Output from the reg layer in RPN.

[blitu12345]

The reg layer in RPN has 4k outputs encoding the coordinates of k boxes.(from the paper) So what actually this layer predicts?Is it predicting the 4 coordinates of boundary boxes directly or predicting the 4 parameterized coordinates of the bounding box.

Any help is appreciated.

[mariolew]

Those outputs only make sense when RPN is trained separately, but here the whole network is trained end to end..