support for stop_gradient? #2
Open
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
I had a case where I stop_gradients in my flow. Due to this, some of my grads are zero. I've proposed a fix for this, but I should at the same time, ask if this invalidates the method or not, or if this is the correct way of handling no gradients?
Owner
|
Thanks for the contribution. Could you provide more context as to what led to zero gradients? If there are no gradients, the back path is generally routed as zero as well. So, this does not need to handled explicitly. Consider ReLU as an example. At 0, its derivatives are not defined so, it's simply routed as zeros. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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.
I had a case where I stop_gradients in my flow. Due to this, some of my grads are zero.
I've proposed a fix for this, but I should at the same time, ask if this invalidates the method or not, or if this is the correct way of handling no gradients?