-
Notifications
You must be signed in to change notification settings - Fork 187
New issue
Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? # to your account
LIQE训练过程中loss不收敛,请问是什么问题呢 #229
Comments
模型默认采用推理模式,因此disable gradient来节省计算量。如果需要训练需要传入 |
但是传入
|
此外,我理解的 |
这里的loss是指用训练好的模型作为一个另一个需要训练的模型(例如图像超分辨率模型)的损失函数。如果你想要训练IQA模型本身,请参考本仓库训练部分的代码 |
`
model = pyiqa.create_metric('liqe', device=device, pretrained=False)
model.to(device)
pred = model(img)
loss = loss_iqa(pred.squeeze(), mos.float().detach())
`
The text was updated successfully, but these errors were encountered: