Building a super-resolution image web-app

I made this app, as my pilot task for Tessellate coding. The task included finding a suitable model, making the inference algorithm, wrapping it in a REST API, and finally dockerizing the application. For the task, I used Keras with a Tensorflow backend and Flask. This blog is about the same challenges I faced in the task, and how to overcome them when you are making your project. For the model, I researched a bit on the topic of the super-resolution of the image, and found the SRCNN model.