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

About training #40

Open
helloful opened this issue Dec 1, 2021 · 4 comments
Open

About training #40

helloful opened this issue Dec 1, 2021 · 4 comments

Comments

@helloful
Copy link

helloful commented Dec 1, 2021

Hi.
Thank you very much for open source your code. But I used your network model and hyperparameters to train on the GoPro dataset (the training process was written by myself), and the gradient explosion problem occurred. I tried for a long time, but I didn’t find the problem. Do you have any suggestions?

@mayorx
Copy link
Collaborator

mayorx commented Dec 2, 2021

Hi, helloful,
Thanks for your attention to HINet.
Are the crop size(256x256) and batch size (8x8) consistent with our setting? If not, you could try to reduce the learning rate.

@ldlshizhu
Copy link

您好,您好, 感谢您对 HINet 的关注。 裁剪大小(256x256)和批量大小(8x8)是否与我们的设置一致?如果没有,您可以尝试降低学习率。

您好,感谢您的贡献。我看到gopro数据集的裁剪在论文和gopro.py中设置的是512x512,是我理解的有误吗

@mayorx
Copy link
Collaborator

mayorx commented May 13, 2022

@ldlshizhu , 您好
不好意思我的表达可能有些歧义。 我们在训练之前先做了一步数据预处理, 将gopro数据集的720x1280图片 crop成 512x512 的patches。 在数据预处理之后, 在训练过程中, 图片是从512x512的patch再random crop 256x256。

@ldlshizhu
Copy link

@ldlshizhu , 您好 不好意思我的表达可能有些歧义。 我们在训练之前先做了一步数据预处理, 将gopro数据集的720x1280图片 crop成 512x512 的patches。 在数据预处理之后, 在训练过程中, 图片是从512x512的patch再random crop 256x256。

非常感谢您的耐心解答,是我粗心了。祝您一切顺利!

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

3 participants