This repository has been archived by the owner on Sep 18, 2024. It is now read-only.
Fix bug for speedup module and enhance the Ut for speedup #3279
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
QuanluZhang
reviewed
Jan 7, 2021
QuanluZhang
reviewed
Jan 7, 2021
J-shang
reviewed
Jan 7, 2021
| @@ -128,6 +128,18 @@ def generate_random_sparsity(model): | |||
| 'sparsity': sparsity}) | |||
| return cfg_list | |||
|
|
|||
| def generate_random_sparsity_v2(model): | |||
There was a problem hiding this comment.
maybe better to use ratio as a parameter, like def generate_random_sparsity(model, layer_ratio):, just personal opinion, the current implementation is fine to me.
Signed-off-by: Ningxin <Ningxin.Zheng@microsoft.com>
QuanluZhang
approved these changes
Jan 7, 2021
J-shang
approved these changes
Jan 7, 2021
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Outdated suggestions cannot be applied.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.
Fix bug for speedup and enhance the UT for speedup.
(1) The generated mask tensor should be on the same device as the original tensor.
(2) Due to
Catoperator, the current speedup module may add a full-ones mask for some layers, the second bug will make the speedup module skip this mask(added by fix mask conflict) and lead to a shape mismatch.