Comments (2)
Hi casarinsof,
Thank you for your interest in our work.
You are on the right track. The projection step refers to the architecture selection, so it is necessary. After the supernet is trained (train_search), you would need to run the architecture selection to pick the final architecture, which is represented as a genotype. Inserting that into the genotype.py file, give it a variable name (e.g. arch1), then run the retrain command in the README.md with "arch1".
Hope that helps!
from darts-pt.
Hello! Thank you for you reply!
Then I have 2 other questions:
- I run the code without the projection step, but juts insertiong the genotype I got after the search and directly running the evaluation, and got the same result of your paper, how so? I mean as I am missing one step, what did happen?
- The architecture selection corresponding to running projection.py, to which step of the algorithm or passage correspond in your paper? It is still not clear to me.
Thanks a lot
from darts-pt.
Related Issues (9)
- Which version of nas-bench-201 does the code use? HOT 2
- For eval.sh on CIFAR10 HOT 3
- Performance in Subspace HOT 1
- About the generation of structures HOT 10
- Search for RNN HOT 2
- The accuracy on cifar10 on NAS-Bench-201 HOT 1
- What is the difference between different versions on NASBench201 HOT 1
- Argument to be given for --arch in evaluating sota. HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from darts-pt.