Keras实时增强功能增加了噪声和对比度
Keras提供了一个 ImageDataGenerator 类用于实时增强,但不包括对比度调整和添加噪声。
Keras provides an ImageDataGenerator class for realtime augmentation, but it does not include contrast adjustment and addition of noise.
在训练过程中如何应用随机的噪声水平和随机的对比度调整?是否可以将这些函数添加到datagen的 preprocessing_function参数中?
How can we apply a random level of noise and a random contrast adjustment during training? Could these functions be added to the 'preprocessing_function' parameter in the datagen?
谢谢。
来自Keras文档:
preprocessing_function:每个输入都会隐含的函数。该功能将在对其进行任何其他修改之前运行。该函数应采用一个参数:一个图像(秩为3的Numpy张量),并应输出具有相同形状的Numpy张量。
preprocessing_function: function that will be implied on each input. The function will run before any other modification on it. The function should take one argument: one image (Numpy tensor with rank 3), and should output a Numpy tensor with the same shape.
因此,我创建了一个简单的函数然后使用 imgaug模块中的图像增强功能。请注意,imgaug要求图片的排名为4。
So, I created a simple function and then used the image augmentation functions from the imgaug module. Note that imgaug requires images to be rank 4.