<p dir="ltr">This item contains a description of the Wadaba dataset that was used to develop the MobileNetV3 architecture for image recognition. The dataset contains 4000 images of plastic objects that vary in colour and transparency, which were separated into 20 different sets of 200 images. The dataset used was secondary data collected from the Wadaba Institute’s database, available at: <a href="https://wadaba.pcz.pl/" target="_blank">https://wadaba.pcz.pl/</a>.</p>