ONNX conversion script. #4176
Closed
ONNX conversion script. #4176
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
julien-c
reviewed
May 6, 2020
julien-c
reviewed
May 6, 2020
| from transformers.tokenization_utils import BatchEncoding | ||
|
|
||
|
|
||
| class OnnxConverterArgumentParser(ArgumentParser): |
There was a problem hiding this comment.
Here you can maybe use HfArgumentParser which is dataclass-based and may be more compact (and more IDE-friendly)
Up to you though, this works too :)
Co-authored-by: Julien Chaumond <chaumond@gmail.com>
2 tasks
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Outdated suggestions cannot be applied.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.
This PR adds conversion script to export our models to ONNX IR.
Plan is to support both PyTorch and TensorFlow:
TensorFlow currently blocked because of an issue in the conversion script provided by ONNX (seems fixed on master : onnx/tensorflow-onnx#876)