George

pyramidbox: why anchor down-sampled?

1

I have a question disturbed me. As we know, the anchor will be expanded to detect head and body from face anchors, but it is down-sampled to calculate IOU with...

loss qusetion?

9

is it loss = positive_distance - negative_distance?and you useloss = negative_distance - positive_distance

batch_size?

6

为什么我把batch_size改到512，训练结果反而变得很差？普通情况是大的batchsize相对来说结果不会比小的差。