Differences with torch.erfinv

torch.erfinv

torch.erfinv(input, *, out=None) -> Tensor

For more information, see torch.erfinv.

mindspore.ops.erfinv(input) -> Tensor

For more information, see mindspore.ops.erfinv.

MindSpore API function is consistent with that of PyTorch, with differences in the data types supported by the parameters.

PyTorch: The dtype of the parameter input can be int or float.

MindSpore: The dtype of the parameter input can be float16, float32, float64.

Categories	Subcategories	PyTorch	MindSpore	Difference
Parameters	Parameter 1	input	input	Both are Tensor, and the dtype of the parameter `input` in torch.erfinv can be `int` or `float`. The dtype of the parameter `input` in mindspore.ops.erfinv can be `float16`, `float32`, `float64`.
	Parameter 2	out	-	For detailed, refer to General Difference Parameter Table.