Plane-Spotting the Deep Learning Way
I am starting my first blog with the quote which inspires me to do new things every day.
“If today were the last day of my life, would I want to do what I am about to do today?” — Steve Jobs
My motivation to write this blog is to spread knowledge about how data science can be leveraged in the aerospace/aviation industry. There are very few blogs/articles in this particular domain focusing on data science. So, this would be my first post in this runway which would be followed by more posts.
I always anticipated how a plane flies since my childhood. I believed that the planes fly just using wings and thought that engines were the guns used to shoot other planes.
In this post, I will be using deep convolution neural networks to predict the aircraft family using images. The data used is a benchmark dataset used for fine-grained visual categorization of aircraft (FGCV-Aircraft).
The dataset contains about 70 classes of aircraft family, in which 3334 images are in train and 3332 images are validation.