Preparing & Uploading Data

A good place to start when creating and training a new model is with a dataset containing at least 500 images. Include diverse lighting, angles, and contexts for real-world applicability. The dataset should also include negative images. Negative images do not include the target object, and are helpful to reduce false positives in your trained model. With a beginning dataset of 500 images, aim for 400 images (or 80%) showing your object, and 100 (20%) negative images.