我遇到一个
Classification metrics can't handle a mix of multilabel-indicator and multiclass targets
错误,当我尝试使用混淆矩阵时。
这是我的第一个深度学习项目。我对此很新。我使用了Keras提供的MNIST数据集。我已经成功地训练和测试了我的模型。
然而,当我尝试使用scikit-learn的混淆矩阵时,我得到了上述错误。我已经搜索了答案,尽管有关于这个错误的回答,但对我都不适用。从我在网上找到的信息来看,这可能与损失函数有关(我在代码中使用了categorical_crossentropy
)。我尝试将其更改为sparse_categorical_crossentropy
,但这只是在运行模型的fit()
函数时给我带来了
Error when checking target: expected dense_2 to have shape (1,) but got array with shape (10,)
错误。
这是我的代码。(为了简洁,我省略了导入部分)
model = Sequential()model.add(Dense(512, activation='relu', input_shape=(28 * 28,)))model.add(Dense(10, activation='softmax')) model.compile(optimizer='Adam', loss='categorical_crossentropy', metrics=['accuracy'])(train_images, train_labels), (test_images, test_labels) = mnist.load_data()train_images = train_images.reshape((60000, 28 * 28))train_images = train_images.astype('float32') / 255test_images = test_images.reshape((10000, 28 * 28))test_images = test_images.astype('float32') / 255train_labels = to_categorical(train_labels)test_labels = to_categorical(test_labels)model.fit(train_images, train_labels, epochs=10, batch_size=128)rounded_predictions = model.predict_classes(test_images, batch_size=128, verbose=0)cm = confusion_matrix(test_labels, rounded_predictions)
我该如何修复这个问题?
回答:
混淆矩阵需要标签和预测都是单一数字,而不是独热编码向量;虽然你已经通过model.predict_classes()
对你的预测做了处理,即
rounded_predictions = model.predict_classes(test_images, batch_size=128, verbose=0)rounded_predictions[1]# 2
你的test_labels
仍然是独热编码的:
test_labels[1]# array([0., 0., 1., 0., 0., 0., 0., 0., 0., 0.], dtype=float32)
因此,你也应该将它们转换为单一数字,如下所示:
之后,混淆矩阵应该能正常生成:
from sklearn.metrics import confusion_matrixcm = confusion_matrix(rounded_labels, rounded_predictions)cm# result:array([[ 971, 0, 0, 2, 1, 0, 2, 1, 3, 0], [ 0, 1121, 2, 1, 0, 1, 3, 0, 7, 0], [ 5, 4, 990, 7, 5, 3, 2, 7, 9, 0], [ 0, 0, 0, 992, 0, 2, 0, 7, 7, 2], [ 2, 0, 2, 0, 956, 0, 3, 3, 2, 14], [ 3, 0, 0, 10, 1, 872, 3, 0, 1, 2], [ 5, 3, 1, 1, 9, 10, 926, 0, 3, 0], [ 0, 7, 10, 1, 0, 2, 0, 997, 1, 10], [ 5, 0, 3, 7, 5, 7, 3, 4, 937, 3], [ 5, 5, 0, 9, 10, 3, 0, 8, 3, 966]])