-
Notifications
You must be signed in to change notification settings - Fork 446
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
HDv3模型的复现 #336
Comments
Hi,我用的是 loss_l1+loss_cons*0.01+loss_vgg(可选);psnr这么低的情况下,是不是有可能数据喂错了 |
请问这里的loss_cons是什么?谢谢 |
@apple1986 是一个 student 向 teacher 学习光流的 loss |
|
@xjjww |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
flow, mask, merged = self.flownet(torch.cat((imgs, gt), 1), scale=scale, training=training)
loss_l1 = (merged[2] - gt).abs().mean()
loss_smooth = self.sobel(flow[2], flow[2]*0).mean()
# loss_vgg = self.vgg(merged[2], gt)
if training:
self.optimG.zero_grad()
loss_G = loss_cons + loss_smooth * 0.1
loss_G.backward()
self.optimG.step()
else:
flow_teacher = flow[2]
return merged[2], {
'mask': mask,
'flow': flow[2][:, :2],
'loss_l1': loss_l1,
'loss_cons': loss_cons,
'loss_smooth': loss_smooth,
}
想问您使用的是几个loss?是”loss_l1+loss_cons+loss_smooth“三个loss吗?还是仅仅loss_cons + loss_smooth * 0.1?
还想问下作者,使用HDv3复现插多帧模型的时候,训练并不成功,模型的psnr值为2.多,是什么原因呢?
The text was updated successfully, but these errors were encountered: