why hrnet use 1/4 downsample in the begin of the net?

[JoyLuo]

the output size of hrnet is 1/4 of input, because the begin of the net use conv with 2 stride 2 times if not use downsample, the result may be more better

[yunhuang1241]

In paper the author did not explain why, but i suppose: 1.GPU memory limit 2.Computation cost