[references/classification] Adding gradient clipping #4824
Merged
Conversation
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
💊 CI failures summary and remediationsAs of commit 330c403 (more details on the Dr. CI page): 💚 💚 Looks good so far! There are no failures yet. 💚 💚 This comment was automatically generated by Dr. CI (expand for details).Please report bugs/suggestions to the (internal) Dr. CI Users group. |
yiwen-song
commented
Nov 2, 2021
kazhang
reviewed
Nov 2, 2021
kazhang
reviewed
Nov 2, 2021
|
Hey @sallysyw! You merged this PR, but no labels were added. The list of valid labels is available at https://github.com/pytorch/vision/blob/main/.github/process_commit.py |
facebook-github-bot
pushed a commit
that referenced
this pull request
Nov 8, 2021
Summary: * [references] Adding gradient clipping * ufmt formatting * remove apex code * resolve naming issue Reviewed By: kazhang Differential Revision: D32216659 fbshipit-source-id: 9c5ffb102fa5fd9861ae5ba0c44052920c34ebaf
cyyever
pushed a commit
to cyyever/vision
that referenced
this pull request
Nov 16, 2021
* [references] Adding gradient clipping * ufmt formatting * remove apex code * resolve naming issue
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Gradient Clipping can be useful in training - it is a technique to prevent exploding gradients in very deep networks.
Pytorch has a related API
torch.nn.utils.clip_grad_norm_which can be utilized here.By applying gradient clipping to training, we significantly improved the training accuracy of our modes. For example:
cc @kazhang @datumbox