Neural Networks using Keras (with Image recognition case study)

Problem Statement:

Here, we need to identify the digit in given images. We have total 70,000 images, out of which 49,000 are part of train images with the label of digit and rest 21,000 images are unlabeled (known as test images). Now, We need to identify the digit for test images.

However there are lots of tutorial on MNIST data, but my purpose for post is to highlight the below points :

1- How to save the train model.
2- How to load a train model and get prediction from that model.
3- How to visualize the model performance using Tensorboard.
4- How to follow modular approach while building model

I have used keras with tensorflow backend. Please find below the link of the github repo where you will find the code and datasets.

https://github.com/abhibisht89/Keras_practice

Enjoy learning “deeplearning”