Coder Social home page Coder Social logo

atulshanbhag / layerwise-relevance-propagation Goto Github PK

View Code? Open in Web Editor NEW
95.0 4.0 25.0 17.42 MB

Implementation of Layerwise Relevance Propagation for heatmapping "deep" layers

Python 100.00%
deep-learning visualization interpretable-deep-learning interpretable-machine-learning

layerwise-relevance-propagation's People

Contributors

atulshanbhag 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 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

Forkers

vseledkin yvonneliyzh sitinggz tiagofrepereira2012 nadezhdakor aniketgupta1997 miss1997yuan baij02 guokailiu bengword2vec mousamustafa zixinyi inderight pstegma eunjuyang shray64 vidhipitroda pann-vandet danny305 choco-py jurijnabergoj manu87ds kuper7 aidenparkerr

layerwise-relevance-propagation's Issues

minist example error

why do I get this error when I run the mnist example?
name = act.name.split('/')[2]

IndexError: list index out of range

Changing neural network architecture doesn't improve heatmaps

In mnist program, I modified it to feed images and changed neural network architecture by including more convolutional layers and tried for cat/Dog images instead of mnist data. I got heat maps which include features other than cat and dog also. please let me know what has to be done for getting proper heat maps.

Missing directories 

logdir = './logs/'
chkpt = './logs/model.ckpt'

Are needed to unload saved model.

License

Dear atulshanbhag,

Could you please add a license?

It's also in your own interest because so far you are not protected against liability claims, e.g. if a Tesla runs into a train and it turns out it happened because of the code failed.

Usually, the MIT license is a good option for the open-source.

https://opensource.org/licenses/MIT

Best regards,
Gregory

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.