This repository has been archived by the owner on Sep 18, 2024. It is now read-only.
Add evalutaion scripts for TextNAS #2220
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
|
pkuyym
changed the title
35 tasks
added 2 commits
March 23, 2020 06:12
pkuyym
changed the title
ultmaster
reviewed
Mar 25, 2020
examples/nas/textnas/macro_child.py
Outdated
| bn_flag = True | ||
| branch_id = self.sample_arc[branch_id] | ||
|
|
||
| for operation_id in [0, 1, 2, 3]: # conv_opt |
There was a problem hiding this comment.
I notice that this is a LayerChoice but it's not using NNI interface. Theoretically, with NNI, you can share the same model class in search and retrain. Are you having any trouble with that?
There was a problem hiding this comment.
Totally agree, it is better to adopt the NNI interface. I need more time to learn the NNI interface and do the adaption.
QuanluZhang
approved these changes
Mar 30, 2020
ultmaster
approved these changes
Mar 30, 2020
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Currently, the reproduction couldn't be guaranteed, will keep polishing this PR.
Since the dataloader changed, we need re-do the hyper-parameter search. The performance of current setting: sst-2: 90.12, sst-5: 53.3