xuebinqin
commented
4 years ago 是这样的，d0-d7已经在BASNet的forward函数里面上采样到与输入图像一样的分辨率了。
On Thu, Oct 31, 2019 at 3:29 AM beichen2012 notifications@github.com wrote:
代码没有条件跑，弱弱的问一下，labels_v从dataloader中取出好，没有做尺度变换，直接给d0~d7做loss了，这里是如何操作的？没有看明白。
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/NathanUA/BASNet/issues/22?email_source=notifications&email_token=ADSGOROPC3XCA6I7KU3FB3LQRKQOZA5CNFSM4JHG6QX2YY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4HVWTWPA, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADSGORMYH6B37XSWKAOWD6TQRKQOZANCNFSM4JHG6QXQ .
-- Xuebin Qin PhD Candidate Department of Computing Science University of Alberta, Edmonton, AB, Canada Homepage:https://webdocs.cs.ualberta.ca/~xuebin/
代码没有条件跑，弱弱的问一下，labels_v从dataloader中取出好，没有做尺度变换，直接给d0~d7做loss了，这里是如何操作的？没有看明白。