Fashion images
In 2019, the DeepFashion2 dataset was presented by Yuying Ge, Ruimao Zhang, and others. The dataset is an improvement on the DeepFashion dataset and includes 491,000 images from both sellers and consumers. The dataset identifies 801,000 clothing items. Each item in the dataset is marked with a scale, occlusion, zoom-in, viewpoint, category, style, a bounding box, dense landmarks, and a per-pixel mask.
The dataset has 391,000 images in the training set, 34,000 images in the validation set, and 67,000 images in the test set. This dataset offers the possibility of coming up with better models that are able to identify fashion clothing and different clothing items from images. One could easily imagine the range of applications ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access