Question

我使用Keras构建了CNN分类器，其中：

训练数据集：3194

验证数据集：1020

测试数据集：1023

我使用下面的代码通过训练和验证数据集来构建和评估分类器。

from keras.models import Sequential
from keras.layers import Conv2D,Activation,MaxPooling2D,Dense,Flatten,Dropout
import numpy as np
from keras.preprocessing.image import ImageDataGenerator
from IPython.display import display
import matplotlib.pyplot as plt
from PIL import Image
from sklearn.metrics import classification_report, confusion_matrix
import keras
from keras.layers import BatchNormalization
from keras.optimizers import Adam

classifier = Sequential()
classifier.add(Conv2D(16,(3,3),input_shape=(200,200,3)))
classifier.add(Activation('relu'))
classifier.add(Flatten())
classifier.add(Dense(128))
classifier.add(Activation('relu'))
classifier.add(Dropout(0.5))
classifier.add(Dense(2))
classifier.add(Activation('softmax'))
classifier.summary()
classifier.compile(optimizer =keras.optimizers.Adam(lr=0.1),
                   loss ='categorical_crossentropy',
                   metrics =['accuracy'])
train_datagen = ImageDataGenerator(rescale =1./255,
                                   shear_range =0.2,
                                   zoom_range = 0.2,
                                   horizontal_flip =True)
test_datagen = ImageDataGenerator(rescale = 1./255)

batchsize=10
training_set = train_datagen.flow_from_directory('/home/osboxes/Downloads/Downloads/Journal_Paper/Benign_Malicious/Spectrogram/Train/',
                                                target_size=(200,200),
                                                batch_size= batchsize,
                                                class_mode='categorical')

test_set = test_datagen.flow_from_directory('/home/osboxes/Downloads/Downloads/Journal_Paper/Benign_Malicious/Spectrogram/Validate/',
                                           target_size = (200,200),
                                           batch_size = batchsize,
                       shuffle=False,
                                           class_mode ='categorical')
history=classifier.fit_generator(training_set,
                        steps_per_epoch = 3194 // batchsize,
                        epochs = 100,
                        validation_data =test_set,
                        validation_steps = 1020 // batchsize)


Y_pred = classifier.predict_generator(test_set, steps= 1020 // batchsize)
y_pred = np.argmax(Y_pred, axis=1)
print('Confusion Matrix')
print(confusion_matrix(test_set.classes, y_pred))
print('Classification Report')
target_names = test_set.classes
class_labels = list(test_set.class_indices.keys()) 
target_names = ['Bening','Malicious'] 
report = classification_report(test_set.classes, y_pred, target_names=class_labels)
print(report) 

# summarize history for accuracy
plt.plot(history.history['accuracy'])
plt.plot(history.history['val_accuracy'])
plt.title('model accuracy 16 with dropout rl .1')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()
# summarize history for loss
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('model loss 16 with dropout rl .1')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()
classifier.save('16_With_Dropout_rl_001.h5')

保存模型后，我使用以下代码加载了模型。另外，我正在尝试使用测试数据集评估模型（在构建和评估过程中分类器尚未看到该模型）。但是，以下代码给了我错误（ValueError：找到的输入变量的样本数不一致：[1023，1020]）。有什么想法吗？


from keras.models import Sequential
from keras.layers import Conv2D,Activation,MaxPooling2D,Dense,Flatten,Dropout
import numpy as np
from keras.preprocessing.image import ImageDataGenerator
from IPython.display import display
import matplotlib.pyplot as plt
from PIL import Image
from keras.models import load_model
from sklearn.metrics import classification_report, confusion_matrix
from keras.models import load_model
import pickle


classifier = load_model('16_With_Dropout_rl_001.h5')

batchsize=10

test_datagen = ImageDataGenerator(rescale = 1./255)

test_set = test_datagen.flow_from_directory('/home/osboxes/Downloads/Downloads/Journal_Paper/Benign_Malicious/Spectrogram/Test/',
                                           target_size = (200,200),
                                           batch_size = batchsize,
                       shuffle=False,
                                           class_mode ='categorical')

Y_pred = classifier.predict_generator(test_set, steps= 1023 // batchsize)
y_pred = np.argmax(Y_pred, axis=1)
print('Confusion Matrix')
print(confusion_matrix(test_set.classes, y_pred))
print('Classification Report')
target_names = test_set.classes
class_labels = list(test_set.class_indices.keys()) 
target_names = ['Bening', 'Malicious'] 
report = classification_report(test_set.classes, y_pred, target_names=class_labels)
print(report)

Answer 1

这是由于predict_generator()中的步骤数所致； 1023//10产生102批；每批大小为10的样本将产生1020个样本；因此，您必须将行更改为：

Y_pred = classifier.predict_generator(test_set, steps= (1023 // batchsize)+1)

CNN加载模型不适用于测试数据集

1 个答案: