We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
作者您好,请问您尝试过使用高分辨率数据集(比如X-TRAIN)训练RIFE吗?我在训练过程中遇到了一些问题。 实验设置如下:
首先是在训练大概1400 step后loss变为NAN:
我尝试将weight decay从1e-3增大到2e-3(没有修改学习率等其他参数),在训练大概5000 step后loss变为NaN:
尝试在IFNet中添加BN层(没有修改学习率等其他参数),训练大概40k step后loss猛增:
会不会是训练集的问题,三帧组包含多种时间间隔(比如0,1,2;0,32,64)。我现在在尝试将训练集换成时间间隔相等的三帧组(0,26,52;1,27,53;...;12,38,64)。请问作者有什么建议吗?
The text was updated successfully, but these errors were encountered:
你好,我建议:
Sorry, something went wrong.
据 VFIMamba 说,这里需要课程学习 https://zhuanlan.zhihu.com/p/923110402
No branches or pull requests
作者您好,请问您尝试过使用高分辨率数据集(比如X-TRAIN)训练RIFE吗?我在训练过程中遇到了一些问题。
实验设置如下:
首先是在训练大概1400 step后loss变为NAN:
我尝试将weight decay从1e-3增大到2e-3(没有修改学习率等其他参数),在训练大概5000 step后loss变为NaN:
尝试在IFNet中添加BN层(没有修改学习率等其他参数),训练大概40k step后loss猛增:
会不会是训练集的问题,三帧组包含多种时间间隔(比如0,1,2;0,32,64)。我现在在尝试将训练集换成时间间隔相等的三帧组(0,26,52;1,27,53;...;12,38,64)。请问作者有什么建议吗?
The text was updated successfully, but these errors were encountered: