代码，我做错了什么？

def recall(y_true, y_pred):
     true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
     possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))
     recall = true_positives / (possible_positives + K.epsilon())
     return recall

def precision(y_true, y_pred):
    true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
    predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
    precision = true_positives / (predicted_positives + K.epsilon())
    return precision

model.compile(loss='categorical_crossentropy', optimizer='Adam', metrics=['accuracy',recall,precision])

Answer 1

我想通了。一旦您 one-hot 对所有分类标签进行编码，上面的代码就可以完美运行。另外，确保你没有 sparse_categorical_crossentropy 作为你的损失函数，而只是使用 categorical_crossentropy。

如果您希望将分类值转换为 Keras 中的 one-hot 编码值，您可以使用以下代码：

from keras.utils import to_categorical
y_train = to_categorical(y_train)

您必须执行上述操作的原因已在 Keras 文档中注明：

"when using the categorical_crossentropy loss, your targets should be in categorical format (e.g. if you have 10 classes, the target for each sample should be a 10-dimensional vector that is all-zeros except for a 1 at the index corresponding to the class of the sample). In order to convert integer targets into categorical targets, you can use the Keras utility to_categorical"

Keras - Precision和Recall大于1（多分类）

Keras - Precision and Recall is greater than 1 (Multi classification)

python

classification

machine-learning

precision-recall