The validation set was annotated using a combination of originally curated labels with incomplete annotations, where were further completed by adding additional labels. The class distributions on train and validation sets are long-tailed. The model was trained and tested on an internal dataset with 9,098 concepts and 20M images, with multiple concepts per image. Limitations: works well when content is prevalent in the image Intended Use: image indexing by tags, filtering, cascade routing ![]() ![]() This model is a great all-purpose solution for most visual recognition needs with industry-leading performance. Purpose: Classifier for a variety of concepts, common objects, etc.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |