* captioning: natural language descriptions of the images (see MS COCO Captions), * object detection: bounding boxes and per-instance segmentation masks with 80 object categories, Additionally, the 2017 release contains a new unannotated dataset of 123K images. The 2017 test set is a subset of 41K images of the 2015 test set. The new split uses the same images and annotations. In 2015 additional test set of 81K images was released, including all the previous test images and 40K new images.īased on community feedback, in 2017 the training/validation split was changed from 83K/41K to 118K/5K. It contains 164K images split into training (83K), validation (41K) and test (41K) sets. The first version of MS COCO dataset was released in 2014. The MS **COCO** (**Microsoft Common Objects in Context**) dataset is a large-scale object detection, segmentation, key-point detection, and captioning dataset.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |