Keras ImageDataGenerator.flow_from_directory 返回 TypeError

Question

我正在嘗試提供一個目錄作為 ImageDataGenerator.flow_from_directory 的輸入，但我無法做到。

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")

上面的代碼返回以下錯誤

---------------------------------------------------------------------------
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'

我該如何解決這個問題？

Answer 1

method from ImageDataGenerator .您不能直接從ImageDataGenerator調用方法。 您必須首先創建此 class 的實例。 嘗試這個：

train_gen = ImageDataGenerator()
val_gen = ImageDataGenerator()

您可以在此處添加增強參數。 參考： https://keras.io/preprocessing/image/
.之后，您可以使用 。

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