Skip to content

annadutkiewicz/Fashion_Class_Classification

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Fashion_Class_Classification

Description

The aim is to predict type of clothes on the image

Fashion dataset consists of 70,000 images divided into 60,000 training and 10,000 testing samples. Dataset sample consists of 28x28 grayscale image, associated with a label.

There are 10 classes (labels) available:

  • 0 => T-shirt/top
  • 1 => Trouser
  • 2 => Pullover
  • 3 => Dress
  • 4 => Coat
  • 5 => Sandal
  • 6 => Shirt
  • 7 => Sneaker
  • 8 => Bag
  • 9 => Ankle boot

Each image is 28 pixels in height and 28 pixels in width, for a total of 784 pixels in total. Each pixel has a single pixel-value associated with it, indicating the lightness or darkness of that pixel, with higher numbers meaning darker. This pixel-value is an integer between 0 and 255.

Workflow

  1. Data import
  • Load libraries
  • Load dataset
  1. Data visualizing
  • Display dataframe
  • Display random images
  1. Model training
  • Prepare train, validation and test datasets
  • Create neural network model
  • Compile model
  • Train model
  1. Model evaluating
  • Test data
  • Print heatmap
  • Print classification report

Conclusions

  1. By using (32,3,3) kernel with dropout, we were able to achieve:
  • Accuracy: 89.55%
  • Test accuracy: 90.10%

Acknowledgements

This implementation was inspired by Kirill Eremenko, Hadelin de Ponteves, Dr. Ryan Ahmed, Ph.D., MBA, SuperDataScience Team, Rony Sulca Machine Learning Practical Udemy course

About

The aim is to predict type of clothes on the image

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published