Neural Networks and TensorFlow - Deep Learning Series [Part 19]

Leaving the MNIST dataset behind, in this lesson we're going to start looking into another dataset, CIFAR10.

This is a popular dataset comprising of a couple of tens of thousands of images which are divided into 10 categories, like: airplane, cat, dog, automobile, car, plane, etc. Unlike MNIST, the images in the CIFAR10 dataset are color images.

So, instead of 1 color channel, we're gonna have 3 color channels, 1 for each of the RGB. This automatically means that the training process of the neural network is going to require more resources (especially time) to get to a decent performance.

Please see the video below for the complete lesson.

To stay in touch with me, follow @cristi

Cristi Vlad Self-Experimenter and Author