Support >2GB ONNX models for fp16 conversion #167
Merged
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
TomWildenhain-Microsoft
approved these changes
Jan 11, 2021
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Outdated suggestions cannot be applied.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.
The original infer_shapes function will fail on model size>2GB, because of protobuf size limitation.
Error message:
For >2GB model shape infer, it should use a new function introduced in onnx 1.7.0, infer_shapes_path. However, this new function requires the input and output to be model path, instead of ModelProto object.
Here is my previous issue report to ONNX: onnx/onnx#3046
Here is the doc for infer_shapes_path: https://github.com/onnx/onnx/blob/master/docs/PythonAPIOverview.md#shape-inference-a-large-onnx-model-2gb