Differences with torch.cos

torch.cos

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

For more information, see torch.cos.

mindspore.ops.cos(input) -> Tensor

For more information, see mindspore.ops.cos.

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 complex, int or float.

MindSpore: The dtype of the parameter input can be float16, float32, float64, complex64 or complex128.

Categories	Subcategories	PyTorch	MindSpore	Difference
Parameters	Parameter 1	input	input	Both are Tensor, and the dtype of the parameter `input` in torch.cos can be `complex`, `int` or `float`. The dtype of the parameter `input` in mindspore.ops.cos can be `float16`, `float32`, `float64`, `complex64` or `complex128`.
	Parameter 2	out	-	For detailed, refer to General Difference Parameter Table.