GithubHelp home page GithubHelp logo

self-distilled-swin's People

Contributors

amiiney avatar

Stargazers

 avatar

Watchers

 avatar  avatar  avatar  avatar

self-distilled-swin's Issues

Is this code base reproduceable?

Hello, based on reading the code and the Miccai 2023 paper.
I was wondering if this code is reproducible, where it seems like it is missing several parts of the code.

Performance of SwinT + MultiT

Hello, Thank you for releasing the code with clear instructions! I have a question regarding the performance of SwinT + MultiT.

When I used the code uploaded on GitHub to reproduce the results, the performance of SwinT + MultiT was worse than that of SwinT alone. In my environment, SwinT achieved a performance of 32.14, while SwinT + MultiT achieved a performance of 32.02.

I'm wondering if, in my opinion, when calculating classwise in train.py, the index should be incremented by 131 for SwinT + MultiT, rather than 100.
Thank you.

classwise

Where is label for phase recognition ??

How can we train the model with multi-task learning, phase-recognition.

in the train.py there is code where it loads

from multihead import * from multihead_phaseprediction import *

However, in the code there isn't multihead .py or multihead_phaseprediction .py

The url of pretrained models is unavailiable

Hi, as I am trying to load from pretrained modules, I find the url where the modules should be downloaded from is unavailiable.

If running generate.py, an error of "socket.gaierror: [Errno -5] No address associated with hostname" will occur.

And if access the url directly, the browser respond with "Can't find the server's IP address".

Grateful if this issue can be solved

Pretrain module avaliablity?

Thank you very much for your hard work. this is outstanding work.

I would like to ask if you have any pretrained modules available for public use so that we (and other workers) can replicate and compare your work in our work? Thank you.

Question about the SwinT+Multi

Hello, Thank you for releasing the code with clear instructions!

I have a question about "SwinT+Multi". In the paper, it was mentioned that phase recognition information is required for training the "SwinT+Multi" model. However, in the code documentation and instructions provided, there seems to be no mention or requirement of phase recognition information for reproducing the "SwinT+Multi" results.

please let me know if I miss understood "SwinT+Multi"

Best

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.