Make InputLayer support masking #10794
Merged
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
fchollet
reviewed
Jul 28, 2018
tests/keras/layers/core_test.py
Outdated
| @@ -4,7 +4,7 @@ | |||
|
|
|||
| from keras import backend as K | |||
| from keras import layers | |||
| from keras.models import Model | |||
| from keras.models import Model, Sequential | |||
tests/keras/layers/core_test.py
Outdated
| @keras_test | ||
| def test_sequential_as_downstream_of_masking_layer(): | ||
|
|
||
| input = layers.Input(shape=(3, 4)) |
There was a problem hiding this comment.
input is a reserved Python keyword, use inputs
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Outdated suggestions cannot be applied.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.
Summary
SequentialaddsInputLayerautomatically if users don't assign. WhenSequentialwas placed as downstream ofMaskinglayer(#10763), even if all users explicitly added layers inSequentialsupport masking, it still throws exception due toInputLayerdoesn't support masking.I think
InputLayershould support masking and it can use the defaultcompute_maskfunction in base layer(just carry over the input mask). Because users don't add this layer explicitly, it should transparent to users.Related Issues
#10763
PR Overview