Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Support for 1D convolutions #11

Closed
dorian95 opened this issue Nov 5, 2018 · 3 comments
Closed

Support for 1D convolutions #11

dorian95 opened this issue Nov 5, 2018 · 3 comments

Comments

@dorian95
Copy link

dorian95 commented Nov 5, 2018

I was wondering if PocketFlow supports 1D convolutions. If not, how could this functionality be added? I want to compress a CNN with 1D convolutions for string classification.

@jiaxiang-wu
Copy link
Contributor

Hi, which of the following two do you mean?

  1. The original network consists of 2D convolutions, and can be compressed with 2 layers of 1D- convolution.
  2. The original network consists of 1D convolutions.

@dorian95
Copy link
Author

dorian95 commented Nov 5, 2018

  1. The original network consists of 1D convolutions.

@jiaxiang-wu
Copy link
Contributor

We do not have a plan to support such feature for the moment. You may implement it by yourself and create a pull request to PocketFlow. You contribution will be greatly appreciated.

@psyyz10 psyyz10 closed this as completed Nov 7, 2018
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants