Conv3D ONNX support and conv3D_ncdhw x86 schedules #4949
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
mbrookhart
changed the title
|
also cc @yzhliu @icemelon9 @anijain2305 @masahi |
icemelon
requested changes
Feb 26, 2020
anijain2305
requested changes
Feb 26, 2020
|
@alexgl-github You might be interested in this. |
|
Thanks, @anijain2305 and @icemelon9! I missed the change in testing strategy when I rebased ontop of @icemelon9 's recent refactor, should be good now. |
mbrookhart
changed the title
anijain2305
approved these changes
Feb 27, 2020
|
Could you rebase to latest master to fix the doc error? @mbrookhart |
mbrookhart
force-pushed
the
mbrookhart/conv3d
branch
3 times, most recently
from
4a7012e
to
dd9ba56
Compare
added 3 commits
March 3, 2020 14:40
add default schedule for conv3d_ncdhw fill in autotvm integration add a fallback for invalid schedules fix fallback fix reduction order to get simd working correctly
respond to PR formatting requests add x86 schedules to conv3d ncdhw test fix a doc string format issue refactor for changed upsream API
mbrookhart
force-pushed
the
mbrookhart/conv3d
branch
from
dd9ba56
to
11d4879
Compare
|
@icemelon9 please followup |
|
hi, I'd like to use this schedule in my next Torch frontend PR (loading resnet 3D from torchvision). Can you merge this? @icemelon9 @anijain2305 |
|
Thanks @mbrookhart @icemelon9 @anijain2305 |
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
Apr 16, 2020
* Support 3d Convolution with the ONNX frontend * add unit tests for conv3d in onnx frontend respond to PR formatting requests add x86 schedules to conv3d ncdhw test fix a doc string format issue refactor for changed upsream API * first attempt at conv3d autotuning add default schedule for conv3d_ncdhw fill in autotvm integration add a fallback for invalid schedules fix fallback fix reduction order to get simd working correctly
zhiics
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Apr 17, 2020
* Support 3d Convolution with the ONNX frontend * add unit tests for conv3d in onnx frontend respond to PR formatting requests add x86 schedules to conv3d ncdhw test fix a doc string format issue refactor for changed upsream API * first attempt at conv3d autotuning add default schedule for conv3d_ncdhw fill in autotvm integration add a fallback for invalid schedules fix fallback fix reduction order to get simd working correctly
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 PR adds support for conv3d to the ONNX frontend and ports the x86 conv2d_nchw schedules to conv3d_ncdhw for improved performance.
Thanks!
cc: @jwfromm @kevinthesun