我得到一個(gè)Classification metrics can't handle a mix of multilabel-indicator and multiclass targets當(dāng)我嘗試使用混淆矩陣時(shí)出錯(cuò)。我正在做我的第一個(gè)深度學(xué)習(xí)項(xiàng)目。我是新手。我正在使用由 keras 提供的 mnist 數(shù)據(jù)集。我已經(jīng)成功地訓(xùn)練和測試了我的模型。但是，當(dāng)我嘗試使用 scikit learn 混淆矩陣時(shí)，我收到了上述錯(cuò)誤。我已經(jīng)搜索了一個(gè)答案，雖然有關(guān)于這個(gè)錯(cuò)誤的答案，但沒有一個(gè)對我有用。從我在網(wǎng)上找到的內(nèi)容來看，它可能與損失函數(shù)有關(guān)（我categorical_crossentropy在我的代碼中使用了）。我嘗試將其更改為，sparse_categorical_crossentropy但這只是給了我Error when checking target: expected dense_2 to have shape (1,) but got array with shape (10,)當(dāng)我fit()在模型上運(yùn)行該函數(shù)時(shí)。這是代碼。（為簡潔起見，我省略了進(jìn)口）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)我怎樣才能解決這個(gè)問題？
2 回答
千萬里不及你
TA貢獻(xiàn)1784條經(jīng)驗(yàn) 獲得超9個(gè)贊
混淆矩陣需要將標(biāo)簽和預(yù)測作為個(gè)位數(shù)，而不是作為單熱編碼向量；盡管您已經(jīng)使用model.predict_classes()，即
rounded_predictions = model.predict_classes(test_images, batch_size=128, verbose=0)
rounded_predictions[1]
# 2
你test_labels仍然是one-hot編碼：
test_labels[1]
# array([0., 0., 1., 0., 0., 0., 0., 0., 0., 0.], dtype=float32)
因此，您也應(yīng)該將它們轉(zhuǎn)換為個(gè)位數(shù)，如下所示：
import numpy as np
rounded_labels=np.argmax(test_labels, axis=1)
rounded_labels[1]
# 2
之后，混淆矩陣應(yīng)該會出現(xiàn)：
from sklearn.metrics import confusion_matrix
cm = 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]])
添加回答
舉報(bào)
0/150
提交
取消