GithubHelp home page GithubHelp logo

deep-fashion-classification's Introduction

Fashion Category and Attribute Prediction!

The goal of this project is to predict the categories and attributes of the clothes. There are 46 categories and 1000 attributesin total. Category training and prediction has been completed.

Project Hierarchy

└── deep-fashion-classification
   ├── main.py
   ├── inference.py
   ├── model.py
   ├── requirements.txt
   ├── README.md
   └── data
      ├── category.csv
	  ├── ...
   └── models
      ├── category.h5
	  ├── ...
   └── samples
      └── pred
	     ├── sample_pred0.png
		 ├── ...
      ├── blouse_cat3.jpg
	  ├── coat_category39.jpg
	  ├── ...

The locations of the files in the project are stated above.

Usage

How to predict labels by types

To predict with the trained model:

python3 main.py --predict --predict-type categories

there are 6 predict types in total:

'categories'
'attribute1'	(Textures)
'attribute2'	(Fabrics)
'attribute3'	(Shapes)
'attribute4'	(Parts)
'attribute5'	(Styles)

How to train a new model from scratch

Will be added after attributes !!


Model specifications:

  • Category:
    • Input Shape: (224, 224, 3) RGB
    • Total params: 11,210,487
    • Trainable params: 7,240,497
    • Non-trainable params: 3,969,990
    • Total layer number: 89

Training on Colab

Whole model is trained on Google Colab. Takes approximately 16 hours for categories.

https://colab.research.google.com/gist/omerferhatt/93850097ac6def4601a2c728a84c82a6/fashion-attribute-classification.ipynb

Project Requirements

Library requirements are mentioned in requirements.txt

Required large file links below:

deep-fashion-classification's People

Contributors

omerferhatt avatar

Stargazers

 avatar  avatar

Watchers

 avatar

deep-fashion-classification's Issues

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.