ONNX Export Slice and Flip ops for opset 10 #20533
Conversation
lara-hdr
changed the title
lara-hdr
changed the title
li-roy
added
the
triaged
There was a problem hiding this comment.
@houseroad has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
|
@houseroad any updates on this? |
…hdr/pytorch into lahaidar/onnx_export_slice
There was a problem hiding this comment.
@houseroad has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
|
@pytorchbot retest this please |
There was a problem hiding this comment.
@houseroad has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
|
@pytorchbot rebase this please |
| @@ -118,3 +117,45 @@ def symbolic_fn(g, input, kernel_size, stride, padding, ceil_mode, count_include | |||
| avg_pool1d = _avg_pool('avg_pool1d', _single) | |||
| avg_pool2d = _avg_pool('avg_pool2d', _pair) | |||
| avg_pool3d = _avg_pool('avg_pool3d', _triple) | |||
|
|
|||
|
|
|||
| def slice_op(g, input, axes, starts, ends, steps=None, dynamic_slice=False): | |||
There was a problem hiding this comment.
wait, is this still necessary? oh you call it in the _slice_op...
There was a problem hiding this comment.
@houseroad has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.
|
Thank you @houseroad!! |
|
@houseroad merged this pull request in cc85c3d. |
No description provided.