bugfix: ReduceSumStaticAxes type correction

[francis2tm]

Hello,

Bug details:

File "onnx2torch/onnx2torch/node_converters/reduce.py", line 159, in forward
    return torch.sum(input_tensor, dim=self._axes, keepdim=self._keepdims)
TypeError: sum() received an invalid combination of arguments - got (Tensor, keepdim=int, dim=list), but expected one of:
 * (Tensor input, *, torch.dtype dtype)
      didn't match because some of the keywords were incorrect: keepdim, dim
 * (Tensor input, tuple of ints dim, bool keepdim, *, torch.dtype dtype, Tensor out)
 * (Tensor input, tuple of names dim, bool keepdim, *, torch.dtype dtype, Tensor out)

Args/Attrs to reproduce
input_tensor.shape: torch.Size([1, 8, 8, 65])
self._axes: [1, 2] <class 'list'>
self._keepdims: 0 <class 'int'>

Solution

My solution is a simple typecast. Only tested against my particular example.

[senysenyseny16]

hi, @francis2tm

[senysenyseny16]

Suggested change

'onnxruntime>=1.15.1',

[senysenyseny16]

Could you please explain why self._axes should be wrapped into tuple?

[sniklaus]

I had the very same error message and for me the bool(...) was sufficient, I didn't need the tuple(...).

[Sbisseb]

I am also using return torch.sum(input_tensor, dim=self._axes, keepdim=bool(self._keepdims)) but I am now getting issues in onnx2torch/node_converters/gather.py in the slicing I am not sure why

return input_tensor[slice_for_take]
IndexError: index 4 is out of bounds for dimension 0 with size 3

Would you have any idea how to fix that?

[senysenyseny16]

#206

[senysenyseny16]

I am also using return torch.sum(input_tensor, dim=self._axes, keepdim=bool(self._keepdims)) but I am now getting issues in onnx2torch/node_converters/gather.py in the slicing I am not sure why

return input_tensor[slice_for_take]
IndexError: index 4 is out of bounds for dimension 0 with size 3

Would you have any idea how to fix that?

Hi, could you please open an issue with instructions for reproducing?