In this Competetion, Kagglers will develop models capable of classifying visual styles of graphic design images. A Style can be interpreted as a specific combination of  relationships between elements in a graphic design work, Designers have mastered the skill to create visual experiences through composing a complex interplay between the content and style. Therefore, one high level motivation is to automate design style analysis to accelerate the understanding between AI and Design industry. Another motivation is to help enterprises obtain AI abilities to insight into the creative content and analyse the style factor affecting the conversion rate based on data return of different groups. 

Except for traditional objects classification of an image, thus far the algorithmic basis of the process that predict visual style of images is unknown and there exists no artificial system with similar capabilities. One of the biggest challenges is that there is no universally accepted or standard definition of design styles. Because this is such a creative and interesting task, To this end, we put together a dataset that contains “representative” design style images so that you can build your skills with the common machine learning task. 

The dataset for this competition consists of 3,000 images in total with style annotation. Images are collected from third-party image URls. We tagged them with style categories, which were carefully chosen considering different factors such as design technique, level of image emotion, average number of style instance. 
You can browse all style tags images here.
Disclaimer：The actual images are not owned by us.  For researchers and educators who wish to use the images for non-commercial research and/or educational purposes, we just provide access through this competition site. 

In this competition, you are challenged to build a model that is capable to predict styles of images,each image in the dataset is annotated with several style labels. We know that design styles are subjective, each style label needs to be voted by different viewers to gain consensus, we got some help from designers in differernt fields to test the style annotations of dataset, so the labels can be regarded as truevalue. You will use the dataset to train a classification model.
This is the home page of the competition. You don't need a subtitle here. The competition sub-title will appear above. This is where you introduce the problem. You can upload images using the "select files" widget on the left in the competition wizard. Upload an image, refresh the page, copy its URL, then insert within the wizard's editor.
If you are copy-pasting from another application, like Word or your browser, try to make sure the html formatting is clean. You can view a page's html using the button at the top right of the editor's toolbar.