[ONNX] Add support for asymmetric padding for Onnx.AveragePool op #3923
Conversation
| 1) * | ||
| strides[dimIdx] + | ||
| dilatedKernelSize - inputShape[dimIdx + 2]; | ||
| totalPad = totalPad >= 0 ? totalPad : 0; |
There was a problem hiding this comment.
Is ceilMode used in calculating the padding when using autopad? If not, why? I think the formulas in https://onnx.ai/onnx/operators/onnx__AveragePool.html differ depending on ceilMode.
|
Looks very good! I made some comments since I have been working on similar changes. However, I am not very familiar with the project itself so some of my comments may be off. In general, I would suggest to add more tests to test different cases of auto_pad and asymmetric and symmetric padding. Also please note that I am out of office until January 7th and likely won't respond during that time. Maybe others can chip in. Previously we have been discussing some changes along these lines with @zjgarvey. |
vivekkhandelwal1
force-pushed
the
fix-avgpool
branch
from
bf1b7bc to
e688390
Compare
This commit also refactors the code for the Onnx's AveragePool and MaxPool op by creating a common utility for both the op lowerings to get the pooling op parameters. Signed-off-by: Vivek Khandelwal <vivekkhandelwal1424@gmail.com>
vivekkhandelwal1
force-pushed
the
fix-avgpool
branch
from
e688390 to
1b926a8
Compare
|
Hi, I have modified the implementation. Can this PR be reviewed again? |
vivekkhandelwal1
requested review from
sahas3 and
tuukkjs
and removed request for
tuukkjs
|
@tuukkjs Can you please review the PR? |
This commit adds support for the asymmetric padding for Onnx's AveragePool op.
This commit also extends the Torch->Linalg lowering of the pooling ops to consider asymmetric padding during the output dim computation.
Signed-off-by: Vivek Khandelwal vivekkhandelwal1424@gmail.com