我正在尝试建立一个图像分类模型，它有 2 个有（1）或没有（0）的类。我可以构建模型并获得 1 的准确度。这太好了，令人难以置信（这是一个问题），但是当我使用 predict_generator 因为我在文件夹中有图像时，它只返回 1 类 0（没有类）。似乎有问题，但我无法解决，我查看了很多文章，但仍然无法解决问题。
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/'
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 - 损失：0.5214 - acc ：0.7357 - val_loss：0.2720 - val_acc：0.8758
纪元 2/10 373/373 [===============================] - 120s 322ms/step - loss: 0.2485 - acc ：0.8935 - val_loss：0.0568 - val_acc：0.9829
纪元 3/10 373/373 [===============================] - 130s 350ms/步 - 损失：0.1427 - acc ：0.9435 - val_loss：0.0410 - val_acc：0.9796
纪元 4/10 373/373 [===============================] - 127s 341ms/step - loss: 0.1053 - acc ：0.9623 - val_loss：0.0197 - val_acc：0.9971
纪元 5/10 373/373 [===============================] - 126s 337ms/step - loss: 0.0817 - acc ：0.9682 - val_loss：0.0136 - val_acc：0.9948
纪元 6/10 373/373 [===============================] - 123s 329ms/步 - 损失：0.0665 - acc ：0.9754 - val_loss：0.0116 - val_acc：0.9985
纪元 7/10 373/373 [===============================] - 140s 376ms/步 - 损失：0.0518 - acc ：0.9817 - val_loss：0.0035 - val_acc：0.9997
纪元 8/10 373/373 [===============================] - 144s 386ms/步 - 损失：0.0539 - acc ：0.9832 - val_loss：8.9459e-04 - val_acc：1.0000
纪元 9/10 373/373 [===============================] - 122s 327ms/步 - 损失：0.0434 - acc ：0.9850 - val_loss：0.0023 - val_acc：0.9997
纪元 10/10 373/373 [===============================] - 125s 336ms/步 - 损失：0.0513 - acc ：0.9844 - val_loss：0.0014 - val_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)
损失：5.404246180551993e-06 精度：1.0
打印（predicted_class_indices） - 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 00 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0]0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0]0 0 0 0 0 0 0 0 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，如您所见，对于无类，所有预测值为 0。
这是我第一次尝试使用 Keras 和 CNN，因此非常感谢任何帮助。
更新
我已经解决了这个问题。我目前正在研究准确性，但现在主要问题已解决。
这是导致问题的线路。
predicted_class_indices=np.argmax(scores,axis=1)
argmax 将返回结果的索引位置，但是当我使用二进制类并且在我的最后一层中，我有 1 个密集的。它只会返回一个值，因此它将始终返回第一个类（0 作为索引位置）。由于网络只设置，返回一个类。
更改以下内容解决了我的问题。
- 将训练和测试生成器的 class_mode 更改为“分类”
- 将最终的密集层从 1 更改为 2，因此这将返回两个类的分数/概率。所以当你使用 argmax 时，它会返回最高分的索引位置，表明它预测了哪个类。