Different depthwise convolution kernel sizes?
xskxzr opened this issue · 1 comments
xskxzr commented
In your paper, I see you use a depthwise convolution with kernel size 5 to generate offsets, but in the code you use different kernel sizes for different input sizes. Am I missing something?
Vladimir2506 commented
In our experiments, k=5 in stage 3, k=3 in stage 4 work well.