search

layumi / Pedestrian_Alignment

TCSVT2018 Pedestrian Alignment Network for Large-scale Person Re-identification
https://ieeexplore.ieee.org/document/8481710
MIT License
236 stars 66 forks source link

proble about how to concentrate on center part #18

Open sillytheif opened 6 years ago

sillytheif commented 6 years ago

哲东大佬好。感谢这篇论文对reid align问题的启示，小星星送上 orz

看这篇论文，我有一个小疑惑是：如何保证STN起始 align的时候是，是从center part 开始。我看文中提到是把scale 参数设置成0.8，其他设置成0，是不是就是 把grid的预测网络，那6个参数的 bias初始化成 0.8和0呢？

best wishes

layumi commented 6 years ago

Hi @sillytheif Thank you for the interest in our paper. Yes. You may refer to https://github.com/layumi/Pedestrian_Alignment/blob/master/resnet52_market_stn_alignment.m#L87

sillytheif commented 6 years ago

恩恩 我看了这一行了。matconvnet我不太懂.......所以就是想问一下是不是初始化 预测网络的bias的意思

layumi commented 6 years ago

是。你可以查matconvnet文档。

sillytheif commented 6 years ago

恩恩 感谢大佬的帮助