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

压缩去伪影问题 #6

Open
baiyu12345 opened this issue Nov 29, 2021 · 7 comments
Open

压缩去伪影问题 #6

baiyu12345 opened this issue Nov 29, 2021 · 7 comments

Comments

@baiyu12345
Copy link

论文中说使用single model处理不同压缩因子,但是训练代码是针对不同压缩因子均训练一个模型,请问具体实验中是如何操作的?

@MC-E
Copy link
Collaborator

MC-E commented Nov 30, 2021

开源的代码和预训练模型是单一模型处理多个q的,请仔细查看。

@MC-E
Copy link
Collaborator

MC-E commented Nov 30, 2021

训练时需要准备好4个q的LR图像放在指定位置。

@baiyu12345
Copy link
Author

这个是给出的训练命令:python train.py --dir_data=DIV2K/ --q=10 --save_path=exp --lr=2e-4 --batch_size=32
其中 q = 10,即为定位到q为10的LR中

@MC-E
Copy link
Collaborator

MC-E commented Nov 30, 2021

代码是按照随机q训练的,没有任何问题,后续会进行优化。

@MC-E
Copy link
Collaborator

MC-E commented Nov 30, 2021

感谢指出问题

@baiyu12345
Copy link
Author

明白了,是这两句实现随机训练
if self.train==True:
id_q=np.random.randint(low=0, high=4)
f_lr=f_lr.replace('/10/',self.list_q[id_q])

@MC-E
Copy link
Collaborator

MC-E commented Nov 30, 2021

是的,后续会优化这个地方。

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