Skip to content

Bump onnx to latest#1756

Merged
BowenBao merged 10 commits intomasterfrom
bowbao/onnx_sparse_tensor
Sep 12, 2019
Merged

Bump onnx to latest#1756
BowenBao merged 10 commits intomasterfrom
bowbao/onnx_sparse_tensor

Conversation

@BowenBao
Copy link
Copy Markdown
Contributor

@BowenBao BowenBao commented Sep 4, 2019

  • Update onnxruntime/protobuf/onnx.in.proto with changes for SparseTensor.
  • Bump onnx to latest to include new opset 11 ops (det, scatternd, gathernd, etc.)

@BowenBao BowenBao requested a review from a team as a code owner September 4, 2019 23:23
@BowenBao BowenBao mentioned this pull request Sep 5, 2019
@yuslepukhin
Copy link
Copy Markdown
Member

This PR is missing significant code changes. One must go through all of the switch() or if/else statements where attribute types are being handles and also oneof value within TensorType to make sure that SparseTensor is properly handled.

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

initializer [](start = 23, length = 11)

Check for places in the code that deal with initializer and see if we need to add handling for sparse initializer

Comment thread onnxruntime/core/protobuf/onnx-ml.proto3 Outdated
@BowenBao BowenBao force-pushed the bowbao/onnx_sparse_tensor branch from 3ceb39b to 09500f0 Compare September 9, 2019 22:02
yuslepukhin
yuslepukhin previously approved these changes Sep 9, 2019
Copy link
Copy Markdown
Member

@yuslepukhin yuslepukhin left a comment

Choose a reason for hiding this comment

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

:shipit:

Comment thread onnxruntime/test/onnx/main.cc Outdated
Comment thread tools/ci_build/github/linux/docker/scripts/install_onnx.sh Outdated
@BowenBao BowenBao force-pushed the bowbao/onnx_sparse_tensor branch from 50ed95f to 386a88a Compare September 10, 2019 18:55
@BowenBao BowenBao changed the title [WIP] Bump onnx to latest Bump onnx to latest Sep 11, 2019
@BowenBao
Copy link
Copy Markdown
Contributor Author

CI failure seems unrelated..

@yuslepukhin
Copy link
Copy Markdown
Member

CI failure seems unrelated..

Yes, those failures are transitory. You just need to re-run them, possibly outside business hours. This happened to my PRs as well.

@BowenBao BowenBao merged commit 8712a52 into master Sep 12, 2019
@prasanthpul prasanthpul deleted the bowbao/onnx_sparse_tensor branch May 16, 2021 18:35
yuslepukhin pushed a commit that referenced this pull request Mar 17, 2026
## Describe your changes

1. Print CLI output model save path (not sure why this was removed
before).
2. Add `input_cols` option to dataset for cli for text-classification
task.
3. Update error message when missing dataset, otherwise it will say the
precision is not supported.
4. Save `hf_task` to `model_attributes` from Conversion pass, this will
be used for later pass.
5. Correct model name and task for dataset config when input model is
`onnxmodel`.

## 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
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants