Files
pytorch/scripts/onnx
Gary Miguel 37688148ae [ONNX] Support opset 15 (#67121) (#67805)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/67805

Also fix Reduce ops on binary_cross_entropy_with_logits

The graph says the output is a scalar but with `keepdims=1`
(the default), the output should be a tensor of rank 1. We set keep
`keepdims=0` to make it clear that we want a scalar output.

This previously went unnoticed because ONNX Runtime does not strictly
enforce shape inference mismatches if the model is not using the latest
opset version.

Test Plan: Imported from OSS

Reviewed By: msaroufim

Differential Revision: D32181304

Pulled By: malfet

fbshipit-source-id: 1462d8a313daae782013097ebf6341a4d1632e2c

Co-authored-by: Bowen Bao <bowbao@microsoft.com>
2021-11-08 14:37:00 -08:00
..