Transfer learning consists in training a base network and reusing some or all of this knowledge in a related but different task.
Transfer Style allows to use the inner understanding of an already trained Convolutional Neural Network to transfer style from one picture to another.
Data augmentation is a basic technique to increase our dataset without new data. Although the technique can be applied in a variety of domains, it’s very commonly used in Computer Vision, and this will be the focus of the post.
Have you ever watched the cooking teaching shows? You have probably noticed that chefs have usually already all the ingredients separated and chopped. Likewise, a data scientist will be more useful and creative building models rather than spending time with data preprocessing…