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
Update ONNX commit #5487
Update ONNX commit #5487
Conversation
There were some changes in proto files although in comments, they clarify the standard with regards to sparse tensors. Please, sync those in. |
This commit should be split in two. One for ONNX and another for version upgrade. if we want to revert for some reason, it would be very messy. |
@@ -46,7 +46,8 @@ TEST(TensorOpTest, Unsqueeze_3) { | |||
} | |||
|
|||
TEST(TensorOpTest, Unsqueeze_Duplicate) { | |||
OpTester test("Unsqueeze", -1); // use latest opset for shape inference errors | |||
// latest valid opset for this test is 12. Since opset 13 attribute axes was made an input. | |||
OpTester test("Unsqueeze", 12); |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
You can not bump it up. Ditto for everything else that requires implementation change.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
These test changes are required because when opset is set to -1 test infra picks up latest available opset which is 13 now and tries to do schema and shape inf verification against latest opset.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
See comments
ORT does not use the private proto file anymore. See this PR #4878 |
Bookkeeping : Nodejs mac pipeline failed during publish test results stage. The actual build and test onnxruntime stage was successful. |
Description: Updating the onnx commit to the latest master. Doing this to validate the onnx changes ahead of the 1.8 onnx release
Motivation and Context