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
感谢作者开源的HAT,在动漫数据集上面进行训练取得了非常好的效果。 目前遇到的问题是:显存不足需要强制切片推理,并且图片前后景有虚化,人物应该是清晰的场景很容易误判景深(如下图绿色框所示): 是否有可能能把全局的信息同步给每个tile,以此来纠正模型超分每个tile的行为?(尝试过”滑窗“等切片策略,但依然不能根除bad case)
The text was updated successfully, but these errors were encountered:
引入全图信息作为condition和一些具有全局degradation的pair数据进行训练理论上是应该可以解决的。Tuning-free的方法感觉应该不太行。
Sorry, something went wrong.
No branches or pull requests
感谢作者开源的HAT,在动漫数据集上面进行训练取得了非常好的效果。
目前遇到的问题是:显存不足需要强制切片推理,并且图片前后景有虚化,人物应该是清晰的场景很容易误判景深(如下图绿色框所示):
是否有可能能把全局的信息同步给每个tile,以此来纠正模型超分每个tile的行为?(尝试过”滑窗“等切片策略,但依然不能根除bad case)
The text was updated successfully, but these errors were encountered: