![]() ![]() ![]() While Keras has several built-in data augmentation layers (like RandomFlip), it doesn’t currently support changing the contrast and brightness. We can therefore increase the effective size of the training dataset and make the ML model more resilient if we augment the training dataset by randomly changing the brightness, contrast, saturation, etc. For example, it is likely that photographs provided to an ML model (especially if these are photographs by amateur photographers) will vary quite considerably in terms of lighting. ![]() Subclass Layer, and implement call() with TensorFlow functionsĭata augmentation can help an image ML model learn to handle variations of the image that are not in the training dataset. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |