Good practices for collecting images

The success depends on the quality of the training dataset. Please consider the following points when preparing a training dataset:

General image collection advice

Specific advice for classification:

• It is recommended to provide a similar amount of training images for all classes.
• Multiple classes should not occur on the same image, as this will confuse the model.
• At least two classes have to be defined for a classification.

How many images are needed?

It is recommended to gather at least 50-100 images for a pilot study. If you want to be more certain about your prediction performance, more data is required. Please have a look at the 'How confident can you be about your evaluation?' on the Evaluation page for more information.