https://github.com/andraxdev/emnist-cnn

A Convolutional Neural Network for EMNIST dataset
https://github.com/andraxdev/emnist-cnn

classification cnn emnist emnist-classification machine-learning mnist mnist-classification neural-network python

Last synced: about 1 year ago
JSON representation

A Convolutional Neural Network for EMNIST dataset

• Host: GitHub
• URL: https://github.com/andraxdev/emnist-cnn
• Owner: AndraxDev
• Created: 2023-01-19T21:23:14.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2023-01-20T10:43:41.000Z (over 3 years ago)
• Last Synced: 2025-02-10T06:41:43.576Z (over 1 year ago)
• Topics: classification, cnn, emnist, emnist-classification, machine-learning, mnist, mnist-classification, neural-network, python
• Language: Python
• Homepage:
• Size: 11.7 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# MNIST-like datasets classifier

Convolutional neural network to recognize symbols using a MNIST-like datasets

## Purpose

Recognize handwritten letters and digits

## Accuracy

```

92%

```

## Requirements

```

PyTorch, TorchVision, Numpy (1.23.1), matplotlib.pyplot

```

## Requirements for datasets

28x28 grayscaled images

## Tested datasets

- MNIST

- EMNIST

## Run

```

python3 cnn.py

```

## Runtime options

```python

# Comment or uncomment necessary functions

train(model, model_path)

test(model_path)

test_all(model_path)

```

> **Warning**

>

> Training NN or testing  all images (function test_all()) may take very long time.

## Output example

![Screenshot_11](https://user-images.githubusercontent.com/43646136/213566800-8456364a-79e6-41ca-932a-5a33b61bfa02.png)

![Screenshot_12](https://user-images.githubusercontent.com/43646136/213566825-073a97c0-3e36-44cc-b53f-21681d28fced.png)