I was reading many blogs about Yolo Algorithm but I have a bit confused about how we label the training data, I will write my explanation and want to know if it's right or not.

In yolo algorithm, if we decide to have the output layer to be something like 1919n so we must make a ground truth label vector for each of the 19*19 cells in the input image in order to be able to train the yolo algorithm? And I see many people just assign output vector with the ground-truth label of the desired object and regardless of any other regions in the image so how would the algorithm be trained like that?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.