wkentaro / pytorch-fcn

PyTorch Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)
MIT License
1.74k stars 480 forks source link

What h[:, :, 31:31 + x.size()[2], 31:31 + x.size()[3]] mean? #161

Open lyw615 opened 3 years ago

lyw615 commented 3 years ago

It looks like array slice, but what 31 means? And 'h[:, :, 5:5 + upscore2.size()[2], 5:5 + upscore2.size()[3]]' also confuses me

mailvijayasingh commented 3 years ago

were you able to understand this?

lyw615 commented 3 years ago

This is 4D array slice. But it makes no sense for index 31

FRANK-RAN commented 3 years ago

but why 5:5 + upscore2.size()[2]? i do not understand why plus 5.

Haoyanlong commented 2 years ago

@lyw615 @FRANK-RAN I also do not understand the index of slice, 5 and 31?Do you understand the params?Could you tell me?Thanck you very much!

zyongqing commented 2 years ago

cut padding

YCakira commented 2 years ago

这是来自QQ邮箱的自动回复邮件。嗨,这里是吴颖的信箱。谢谢你的来信,我将会尽快给你回复。