Conversation
krzentner
approved these changes
Apr 6, 2020
Contributor
krzentner
left a comment
krzentner
left a comment
There was a problem hiding this comment.
Oh! That makes sense, and is surprisingly simple. LGTM.
ryanjulian
approved these changes
Apr 6, 2020
Codecov Report
@@ Coverage Diff @@
## master #1283 +/- ##
=======================================
Coverage 89.10% 89.10%
=======================================
Files 194 194
Lines 9652 9655 +3
Branches 1226 1226
=======================================
+ Hits 8600 8603 +3
Misses 816 816
Partials 236 236
Continue to review full report at Codecov.
|
avnishn
approved these changes
Apr 7, 2020
Member
Author
|
@Mergifyio rebase |
Grad of tensor is needed for the next grad update. Keep grad except for the last grad update.
Contributor
|
Command
|
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This fixes #1269 , that MAML breaks when
num_grad_updateis larger than 1.This is because gradient information is cleared out after the first gradient update, but it is needed for later gradient updates.