ResNet-101’s effective stride from 32 pixels to 16 pixels, increasing the score map resolution. All
layers before and on the conv4 stage [9] (stride=16) are unchanged; the stride=2 operations in the
first conv5 block is modified to have stride=1, and all convolutional filters on the conv5 stage are
modified by the “hole algorithm” [15,2] ```
can you please tell me what is effective stride? i dont see stride of 32 in the resnet architecture... am i missing something?
I see in the paper they said: