averagePooling2D calculates wrongly with torch backend about keras

[AGFACBNNR]

Besides, averagePooling3D and maxpooling2D have similar problems, possibly because of their same base class.

[mattdangerw]

Sorry for the delay on this! Valid bug!

In fact we have some tests disabled on the torch backend for padding same for this reason it looks like.

keras/keras/src/ops/nn_test.py

Lines 1338 to 1342 in 61ea9c6

	@pytest.mark.skipif(
	backend.backend() == "torch",
	reason="Torch outputs differently from TF when using `same` padding.",
	)
	def test_average_pool_same_padding(self):

Marking this as open for contributions in case anyone would like to take this one. If not will try to get to this soon.

[google-ml-butler]

Are you satisfied with the resolution of your issue?
Yes
No

[google-ml-butler]

Are you satisfied with the resolution of your issue?
Yes
No