A scratch implementation of Convolutional Neural Network in Python using only numpy and validated over CIFAR-10 & MNIST Dataset
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%.
INPUT - CONV1 - RELU - CONV2 - RELU- MAXPOOL - FC1 - OUT
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.
Followings are also required if working/testing on the app.py
git clone https://github.com/zishansami102/CNN-from-Scratch
python train.py
Output:
line No. - 30-31
and comment out the training part form the code in run.py: line No. - 42-111
python app.py
App will start running on the local server http://127.0.0.1:5000 as shown below :
Mail me at [email protected] if you want to contribute to this project
Build websites with AI, publish in seconds - Makeweb.ai