search

xuebinqin / U-2-Net

The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."
Apache License 2.0
8.52k stars 1.47k forks source link

u2net_train.py第130行 #63

Closed hpc203 closed 4 years ago

hpc203 commented 4 years ago

在u2net_train.py第130行，为什么输入张量和标签的requires_grad=False，按理来说，在训练的时候应该设置为True的

xuebinqin commented 4 years ago

They are constant (x,y') and no need to compute their gradients for updating their values.

On Thu, Sep 3, 2020 at 8:25 PM hpc203 notifications@github.com wrote:

在u2net_train.py第130行，为什么输入张量和标签的requires_grad=False，按理来说，在训练的时候应该设置为True的

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/NathanUA/U-2-Net/issues/63, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADSGORO73UVVC3CLLTEA323SEBFYHANCNFSM4QWYNFFA .

-- Xuebin Qin PhD Department of Computing Science University of Alberta, Edmonton, AB, Canada Homepage:https://webdocs.cs.ualberta.ca/~xuebin/