ConvNet具有98%的测试精度，但预测总是错误的

Question

我目前正在建立一个卷积神经网络来区分清晰的心电图像和有噪声的心电图像。

带噪声：

无噪音：

from keras.models import Sequential
from keras.datasets import mnist
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Activation,Dropout,Flatten,Dense
from keras.preprocessing.image import ImageDataGenerator
from keras.callbacks import TensorBoard
from keras.layers import ZeroPadding2D
from keras.optimizers import Adam
from keras.callbacks import EarlyStopping

tensorboard = TensorBoard(log_dir="./logs",histogram_freq=0,write_graph=True,write_images=True)
earlystop = EarlyStopping(monitor='val_loss',patience=2,verbose=1)

# Variables
batchSize = 15
num_of_samples = 15000
num_of_testing_samples = 3750
num_of_val_samples = 2000

training_imGenProp = ImageDataGenerator(rescale = 1./255,
                                width_shift_range=0.02,
                                height_shift_range=0.02,
                                horizontal_flip=False,
                                fill_mode='nearest'
                                )   

testing_imGenProp = ImageDataGenerator(
                                rotation_range=5,
                                horizontal_flip=False,
                                fill_mode='nearest'
                                )

val_imGenProp = ImageDataGenerator(rescale = 1./255,
                                rotation_range=5,
                                zoom_range=0.2,
                                horizontal_flip=False,
                                fill_mode='nearest'
                                )                                    



# Create the model                                    
classifier = Sequential()
classifier.add(ZeroPadding2D(padding=(374,0),input_shape=(74,448,3)))
classifier.add(Conv2D(32, (3, 3), activation = 'relu'))

classifier.add(MaxPooling2D(pool_size = (2, 2)))
classifier.add(Conv2D(32, (3, 3), activation = 'relu'))
classifier.add(MaxPooling2D(pool_size = (2, 2)))

classifier.add(Flatten())
classifier.add(Dense(units = 128, activation = 'relu'))
classifier.add(Dropout(0.8))
classifier.add(Dense(units = 1, activation = 'sigmoid'))
classifier.summary()

adam = Adam(lr=0.00005)
classifier.compile(loss='binary_crossentropy',optimizer=adam,metrics=['accuracy'])

training_imGen = training_imGenProp.flow_from_directory(
                                'Directory\Training',
                                target_size=(74,448),
                                batch_size=batchSize,
                                class_mode='binary',

                                )

testing_imGen = testing_imGenProp.flow_from_directory(
                                'Directory\Testing',
                                target_size=(74,448),
                                batch_size=batchSize,
                                class_mode='binary',

                                )   

val_imGen = testing_imGenProp.flow_from_directory(
                                'Directory\Validation', 
                                target_size=(74,448),
                                batch_size=batchSize,
                                class_mode='binary',

                                )                                   

classifier.fit_generator(
                            training_imGen,
                            callbacks = [tensorboard,earlystop], 
                            steps_per_epoch=num_of_samples // batchSize,
                            epochs=30, 
                            validation_data = val_imGen,
                            validation_steps = num_of_val_samples // batchSize
                         ) 

score, acc = classifier.evaluate_generator(
                        testing_imGen,
                        num_of_testing_samples // batchSize,
                        verbose = 0
                    )     
print('Test score:', score)
print('Test accuracy:', acc)
classifier.save('Directory\Config_10_Model.h5')

下面是我用来预测训练模型的代码。

from keras.models import load_model
import numpy as np
from keras.preprocessing import image

model = load_model('Directory\Config_10_Model.h5')

test_image = image.load_img('Path_to_Without_Noise_Image\image3452.png', target_size = (74, 448))
test_image = image.img_to_array(test_image)
test_image = test_image/255
test_image = np.expand_dims(test_image, axis = 0)
result = model.predict(test_image)
y_classes = result.argmax(axis=-1)
print(y_classes)

我不知道为什么会发生这种情况，即使我从未使用相同的图像进行测试、验证或培训。有人能帮我一下吗？我尝试了所有的方法，用不同的超参数训练模型，但每次这个模型都输出[0]。

Answer 1

你在做二进制分类。结果的形状为[batch_size,1]。因此，如果您正在执行argmax()，您将始终得到0。

>>> import numpy as np
>>> result = np.random.rand(5,1)
>>> result
array([[ 0.54719484],
       [ 0.31675804],
       [ 0.55151251],
       [ 0.25014937],
       [ 0.00724972]])
>>> result.argmax(axis=-1)
array([0, 0, 0, 0, 0])
>>> (result > 0.5).astype(int)
array([[1],
       [0],
       [1],
       [0],
       [0]])
>>>