Add PReLULayer #1880
Closed
Add PReLULayer #1880
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
described in Kaiming He et al, "Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification", arxiv 2015. Conflicts: src/caffe/proto/caffe.proto
|
Doesn't relu_layer already have negative_slope, which could be the same as the 'a' parameter in the paper? |
|
@pannous The differences between them are that
|
|
I see, thanks. Nice PR |
|
Modified to allow in-place computation. |
tnarihi
force-pushed
the
prelu
branch
2 times, most recently
from
6bc51c0
to
366c332
Compare
Merged
|
Replaced by #1940 |
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Outdated suggestions cannot be applied.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.
I implemented parameterized ReLU unit, which is described in http://arxiv.org/abs/1502.01852 . In my caffe fork, I tried RReLU for CIFAR10 quick examples and the performance was improved about 3%. I am happy If it is worth merging. I don't care even if it is not because I implemented it just for my purpose.