Git Product home page Git Product logo

doguilmak / cat-dog-classification-with-vgg-16 Goto Github PK

View Code? Open in Web Editor NEW
1.0 2.0 0.0 8.71 MB

In the project, within the scope of the Computer Vision course with the code 02010012 given by the Faculty of Computer Engineering, cat and dog classification was made with the VGG-16 architecture.

License: GNU General Public License v3.0

Python 0.15% Jupyter Notebook 99.21% PureBasic 0.63%
cat-dog-classification computer-vision convolutional-neural-networks vgg16

cat-dog-classification-with-vgg-16's Introduction

Classify Cat and Dog Images with VGG-16

https://d.newsweek.com/

Picture Source: Newsweek


Context

Project was conducted as part of the Computer Vision lecture with the code 02010012, which is a course offered by the Computer Engineering faculty. Computer Vision is an interdisciplinary field of study that focuses on enabling computers to interpret and understand visual information from the world around us. It involves the use of various techniques, including image processing, pattern recognition, and machine learning, to analyze and interpret digital images and videos. This project specifically focused on the use of deep learning, which is a subfield of machine learning that involves the use of neural networks to model complex relationships between input and output data. The VGG-16 model is a deep neural network architecture that has proven to be highly effective in image classification tasks, as demonstrated by its success in the ImageNet Large Scale Visual Recognition Challenge.


By applying this knowledge and utilizing the VGG-16 model, you were able to develop a high-performing image classification model for cats and dogs. This project showcases the practical application of computer vision and deep learning techniques in solving real-world problems, and highlights the importance of these techniques in the field of computer engineering.


The objective of this project is to develop a deep learning model using the VGG-16 architecture to classify images of cats and dogs with high accuracy. The model will be trained on a dataset of labeled images and evaluated. The ultimate goal is to create a model that can accurately distinguish between images of cats and dogs in real-world scenarios.


The dataset consists of 1,425 digital images of domestic animals, specifically 713 images of dogs and 712 images of cats. These images were collected for the purpose of training a deep learning model to classify images of cats and dogs with high accuracy. All images were obtained from various online sources and manually labeled by experts to ensure accuracy of the dataset. The images vary in size and resolution, and were preprocessed to remove any artifacts or unwanted information.


Objectives

The objective of this project is to develop a deep learning model using the VGG-16 architecture to classify images of cats and dogs with high accuracy. The model will be trained on a dataset of labeled images and evaluated. The ultimate goal is to create a model that can accurately distinguish between images of cats and dogs in real-world scenarios.

  • Understand the dataset and batches.
  • Build classification models to predict the class.
  • Evaluate the model.
  • Upload and predict your own picture.

Keywords

  • Computer Science
  • Classification
  • Convolutional Neural Networks (CNN, or ConvNet)
  • Cat & Dog Classification

Notebooks

On below, there are informations about the notebooks created respectively.

  1. In this section, I build classification model_1 with VGG-16. After that, predictions and evaluations (plot train - validation loss and accuracy graph) made from train and validation data.
    Notebook:

    1. cat_dog_vgg16_1.ipynb
  2. In this section, I build classification model_2 with VGG-16. After that, predictions and evaluations (train-validation loss and accuracy graph, F1 score, precision, recall, support, ROC graph and AUC score) made from train, validation and test data. The results of the model on the test data are in the model_predictions.csv file. Just click the link to view.
    Notebook:

    1. cat_dog_vgg16_2.ipynb

License

GNU General Public License v3.0


Contact Me

If you have something to say to me please contact me:

cat-dog-classification-with-vgg-16's People

Contributors

doguilmak avatar

Stargazers

 avatar

Watchers

 avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.