This repository has been archived by the owner on Sep 18, 2024. It is now read-only.
Add network trimming pruning algorithm and fix bias mask(testing) #1867
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
tanglang96
changed the title
xuehui1991
reviewed
Dec 23, 2019
xuehui1991
reviewed
Dec 23, 2019
| print('# Epoch {} #'.format(epoch)) | ||
| train(model, device, train_loader, optimizer_finetune) | ||
| top1 = test(model, device, test_loader) | ||
| if top1 > best_top1: |
There was a problem hiding this comment.
do we need to use a validate dataset here?
There was a problem hiding this comment.
Strictly speaking it should be a validation dataset, but this way is commonly used in other release code of papers, so I followed this way.
There was a problem hiding this comment.
It's wired that we test directly in test dataset. I think we could change it.
xuehui1991
reviewed
Dec 23, 2019
44 tasks
QuanluZhang
reviewed
Dec 23, 2019
QuanluZhang
reviewed
Dec 23, 2019
QuanluZhang
reviewed
Dec 23, 2019
QuanluZhang
reviewed
Dec 23, 2019
QuanluZhang
reviewed
Dec 23, 2019
QuanluZhang
reviewed
Dec 23, 2019
QuanluZhang
reviewed
Dec 23, 2019
QuanluZhang
reviewed
Dec 23, 2019
QuanluZhang
reviewed
Dec 23, 2019
QuanluZhang
reviewed
Dec 23, 2019
|
look great. please resolve comments :) |
chicm-ms
reviewed
Dec 23, 2019
chicm-ms
reviewed
Dec 23, 2019
chicm-ms
reviewed
Dec 23, 2019
chicm-ms
reviewed
Dec 23, 2019
| assert all(mask1['weight'].numpy() == np.array([0., 0., 0., 1., 1.])) | ||
| assert all(mask2['weight'].numpy() == np.array([0., 0., 0., 1., 1.])) | ||
| assert all(mask1['bias'].numpy() == np.array([0., 0., 0., 1., 1.])) | ||
| assert all(mask2['bias'].numpy() == np.array([0., 0., 0., 1., 1.])) |
There was a problem hiding this comment.
is it possible to add UT for new activation pruners?
There was a problem hiding this comment.
yes I'm working on it
Cjkkkk
reviewed
Dec 23, 2019
QuanluZhang
reviewed
Dec 23, 2019
QuanluZhang
approved these changes
Dec 24, 2019
chicm-ms
approved these changes
Dec 24, 2019
xuehui1991
approved these changes
Dec 24, 2019
19 tasks
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.
Add pruning algorithm based on the activation statistics(network trimming in the iteration plan, more detailed docs will be updated later); Fix bias mask in the pruning.