mean¶
dragon.vm.torch.
mean
(
input,
dim=None,
keepdim=False,
out=None
)[source]¶Compute the mean value of elements along the given dimension.
dim
could be negative orNone
:x = torch.tensor([[1, 2, 3], [4, 5, 6]], dtype=torch.float32) # A negative dimension is the last-k dimension print(torch.mean(x, dim=1)) print(torch.mean(x, dim=-1)) # Equivalent # If dimension is None, reduce input as a vector # and return a scalar result print(torch.mean(x)) # 3.5 # Also, dimension could be a sequence of integers print(torch.mean(x, dim=(0, 1))) # 3.5
- Parameters:
- input (dragon.vm.torch.Tensor) – The input tensor.
- dim (Union[int, Sequence[int]], optional) – The dimension to reduce.
- keepdim (bool, optional, default=False) – Keep the reduced dimension or not.
- out (dragon.vm.torch.Tensor, optional) – The output tensor.
- Returns:
dragon.vm.torch.Tensor – The output tensor.