python - keras cnn模型仅针对所有测试图像预测一个类别

Question

我试图建立一个图像分类模型，其中有两个类，分别有（1）或没有（0）我可以建立模型并得到1的精度这太好了，不可能是真的（这是个问题），但是当我使用predict_generator时，因为我的图像在文件夹中，它只返回1个类0（不带类）。好像有个问题，但我解决不了，我看了很多文章，但还是解决不了。

image_shape = (220, 525, 3) #height, width, channels
img_width = 96
img_height = 96
channels = 3

epochs = 10

no_train_images = 11957              #!ls ../data/train/* | wc -l
no_test_images = 652                 #!ls ../data/test/* | wc -l
no_valid_images = 6156               #!ls ../data/test/* | wc -l

train_dir = '../data/train/'
test_dir = '../data/test/'
valid_dir = '../data/valid/'


test folder structure is the following:
test/test_folder/images_from_both_classes.jpg


#!ls ../data/train/without/ | wc -l 5606        #theres no class inbalance
#!ls ../data/train/with/ | wc -l 6351

#!ls ../data/valid/without/ | wc -l 2899
#!ls ../data/valid/with/ | wc -l 3257

classification_model = Sequential()

# First layer with 2D convolution (32 filters, (3, 3) kernel size 3x3, input_shape=(img_width, img_height, channels))
classification_model.add(Conv2D(32, (3, 3), input_shape=input_shape))
# Activation Function = ReLu increases the non-linearity
classification_model.add(Activation('relu'))
# Max-Pooling layer with the size of the grid 2x2
classification_model.add(MaxPooling2D(pool_size=(2, 2)))
# Randomly disconnets some nodes between this layer and the next 
classification_model.add(Dropout(0.2))

classification_model.add(Conv2D(32, (3, 3)))
classification_model.add(Activation('relu'))
classification_model.add(MaxPooling2D(pool_size=(2, 2)))
classification_model.add(Dropout(0.2))

classification_model.add(Conv2D(64, (3, 3)))
classification_model.add(Activation('relu'))
classification_model.add(MaxPooling2D(pool_size=(2, 2)))
classification_model.add(Dropout(0.25))

classification_model.add(Conv2D(64, (3, 3)))
classification_model.add(Activation('relu'))
classification_model.add(MaxPooling2D(pool_size=(2, 2)))
classification_model.add(Dropout(0.3))

classification_model.add(Flatten())
classification_model.add(Dense(64))
classification_model.add(Activation('relu'))
classification_model.add(Dropout(0.5))
classification_model.add(Dense(1))
classification_model.add(Activation('sigmoid'))

# Using binary_crossentropy as we only have 2 classes
classification_model.compile(loss='binary_crossentropy', optimizer='rmsprop', metrics=['accuracy'])



batch_size = 32

# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
    rescale=1. / 255,
    zoom_range=0.2)

# this is the augmentation configuration we will use for testing:
# only rescaling
valid_datagen = ImageDataGenerator(rescale=1. / 255)
test_datagen = ImageDataGenerator()

train_generator = train_datagen.flow_from_directory(
    train_dir,
    target_size = (img_width, img_height),
    batch_size = batch_size,
    class_mode = 'binary',
    shuffle = True)

valid_generator = valid_datagen.flow_from_directory(
    valid_dir,
    target_size = (img_width, img_height),
    batch_size = batch_size,
    class_mode = 'binary',
    shuffle = False)

test_generator = test_datagen.flow_from_directory(
    test_dir,
    target_size = (img_width, img_height),
    batch_size = 1,
    class_mode = None,
    shuffle = False)

mpd = classification_model.fit_generator(
    train_generator,
    steps_per_epoch = no_train_images // batch_size,         # number of images per epoch
    epochs = epochs,                                         # number of iterations over the entire data
    validation_data = valid_generator,
    validation_steps = no_valid_images // batch_size)  

纪元1/10
373/373[=========]-119s 320ms/步-损耗：0.5214-acc:0.7357-valu损耗：0.2720-valu acc:0.8758
纪元2/10
373/373[=========]-120s 322ms/步-损耗：0.2485-acc:0.8935-valu损耗：0.0568-valu acc:0.9829
纪元3/10
373/373[=========]-130s 350ms/步-损耗：0.1427-acc:0.9435-valu损耗：0.0410-valu acc:0.9796
纪元4/10
373/373[=========]-127S 341Ms/步-损耗：0.1053-acc:0.9623-valu损耗：0.0197-valu acc:0.9971
纪元5/10
373/373[=========]-126S 337MS/步-损耗：0.0817-acc:0.9682-valu损耗：0.0136-valu acc:0.9948
纪元6/10
373/373[==========]-123s 329ms/步-损耗：0.0665-acc:0.9754-val_损耗：0.0116-val_acc:0.9985
纪元7/10
373/373[=========]-140S 376ms/步-损耗：0.0518-acc:0.9817-valu损耗：0.0035-valu acc:0.9997
纪元8/10
373/373[=======]-144s 386ms/步-损耗：0.0539-acc:0.9832-valu损耗：8.9459e-04-valu acc:1.0000
纪元9/10
373/373[=========]-122S 327MS/步-损耗：0.0434-acc:0.9850-valu损耗：0.0023-valu acc:0.9997
纪元10/10
373/373[=========]-125S 336ms/步-损耗：0.0513-acc:0.9844-valu损耗：0.0014-valu acc:1.0000

valid_generator.batch_size=1
score = classification_model.evaluate_generator(valid_generator, 
                                                no_test_images/batch_size, pickle_safe=False)
test_generator.reset()
scores=classification_model.predict_generator(test_generator, len(test_generator))

print("Loss: ", score[0], "Accuracy: ", score[1])

predicted_class_indices=np.argmax(scores,axis=1)
print(predicted_class_indices)

labels = (train_generator.class_indices)
labelss = dict((v,k) for k,v in labels.items())
predictions = [labelss[k] for k in predicted_class_indices]

filenames=test_generator.filenames
results=pd.DataFrame({"Filename":filenames,
                      "Predictions":predictions})

print(results)

损耗：5.404246180551993e-06精度：1.0
打印（预测的分类索引）-全部0
[0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0]

                              Filename Predictions
0      test_folder/video_3_frame10.jpg   without
1    test_folder/video_3_frame1001.jpg   without
2    test_folder/video_3_frame1006.jpg   without
3    test_folder/video_3_frame1008.jpg   without
4    test_folder/video_3_frame1009.jpg   without
5    test_folder/video_3_frame1010.jpg   without
6    test_folder/video_3_frame1013.jpg   without
7    test_folder/video_3_frame1014.jpg   without
8    test_folder/video_3_frame1022.jpg   without
9    test_folder/video_3_frame1023.jpg   without
10    test_folder/video_3_frame103.jpg   without
11   test_folder/video_3_frame1036.jpg   without
12   test_folder/video_3_frame1039.jpg   without
13    test_folder/video_3_frame104.jpg   without
14   test_folder/video_3_frame1042.jpg   without
15   test_folder/video_3_frame1043.jpg   without
16   test_folder/video_3_frame1048.jpg   without
17    test_folder/video_3_frame105.jpg   without
18   test_folder/video_3_frame1051.jpg   without
19   test_folder/video_3_frame1052.jpg   without
20   test_folder/video_3_frame1054.jpg   without
21   test_folder/video_3_frame1055.jpg   without
22   test_folder/video_3_frame1057.jpg   without
23   test_folder/video_3_frame1059.jpg   without
24   test_folder/video_3_frame1060.jpg   without

…只是一些输出，但所有650+都没有类。
这是输出，正如您所看到的，对于without类，所有预测值都为0。
这是我第一次尝试使用Keras和CNN，所以任何帮助都会非常感谢。
更新
我已经解决了。我目前正在研究精确度，但主要问题现在已经解决了。
这是引起问题的线路。

predicted_class_indices=np.argmax(scores,axis=1)

argmax将返回结果的索引位置，但由于我使用的是二进制类，在我的最后一层，我有1密集它将只返回一个值，因此它将始终返回第一个类（0作为索引位置）。由于网络是唯一设置的，返回一个类。
更改以下内容修复了我的问题。
将列车和测试发电机的“分类”模式更改为“分类”
将最终密集层从1更改为2，这样将返回两个类的分数/概率。因此，当您使用argmax时，它将返回最高分的索引位置，指示它预测了哪个类。

Answer 1

您应该更改此行：

test_datagen = ImageDataGenerator()

签署人：

test_datagen = ImageDataGenerator(rescale=1. / 255)

如果不以与列车/有效集相同的方式对测试集进行预处理，将无法获得预期的结果