[WIP] Overfeat layers #13
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 reviewed it, see if you agree with my comments inline. |
|
I agree with your comments. Also I found some other minor mistakes. I will fix them and commit changes tomorrow evening. |
lucasb-eyer
added a commit
to lucasb-eyer/DeepFried2
that referenced
this pull request
Aug 5, 2015
(I need it for ILSVRC-pretrained VGG)
lucasb-eyer
added a commit
to lucasb-eyer/DeepFried2
that referenced
this pull request
Aug 6, 2015
(I need it for ILSVRC-pretrained VGG)
lucasb-eyer
added a commit
to lucasb-eyer/DeepFried2
that referenced
this pull request
Aug 31, 2015
(I need it for ILSVRC-pretrained VGG)
lucasb-eyer
added a commit
to lucasb-eyer/DeepFried2
that referenced
this pull request
Aug 31, 2015
Credit also goes to Ilya Kostrikov.
lucasb-eyer
added a commit
to lucasb-eyer/DeepFried2
that referenced
this pull request
Aug 31, 2015
Credit also goes to Ilya Kostrikov.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.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 added OverfeatRoll and OverfeatUnroll that perform the efficiency trick from http://arxiv.org/abs/1312.6229 . I demonstrate a usage of these layers on a semantic segmentation example.
Also I added DuringTesting and DuringTraining layers that allow certain layers to be called only during testing and training correspondingly.
Also this commit contains some minor fixes like a removal on an extra line, etc.