[BYOC][TRT] Fix weight conversion when first dim of weight shape is 1 #7253
Conversation
This file contains hidden or 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
Contributor
Author
@comaniac Thanks for the review! |
trevor-m
force-pushed
the
trt-weight-begin-with-1
branch
from
398c069 to
089dbca
Compare
Contributor
|
Thanks @trevor-m |
masahi
pushed a commit
to masahi/tvm
that referenced
this pull request
Jan 14, 2021
masahi
pushed a commit
to masahi/tvm
that referenced
this pull request
Jan 18, 2021
TusharKanekiDey
pushed a commit
to TusharKanekiDey/tvm
that referenced
this pull request
Jan 20, 2021
trevor-m
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Jan 21, 2021
electriclilies
pushed a commit
to electriclilies/tvm
that referenced
this pull request
Feb 18, 2021
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Fixes conversion of weight shape to work with TensorRT's implicit batch dimension.
Added test cases which failed before this change.
Before this PR, a conv2d or dense op which has a kernel weight beginning with 1 (
[1, 32, 3, 3]or[1, 128]for example) would cause an error.Also, there is an unrelated change to add conv2d_transpose to ConvertLayout list in partition_for_tensorrt.