NAFNet

NAFNet copied to clipboard

about the MACs of the model

1

hi, Thanks first for the excellent work! And can you share the script of counting model MACs?

knsong

合成图像去噪

1

请问有没有合成噪声图像去噪的代码，是需要把噪声图像先存到本地吗？

ruibinzhuge

For StereoSR Task, How do I prepare the training dataset?

1

Hi, thanks for your wonderful work. May I know how I can prepare the dataset when training on SSR task? It seems that there are 298143 images in patches_x2 but...

HanshengGUO

train on our dataset

1

can you put complete code to train network on our dataset??

mhfatemi

Denoise大图像测试问题

1

你好， 请问NAFNet在Denoise中如何测试大图像呢，要切成多个小图像再进行测试吗？

958984240

LayerNorm's position in NAFBlock

1

Hi, refer from "Attention Is All You Need", the LN position is in the tail of the attention and feedforward block, but you put the LN at the head of...

four1000

ask for advice

3

你们做的工作太漂亮了！ 我想请教一下，你们首页的gif是怎么制作的，有没有教程啥的，我想学着做一个。 谢谢了，真的很酷。

caiyuanhao1998

Dear author,I want to why not use weight decay to train this model?

1

想知道为什么不使用weight-decay来训练模型，这样不会导致过拟合嘛？

BrotherHappy

SimpleGate and SCA

3

你好，很高兴看到MEGVII在low-level任务上的新工作，在跑过demo之后，我在Imagenet分类任务上了尝试由NAFBlock组成的网络，但是取得的效果都比较差，请问这部分网络改进在high-level任务上有尝试过吗，或者说之后有相关工作会分享吗，非常感谢。

kings-rgb

Hi

3

《NAFSSR: Stereo Image Super-Resolution Using NAFNet》这篇文章可以从哪里找到

ZW-PRO