huage001 / adaattn Goto Github PK
View Code? Open in Web Editor NEWOfficially unofficial PyTorch re-implementation of paper: AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer, ICCV 2021.
License: Apache License 2.0
Officially unofficial PyTorch re-implementation of paper: AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer, ICCV 2021.
License: Apache License 2.0
Hi, Dose this project support the video inference?
Hi , thanks for your code. As for the code in inference_frame.py, the line 110 in class AttnAdaINCos
G_norm = torch.sqrt((G ** 2).sum(1).view(b, 1, -1)) b, _, h, w = F.size() F = F.view(b, -1, w * h) F_norm = torch.sqrt((F ** 2).sum(1).view(b, -1, 1)) F = F.permute(0, 2, 1) S = torch.relu(torch.bmm(F, G) / (F_norm + 1e-5) / (G_norm + 1e-5) + 1) # S: b, n_c, n_s S = S / (S.sum(dim=-1, keepdim=True) + 1e-5)
Hello, I have tried using the pre-training model you provided, and the effect is very good. Is the pre-training model you provided trained on Wikiart? If I want to train in more styles. Can you provide more details on how to train video style transfer? Just like readme said, is it OK to train directly on the coco dataset?
Hello. Sorry to bother you. Is it convenient for the author to share the relevant code controlled by the user?
谢谢作者在图像风格转换任务上的杰出工作。介绍里面的“officially unofficial”应该怎么翻译呢?官方的非正式?
Hi! thanks for you great works. Is there anything in here that the title says?
Hi , i want to konw the pre-trained VGG encoder is pre-trained on which dataset?
In my screen, the lambda_content is always zero, i find the lambda_content is zero by default, i dont know how to set it , could you tell me how to set? Thanks!
How many epochs have been trained for the model in this paper?
Thanks~
Hi, thanks for the repo and for the video test code posted in the issues!
It would be extremely helpful for the video training script to be posted as well, so we can experiment training on specific datasets.
Thanks anyways
Hi , thanks for your code. I have two questions about it.
I don't understand what self.device
means here, it doesn't seem to be defined.
In addition, I would like to ask whether local feature loss is taking up too much memory.Because I ran out of memory when I tried to import this module into other code.
Thanks!
Did you use all the images in the dataset during training? There are many sub files in the data set wikiart. How do you train?
Hi, I am interested in this article AdaAttN. The paper only introduced two losses, Lgs and Llf, but why is there a content loss in your code?
Dear authors of AdaAttN,
Thank you for releasing this project for further reproduction of your excellent work. I would like to know if the 'Multi-style transfer' has been implemented in this version of code? If not, could you please give more details of how can we implement the idea of 'averaging their mean and standard variance maps of different styles'? How can we merge this function into the current codes?
Thank you so much for reading this issue and I look forward for your kind response:)
Can this be used for color-enhancement task? my training datasets is paired. The difference between images is in brightness, saturation, contrast.
Thank you
Thanks for the great work! It looks like this repo currently only hosts code and model for image style transfer. Could you provide a pre-trained model (and perhaps test scripts) for video style transfer as discussed in the paper? Thank you.
Hi @Huage001
I read the paper and found that mean variance norm mean 'mean-variance channel-wise norm' works quite like instance norm. Can you explain to me why use mean-variance-norm
function instead of instance norm
?
Thank you so much.
The results of your paper is interesting.
So, I want to train your model from scratch.
Before training, I want to know approximate training time when you trained your model.
Thanks.
Thanks for your sharing! May I know how can I get the test image? I noted that many papers just only mentioned the training set.
1, Should I randomly change any image to test?
2, But some papers use unified images to show their performance. May I have the same testing image as this paper?
Thank you very much
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.