Skip to content
This repository has been archived by the owner on Nov 22, 2022. It is now read-only.

implemented causal convolutions for deep cnn representation #811

Closed

Conversation

shreydesai
Copy link
Contributor

Differential Revision: D16403554

@facebook-github-bot facebook-github-bot added the CLA Signed Do not delete this pull request or issue due to inactivity. label Jul 20, 2019
shreydesai added a commit to shreydesai/pytext that referenced this pull request Jul 27, 2019
Summary:
Pull Request resolved: facebookresearch#811

Implements causal convolutions -- in this type of convolution, each output o_n only depends on i_{<n}, that is, the inputs that came before it. This is achieved by left-padding the input to ensure the convolution respects the temporal ordering of the inputs.

Differential Revision: D16403554

fbshipit-source-id: 68d4e3c309d40ee2bc8eae696f92a693564dcfbd
Differential Revision: D16403533

fbshipit-source-id: 8c131156a7a9990ba043cdf4e381ceacb56e0883
Differential Revision: D16403538

fbshipit-source-id: 11e8ee6a4911a10d9dbf62b7072fa5aefbb37de6
Summary:
Pull Request resolved: facebookresearch#811

Implements causal convolutions -- in this type of convolution, each output o_n only depends on i_{<n}, that is, the inputs that came before it. This is achieved by left-padding the input to ensure the convolution respects the temporal ordering of the inputs.

Reviewed By: geof90

Differential Revision: D16403554

fbshipit-source-id: 416b0fe2b5a0b25fbb75277463ac49eb3ca234dc
@facebook-github-bot
Copy link
Contributor

This pull request has been merged in b699c0a.

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
CLA Signed Do not delete this pull request or issue due to inactivity. Merged
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants