zishansami102 / CNN-from-Scratch

A scratch implementation of Convolutional Neural Network in Python using only numpy and validated over CIFAR-10 & MNIST Dataset

Home Page:http://cnndigits.pythonanywhere.com/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Convolutional Neural Network from scratch Awesome

Objective of this work was to write the Convolutional Neural Network without using any Deep Learning Library to gain insights of what is actually happening and thus the algorithm is not optimised enough and hence is slow on large dataset like CIFAR-10. This piece of code could be used for learning purpose and could be implemented with trained parameter available in the respective folders for any testing applications like Object Detection and Digit recognition.
It's Accuracy on MNIST test set is above 97%.

alt text

Architecture

INPUT - CONV1 - RELU - CONV2 - RELU- MAXPOOL - FC1 - OUT

alt text

alt text

Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.

Prerequisites

Followings are also required if working/testing on the app.py

  • Flask - A microframework for Python
  • Gunicorn - A Python WSGI HTTP Server for UNIX
  • OpenCV - An open-source library that includes several hundreds of computer vision algorithms

Directories

  • CIFAR-10 : Object detection with CIFAR-10
  • MNIST : Handwritten Digits Recognition with MNIST

Installing

  • Clone the repository
git clone https://github.com/zishansami102/CNN-from-Scratch
  • Downlad the dataset and copy that to it's corresponding folder(CIFAR-10/MNIST).
  • Move into the required directory (/CNN-from-Scratch/MNIST or /CNN-from-Scratch/CIFAR-10) and then run the following command to start training model
python train.py

Output:

alt text

  • To load pre-trained models, change the pickle filename from 'output.pickle' to 'trained.pickle' in run.py: line No. - 30-31 and comment out the training part form the code in run.py: line No. - 42-111

Application Testing/Running

  • In the the directory /CNN-from-Scratch run the following command.
python app.py

App will start running on the local server http://127.0.0.1:5000/ as shown below :

alt text

Contributing

Mail me at zishansami102@gmail.com if you want to contribute in this project
My homepage - zishansami102.github.io

Acknowledgments

Other Proud Works

Executable solutions for CaptureTheEther - capture-the-ether-sols

About

A scratch implementation of Convolutional Neural Network in Python using only numpy and validated over CIFAR-10 & MNIST Dataset

http://cnndigits.pythonanywhere.com/

License:GNU General Public License v3.0


Languages

Language:Python 70.1%Language:HTML 23.1%Language:JavaScript 6.7%Language:Procfile 0.0%