Git Product home page Git Product logo

Comments (3)

tahmid0007 avatar tahmid0007 commented on July 23, 2024

Hi there,
Thanks for your interest. There are albeit minor differences but I can assure you none of these will result in significant deviation in inference. Again thanks for your pointer and I will look to tighten the gap in future repos.

from visualtransformers.

lclkent avatar lclkent commented on July 23, 2024

Thanks for your reply! I still have some questions regarding the original paper of Visual Transformer, hopefully you could help me out.
1.In the paper, they set the token channel size to 1024. However, according to Fig.2 and the residual adding in equation 3 and 4, I assume the channel size is always the same with input feature map channel size (for ResNet18&34, the channel size is 256).
2. They adopt transformer encoder, however it seems to me that no multi-head attention is used from equation 3.
I appreciate it very much if you could help me out.

from visualtransformers.

lclkent avatar lclkent commented on July 23, 2024

Never mind, the first version paper have help me out.

from visualtransformers.

Related Issues (12)

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.