If you are looking to label entire images as belonging to a class, then you will need to upload a classification dataset. Classification datasets require images/videos and in distinct folders. Class names are derived based on the folder names.
For example, if you are uploading images of dogs, cats, and raccoons, you should have three folders.
One folder should be called "dogs" and contain all dog images.
Another folder should be called "cats" and contain all cat images.
The third folder should be called "raccoons" and contain all raccoon images.
If an image contains multiple items (e.g. a dog and a raccoon), it may make more sense to approach this as an object detection problem.
We have built out notebooks and tutorials for fitting five classification models:
New, as of January 2021: OpenAI CLIP
You can use these tutorials to fit classification models to your own datasets. If you want to explore one-click AutoML for classification, reach out to us.
We have made available a few image classification datasets.
We regularly write and share blog posts, including tutorials, recommendations for preprocessing and augmenting data, and techniques for improving model performance. Check out our computer vision modeling-related blog posts here and all blog posts here.