YOLO — ‘You only look once’ for Object Detection explained
Aashay Sachdeva

Thank you for your great post. I didn’t understand the network architecture. In the main paper 7*7*30 tensor is not a flatten layer, but in your github code it is a dense layer. I want to train the network from scratch, not loading weights. can you please help me. Is there any implementation of loss function and feeding dataset to network? thank you

Show your support

Clapping shows how much you appreciated Isaac Kargar’s story.