-
-
Notifications
You must be signed in to change notification settings - Fork 611
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
Change DepthwiseConv()
to use in=>out
instead of in=>mult
.
#756
Merged
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
staticfloat
force-pushed
the
sf/depthwise_inout
branch
3 times, most recently
from
April 26, 2019 22:36
02571db
to
77af671
Compare
Agreed on all counts. Especially with leaving out the input channel; we should prepare our APIs for this so we can eventually do #703. It's just a shame we can't deprecate this. But I guess for the most part people will get a fairly obvious shape error, if not an assertion error. |
Oh, worth adding a news item for this though! |
staticfloat
added a commit
that referenced
this pull request
Apr 30, 2019
Anything else to do here? |
This is an API change, but I think it makes more sense, and is more consistent with our `Conv()` api.
staticfloat
force-pushed
the
sf/depthwise_inout
branch
from
May 12, 2019 18:20
203fe9c
to
06da965
Compare
Lgtm |
bors r+ |
bors bot
added a commit
that referenced
this pull request
May 13, 2019
756: Change `DepthwiseConv()` to use `in=>out` instead of `in=>mult`. r=MikeInnes a=staticfloat This is an API change, but I think it makes more sense, and is more consistent with our `Conv()` API. This also dumps the `DepthwiseConv((3,3), C_in)` API, as I'm not sure why you would want to specify only the input channel count and default the output to a channel multiplier of 1; if anything I would think you'd want to specify the channel output and leave the input to be default. In any case, I think consistency with `Conv()` is the best thing to chase after here. Co-authored-by: Elliot Saba <staticfloat@gmail.com>
Build succeeded |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
This is an API change, but I think it makes more sense, and is more consistent with our
Conv()
API. This also dumps theDepthwiseConv((3,3), C_in)
API, as I'm not sure why you would want to specify only the input channel count and default the output to a channel multiplier of 1; if anything I would think you'd want to specify the channel output and leave the input to be default. In any case, I think consistency withConv()
is the best thing to chase after here.