Welcome to ClosetCoach, a Fashion Wardrobe Assistant project, designed to help you develop your Deep Learning based Computer Vision skills. In this project, we will guide you through the process of building a fashion wardrobe assistant from scratch, using cutting-edge Deep Learning techniques.
We've designed ClosetCoach with features that cater to your every fashion need. Here's a closer look at what we offer:
Have you ever wondered what category your clothes fall under? Our advanced algorithm can analyze your attire picture and tag it with all the product and meta attributes, so you don't have to. Our feature can recognize product super categories like TopWear, BottomWear, FootWear, Sports Wear, Accessories, SleepWear, and Ethnic and FestiveWear. We also recognize specific product categories like T-shirts, Shirts, Jeans, Casual Trousers, Formal Trousers, Shorts, and Track Pants & many more.Additionally, we provide product metadata, including color information, product style, print type, and much more, so you have a complete understanding of your clothes.
No more digging through piles of clothes in your closet! Our digital wardrobe creation feature enables you to upload pictures of your clothes and create a virtual wardrobe. Now you can access all your clothes in one place and easily plan your outfits for the week.
Defining your unique style can be challenging, but not with ClosetCoach. Based on your digital wardrobe, our algorithm will analyze your clothes and create a personalized style profile that captures your unique style. Our feature will provide you with fashion recommendations that align with your style preferences, ensuring you look your best every time you step out.
Ready to explore new fashion trends? Our fashion recommendation feature is here to help you discover new clothes that fit your personal style. Whether you want to find clothes that go well with your existing clothes in your digital wardrobe or explore new attire that aligns with your style preferences, we've got you covered. With ClosetCoach, you can discover new fashion pieces effortlessly.
Firstly, let me explain that this project is split into two main parts
- Codebase
- Documentation plus Tutorials.
The Codebase is where you'll find all the actual project files, including the source code, which is located in the ClosetCoach folder under the project root directory. This is where the real magic happens, where all the coding and development work takes place to bring the project to life.
The second part of the project is the Documentation plus Tutorials. This is where we'll be providing helpful guides, tips and tutorials on how a particular feature of the project was developed and how to use it . Every alternate week, we'll be updating this section with new information on how specific features were implemented, as well as tutorials on how to use them. You can find this section in the docs folder located in the project root directory.
We believe that having a strong Documentation plus Tutorials section is just as important as having a well-functioning Codebase. This is because it's the place where users can learn how to implement features of ClosetCoach using Deep learning based Computer Vision skills and find helpful information on how to use the project to its full potential. We understand that sometimes technical jargon can be intimidating, which is why we're committed to making our documentation as user-friendly and engaging as possible.
Are you curious about what features ClosetCoach has in store for you in the coming weeks and months? Look no further than our roadmap! Our roadmap provides you with an overview of the features we are currently working on, what stage they are in, and when we expect to release them.
We welcome feedback from our users through our public discussion forums, as we believe in the power of collaboration and the open source community.
Our project board is organized by priority and timeline, making it easy for you to follow our progress and stay up-to-date on the latest developments.We are committed to providing the best possible experience for our users and believe that the open source nature of our project will allow for continued growth and improvement.
Join us on our journey to improve computer vision skills and create a thriving open source community!
We use Github issues to track public bugs and feature updates or enhancements and public discussion forums for any questions or feedback issues. Please make sure to follow one of the issue templates when reporting any issues.
We actively welcome pull requests.
However, if you’re adding any significant features (e.g. > 50 lines), please make sure to discuss with maintainers about your motivation and proposals in an issue before sending a PR. This is to save your time so you don’t spend time on a PR that we’ll not accept.