Fashion AI

We concentrate on the task of Fashion AI, which entails creating images that are multimodal in terms of semantics. Previous research has attempted to make use of several generators for particular classes, which limits its application to datasets that have a just a few classes available. Instead, I suggest a new Group Decrease Network GroupDNet , which takes advantage in the generator of group convolutions and gradually reduces the percentages of the groups decoders convolutions. As a result, GroupDNet has a lot of influence over converting natural images with semantic marks and can produce high quality outcomes that are feasible for containing a lot of groups. Experiments on a variety of difficult datasets show that GroupDNet outperforms other algorithms in task. Ashish Jobson | Dr. Kamlraj R "Fashion AI" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-5 | Issue-4 , June 2021, URL: https://www.ijtsrd.compapers/ijtsrd41256.pdf Paper URL: https://www.ijtsrd.comcomputer-science/artificial-intelligence/41256/fashion-ai/ashish-jobson