Giter Club home page Giter Club logo

Comments (4)

iboing avatar iboing commented on June 16, 2024

Hi, thanks for your attention.
I think the "weight of operations" in your sense refers to the z values. Here we use the magnitude of z value to represent the importance of its corresponding connection, regardless of its sign. The feature output from each connection also could contain negative values, so restricting the weight positive does not make sense. Our goal is to optimize the choice of two connections to combine for each intermediate node. The weight values (not close to 1) indeed contribute to the optimized model. But I think the weights as scalar coefficients could be easily learned by retraining. Besides, in our one-stage ISTA-NAS with no need of retraining, the weights are coupled into the optimized model, which eliminates the gap you are concerned about.

from ista-nas.

XinleWu avatar XinleWu commented on June 16, 2024

Thanks for your reply.
Actually, the "weight of operations" I said refers to b^T * A(S) - z(S)^T *E(S,S), where the weight values can be negative and not close to 1. And I'm confused why we can evaluate the model searched by one-stage ISTA-NAS independently, because it changes the above weight matrix to a 'multi-hot' matrix.
Besides, I can't reproduce the cifar10 result under your guidance, I used the following command:
nohup python3 -u ./tools/train_search_single.py --cutout --auxiliary > ista.log 2>&1 &
and the accuracy is 96.56%.
Thanks again.

from ista-nas.

XinleWu avatar XinleWu commented on June 16, 2024

This is my training log.
ista.log
I'm trying other random seeds.

from ista-nas.

iboing avatar iboing commented on June 16, 2024

Hi, what you refer to is equal to z values (Eq. 11). Here we relax z from binary space to real space. We use the magnitude of z to indicate the importance of connections, with no regard to whether it is close to 1 or not. The weight value itself is acutally absorbed into the parameter learning of its corresponding connection in retraining. The search result could be quite diverse. So I suggest using the evaluation code to reproduce the performance of our architectures. The following files are our evaluation logs.
One stage Imgnet.log
One stage Imgnet resume.log
One stage cifar.log

from ista-nas.

Related Issues (4)

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.