Code Monkey home page Code Monkey logo

unsuperviseddeephomography-pytorch's People

Contributors

breadcake 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

Watchers

 avatar  avatar

unsuperviseddeephomography-pytorch's Issues

dear breadcake

尊敬的张先生,您好:
在看了您对《Deep Image Homography Estimation》和《Unsupervised Deep Homography:A Fast and Robust Homography Estimation Model》的pytorch实现后,我深受启发,读了您的代码之后,我受益匪浅,对于文章中我不理解的地方,您的代码给了我解答,所以,请允许我向您表示感谢。
如果我没猜错的话,您应该是一名优秀且已经毕业的研究生。在您的“基于深度学习的图像拼接”的毕业论文中,我惊叹于您丰富的研究内容和创新点。我现在对图像拼接也十分感兴趣,虽然我还是一只菜鸟,但我很愿意学,请您给我一个向您请教的机会。
我最近正在学习深度学习在图像拼接方面的应用,并对此产生了浓厚的兴趣,我斗胆向您讨要一份“基于深度学习的图像拼接”这一论文的代码,我对您的工作实在非常感兴趣和佩服,希望向您学习。谢谢您。

Mr.Zhang:
After reading your implementation of “Deep Image Homography Estimation” and “Unsupervised Deep Homography:A Fast and Robust Homography Estimation Model” using pytorch, I am deeply inspired. After reading your code, I benefited a lot. For what I don't understand in the articles, your codes give me answer, so please allow me to thank you.
If I guess correctly, you should be an excellent graduate student who has graduated. In your graduation thesis of "image mosaic based on deep learning", I was amazed at your rich research content and innovation. I'm also very interested in image mosaic, although I am still a rookie, I am willing to learn, please give me a chance to learn from you.
Recently, I am studying the application of deep learning in image mosaic and have a strong interest in it, could I ask you for the code of the paper "image mosaic based on deep learning". I am really interested in and admire your work and hope to learn from you. Thank you very much.

gpu上训练

我在跑这个模型的时候,无法把它放在gpu上跑,请问,您使用gpu跑这个深度学习项目时,直接使用的这份代码,没有再添加其他的语句吗。我直接使用这份代码时,代码还是在cpu上运行。(我的cuda是可用的,is_available返回true

tensorflow转pytorch

您好,请问在:“Unsupervised Deep Image Stitching Reconstructing Stitched Features to Images”论文中的项目代码中,可否将tensorflow转换为pytorch,我是想问,从理论上来说,是否所有的tensorflow代码都可以转换为对应的pytorch,我在网络、知乎等平台搜索和提问过,但都没能得到很好的解答。
另外,我找到一个新的拼接项目,但是效果可能不是很好,也是pytorch的,您可以看一下:https://github.com/michael-1003/DeepImageStitching

配置环境相关问题

您好,想请教一下您这里运行该代码需要配置相关的什么样的pytorch环境呢,以及依赖的各个包是什么样的版本呢?可以提供一下相关的requirements.txt文件吗?感谢!

训练报错

请问博主使用的具体环境是什么呢?
我在使用pytorch=1.7使用预训练模型测试时一切正常,然而在训练时,出现了以下错误:RuntimeError: CUDA error: no kernel image is available for execution on the device
但是我的这个虚拟环境经过测试是可以正常训练Deep Homography Estimation代码的

tensorflow转pytorch

您好,请问在:“Unsupervised Deep Image Stitching Reconstructing Stitched Features to Images”论文中的项目代码中,可否将tensorflow转换为pytorch,我是想问,从理论上来说,是否所有的tensorflow代码都可以转换为对应的pytorch,我在网络、知乎等平台搜索和提问过,但都没能得到很好的解答。
另外,我找到一个新的拼接项目,但是效果可能不是很好,也是pytorch的:https://github.com/michael-1003/DeepImageStitching,您可以看一下。

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.