如何解决class_mode中的binary，sparse和categorical有什么区别
下面的代码便于理解，
#Fitting the CNN to the images
from keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(
rescale = 1.0 / 255,shear_range = 0.2,zoom_range = 0.2,horizontal_flip = True
)
test_datagen = ImageDataGenerator(rescale= 1.0 / 255)
training_set = train_datagen.flow_from_directory(
'dataset/training_set',target_size = (64,64),batch_size = 32,class_mode = 'binary'
)
test_set = test_datagen.flow_from_directory(
'dataset/test_set',class_mode = 'binary'
)
当我使用稀疏 / 类别时。显示相同的输出，
在输出下方
Found 214 images belonging to 5 classes.
Found 20 images belonging to 5 classes.
注意：该代码用于训练数据集，但不幸的是它不能训练
所以需要帮助
解决方法
它们与loss function相关。
'binary'班级模式为您提供了许多每个班级。例如，如果您的数据集具有3个A，B，C类，则目标数据将为A类为0，B为1，C为2。
categorical给您one hot encoding，(1,0)代表A，(0,1,0)代表B，(0,1)代表C。
您可以为此寻找不同的东西。
test_set = test_datagen.flow_from_directory(
'dataset/test_set',target_size = (64,64),batch_size = 32,class_mode = 'binary'
)
x,y = test_set[0]
print(y.shape) # (32,)
print(y)
test_set = test_datagen.flow_from_directory(
'dataset/test_set',class_mode = 'categorical'
)
x,n) where n is equal to how many folder you have in 'dataset/test_set'
print(y)
sparse中不使用flow_from_directory，通常在图像可以超过一个类别时使用。例如，如果图像可以是A和C，则目标将是(1,1)。
binary之所以这样称呼，是因为在早期版本中，它只给您1和0。
来自：https://www.tensorflow.org/api_docs/python/tf/keras/preprocessing/image/ImageDataGenerator “分类”、“二进制”、“稀疏”、“输入”或“无”之一。默认值：“分类”。确定返回的标签数组的类型：
"categorical" will be 2D one-hot encoded labels,"binary" will be 1D binary labels,"sparse" will be 1D integer labels,"input" will be images identical to input images (mainly used to work with autoencoders).
If None,no labels are returned (the generator will only yield batches of image data,which is useful to use with model.predict()). Please note that in case of class_mode None,the data still needs to reside in a subdirectory of directory for it to work correctly.