python - 使用 sklearn 使用 Keras 数据生成器绘制混淆矩阵

Question

Sklearn 明确定义了如何使用自己的分类模型绘制混淆矩阵 1 .
但是如何将它与使用数据生成器的 Keras 模型一起使用。让我们看一个示例代码:
首先我们需要训练模型。

import numpy as np
from keras import backend as K
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.preprocessing.image import ImageDataGenerator
from sklearn.metrics import classification_report, confusion_matrix

#Start
train_data_path = 'F://data//Train'
test_data_path = 'F://data//Validation'
img_rows = 150
img_cols = 150
epochs = 30
batch_size = 32
num_of_train_samples = 3000
num_of_test_samples = 600

#Image Generator
train_datagen = ImageDataGenerator(rescale=1. / 255,
                                   rotation_range=40,
                                   width_shift_range=0.2,
                                   height_shift_range=0.2,
                                   shear_range=0.2,
                                   zoom_range=0.2,
                                   horizontal_flip=True,
                                   fill_mode='nearest')

test_datagen = ImageDataGenerator(rescale=1. / 255)

train_generator = train_datagen.flow_from_directory(train_data_path,
                                                    target_size=(img_rows, img_cols),
                                                    batch_size=batch_size,
                                                    class_mode='categorical')

validation_generator = test_datagen.flow_from_directory(test_data_path,
                                                        target_size=(img_rows, img_cols),
                                                        batch_size=batch_size,
                                                        class_mode='categorical')

# Build model
model = Sequential()
model.add(Convolution2D(32, (3, 3), input_shape=(img_rows, img_cols, 3), padding='valid'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Convolution2D(32, (3, 3), padding='valid'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Convolution2D(64, (3, 3), padding='valid'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(5))
model.add(Activation('softmax'))

model.compile(loss='categorical_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])

#Train
model.fit_generator(train_generator,
                    steps_per_epoch=num_of_train_samples // batch_size,
                    epochs=epochs,
                    validation_data=validation_generator,
                    validation_steps=num_of_test_samples // batch_size)

现在在训练模型之后，让我们构建一个混淆矩阵。

#Confution Matrix and Classification Report
Y_pred = model.predict_generator(validation_generator, num_of_test_samples // batch_size+1)
y_pred = np.argmax(Y_pred, axis=1)
print('Confusion Matrix')
print(confusion_matrix(validation_generator.classes, y_pred))
print('Classification Report')
target_names = ['Cats', 'Dogs', 'Horse']
print(classification_report(validation_generator.classes, y_pred, target_names=target_names))

现在这到目前为止工作正常。但是如何将其保存为与上述 sklearn 示例相同的布局中的 png？
任何想法都受到高度赞赏。
提前致谢

Answer 1

像这样(另见 ConfusionMatrixDisplay 和 confusion_matrix ):

from sklearn.metrics import ConfusionMatrixDisplay
from sklearn.metrics import confusion_matrix
import matplotlib.pyplot as plt
import numpy as np


y_pred = np.array([0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2])
y_test = np.array([0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 2, 2, 2, 1, 2])
labels = ["Cats", "Dogs", "Horses"]

cm = confusion_matrix(y_test, y_pred)

disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=labels)

disp.plot(cmap=plt.cm.Blues)
plt.show()

结果: