I'm looking at the architecture proposed in the following paper: Baoguang Shi et al, An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition.
If i have an input of size (32 x 8), then the output would be:
(32-1)/2 + 1 = 16.5, <- this part doesn't make sense to me
(8-2)/2 + 1 = 4
*ignoring depth and batch size here