To test the model, images of a person wearing a helmet or not wearing a helmet are needed. The dataset was split earlier, with 20% being set aside for Testing, that can be used now. The Studio takes the input image as a parameter and predicts the class it belongs to. Before passing the image, we need to ensure that we are using the same dimensions that we used during the training phase; here it’s by default the same dimension. You can also test with a live image taken directly from the development board, if you have a camera attached. In this case, we have a low resolution camera with our kit, and lighting is not optimal, so the images are dark. However, with a high resolution camera and proper lighting condition, better results can be acheived. But having another look at the Test dataset images, which are bright and high quality, we can see that the model is predicting results (hardhats) effectively.