Sometimes, object detection is overkill for a problem. Classification may be all you need. With Roboflow it's easy to test it out and see. You can import, export, and train, any dataset as multiclass classification to drop the bounding box information and just get a CSV containing the names of the classes contained in each image.
Below, learn the structure of Multiclass Classification CSV.
filename, head, helmet, person
000001.jpg, 0, 1, 0
000007.jpg, 0, 1, 0
000012.jpg, 0, 1, 0
000013.jpg, 0, 1, 0
000014.jpg, 0, 1, 0
000016.jpg, 0, 1, 0
000017.jpg, 0, 1, 0
000018.jpg, 0, 1, 0
000019.jpg, 1, 0, 0With Roboflow supervision, an open source Python package with utilities for completing computer vision tasks, you can merge and split detections in Multiclass Classification CSV. Read our dedicated guides to learn how to merge and split Multiclass Classification CSV detections.
Below, see model architectures that require data in the Multiclass Classification CSV format when training a new model.
On each page below, you can find links to our guides that show how to plot predictions from the model, and complete other common tasks like detecting small objects with the model.