Skip to content

Sommie-Kay/Image_Classification_CNN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 

Repository files navigation

Fashion Classification Using Convolutional Neural Network (CNN)

Overview

This project involves the training and evaluation of Convolutional Neural Network (CNN) models for classifying fashion items using the Fashion MNIST dataset. The main goal is to achieve high accuracy in recognizing different fashion categories.

Dataset

The dataset used is the Fashion MNIST dataset, a collection of 28x28 grayscale images of 10 fashion categories, such as T-shirts, trousers, dresses, etc.

Model Architecture

The CNN model is designed with three blocks, each consisting of convolutional layers, batch normalization, max-pooling, and dropout for effective feature extraction and classification.

Training

The models were trained using a subset of the data for a specified number of epochs. Additionally, data augmentation was implemented to enhance the model's ability to generalize.

Model Evaluation

Evaluation metrics include accuracy, loss, and a detailed classification report showcasing precision, recall, and F1-score for each category.

Results

  • Base Model Accuracy: 92.22%
  • Alternative Model Accuracy: 92.18%
  • Final Model Accuracy: 93%

Visualizations

  • Plots illustrating training and validation loss and accuracy over epochs.
  • Confusion matrix for a detailed understanding of classification performance.
  • Correct and incorrect predictions showcased through image plots.

Conclusion

The project demonstrates the successful training and evaluation of CNN models for fashion classification. The models show promising accuracy, and visualizations provide insights into their performance.

Next Steps

  • Monitor and assess model performance over time.
  • Consider fine-tuning or experimenting with different architectures.
  • Deployment for predictions on new fashion images.

Feel free to explore the Jupyter notebooks and code for detailed insights into the project.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors