Coder Social home page Coder Social logo

mvp18 / popular-zsl-algorithms Goto Github PK

View Code? Open in Web Editor NEW
60.0 60.0 16.0 67 KB

Python Implementation of Zero Shot Learning Algorithms (ALE, DeViSE, ESZSL, SAE, SJE) under ZSLGBU protocol

License: MIT License

Python 99.88% Shell 0.12%
ale computer-vision devise eszsl paper-implementations sae sje zero-shot-learning

popular-zsl-algorithms's People

Contributors

mvp18 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  avatar  avatar

popular-zsl-algorithms's Issues

Internal Server Error

Hi,
I want to run the code provided. However, the wget return an "Internal Server Error" when trying to download the file found at "datasets.d2.mpi-inf.mpg.de/xian/xlsa17.zip"
Is there an alternative location to obtain the file in question?

Thanks

SJE Normalization

I believe that line 112 of SJE/sje.py (replicated here) serves to normalize the projected image feature vector before taking its dot product with the class embeddings.
line 112: XW = preprocessing.scale(XW)

However, using this function normalizes the elements of the vector XW such that it has zero mean and unit variance, instead of scaling it by its L2 norm. This would then change the direction of XW itself, making the dot product meaningless.

Should this be changed to the following?
line 112: XW = XW / np.linalg.norm(XW)

What's surprising to me is that decent results are achieved even with the original version. I tested a few hyperparameter configs with the new code (by no means the full grid search), and achieved similar results on AWA2 with a lower margin of 0.25 (makes sense given that it now actually has unit norm).

How to generate att_splits.mat?

Hi, I would like to know how the 'att_splits.mat ' file in the xlsa17 file is formed, can you provide the exact code or link?

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.