Git Product home page Git Product logo

Comments (10)

SeokjuLee avatar SeokjuLee commented on July 21, 2024 1

@harrygcoppock Thanks Harry.

from self-attention-gan.

harrygcoppock avatar harrygcoppock commented on July 21, 2024

My model often learns a negative gamma. I do not think that this means that it has a negative affect, the most important part is the magnitude. out = input + gamma*attentionOutput.

from self-attention-gan.

csyhping avatar csyhping commented on July 21, 2024

@harrygcoppock @SeokjuLee Hi, I've got the negative gamma, may I ask what value do you get?

from self-attention-gan.

harrygcoppock avatar harrygcoppock commented on July 21, 2024

sorry I never saved the gamma results and cannot remember. A guess was that it slowing increased to 1 or -1 but again that is just a guess. I think it plateaued at this magnitude.

from self-attention-gan.

csyhping avatar csyhping commented on July 21, 2024

@harrygcoppock thanks for your quick reply, I got the gamma about -0.01, do you think this is normal?

from self-attention-gan.

harrygcoppock avatar harrygcoppock commented on July 21, 2024

The point of the gamma parameter is that at the start of training (when gamma = 0) the model can quickly learn the easier convolutional features. Then the model can slowly introduce information from the attention layer. I recall that the paper argues that this is a somewhat harder task. If your gamma value remains low maybe the model struggles to make use of the attention layer? However this is just speculation. Maybe first investigate the relative magnitudes of the skip connection and the output of the attention layer before gamma is applied (if |output from attention| >>|skip connection| then a gamma value of 0.01 could still be significant?). Finally did the gamma value plateau at this level?

from self-attention-gan.

csyhping avatar csyhping commented on July 21, 2024

@harrygcoppock ,yes the value plateau at this level. I'm a rookie to self-attention, so I have no experience on whether -0.01 is a normal value.

from self-attention-gan.

harrygcoppock avatar harrygcoppock commented on July 21, 2024

I too am relatively new to the field, however if you are interested in finding out why all I can think of is my above point. That and postulating that maybe self attention is not helping you here - maybe the problem set is not a good match or you have initialised your attention layer poorly.

from self-attention-gan.

csyhping avatar csyhping commented on July 21, 2024

@harrygcoppock thanks a lot for your kindly help!I will do more checks. Besiedes, may I ask what should be a normal value of gamma when self-attention works well? 0.1 or any?

from self-attention-gan.

SeokjuLee avatar SeokjuLee commented on July 21, 2024

@csyhping Hi, I can't remember the detailed value, but I think I got a similar result. As Harry commented, the magnitude of gamma gradually increased from zero.

from self-attention-gan.

Related Issues (20)

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.