Code Monkey home page Code Monkey logo

midas-mnist's Introduction

MIDAS-MNIST

Abstract:

This repository contains the CNN model capable of recognising hand-written digits from the MNIST Dataset.

Environment Requirements:

Python 3.0
Google Collab
GPU support
Keras-backend
numpy
split_folders

Dataset Links:

Part 1:

(trainPart1.zip): https://www.dropbox.com/s/pan6mutc5xj5kj0/trainPart1.zip

Part 2:

MNIST.zip: provided in this repository

Part 3:

mnistTask3.zip: https://www.dropbox.com/s/otc12z2w7f7xm8z/mnistTask3.zip

Observations:

TRAINING DATASET:

    A final accuracy of ~98.30% is found in part 1, ~92.75% in part 2 and ~90% in part 3.

TESTING DATASET:

    Part 1: '4' was predicted as 'K' (Sample021) with a probability of 1.0
    Part 2: '7' was predicted as '7' (Sample008) with a probability of 1.0
    Part 3: '6' was predicted as '5' with a probability of 1.0

ISSUES:

The model always gives a prediction probability of 1.0 on the testing data for most of the cases.

Author:

Shirshakk Purkayastha

midas-mnist's People

Contributors

shirshakk-p avatar

Watchers

avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.