srikavin
Srikavin Ramkumarmaintainer
This repository contains code for training a neural network in pytorch to classify MNIST digits.
The following dependencies are used: PyTorch PyTorch Vision Numpy Matplotlib
They can be installed by running pip install -r requirements.txt
.
identify.py
is a CLI application used to identify digits in an image.
main.ipynb
is a Jupyter notebook that can be used to train the model using the MNIST dataset.
It can also be viewed on Google Colab.
usage: identify.py [-h] [-m MODEL] input_file
There are two test images in this repository. The trained model can be used to identify the numbers within the images using the following commands:
python identify.py test.png
python identify.py test1.png
A screen recording is available on YouTube.