Skip to content

carsonmdd/Flower-Classification

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 

Repository files navigation

Flower-Classification

Basic Overview

This flower classification project utilizes a convolutional neural network (CNN) to classify images of flowers among 16 different species.

Methods

Once the data was retrieved, I organized the data into a dataframe for manageability and visualization. After viewing some of the data points, I split the data and incorporated data augmentation to help prevent overfitting. Following data preprocessing, I constructed my model with four convolutional layers and fit it over 30 epochs. I then graphed the resulting losses and accuracies and evaluated the model. Upon saving, I used the model to predict 16 new flower images (one for each species) and visualized the results.

Accuracy of the CNN model

Validation accuracy: 83.10%
Testing accuracy: 82.97%

Dataset

Total images: 15,740
Total classes: 16
Dataset: https://www.kaggle.com/datasets/l3llff/flowers/data

Google Drive Project link

https://drive.google.com/drive/folders/1eNe23cejI8qo9lPyWx5HQlmQMbJ4lwEU?usp=drive_link

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published