Skip to content
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

v3模型视频推理问题 #343

Open
fzuqxt opened this issue Nov 17, 2023 · 8 comments
Open

v3模型视频推理问题 #343

fzuqxt opened this issue Nov 17, 2023 · 8 comments

Comments

@fzuqxt
Copy link

fzuqxt commented Nov 17, 2023

作者您好,我重新训练V3模型,4倍插帧推理视频的时候会出现插的3帧基本不变,像是复制的是什么原因呢?推理图片的时候不会有这种情况。

@hzwer
Copy link
Owner

hzwer commented Nov 17, 2023

如果视频和图片有差异,最大可能是推理脚本写错了 😵
三帧像复制的听起来是没有加载权重

@fzuqxt
Copy link
Author

fzuqxt commented Nov 20, 2023

视频的推理脚本是您的文件里的,很奇怪权重也有加载,就是推理视频的时候会

@fzuqxt
Copy link
Author

fzuqxt commented Nov 20, 2023

我是分布式训练,加载权重的时候from train_log.RIFE_HDv3 import Model
model = Model()
model.load_model(args.modelDir, -1)是这样吗,脚本里这样的

@fzuqxt
Copy link
Author

fzuqxt commented Nov 20, 2023

我如果将-1设置成0,中间插出来的三帧就不是复制的,但是插出来效果很差,是不是权重什么参数转换的原因呢

@hzwer
Copy link
Owner

hzwer commented Nov 20, 2023

应该是 model.load_model(args.modelDir, -1),不然会报错

你的模型训练表现怎么样?训练和测试的数据差异大吗?

@fzuqxt
Copy link
Author

fzuqxt commented Nov 20, 2023

训练插多帧的psnr是正常的30左右现在

@fzuqxt
Copy link
Author

fzuqxt commented Nov 20, 2023

按理说图片推理没问题,视频也不该有问题呀

@hzwer
Copy link
Owner

hzwer commented Nov 20, 2023

视频推理脚本支持 png 输入 png 输出的,你可以试试;可以打印调试前几帧

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants