Subtract merge layer #7573
Merged
Subtract merge layer #7573
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
With the merge method being deprecated by end of 8/2017, there needs to be a way to define a subtraction of two layers. This Subtract layer takes exactly two tensors and returns the difference.
Adding Subtract unit test
Dref360
reviewed
Aug 9, 2017
keras/layers/merge.py
Outdated
| """Layer that subtracts two inputs. | ||
|
|
||
| It takes as input a list of tensors of size 2, | ||
| both of the same shape, and returns |
There was a problem hiding this comment.
Not necessarily the same shape?
x = K.ones([10,10])
y = K.ones([1,10])
x - y # Does not raise.There was a problem hiding this comment.
Thanks, added support and unit test for shape mismatch.
Dref360
approved these changes
Aug 9, 2017
fchollet
reviewed
Aug 9, 2017
keras/layers/merge.py
Outdated
|
|
||
| It takes as input a list of tensors of size 2, | ||
| both of the same shape, and returns | ||
| a single tensor (also of the same shape). |
There was a problem hiding this comment.
Explicitly state that it returns inputs[0] - inputs[1].
There was a problem hiding this comment.
Thanks, updated the documentation.
|
All the tests passed, but the pull request failed. Is this related to this request, or possibly another issue? |
|
It's a temporary file system-related issue with Travis. Cause unclear; maybe Travis itself, or a recent update to pytest. |
fchollet
previously approved these changes
Aug 10, 2017
fchollet
approved these changes
Aug 10, 2017
ahundt
added a commit
to ahundt/keras
that referenced
this pull request
Aug 11, 2017
* master: model.fit(steps_per_epoch), mnist_tfrecord.py, progbar np.mean (keras-team#7113) Change default size to allow different MobileNet sizes (keras-team#7586) cntk backend: fix the reversed rnn bug (keras-team#7593) Fix mask for multi output --> multi inputs (keras-team#7591) [RELNOTES] Subtract merge layer (keras-team#7573) update docker with cntk 2.1 (keras-team#7565) [RELNOTES] Move constraint management to be based on variable attributes (like TF). (keras-team#7564) Add handling for `dtype` arg in initializer config. Fix keras-team#7550. (keras-team#7552) remove unnecessary function definition (keras-team#7542) refactor the function - _convert_string_dtype (keras-team#7540) Add batchnorm tests for CNTK (keras-team#7534) Clean up RNN tests (keras-team#7529) Add merge tests (keras-team#7533) # Conflicts: # examples/mnist_tfrecord.py # keras/engine/training.py # keras/utils/generic_utils.py # tests/keras/engine/test_training.py
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.
With the merge method being deprecated by end of 8/2017, there needs to be a way to define a subtraction of two layers. This Subtract layer takes exactly two tensors and returns the difference.