混淆矩阵错误 "Classification metrics can't handle a mix of multilabel-indicator and multiclass targets"
confusion matrix error "Classification metrics can't handle a mix of multilabel-indicator and multiclass targets"
我得到一个
Classification metrics can't handle a mix of multilabel-indicator and multiclass targets
当我尝试使用混淆矩阵时出错。
我正在做我的第一个深度学习项目。我是新手。我正在使用 keras 提供的 mnist 数据集。我已经成功地训练和测试了我的模型。
但是，当我尝试使用 scikit 学习混淆矩阵时，出现了上述错误。我已经搜索了一个答案，虽然有关于此错误的答案，但其中 none 对我有用。从我在网上找到的，它可能与损失函数有关（我在我的代码中使用 categorical_crossentropy ）。我尝试将其更改为 sparse_categorical_crossentropy 但这只是给了我
Error when checking target: expected dense_2 to have shape (1,) but got array with shape (10,)
当我 运行 模型上的 fit() 函数时。
这是代码。 （为了简洁起见，我省略了进口）
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') / 255
test_images = test_images.reshape((10000, 28 * 28))
test_images = test_images.astype('float32') / 255
train_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)
我该如何解决这个问题？
混淆矩阵需要将标签和预测都作为单个数字，而不是单热编码向量；尽管您已经使用 model.predict_classes() 对您的预测进行了此操作，即
rounded_predictions = model.predict_classes(test_images, batch_size=128, verbose=0)
rounded_predictions[1]
# 2
你的 test_labels 仍然是单热编码的：
test_labels[1]
# array([0., 0., 1., 0., 0., 0., 0., 0., 0., 0.], dtype=float32)
所以，你也应该将它们转换为个位数，如下所示：
import numpy as np
rounded_labels=np.argmax(test_labels, axis=1)
rounded_labels[1]
# 2
之后，混淆矩阵应该就OK了：
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]])
这里重复了同样的问题here, and the solution is overall the same. That's why, that question is closed and unable to receive an answer. So I like to add an answer to this question（希望这不是非法的）。
下面的代码是不言自明的。 @desertnaut 给出了确切的原因，所以不需要解释更多的东西。 question的作者尝试将预测的特征分别传递给fit的函数，相信可以让新手更好的理解
import numpy as np
import pandas as pd
import tensorflow as tf
from sklearn.model_selection import train_test_split
from tensorflow.keras.applications.resnet50 import ResNet50
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
x_train = np.expand_dims(x_train, axis=-1)
x_train = np.repeat(x_train, 3, axis=-1)
x_train = x_train.astype('float32') / 255
y_train = tf.keras.utils.to_categorical(y_train, num_classes=10)
print(x_train.shape, y_train.shape)
# (60000, 28, 28, 3) (60000, 10)
从预训练权重中提取特征（迁移学习）。
base_model = ResNet50(weights='imagenet', include_top=False)
pred_x_train = base_model.predict(x_train)
pred_x_train.shape
# (60000, 1, 1, 2048)
为进一步的训练过程重塑。
pred_x_train = pred_x_train.reshape(60000, 1*1*2048)
pred_x_train.shape
# (60000, 2048)
具有顺序的模型API。
model = tf.keras.Sequential()
model.add(tf.keras.layers.Dense(512, activation='relu', input_shape=(2048,)))
model.add(tf.keras.layers.Dropout(0.5))
model.add(tf.keras.layers.Dense(10, activation='softmax'))
编译并运行.
model.compile(loss='categorical_crossentropy',optimizer='Adam',metrics=['accuracy'])
model.fit(pred_x_train, y_train, epochs=2, verbose=2)
Epoch 1/2
1875/1875 - 4s - loss: 0.6993 - accuracy: 0.7744
Epoch 2/2
1875/1875 - 4s - loss: 0.4451 - accuracy: 0.8572
评价。
from sklearn.metrics import classification_report
# predict
pred = model.predict(pred_x_train, batch_size = 32)
pred = np.argmax(predictions, axis=1)
# label
y_train = np.argmax(y_train, axis=1)
print(y_train.shape, pred.shape)
print(y_train[:5], pred[:5])
# (60000,) (60000,)
# [5 0 4 1 9] [5 0 4 1 9]
print(classification_report(y_train, pred))
precision recall f1-score support
0 0.95 0.97 0.96 5923
1 0.97 0.99 0.98 6742
2 0.90 0.94 0.92 5958
3 0.89 0.91 0.90 6131
4 0.97 0.89 0.93 5842
5 0.88 0.91 0.89 5421
6 0.95 0.97 0.96 5918
7 0.94 0.95 0.94 6265
8 0.94 0.78 0.85 5851
9 0.87 0.93 0.90 5949
accuracy 0.93 60000
macro avg 0.93 0.92 0.92 60000
weighted avg 0.93 0.93 0.92 60000
我得到一个
Classification metrics can't handle a mix of multilabel-indicator and multiclass targets
当我尝试使用混淆矩阵时出错。
我正在做我的第一个深度学习项目。我是新手。我正在使用 keras 提供的 mnist 数据集。我已经成功地训练和测试了我的模型。
但是，当我尝试使用 scikit 学习混淆矩阵时，出现了上述错误。我已经搜索了一个答案，虽然有关于此错误的答案，但其中 none 对我有用。从我在网上找到的，它可能与损失函数有关（我在我的代码中使用 categorical_crossentropy ）。我尝试将其更改为 sparse_categorical_crossentropy 但这只是给了我
Error when checking target: expected dense_2 to have shape (1,) but got array with shape (10,)
当我 运行 模型上的 fit() 函数时。
这是代码。 （为了简洁起见，我省略了进口）
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') / 255
test_images = test_images.reshape((10000, 28 * 28))
test_images = test_images.astype('float32') / 255
train_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)
我该如何解决这个问题？
混淆矩阵需要将标签和预测都作为单个数字，而不是单热编码向量；尽管您已经使用 model.predict_classes() 对您的预测进行了此操作，即
rounded_predictions = model.predict_classes(test_images, batch_size=128, verbose=0)
rounded_predictions[1]
# 2
你的 test_labels 仍然是单热编码的：
test_labels[1]
# array([0., 0., 1., 0., 0., 0., 0., 0., 0., 0.], dtype=float32)
所以，你也应该将它们转换为个位数，如下所示：
import numpy as np
rounded_labels=np.argmax(test_labels, axis=1)
rounded_labels[1]
# 2
之后，混淆矩阵应该就OK了：
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]])
这里重复了同样的问题here, and the solution is overall the same. That's why, that question is closed and unable to receive an answer. So I like to add an answer to this question（希望这不是非法的）。
下面的代码是不言自明的。 @desertnaut 给出了确切的原因，所以不需要解释更多的东西。 question的作者尝试将预测的特征分别传递给fit的函数，相信可以让新手更好的理解
import numpy as np
import pandas as pd
import tensorflow as tf
from sklearn.model_selection import train_test_split
from tensorflow.keras.applications.resnet50 import ResNet50
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
x_train = np.expand_dims(x_train, axis=-1)
x_train = np.repeat(x_train, 3, axis=-1)
x_train = x_train.astype('float32') / 255
y_train = tf.keras.utils.to_categorical(y_train, num_classes=10)
print(x_train.shape, y_train.shape)
# (60000, 28, 28, 3) (60000, 10)
从预训练权重中提取特征（迁移学习）。
base_model = ResNet50(weights='imagenet', include_top=False)
pred_x_train = base_model.predict(x_train)
pred_x_train.shape
# (60000, 1, 1, 2048)
为进一步的训练过程重塑。
pred_x_train = pred_x_train.reshape(60000, 1*1*2048)
pred_x_train.shape
# (60000, 2048)
具有顺序的模型API。
model = tf.keras.Sequential()
model.add(tf.keras.layers.Dense(512, activation='relu', input_shape=(2048,)))
model.add(tf.keras.layers.Dropout(0.5))
model.add(tf.keras.layers.Dense(10, activation='softmax'))
编译并运行.
model.compile(loss='categorical_crossentropy',optimizer='Adam',metrics=['accuracy'])
model.fit(pred_x_train, y_train, epochs=2, verbose=2)
Epoch 1/2
1875/1875 - 4s - loss: 0.6993 - accuracy: 0.7744
Epoch 2/2
1875/1875 - 4s - loss: 0.4451 - accuracy: 0.8572
评价。
from sklearn.metrics import classification_report
# predict
pred = model.predict(pred_x_train, batch_size = 32)
pred = np.argmax(predictions, axis=1)
# label
y_train = np.argmax(y_train, axis=1)
print(y_train.shape, pred.shape)
print(y_train[:5], pred[:5])
# (60000,) (60000,)
# [5 0 4 1 9] [5 0 4 1 9]
print(classification_report(y_train, pred))
precision recall f1-score support
0 0.95 0.97 0.96 5923
1 0.97 0.99 0.98 6742
2 0.90 0.94 0.92 5958
3 0.89 0.91 0.90 6131
4 0.97 0.89 0.93 5842
5 0.88 0.91 0.89 5421
6 0.95 0.97 0.96 5918
7 0.94 0.95 0.94 6265
8 0.94 0.78 0.85 5851
9 0.87 0.93 0.90 5949
accuracy 0.93 60000
macro avg 0.93 0.92 0.92 60000
weighted avg 0.93 0.93 0.92 60000