https://github.com/kampi/dogsvscats

Kaggle Dogs vs. Cats challenge.
https://github.com/kampi/dogsvscats

keras machine-learning python

Last synced: 22 days ago
JSON representation

Kaggle Dogs vs. Cats challenge.

• Host: GitHub
• URL: https://github.com/kampi/dogsvscats
• Owner: Kampi
• License: gpl-3.0
• Created: 2019-06-13T09:10:11.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2020-04-22T05:27:35.000Z (almost 5 years ago)
• Last Synced: 2025-01-19T02:08:30.798Z (24 days ago)
• Topics: keras, machine-learning, python
• Language: Java
• Homepage: https://www.kampis-elektroecke.de
• Size: 88.1 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# DogsVsCats

This is a private project to classify images of cats and dogs with an convolutional neural network.

Please write an e-mail to [[email protected]]([email protected]) if you have any questions.

## Table of Contents

- [DogsVsCats](#dogsvscats)

  - [About](#about)

  - [How does it work?](#how-does-it-work)

  - [History](#history)

 

### About

This is a machine learning project and this application can classify dogs and cats by using a neural network with name [AlexNet](https://en.wikipedia.org/wiki/AlexNet).

You train the network with data from the [Kaggle Dogs vs. Cats](https://www.kaggle.com/c/dogs-vs-cats) competition and after the training the network will classify similar images.

## How does it work

1) Download the data from [Kaggle](https://www.kaggle.com/c/dogs-vs-cats/data)

2) Download [my Python modules](https://gitlab.com/Kampi/Python)

2) Unzip the data

3) Update `Network.py` in the `config` folder with the current path and your settings

## History

| **Version**  | **Description**                            | **Date**   |

|:------------:|:------------------------------------------:|:----------:|

| 1.0          | First release                              | 04.11.2019 |

## Maintainer

- [Daniel Kampert](mailto:[email protected])