由于训练数据集的数据扩充需求，通常需要ImageDataGenerator的多个示例，而没有扩充的相同ImageDataGenerator可用于验证和测试数据集（以及它们对应的目录路径）。在训练模型之后，model.evaluate_generator可用于评估测试数据集上的模型性能。以下是给定模型和数据集有效目录的简单示例：

import tensorflow as tf
from tensorflow.keras.preprocessing.image import ImageDataGenerator

#An ImageDataGenerator with augmentation to generate images for training dataset
train_datagen = ImageDataGenerator(
    rescale=1./255,
    rotation_range=40,
    zoom_range=0.15,
    shear_range=0.1,
    height_shift_range=0.1,
    width_shift_range=0.1,
    horizontal_flip=True,
    fill_mode='nearest')
train_generator = train_datagen.flow_from_directory(
    './train_dir',
    target_size=(150, 150),
    batch_size=32,
    class_mode='binary')

#An ImageDataGenerator to generate images for both validation and test datasets
test_datagen = ImageDataGenerator(rescale=1./255)
validation_generator = test_datagen.flow_from_directory(
    './val_dir',
    target_size=(150, 150),
    batch_size=32,
    class_mode='binary')
test_generator = test_datagen.flow_from_directory(
    './test_dir',
    target_size=(150, 150),
    batch_size=32,
    class_mode='binary')

#compiling the model
model.compile(
    loss='binary_crossentropy',
    optimizer=tf.keras.optimizers.Adam(1e-4),
    metrics=['acc'])

#Training
history = model.fit_generator(
    train_generator,
    steps_per_epoch=100,
    epochs=3,
    validation_data=validation_generator,
    validation_steps=50)

#Evaluation on test dataset
test_loss, test_acc = model.evaluate_generator(test_generator, steps=50)
print('test loss:', test_loss)
print('test acc:', test_acc)