Differences with torch.polygamma

torch.polygamma

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

For more information, see torch.polygamma.

mindspore.ops.polygamma(n, input) -> Tensor

For more information, see mindspore.ops.polygamma.

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 or float64.

Categories	Subcategories	PyTorch	MindSpore	Difference
Parameters	Parameter 1	n	n	-
	Parameter 2	input	input	Both are Tensor, and the dtype of the parameter `input` in torch.polygamma can be `int` or `float`. The dtype of the parameter `input` in mindspore.ops.polygamma can be `float16`, `float32` or `float64`.
	Parameter 3	out	-	For detailed, refer to General Difference Parameter Table.