Keras 中的类数错误

Question

Keras 在训练集和测试集文件夹中发现错误数量的类。我有 3 节课，但它一直说有 4 节课。有人可以帮助我吗？

这里是代码：

cnn = Sequential()

cnn.add(Conv2D(32, (3, 3), input_shape = (64, 64, 3), activation = 'relu'))
cnn.add(Dropout(0.5))
cnn.add(MaxPooling2D(pool_size = (2, 2)))


cnn.add(Conv2D(32, (3, 3), activation = 'relu'))
cnn.add(Dropout(0.5))
cnn.add(MaxPooling2D(pool_size = (2, 2)))


cnn.add(Conv2D(64, (3, 3), activation = 'relu'))
cnn.add(Dropout(0.5))
cnn.add(MaxPooling2D(pool_size = (2, 2)))

cnn.add(Conv2D(128, (3, 3), activation = 'relu'))
cnn.add(Dropout(0.5))
cnn.add(MaxPooling2D(pool_size = (2, 2)))

#Full connection
cnn.add(Dense(units = 64, activation = 'relu'))
cnn.add(Dense(units = 64, activation = 'relu'))
cnn.add(Dense(units = 3, activation = 'softmax'))

# Compiling the CNN
cnn.compile(optimizer = OPTIMIZER, loss = 'categorical_crossentropy', metrics = ['accuracy'])


     #Fitting
    from keras.preprocessing.image import ImageDataGenerator

    train_datagen = ImageDataGenerator(rescale = 1./255,
                                       shear_range = 0.2,
                                       zoom_range = 0.2,
                                       horizontal_flip = True)

    test_datagen = ImageDataGenerator(rescale = 1./255)

    training_set = train_datagen.flow_from_directory('dataset/training_set',
                                                     target_size = tgt_size,
                                                     batch_size = batch_size,
                                                     class_mode = 'categorical')

    test_set = test_datagen.flow_from_directory('dataset/test_set',
                                                target_size = tgt_size,
                                                batch_size = batch_size,
                                                class_mode = 'categorical')

和错误：

Found 12000 images belonging to 4 classes.
Found 3000 images belonging to 4 classes.

Epoch 1/10
---------------------------------------------------------------------------
ValueError: Error when checking target: expected dense_15 to have 4 dimensions, but got array with shape (3, 4)

编辑：

只有 Google Cloud 中的 Jupyter Notebook 才会出现这种情况。当我在本地使用 Spyder 时，它会找到正确的类数。

Answer 1

您现在可能已经自己发现，Jupyter 创建隐藏的检查点文件夹用于备份目的。这就是为什么在使用 flow_from_directory 时总是有一个额外的类（如文件夹中）的原因。最简单的解决方案是删除该隐藏文件夹。