我尝试使用Keras中的ImageDataGenerator将validation_split设置为某个分数来拆分数据（图像）。
这是我代码

#Generate batches of tensor image data with real-time data augmentation, 
looped over in batches 
train_DataGen_Augmnt =ImageDataGenerator(
    rescale=1./255, 
    featurewise_center=True,
    validation_split=0.2,
    rotation_range=30,
    horizontal_flip=True,
    )

#validation data not augmented!
Validation_DataGen = ImageDataGenerator(rescale=1./255)

# Flow training images in batches of 32 using train_datagen generator
train_generator = train_DataGen_Augmnt.flow_from_directory(
    base_dir,
    subset='training',   
    target_size=(150, 150),  
    batch_size=32,
    #save_to_dir='images/Agumented'
    )

# Flow validation images in batches of 32 using test_datagen generator
validation_generator = Validation_DataGen.flow_from_directory(
    base_dir,
    subset='validation',
    target_size=(150, 150),
    batch_size=32,
    )

分割似乎在分割数据时起作用，但仅显示用于训练的分割
以下是运行此命令时的输出

Found 89 images belonging to 3 classes.
Found 0 images belonging to 3 classes.