Skip to content
This repository was archived by the owner on Jul 1, 2023. It is now read-only.

Add support for dilated Conv1D and Conv2D #275

Merged
merged 4 commits into from
Jun 22, 2019

Conversation

jon-tow
Copy link
Contributor

@jon-tow jon-tow commented Jun 22, 2019

#274

The documentation for some layers seem to be lacking in detail. I'll try to clarify some things when I get the chance.

@jon-tow
Copy link
Contributor Author

jon-tow commented Jun 22, 2019

@eaplatanios Thanks for pointing that out. Wish we had a designated formatter 😄.

Copy link
Contributor

@rxwei rxwei left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nice, thank you!

@eaplatanios eaplatanios merged commit ed5e615 into tensorflow:master Jun 22, 2019
@jon-tow jon-tow deleted the layers/dilated-conv branch June 22, 2019 05:39
@Shashi456
Copy link
Contributor

Shashi456 commented Jun 22, 2019

@eaplatanios @rxwei Although I see the extensions have dilation as optional, I'm wondering why dilation wasn't made optional in the main public init, because the dilated convolutions aren't used by everyone. Even within the raw bindings, they are an optional parameter with some default value declared. So is the case for the tensorflow and keras convolution APIs. Wdyt?

@eaplatanios
Copy link
Contributor

@Shashi456 good point. I added some defaults along with some minor stylistic changes in #277.

@rxwei
Copy link
Contributor

rxwei commented Jun 22, 2019

+1 to default arguments.

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

5 participants