Add the ORTModelForSemanticSegmentation class (#539)
* Initial commit for ORTModelForImageSegmentation
* Example name and io binding output size fix
* Refactor to ORTModelForSemanticSegmentation
* IOBindingHelper for io_binding in ORTModelForSemanticSegmentation
* Black and isort formatting
* Apply various suggestions from code review
Co-authored-by: Jingya HUANG <44135271+JingyaHuang@users.noreply.github.com>
* Alphanumeric order in modeling_ort init
* Fixing docstring model name and removing comments
* Fixing tests and add import
* Black formatting and fixed unmatched quote
* Removing export_feature class attribute
* Fixing test model name
* Adding 'image-segmentation' task to optimum/pipelines and fixing tests
Co-authored-by: Jingya HUANG <44135271+JingyaHuang@users.noreply.github.com>