Immersive Data Science & Machine Learning
SpotDbuy provides personalized clothing recommendations for sportwear shoppers based on detecting the clothing items in user's input image, hence enhancing users' shopping experience with efficiencies and conveniences. Through the utilizing of yoloV4 technology to detect the objects from user's input image, and using the VGG16 model to find and recommend the items in term of similarity to users, base on our database with over 8,000 items and 8 categories. SpotDbuy has been deployed in Streamlit, which is an open-source app framework for Machine Learning, and first provides users recommendation of Adidas sportwears and will further expand to more brands.
DigiDoc: AI-powered web application to digitalize document for images to common file types, like txt or csv.
Project description DigiDoc is a one-stop text digitization solution for businesses which can convert documents, invoices or other physical…
LOGO⅃: Logo generator that uses GAN model to create thousands of new logos within minutes.
Project description LOGO⅃ is an image generator that produces new logos in a snap. The logo generator is built upon Deep Convolutional…