forked from microsoft/onnxconverter-common
-
Notifications
You must be signed in to change notification settings - Fork 0
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
Merge master #1
Merged
Merged
Merge master #1
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
* apply_pad for opset 11
* Support input is list for apply_pad (#30)
* add apply_flatten() function * properly format .gitignore
…11 (#32) * Set mode for Resize opset 11
* Bump to version 1.6.0
* Generate graph after optimizing onnx
* Handle case input_name is list for apply_reshape
* Handle dynamic shape in apply_reshape
* Support dynamic pads for Pad opset 11
* A better operator builder for ONNXConverter-Common * taking opset=7 for unit test.
* Fixes #17, update clip operator (#18) * Fixes #17, update clip operator (updated in ONNX 11) * handle min or max = None * Support dynamic inputs for apply_slice Co-authored-by: Xavier Dupré <[email protected]>
* Fixes #17, update clip operator (#18) * Fixes #17, update clip operator (updated in ONNX 11) * handle min or max = None * Handle axes=None for apply_slice when opset < 10 Co-authored-by: Xavier Dupré <[email protected]>
) * Fixes #17, update clip operator (#18) * Fixes #17, update clip operator (updated in ONNX 11) * handle min or max = None * Handle NextToOutputSolution when begin node has multiple successors Co-authored-by: Xavier Dupré <[email protected]>
* Add a const folding optimizer. * opset * better naming and disable tp-sort on opset above 9
* Fixes #17, update clip operator (#18) * Fixes #17, update clip operator (updated in ONNX 11) * handle min or max = None * test Co-authored-by: Xavier Dupré <[email protected]>
Co-authored-by: David Fan <[email protected]>
* Fix process_optimization logic * Fix process_optimization logic
* Merge common sequence * Merge common sequence
…mprove TransposeFanOut (#81)
* Hanlde Mul for FanIn and PushTranspose case * Hanlde Mul for FanIn and PushTranspose case
* a specified opset number for the converter. * polish
* upgrade oc-common and handle make_model in a better way. * fixing 1 * polish. * add a version function
* remove support for python 2.7 * Update optimizer.py Co-authored-by: xavier dupré <[email protected]>
* unifying the code format * increase the test coverage and a better oopb
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.
No description provided.