keras ImageDataGenerator.flow with color_mode

Question

我正在将python与keras一起使用，并希望使用keras图像预处理，我的一些图像是rgb而有些是灰度的，我需要阅读所有图像并将灰度图像的尺寸更改为x，x，3或进行处理它们，并希望将其作为.flow函数的一部分，就像我可以将color_mode与.flow_from_directory一起使用一样，可以将其设置为rgb并将所有图像读取为rgb，即使它们是灰度的，这可能吗？

Answer 1

You can't do it as part of .flow because that assumes you already have loaded an prepared your images into a 4D tensor. You can use the load_img function which the .flow_from_directory uses that actually consumes the color_mode argument:

img = load_img(os.path.join(self.directory, fname),
               color_mode=self.color_mode,
               target_size=self.target_size,
               interpolation=self.interpolation)

This is from the flow_from_directory code. You can use this function to load your images and then call .flow .