Skip to content
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 71 commits into from
May 8, 2020
Merged

Merge master #1

merged 71 commits into from
May 8, 2020

Conversation

stevenlix
Copy link
Owner

No description provided.

jiafatom and others added 30 commits October 11, 2019 16:12
* apply_pad for opset 11
* Support input is list for apply_pad (#30)
* add apply_flatten() function

* properly format .gitignore
* 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]>
jiafatom and others added 29 commits March 3, 2020 16:34
* Fix process_optimization logic

* Fix process_optimization logic
* Merge common sequence

* Merge common sequence
* 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
@stevenlix stevenlix merged commit 1801984 into stevenlix:master May 8, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

6 participants