This repository has been archived by the owner on Nov 22, 2022. It is now read-only.
implemented dilation for deep cnn representation #810
Closed
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
facebook-github-bot
added
the
CLA Signed
shreydesai
force-pushed
the
export-D16403538
branch
from
4fe957e
to
ed04047
Compare
shreydesai
added a commit
to shreydesai/pytext
that referenced
this pull request
Jul 27, 2019
Summary: Pull Request resolved: facebookresearch#810 Implements dilated convolutions with associated changes to the padding of a convolutional layer. Regular convolutions -- especially those with smaller kernel sizes -- have small receptive fields. Achieving a large receptive requires stacking a lot of convolutions, which creates a deeper network and more difficult optimization problem. Dilated convolutions evaluate the convolution at spaced intervals -- the dilation rate -- which has the effect of increasing the receptive field with a lesser amount of convolutions. They are commonly stacked with the dilation factor increasing by a power of 2 in each successive layer -- this means we only need ceil(log2(n)) convolutional layers to cover a receptive field of size n. Differential Revision: D16403538 fbshipit-source-id: baf0744ce5f51dd599e07dcb7068033edf698e58
Differential Revision: D16403533 fbshipit-source-id: fa8889794e6cf8479206a6f3ebe47ffc42a87faa
Summary: Pull Request resolved: facebookresearch#810 Implements dilated convolutions with associated changes to the padding of a convolutional layer. Regular convolutions -- especially those with smaller kernel sizes -- have small receptive fields. Achieving a large receptive requires stacking a lot of convolutions, which creates a deeper network and more difficult optimization problem. Dilated convolutions evaluate the convolution at spaced intervals -- the dilation rate -- which has the effect of increasing the receptive field with a lesser amount of convolutions. They are commonly stacked with the dilation factor increasing by a power of 2 in each successive layer -- this means we only need ceil(log2(n)) convolutional layers to cover a receptive field of size n. Reviewed By: geof90 Differential Revision: D16403538 fbshipit-source-id: a4ad0becde46975ab9439ec7f76a6dba3b804e97
shreydesai
force-pushed
the
export-D16403538
branch
from
ed04047
to
9ede6f6
Compare
|
This pull request has been merged in 7dbc8e8. |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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.
Differential Revision: D16403538