Fix the "Gradients and Layers" documentation (#2628) #2629
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
… Layer initialization
…ction in Layer initialization" This reverts commit 9c90afb.
…y function in Layer initialization
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Outdated suggestions cannot be applied.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.
Fix the "Gradients and Layers" documentation issue #2628
target document part
In model3, the second layer does not have a sigmoid activation, whereas in model1 and model2 the second layer does include a sigmoid activation. As a result, the structures of model1/model2 and model3 are actually quite different, but in the “Flux’s layers” section the text implies that model1 and model3 are structurally almost the same, which is contradictory. If we make the second layer of model1 and model2 linear, this inconsistency disappears.
PR Checklist