Giter Site home page Giter Site logo

rayabhisek123 / cfat Goto Github PK

View Code? Open in Web Editor NEW
60.0 2.0 3.0 3.56 MB

[CVPR 2024] "CFAT: Unleashing Triangular Windows for Image Super-resolution"

Home Page: https://arxiv.org/abs/2403.16143

Python 100.00%
attention-mechanism attention-model deep-learning-framework image-restoration image-sr image-super-resolution light-weight-image-super-resolution low-level-vision rectangular-window restoration

cfat's People

Contributors

rayabhisek123 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

cfat's Issues

Depth of CFAT

Thank you for sharing an amazing work.

I have a small question about the depth of CFAT. When i read the main paper, in the section 5.2, you wrote that "While configuring the proposed CFAT, we put 3 DWAB and 3 SWAB in an alternative order.". I understand that have 6 Window Attention Blocks in total. But when i looked at the supp. file, in the section 1., you wrote "We take (8, 8, 8, 8, 8, 8, 8, 8) WAB units for CFAT-l, (8, 8, 8, 8, 8) for CFAT, and (8, 8, 8) for CFAT-r.", it means CFAT has 5 Window Attention Blocks.
It's quite confused to me, can you confirm this point?

custom dataset issues

ValueError: At least one stride in the given numpy array is negative, and tensors with negative strides are not currently supported. (You can probably work around this by making a copy of your array with array.copy().)

setup.py

Hello,

is there a setup.py file missing?

Issue for input

if the input is (1,1,40,28)
how to modify your code parameter to make your network work?
RuntimeError: shape '[1, 5, 8, 3, 8, 1]' is invalid for input of size 1120

gpu

请问怎么在一台有两张gpu的电脑上复现您的代码呢

移位是怎么移位的

矩形窗口的移位和三角形的移位是从左到右、从上到下吗,和swintransformer中的shifted window不一样吗

Issue about python setup.py develop

Traceback (most recent call last):
File "setup.py", line 81, in
write_version_py()
File "setup.py", line 58, in write_version_py
with open('VERSION', 'r') as f:
FileNotFoundError: [Errno 2] No such file or directory: 'VERSION'

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.