keras 报错---`validation_steps=None` is only valid for a generator based on the `keras.utils.Sequence

最新推荐文章于 2021-05-17 15:00:01 发布

静茹秋叶

最新推荐文章于 2021-05-17 15:00:01 发布

阅读量6.1k

点赞数 3

CC 4.0 BY-SA版权

分类专栏： keras 文章标签： keras ValueError: `validation_steps= ImageDataGenerator

本文链接：https://blog.youkuaiyun.com/zhang_cherry/article/details/90477307

keras 专栏收录该内容

1 篇文章

订阅专栏

博客主要围绕Keras出现的错误提示展开。当出现`validation_steps=None`和`steps_per_epoch=None`的错误时，提示仅适用于基于`keras.utils.Sequence`类的生成器，需为`validation_steps`和`steps_per_epoch`指定明确的值，还提及有使用fit_generator的例子。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

ValueError: `validation_steps=None` is only valid for a generator based on the `keras.utils.Sequence` class. Please specify `validation_steps` or use the `keras.utils.Sequence` class.

提示validation_steps=None is only valid

说明要赋值给validation_steps

history = model_vgg.fit_generator(
    train_generator,
    steps_per_epoch=1000,
    epochs=epochs,
    validation_data=validation_generator,
    validation_steps=200,  # 这一句不能省略，否则报错
    callbacks=[checkpointer]
)

同样，如果报如下的错误

ValueError: `steps_per_epoch=None` is only valid for a generator based on the `keras.utils.Sequence` class. Please specify `steps_per_epoch` or use the `keras.utils.Sequence` class.
根据提示，需要给steps_per_epoch给一个明确的值

下面有使用fit_generator的例子

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)

train_generator = train_datagen.flow_from_directory(
        'data/train',
        target_size=(150, 150),
        batch_size=32,
        class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
        'data/validation',
        target_size=(150, 150),
        batch_size=32,
        class_mode='binary')

model.fit_generator(
        train_generator,
        steps_per_epoch=2000,
        epochs=50,
        validation_data=validation_generator,
        validation_steps=800)

上面的例子来自keras中文社区文档