Image Captioning is the technique in which automatic descriptions are generated for an image. In this blog post, I will tell you about the choices that I made regarding which pretrained network to use and how batch size as an hyperparameter can affect your training process.
Andrew Ng said during his widely popular NIPS 2016 tutorial that transfer learning, after supervised learning, will be the next driver of ML commercial success.
Neural Style Transfer is the process in which content of an image and style of another image are combined together to create a new image. Prisma uses style transfer to transform your photos into works of art using style of famous artists.
Convolutional Neural Networks have changed the way we classify images. It is being used in almost all the computer vision tasks. From 2012, CNN’s have ruled the Imagenet competition, dropping the classification error rate each year. MNIST is the most studied dataset (link).