A CNN based model for recognizing digits in the famous MNIST digit dataset
MNIST ("Modified National Institute of Standards and Technology") is the de facto “hello world” dataset of computer vision. Since its release in 1999, this classic dataset of handwritten images has served as the basis for benchmarking classification algorithms. As new machine learning techniques emerge, MNIST remains a reliable resource for researchers and learners alike.
In this competition, your goal is to correctly identify digits from a dataset of tens of thousands of handwritten images. We’ve curated a set of tutorial-style kernels which cover everything from regression to neural networks. We encourage you to experiment with different algorithms to learn first-hand what works well and how techniques compare.
The entire dataset is available here:
https://www.kaggle.com/c/digit-recognizer/data
This project was made as a learning experience for an old kaggle competition. It achieved an accuracy of 99.2% in the competition It is made in an explained way. Here is a link to the notebook: https://www.kaggle.com/niteshksingh/99-explained-simple-cnn-model
A saved Model that can be easily used with tensorflow has been included in the "Model" directory.