Closed jackkwok closed 5 years ago
I think I found the reason. The 2D pooling layer (size=3, stride=2) doesn't have padding so the scaling factor is not necessarily precisely a whole number (2). That may explain the 1 pixel deviation.
Yes exactly, it is worth stressing that the lack of padding is a necessary condition for the the network to be "fully-convolutional", as it is explained in the paper.
In make_score_map(), I found cases when the input shape is different from score map shape by 1 pixel. e.g. image shape: (2000, 1359) score map shape (2000, 1360)
Can you please explain the calculation behind the offset value:
Quote from producer.py: