From the course: Neural Networks and Convolutional Neural Networks Essential Training

Unlock the full course today

Join today to access over 22,600 courses taught by industry experts or purchase this course individually.

Image augmentation in Keras

Image augmentation in Keras

From the course: Neural Networks and Convolutional Neural Networks Essential Training

Start my 1-month free trial

Image augmentation in Keras

- So remember, what we're trying to achieve here is we're going to look at our training data set and try and manipulate as many of the images as possible to alter them. We are trying to create more images for our training data in this way. So let's head over to our notebook, and let's first check these two folders. So we go to images, sample-train, and we see in our images folder, sample-train, we've separated out the two categories, so that's the cats in one folder, and we've got all of the photos of cats in one folder. And this is the third cat. And we've got all of the three dogs in the other folder. If you go back to images, and now if you go to sample-confirm, because this is going to be the folder where we're going to populate our changes to the training data set or the training images, you can see that there are no files at the moment. Now, what we're going to do is image augmentation, and we're going to be using the image data generator that Keras provides. So I'm going to…

Contents