Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[discussion] Support Advanced NAS Algorithms #461

Open
gaocegege opened this issue Apr 19, 2019 · 10 comments
Open

[discussion] Support Advanced NAS Algorithms #461

gaocegege opened this issue Apr 19, 2019 · 10 comments

Comments

@gaocegege
Copy link
Member

Now we are using a custom IR (architecture + nn_config) to represent a candidate model, which may be insufficiently expressive, I think.

I think we should use mature IRs such as Relay IR or ONNX to represent the candidate model.

/cc @DeeperMind @andreyvelich

@gaocegege
Copy link
Member Author

Ref apache/tvm#1673

@andreyvelich
Copy link
Member

@gaocegege This is make sense. What changes in API do we need to make IR like Relay IR or ONNX. And what will be the best for the NAS tasks?
/cc @johnugeorge @richardsliu @hougangliu @YujiOshima

@gaocegege
Copy link
Member Author

We need to investigate which IR works well for the case. microsoft/nni uses ONNX. While I think ONNX is not expressive.

@anchovYu is working on this issue.

@andreyvelich
Copy link
Member

That is cool! Just let us know which structure you want to use and will our definition of Neural Network work for that. For RL you can find it here.

@gaocegege
Copy link
Member Author

@andreyvelich Yeah, sure. Maybe we could discuss it in the katib meeting. Actually, we are not sure about the choice, too.

There are several ways to represent the search space of NAS: chain-structured (what we are using now), chain-structured with jumps and other advanced links, and cell-structured. I cannot figure a way to represent such complex space definition, even via ONNX or Relay IR or other IRs.

@andreyvelich
Copy link
Member

Alright, let discuss at Katib meeting in this week.
/cc @DeeperMind

@gaocegege gaocegege changed the title [discussion] Intermediate representation of graph in NAS [discussion] Support Advanced NAS Algorithms Apr 3, 2020
@gaocegege
Copy link
Member Author

https://github.com/microsoft/onnxruntime/tree/master/orttraining ONNX runtime supports training ONNX. Maybe we could have a look.

/cc @andreyvelich

@issue-label-bot
Copy link

Issue-Label Bot is automatically applying the labels:

Label Probability
area/katib 0.74
kind/question 0.84

Please mark this comment with 👍 or 👎 to give our bot feedback!
Links: app homepage, dashboard and code for this bot.

@stale
Copy link

stale bot commented Nov 24, 2020

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

@andreyvelich
Copy link
Member

/lifecycle frozen

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

3 participants