Support seq(tensor), implement 2 sequence ops that use the new type.#1983
Merged
pranavsharma merged 53 commits intomasterfrom Oct 7, 2019
Merged
Support seq(tensor), implement 2 sequence ops that use the new type.#1983pranavsharma merged 53 commits intomasterfrom
pranavsharma merged 53 commits intomasterfrom
Conversation
added 30 commits
July 22, 2019 11:09
skottmckay
reviewed
Oct 4, 2019
skottmckay
reviewed
Oct 4, 2019
skottmckay
reviewed
Oct 4, 2019
skottmckay
reviewed
Oct 4, 2019
skottmckay
reviewed
Oct 4, 2019
skottmckay
reviewed
Oct 4, 2019
added 6 commits
October 4, 2019 12:25
Contributor
Author
|
The recent commits make 2 updates
|
pranavsharma
changed the title
pranavsharma
force-pushed
the
fix_seq_tensor_type
branch
from
d9baf3c to
eb1339e
Compare
pranavsharma
force-pushed
the
fix_seq_tensor_type
branch
from
ef2c26c to
cd103e4
Compare
Contributor
Author
|
@skottmckay all the mandatory builds have passed and this is ready to to be reviewed again. Thanks! |
skottmckay
reviewed
Oct 7, 2019
skottmckay
reviewed
Oct 7, 2019
|
|
||
| // use the data type of the first tensor as the data type of the seq | ||
| seq_ptr->dtype = reinterpret_cast<const OrtValue*>(in[0])->Get<Tensor>().DataType(); | ||
|
|
Contributor
There was a problem hiding this comment.
Should TensorSeq have a ctor that requires the data type to be set?
Contributor
Author
There was a problem hiding this comment.
Yeah, let me check if there're other problems in doing this. Will address in follow up PR.
skottmckay
reviewed
Oct 7, 2019
| auto data = tensor.Data<T>(); | ||
| if (!data) { | ||
| return OrtApis::CreateStatus(ORT_FAIL, "Encountered nullptr."); | ||
| auto& one_tensor = reinterpret_cast<const OrtValue*>(in[idx])->Get<Tensor>(); |
Contributor
There was a problem hiding this comment.
reinterpret_cast<const OrtValue*> [](start = 23, length = 33)
Why do we need the reinterpret_cast?
Contributor
Author
There was a problem hiding this comment.
May be we don't. Probably a copy-paste error. Will address in follow up PR.
yuslepukhin
pushed a commit
that referenced
this pull request
Mar 17, 2026
## Describe your changes Remove marshmallow version pin. The pipeline can pass now. ## Checklist before requesting a review - [ ] Add unit tests for this change. - [ ] Make sure all tests can pass. - [ ] Update documents if necessary. - [ ] Lint and apply fixes to your code by running `lintrunner -a` - [ ] Is this a user-facing change? If yes, give a description of this change to be included in the release notes. - [ ] Is this PR including examples changes? If yes, please remember to update [example documentation](https://github.com/microsoft/Olive/blob/main/docs/source/examples.md) in a follow-up PR. ## (Optional) Issue link
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
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.
Description: Support seq(tensor), implement 2 sequence ops that uses the new type.
Motivation and Context
The current implementation of seq(tensor) type is inadequate in that it doesn't account for the shape of the contained tensors. A bunch of sequence ops were added to opset11 that uses this type.