E-RotaNet- 1 min
Table of Contents:
E-RotaNet is a Computer Vision pipeline, which can rotate images in proportion to human-level vision.
What is ‘E’ in E-Rotanet?
‘E’ stands for the Efficientnet backbone used to learn the features and the context of the images.
EfficientNets are a family of image classification models which use compound scaling, and achieve state-of-the-art accuracy, yet being an order-of-magnitude smaller and faster than previous models.
About the dataset
Documentation can be found at GitHub.
The bare source code can rotate images and generate a plot like this:
However, the repository also contains a deployed Flask application, such that it attains following proof of concept: