One of the hardest problems to solve in deep learning has nothing to do with neural networks: it's the problem of getting the right data in the right format. However, the Kaggle platform (https://www.kaggle.com/) provides new problems, and new datasets to study.
Kaggle was founded in 2010 as a platform for predictive modeling and analytics competitions on which companies and researchers post their data and statisticians and data miners from all over the world compete to produce the best models. In this section, we show how to make a CNN for emotion detection from facial images. The train and test set of this example can be downloaded from https://inclass.kaggle.com/c/facial-keypoints-detector/data.
The train set consists of 3,761 grayscale images that are 48×48 pixels in size and 3,761 labels, each with 7 elements.
Each element encodes an emotion: 0 = anger, 1 = disgust, 2 = fear, 3 = happiness, 4 = sadness, 5 = surprise, 6 = neutral...