* Simplify function definition of context-dependent functions
Signed-off-by: NGanesan Ramalingam <grama@microsoft.com>

* Add missing parenthesis
Signed-off-by: NGanesan Ramalingam <grama@microsoft.com>

* Fix errors in function defs
Signed-off-by: NGanesan Ramalingam <grama@microsoft.com>

* Eliminate unused variable
Signed-off-by: NGanesan Ramalingam <grama@microsoft.com>

* Add int64 type specifier to literal
Signed-off-by: NGanesan Ramalingam <grama@microsoft.com>
Co-authored-by: NAshwini Khade <askhade@microsoft.com>

* remind release manager to remove old onnx-weekly packages
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* add steps
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* 3.8 and 3.9 use numpy 1.21.5
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* 1.21.4
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* 6be8011a073feeca08d256ac64335a19fc8eee4c6312668b6781ace71db0de20
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* 2021-12-19-a4d7f5a
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* 1.21.5
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* 1.16.6
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* 1.16.6
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* do not check generated
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* remove unrelated numpy
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* if
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* remove generation
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* name
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* add back
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* for testing
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* no 1.16.6
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* Fixed ConvTranspose-1 shape inference

Brings change from https://github.com/onnx/onnx/pull/3188 (for ConvTranspose-11) into old shape inference
Signed-off-by: NMatteo Salvarezza <matteo.salvarezza@gmail.com>

* Fix softmax adapter
Signed-off-by: NMatteo Salvarezza <matteo.salvarezza@gmail.com>
Co-authored-by: NG. Ramalingam <grama@microsoft.com>

* add shape inference for model local functions
Signed-off-by: NAshwini Khade <askhade@microsoft.com>

* Plus tests and more changes
Signed-off-by: NAshwini Khade <askhade@microsoft.com>

* fix typo
Signed-off-by: NAshwini Khade <askhade@microsoft.com>

* Plus updates
Signed-off-by: NAshwini Khade <askhade@microsoft.com>

* Plus updates per review
Signed-off-by: NAshwini Khade <askhade@microsoft.com>

* plus updates
Signed-off-by: NAshwini Khade <askhade@microsoft.com>

Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

Signed-off-by: NAlexandre Eichenberger <alexe@us.ibm.com>

* Honor existing dim_param

Before this change, existing dim_param was overwritten by generated
symbols like `unk__`. `NonZero` is used to test the behavior.
Signed-off-by: NShinichiro Hamaji <shinichiro.hamaji@gmail.com>

* Fix test expectation of symbolic_shape_test.py
Signed-off-by: NShinichiro Hamaji <shinichiro.hamaji@gmail.com>

* Keep the original check as suggested in review
Signed-off-by: NShinichiro Hamaji <shinichiro.hamaji@gmail.com>

* Simplify the logic of mergeShapesAndTypes
Signed-off-by: NShinichiro Hamaji <shinichiro.hamaji@gmail.com>
Co-authored-by: NAshwini Khade <askhade@microsoft.com>

Signed-off-by: NLewis Tunstall <lewis.c.tunstall@gmail.com>

* azp purposes
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* finish all
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* Reorder number point
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* source py$(python.version)/bin/activate
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* improve words
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* restructure
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* nit: change flow
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* fix typo
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* When the release CIs will run
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>
Co-authored-by: NAshwini Khade <askhade@microsoft.com>

* point installation guide to readme
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* add hub, compose des
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* polish
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* nit
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* nit ONNX
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

Signed-off-by: NGong Su <gong_su@hotmail.com>
Co-authored-by: NAshwini Khade <askhade@microsoft.com>

* check negative value
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* only perform rank inference
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* resolve warning
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* fix warning
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* starts + ends
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* change if; any_of; update comments
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>
Co-authored-by: NAshwini Khade <askhade@microsoft.com>

* Add onnx.compose.merge
Signed-off-by: NJoaquin Anton <janton@nvidia.com>

* Add model check
Signed-off-by: NJoaquin Anton <janton@nvidia.com>

* Add add_prefix and expand_out_dim
Signed-off-by: NJoaquin Anton <janton@nvidia.com>

* Test negative indices for expand_out_dim
Signed-off-by: NJoaquin Anton <janton@nvidia.com>

* Add missing type check
Signed-off-by: NJoaquin Anton <janton@nvidia.com>

* Improve error reporting
Signed-off-by: NJoaquin Anton <janton@nvidia.com>

* Remove unused variables
Signed-off-by: NJoaquin Anton <janton@nvidia.com>

* Add merge_models
Signed-off-by: NJoaquin Anton <janton@nvidia.com>

* style fix
Signed-off-by: NJoaquin Anton <janton@nvidia.com>

* style fixes
Signed-off-by: NJoaquin Anton <janton@nvidia.com>

* Remove unused import
Signed-off-by: NJoaquin Anton <janton@nvidia.com>

* Address code review comments
Signed-off-by: NJoaquin Anton <janton@nvidia.com>

* Fix import
Signed-off-by: NJoaquin Anton <janton@nvidia.com>

* Fix LGTM issues
Signed-off-by: NJoaquin Anton <janton@nvidia.com>

* Add Python API usage, address code review issues, improve testing
Signed-off-by: NJoaquin Anton <janton@nvidia.com>

* Fix flake8 issues
Signed-off-by: NJoaquin Anton <janton@nvidia.com>

* add_prefix to rename local function. Drop unused initializers when merging graphs/models
Signed-off-by: NJoaquin Anton <janton@nvidia.com>

* Drop unnecessary value_info entries when merging models
Signed-off-by: NJoaquin Anton <janton@nvidia.com>

* Shape inference should not propagate missing optional outputs 
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

- test_argmax_no_keepdims_example
- test_argmax_default_axis_example
- test_argmax_no_keepdims_example_select_last_index
Signed-off-by: NYi-Hong Lyu <yilyu@microsoft.com>

* add draft grid_sampler spec
Signed-off-by: Nhwangdeyu <dejack953@outlook.com>

* fix Type And Shape add some detail
Signed-off-by: Nhwangdeyu <dejack953@outlook.com>

* add more shape tests
Signed-off-by: Nhwangdeyu <dejack953@outlook.com>

* add node tests
Signed-off-by: Nhwangdeyu <dejack953@outlook.com>

* rebase master and add torch test
Signed-off-by: Nhwangdeyu <dejack953@outlook.com>

* remove unuse code
Signed-off-by: Nhwangdeyu <dejack953@outlook.com>

* fix comments border
Signed-off-by: Nhwangdeyu <dejack953@outlook.com>

* change Gridsampler to Gridsample
Signed-off-by: Nhwangdeyu <dejack953@outlook.com>

* fix the description of the reflect attribute and padding_mode
Signed-off-by: Nhwangdeyu <dejack953@outlook.com>

* move gridSample version 15 to 16
Signed-off-by: Nhwangdeyu <dejack953@outlook.com>
Co-authored-by: NAshwini Khade <askhade@microsoft.com>

* string check if it has raw_data
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* empty string should be OK
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* quant-10 as well
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* nit: improve error msg
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* add 2 shape inference tests
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>
Co-authored-by: NAshwini Khade <askhade@microsoft.com>

* Document that Where supports multidirectional broadcasting.

Remove the history section. Although this is useful information, it made
it tricky to insert the broadcasting text at the right place, and it's
inconsistent with all the other operators, which don't have a history
section.
Signed-off-by: NGary Miguel <garymiguel@microsoft.com>

* Update Where-9 as well.

Keep the history section too.
Signed-off-by: NGary Miguel <garymiguel@microsoft.com>

* Undo unintentional indentation.
Signed-off-by: NGary Miguel <garymiguel@microsoft.com>

* Fix bug in pad converter, value only needed in constant mode.
Signed-off-by: NYu Liu <yu.liu@enflame-tech.com>

* Fix bug in pad converter, value only needed in constant mode or default (constant).
Signed-off-by: NYu Liu <yu.liu@enflame-tech.com>

* Fix bug in pad converter. input_rank maybe 0 and will set wrong t_pads.sizes().
Signed-off-by: NYu Liu <yu.liu@enflame-tech.com>

* Fix bug in pad converter. input_rank maybe 0 and will set wrong t_pads.sizes().
Signed-off-by: NYu Liu <yu.liu@enflame-tech.com>
Co-authored-by: NYu Liu <yu.liu@enflame-tech.com>
Co-authored-by: NG. Ramalingam <grama@microsoft.com>

* Improve rank inference for Expand op
Signed-off-by: NTom Wildenhain <tomwi@microsoft.com>

* Unnecessary dtype check in Expand shape inference
Signed-off-by: NTom Wildenhain <tomwi@microsoft.com>

* Add test for Expand rank inference
Signed-off-by: NTom Wildenhain <tomwi@microsoft.com>

Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* make shape inference handle MapProto
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* add more part which needs map
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* use todatatypestring again
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* refactor mergeInShapeInfo
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* add AddExistingSymbolicDims propagateElemTypeWithValidation
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* remove duplicate data_type_utils.h
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* move to .cc
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>
Co-authored-by: NAshwini Khade <askhade@microsoft.com>

* Clarify definition of a tensor in IR docs
Signed-off-by: NTom Wildenhain <tomwi@microsoft.com>

* Update docs/IR.md

Fix typo
Co-authored-by: NKevin Chen <45886021+kevinch-nv@users.noreply.github.com>
Signed-off-by: NTom Wildenhain <tomwi@microsoft.com>

* Update tensor definition according to review
Signed-off-by: NTom Wildenhain <tomwi@microsoft.com>
Co-authored-by: NChun-Wei Chen <jacky82226@gmail.com>
Co-authored-by: NKevin Chen <45886021+kevinch-nv@users.noreply.github.com>

* add test for spacetodepth
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* update op.md
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>
Co-authored-by: NAshwini Khade <askhade@microsoft.com>

Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* ONNX Hub Docs
Signed-off-by: NMark <mhamilton723@gmail.com>

* Finish sections
Signed-off-by: NMark <mhamilton723@gmail.com>

* Extend optional type inference
Signed-off-by: Nneginraoof <neginmr@utexas.edu>

* fix loop test
Signed-off-by: Nneginraoof <neginmr@utexas.edu>
Co-authored-by: NChun-Wei Chen <jacky82226@gmail.com>

* __STDC_FORMAT_MACROS
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* add comments
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* simply define
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* define 1
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* try .h
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* -D__STDC_FORMAT_MACROS
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* cmakelist
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* nit: comment
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>
Co-authored-by: NG. Ramalingam <grama@microsoft.com>

* Factor out common adapter design patterns
Signed-off-by: NGanesan Ramalingam <grama@microsoft.com>

* Undo format change
Signed-off-by: NGanesan Ramalingam <grama@microsoft.com>

* Remove unused includes
Signed-off-by: NGanesan Ramalingam <grama@microsoft.com>

* Remove unused adapter files
Signed-off-by: NGanesan Ramalingam <grama@microsoft.com>

* Handle unused parameter warning
Signed-off-by: NGanesan Ramalingam <grama@microsoft.com>

* Fix one more unused parameter warning
Signed-off-by: NGanesan Ramalingam <grama@microsoft.com>
Co-authored-by: NAshwini Khade <askhade@microsoft.com>

* USE_MSVC_STATIC_RUNTIME=OFF for release
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* Update ONNX_USE_MSVC_STATIC_RUNTIME=0 by default in docs
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

* updated default as 0
Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

Clarify that shapes of scale and zero point must match for QuantizeLinear and DequantizeLinear (#3754)

* Clarify that shapes of scale and zero point must match for QuantizeLinear and DequantizeLinear
Signed-off-by: NTom Wildenhain <tomwi@microsoft.com>

* Update .md files with changes
Signed-off-by: NTom Wildenhain <tomwi@microsoft.com>

* Move comments to be included in inspect.getsource
Signed-off-by: NTom Wildenhain <tomwi@microsoft.com>

* Fix typo
Signed-off-by: NTom Wildenhain <tomwi@microsoft.com>
Co-authored-by: NAshwini Khade <askhade@microsoft.com>

* specify behaviour with groups more precisely
Signed-off-by: NAlexandre Eichenberger <alexe@us.ibm.com>

* update before regen the files
Signed-off-by: NAlexandre Eichenberger <alexe@us.ibm.com>

* added the auto-generated files
Signed-off-by: NAlexandre Eichenberger <alexe@us.ibm.com>

* updates of generated docs with latest onnx installed
Signed-off-by: NAlexandre Eichenberger <alexe@us.ibm.com>
Co-authored-by: NG. Ramalingam <grama@microsoft.com>

* Fixed LSTM documentation
Signed-off-by: NMatteo Salvarezza <matteo.salvarezza@gmail.com>

* Regenerated docs
Signed-off-by: NMatteo Salvarezza <matteo.salvarezza@gmail.com>

* Manually removed unwanted doc change
Signed-off-by: NMatteo Salvarezza <matteo.salvarezza@gmail.com>

Signed-off-by: NChun-Wei Chen <jacky82226@gmail.com>

Signed-off-by: NGanesan Ramalingam <grama@microsoft.com>

Signed-off-by: NJoaquin Anton <janton@nvidia.com>