Keras ImageDataGenerator.flow_from_directory返回TypeError

2024-05-05 • 问答

我正在尝试提供一个目录作为ImageDataGenerator.flow_from_directory的输入，但是我无法做到这一点。

train_data_dir = "/train"
validation_data_dir = "/test"

train_generator = ImageDataGenerator.flow_from_directory(directory=train_data_dir,target_size = (img_height,img_width),batch_size = batch_size,class_mode = "categorical")

validation_generator = ImageDataGenerator.flow_from_directory(directory=validation_data_dir,class_mode = "categorical")

上面的代码返回以下错误

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-126-39ed634afa51> in <module>
      2 target_size = (img_height,3 batch_size = batch_size,----> 4 class_mode = "categorical")
      5 
      6 validation_generator = ImageDataGenerator.flow_from_directory(validation_data_dir,TypeError: flow_from_directory() missing 1 required positional argument: 'self'

我该如何解决？

liweisb 回答：Keras ImageDataGenerator.flow_from_directory返回TypeError

您不能直接从 ImageDataGenerator 调用 flow_from_directory 方法。您必须首先创建此类的实例。试试这个：

train_gen = ImageDataGenerator()
val_gen = ImageDataGenerator()

您可以在此处添加用于扩充的参数。参考：https://keras.io/preprocessing/image/
之后，您可以使用 flow_from_directory 。

train_generator = train_gen.flow_from_directory(directory=train_data_dir,target_size = (img_height,img_width),batch_size = batch_size,class_mode = "categorical")

deep-learning image-preprocessing keras machine-learning

本文链接：https://www.f2er.com/3134025.html

Keras ImageDataGenerator.flow_from_directory返回TypeError

liweisb 回答：Keras ImageDataGenerator.flow_from_directory返回TypeError

大家都在问