GithubHelp home page GithubHelp logo

mohammadfneish7 / keras_lstm_diagram Goto Github PK

View Code? Open in Web Editor NEW
207.0 7.0 34.0 385 KB

Understanding Keras Recurrent Nets' structure and data flow (mainly LSTM) in a single diagram.

License: GNU General Public License v3.0

keras_lstm_diagram's People

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  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar

keras_lstm_diagram's Issues

Batch size and samples confusion

Thank you Mohammad for the diagram, it's very useful however I'm a little confused about one thing.

In the part of the diagram showing the reshaped input data, one axis is labelled "No. of samples (batch size)" and in the text panel to the right under the Input Layer heading you describe the first axis of the 3D input as "No. of batches or samples". Is this intentional? It seems to imply Batch Size == No. of batches, or am I misunderstanding something here?

Features length and output

Greetings Mohammad and thanks for the useful diagram.

I wanted to clarify a few things regarding how LSTM handles operations with regard to different feature length / sequence length, and I came across this repo.

From your diagram (alone), it seems like the number of features affects the output dimension, while this, from my understanding, is depended only on the number of units.
You mention after all that the number of output units can be any number we desire.
Am I missing something? (regarding what the diagram shows)

Thanks,
Alex

Mohammad, really thanks from Korea.

finally I got to your fancy explaination, midnight south Korea. really thank your for your dedication for sily like me. haha Thanks again!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!

PS. if you don't mind, Can I translate it into Korean?

"Shuffle" mis-spelled

Mohammad, great diagram, I noticed the parameter "shuffle" is mis-spelled (no "h") in the 4th text block under "Input Data".

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.