fix(coreml): w/a fallback to EnableOnSubgraphs=0 on exception #1872
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
to eliminate the error: Microsoft.ML.OnnxRuntime.OnnxRuntimeException: [ErrorCode:Fail] Error compiling model: compiler error: Error reading protobuf spec. validator error: Layer '/variance_predictor/velocity_fn/input_projection/Add' consumes an input named 'variance_predictor.velocity_fn.input_projection.bias' which is not present in this network.
Contributor
There was a problem hiding this comment.
Pull request overview
This PR implements a workaround for CoreML execution provider failures when processing complex ONNX models with topological issues. The fix adds a fallback mechanism that retries session creation with subgraph processing disabled if the initial attempt fails.
Key Changes:
- Adds fallback logic to retry CoreML session creation with
EnableOnSubgraphs=0when initial creation fails - Updates CoreML configuration to use dictionary-based provider options instead of the deprecated flag-based API
- Upgrades Microsoft.ML.OnnxRuntime package version from 1.23.0 to 1.23.2 for non-Windows platforms
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
| OpenUtau.Core/Util/Onnx.cs | Implements try-catch fallback logic for CoreML session creation and updates provider configuration API |
| OpenUtau.Core/OpenUtau.Core.csproj | Updates OnnxRuntime package version to 1.23.2 for non-Windows platforms |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Contributor
Author
|
Please note that the macos-13, osx-x64 is retired and canceled, so that it cannot pass all tests. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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.
to eliminate the error in MacOS CoreML:
Microsoft.ML.OnnxRuntime.OnnxRuntimeException: [ErrorCode:Fail] Error compiling model: compiler error: Error reading protobuf spec. validator error: Layer '/variance_predictor/velocity_fn/input_projection/Add' consumes an input named 'variance_predictor.velocity_fn.input_projection.bias' which is not present in this network.