Galas are the biggest party of the year. Hosting firms of these events are well aware that everyone from around the world has their eyes on these nights—be it for inspiration or for critique. It takes months of meticulous planning and delegation to host these events impeccably.
One such firm has decided to take a data-driven approach for planning their gala nights. Aesthetics and entertainment are the most crucial segments of these events. So, this firm has hired you to help them aggregate and classify all images. These images are published by attendees and the paparazzi on various social media channels and other sources. You are required to build an image auto-tagging model to classify these images into separate categories.
The dataset consists of 5,983 images that belong to 4 categories. These categories are food, attire, decor and signage, and miscellaneous.
The benefits of practicing this problem by using Machine Learning or Deep Learning techniques are as follows:
This challenge encourages you to apply your Machine Learning skills to build models that classify images into multiple categories This challenge helps you enhance your knowledge of classification actively. It is one of the basic building blocks of Machine Learning and Deep Learning techniques. You are required to build a model that auto-tag images and classifies them into various categories of aesthetics and entertainment for a gala night.
My solution to this problem was using the Transfer Learning VGG16 model. The resultant score to this challenge was 80(approx.)