Sumit Agarwal 2abfea5372 Introduce new optimizer Pad + Conv/MaxPool (#18136) ... ### Description Introducing new L1 optimizer to fuse Pad to it's child node if the child node is Conv or MaxPool. Pad -> Conv = Conv Pad -> MaxPool = MaxPool Major Conditions: - It will only fuse for the `Constant` mode of padding. - Conv/MaxPool should not have optional `indices` output tensor - Padding value for non-spatial dimensions should be zero and for spatial dimensions padding values should be positive for `pad` operator. For other conditions please see `SatisfyCondition()` in `pad_fusion.cc`. ### Motivation and Context <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. -->		2023-11-03 09:18:36 -05:00
..
contrib_ops	[ROCm] Generalize FastGeLU (#16623)	2023-07-18 11:23:12 +08:00
core	Introduce new optimizer Pad + Conv/MaxPool (#18136)	2023-11-03 09:18:36 -05:00
python	Cherry-pick b8f373b0ae (#17895) (#17926)	2023-10-12 16:56:40 -07:00
test	Introduce new optimizer Pad + Conv/MaxPool (#18136)	2023-11-03 09:18:36 -05:00
tool/etw
wasm
__init__.py
ReformatSource.ps1
ReformatSourcePython.bat
VSCodeCoverage.runsettings