I have some confusions about how SSD object detection algorithm works.
- Where the anchor boxes are applied? (Only to the ground truth boxes or predictions also)
- How the loss function is calculated
- Why did Jeremy chose number of output as 4x4x(4+c)
I have some confusions about how SSD object detection algorithm works.
Here’s a very detailed and great write up about SSD, hopefully you’ll find your answers there !
Thanks a lot:)