-
Notifications
You must be signed in to change notification settings - Fork 197
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
About SyncNet #90
Comments
我试过加上optimizer.zero_grad(set_to_none=True)后,loss会很小,偶尔会报错。尝试改动train.py中相应的10*sync_loss,区别不太大。也想知道作者大大累加梯度的本意 |
加上optimizer.zero_grad()后训练大约十来个epoch就可以收敛了,因为只有单个样本。 |
请教下,意思是说整个unet的训练也梯度累积了么?清零后是不是可以保证质量的情况下缩短训练时长呢? |
是的,我感觉清零后效果是可以接受的,下面这个是简单尝试的,用的wenet,因为训练时是英文的,用英文的测试感觉更自然,那个视频太大了发不上来。 6bcbf4f8a55c07cb5f1a055cb65511b8.mp4 |
感谢,这么说还是可以尝试下的,口型中英文训练的互泛性本身就不太好 |
为什么 SyncNet训练时不用进行optimizer.zero_grad()?
The text was updated successfully, but these errors were encountered: