By default, the modifications will be applied randomly, so not every image will be changed every time. We will then call the fit() function on our image generator which will apply the changes to the images batch by batch. First we need to create an image generator by calling the ImageDataGenerator() function and pass it a list of parameters describing the alterations that we want it to perform on the images. A shoutout to Jason Brownlee who provides a great tutorial on this. Create an image generator from ImageDataGenerator()Īugmenting our image data with keras is dead simple. ![]() ![]() ![]() The cifar10 images are only 32 x 32 pixels, so they look grainy when magnified here, but the CNN doesn’t know it’s grainy, all it sees is DATA.
0 Comments
Leave a Reply. |