[WIP] Deprecate old models with opset3 which cannot be shape inferred #389
Conversation
This file contains 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
Signed-off-by: Chun-Wei Chen <jacky82226@gmail.com>
|
Did all of them have the opset upgraded versions? |
Yes, all of them have models with upgraded versions. |
|
Instead of deleting them, it could be done by adding some comments in the Readme.md. Close it now |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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
One possible solution: Deprecated those models of opset3 which cannot be shape inferred.
Motivation
According to this PR onnx/onnx#3051, some models with opset_version=3 cannot pass
onnx.checker.check_model(model, full_check=True)because some operators of opset_version=3 do not supportTypeAndShapeInferenceFunctionfor shape_inference (e.g., Relu https://github.com/onnx/onnx/blob/531e6dd459003fc8d13b8abb66b29a72a571c865/onnx/defs/math/old.cc#L1535)The solution would be either remove those deprecated models or update those old opsets.