HOG sizes

The shape training computes HOG from views with a size of 120x120, 60x60 and 30x30. However, how does it come possible since HOG cells have a size of 8x8 which is not a multiple of 60 nor 30.

There will be padding. We are using the HoG feature extracted by Pitor Dollar's toolbox. You can take a look into the source code.

I checked the code but there is no information about the block padding for L2-normalization computing.