This repository has been archived by the owner on Nov 22, 2022. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 801
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
c62a775
to
c29d909
Compare
shreydesai
added a commit
to shreydesai/pytext
that referenced
this pull request
Jul 27, 2019
Summary: Pull Request resolved: facebookresearch#830 Implements depthwise separable convolutions. The depthwise convolution spatially convolves each input channel separately, then the pointwise convolution projects this result into a new channel space. Separable convolutions achieve similar performance to regular convolutions with a large reduction in the number of parameters. Grouped convolutions also have cuDNN support, so using them can give latency advantages as well. Differential Revision: D16466988 fbshipit-source-id: 9b4bb616dbbb202d5f10e523e646d04d477b1eed
c29d909
to
37d1a55
Compare
shreydesai
added a commit
to shreydesai/pytext
that referenced
this pull request
Jul 27, 2019
Summary: Pull Request resolved: facebookresearch#830 Implements depthwise separable convolutions. The depthwise convolution spatially convolves each input channel separately, then the pointwise convolution projects this result into a new channel space. Separable convolutions achieve similar performance to regular convolutions with a large reduction in the number of parameters. Grouped convolutions also have cuDNN support, so using them can give latency advantages as well. Differential Revision: D16466988 fbshipit-source-id: a2041cd104ef89215c20f7789326a721ff133c61
37d1a55
to
b5eda6d
Compare
shreydesai
added a commit
to shreydesai/pytext
that referenced
this pull request
Jul 31, 2019
Summary: Pull Request resolved: facebookresearch#830 Implements depthwise separable convolutions. The depthwise convolution spatially convolves each input channel separately, then the pointwise convolution projects this result into a new channel space. Separable convolutions achieve similar performance to regular convolutions with a large reduction in the number of parameters. Grouped convolutions also have cuDNN support, so using them can give latency advantages as well. Differential Revision: D16466988 fbshipit-source-id: b5aec14c9c21816cd6d090ee045d56bb39e314ac
Differential Revision: D16403533 fbshipit-source-id: 6b14ba122523e96dfab37791ce3d7ea77121f9dd
Differential Revision: D16403538 fbshipit-source-id: 7d3784a2726143146206debc5a9b9b8384a1d59e
Differential Revision: D16403554 fbshipit-source-id: c02fa96bd6a9348b7424b594d19f83a5300847df
Differential Revision: D16462672 fbshipit-source-id: a06e3f6592506085f2ff9b2a0a24cc09a56c80e5
Summary: Pull Request resolved: facebookresearch#830 Implements depthwise separable convolutions. The depthwise convolution spatially convolves each input channel separately, then the pointwise convolution projects this result into a new channel space. Separable convolutions achieve similar performance to regular convolutions with a large reduction in the number of parameters. Grouped convolutions also have cuDNN support, so using them can give latency advantages as well. Reviewed By: geof90 Differential Revision: D16466988 fbshipit-source-id: 2cf0dfc127b96c9ec0ca9573082719eb4c620b4b
b5eda6d
to
9b8ae67
Compare
This pull request has been merged in e0ab238. |
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.
Summary: Implements depthwise separable convolutions. The depthwise convolution spatially convolves each input channel separately, then the pointwise convolution projects this result into a new channel space. Separable convolutions achieve similar performance to regular convolutions with a large reduction in the number of parameters. Grouped convolutions also have cuDNN support, so using them can give latency advantages as well.
Differential Revision: D16466988