[Frontend][ONNX]support Pool2D layout is CHW

[chengven027]

Hi， my onnx model is superpoint. it's converted from a pytorch model.
When I import the model. I get the relay as follow:

...
%38 = transpose(%37, axes=[0, 1, 3, 2, 4]);
%39 = reshape(%38, newshape=[1, 480, 640]);
%40 = nn.max_pool2d(%39, pool_size=[9, 9], padding=[4, 4, 4, 4], layout="NCW");
%41 = equal(%39, %40);
cast(%41, dtype="float32")

The model layer in Netron is:

Then we can see the %39 reshape is a 3 dimensions. It is legal in pytorch model. But in ONNX, I will get a error.
Then I will add a expand_dims before pool2D and a squeeze after pool2D like the code I commited.

But i don`t know how to add a unit test case. because there will be error in onnxruntime if the pool2D shape is 3D.

cc: @MatthewARM @jwfromm @AndrewZhaoLuo

[AndrewZhaoLuo]

The central issue is that onnx expects a batch dimension: https://github.com/onnx/onnx/blob/main/docs/Operators.md#maxpool

So technically your onnx model is malformed (probably pytorch onnx converter is non spec compliant) since it does not have a batch dimension input to the pooling op. We have seen this before so I'm fine with the change in general. Just address comments and also document this fact.

[AndrewZhaoLuo]

Can you make this so if kernel_shape rank and ndim differ by 1 we assume it's missing a batch dimension and runs below code? (same thing for _run_calculation)

[chengven027]

ok, thanks @AndrewZhaoLuo
I have made the modifications as you said, and run it successed again.