-
Notifications
You must be signed in to change notification settings - Fork 115
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
Can you provide the code for training? Thanks #10
Comments
你好,可以分享下数据集吗? |
我看了你们的报告,很感兴趣,谢谢! |
@Ir1d 好的,没注意 |
@Ir1d do you realize the demo ? |
@tkone2018 demo 没问题啊? training code 的确没有 |
@Ir1d 你理解那个attention模块吗? |
@Ir1d 我用demo的时候显示cuda内存不够,很尴尬 |
When is it possible to provide training code for the algorithm? I have tested some pictures from web, and found that the effect is not good. |
@YiLiangNie Welcome to try my implementation and train your own model:) https://github.com/MaybeShewill-CV/attentive-gan-derainnet |
我是我根据论文自己复现的基于pytorch的代码 https://github.com/7568/DeRaindrop , 里面有训练代码和测试代码 |
你好,我用你的代码进行训练,训练结果和原文给出的权重差一点。这和您没有使用dataloader、和没有使用动态学习率有关吗 |
@7568 你好,我用你的代码进行训练,训练结果和原文给出的权重差一点。这和您没有使用dataloader、和没有使用动态学习率有关吗 |
@tkone2018 你好,你可以在作者 predict.py 文件下 ”if args.mode == 'demo':“ 语句后面加上 ”with torch.no_grad ():“。我加上之后程序可以运行,之前也是 out of memory |
@Rayn-Wu 好的,谢谢 |
@7568 |
No description provided.
The text was updated successfully, but these errors were encountered: