Python 目录中的Keras ImageDataGenerator.flow_返回TypeError
我试图从目录中为ImageDataGenerator.flow\u提供一个目录作为输入,但我无法这样做Python 目录中的Keras ImageDataGenerator.flow_返回TypeError,python,machine-learning,keras,deep-learning,image-preprocessing,Python,Machine Learning,Keras,Deep Learning,Image Preprocessing,我试图从目录中为ImageDataGenerator.flow\u提供一个目录作为输入,但我无法这样做 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_
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,
target_size = (img_height, img_width),
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, img_width),
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'
---------------------------------------------------------------------------
TypeError回溯(最近一次调用上次)
在里面
2目标尺寸=(图像高度、图像宽度),
3批次尺寸=批次尺寸,
---->4 class_mode=“分类”)
5.
6验证\u生成器=来自\u目录的ImageDataGenerator.flow\u(验证\u数据\u目录,
TypeError:flow_from_directory()缺少1个必需的位置参数:“self”
如何解决此问题?您不能直接从ImageDataGenerator的目录方法调用flow\u。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。请参阅:
之后,您可以使用来自目录的流
train_generator = train_gen.flow_from_directory(directory=train_data_dir,
target_size = (img_height, img_width),
batch_size = batch_size,
class_mode = "categorical")