mean¶
Documentation¶
-
treetensor.torch.
mean
(input, *args, reduce=None, **kwargs)[source]¶ Returns the mean value of all elements in the
input
tensor.Examples:
>>> import torch >>> import treetensor.torch as ttorch >>> t = torch.randn((2, 3)) * 30 >>> t tensor([[ 26.6598, 27.8008, -59.4753], [-79.1833, 3.3349, 20.1665]]) >>> ttorch.mean(t) tensor(-10.1161) >>> tt = ttorch.randn({ ... 'a': (2, 3), ... 'b': {'x': (3, 4)}, ... }) * 30 >>> tt <Tensor 0x7f2f5b9f6cf8> ├── a --> tensor([[ 25.2702, 37.4206, -37.1401], │ [ -7.7245, -91.3234, -27.9402]]) └── b --> <Tensor 0x7f2f5b9f6c18> └── x --> tensor([[ 3.2028, -14.0720, 18.1739, 8.5944], [ 41.7761, 36.9908, -20.5495, 5.6480], [ -9.3438, -0.7416, 47.2113, 6.9325]]) >>> ttorch.mean(tt) tensor(1.2436) >>> ttorch.mean(tt, reduce=False) <Tensor 0x7f1321caf080> ├── a --> tensor(-16.9062) └── b --> <Tensor 0x7f1321caf048> └── x --> tensor(10.3186) >>> ttorch.mean(tt, dim=1) <Tensor 0x7f63dbbc9828> ├── a --> tensor([ 8.5169, -42.3294]) └── b --> <Tensor 0x7f63dbbc9780> └── x --> tensor([ 3.9748, 15.9663, 11.0146])
Torch Version Related
This documentation is based on torch.mean in torch v1.10.0+cu102. Its arguments’ arrangements depend on the version of pytorch you installed.
If some arguments listed here are not working properly, please check your pytorch’s version with the following command and find its documentation.
1 | python -c 'import torch;print(torch.__version__)' |
The arguments and keyword arguments supported in torch v1.10.0+cu102 is listed below.
Description From Torch v1.10.0+cu102¶
-
torch.
mean
(input, *, dtype=None) → Tensor¶ Returns the mean value of all elements in the
input
tensor.- Args:
input (Tensor): the input tensor.
- Keyword args:
- dtype (
torch.dtype
, optional): the desired data type of returned tensor. If specified, the input tensor is casted to
dtype
before the operation is performed. This is useful for preventing data type overflows. Default: None.
- dtype (
Example:
>>> a = torch.randn(1, 3) >>> a tensor([[ 0.2294, -0.5481, 1.3288]]) >>> torch.mean(a) tensor(0.3367)
-
torch.
mean
(input, dim, keepdim=False, *, dtype=None, out=None) → Tensor
Returns the mean value of each row of the
input
tensor in the given dimensiondim
. Ifdim
is a list of dimensions, reduce over all of them.If
keepdim
isTrue
, the output tensor is of the same size asinput
except in the dimension(s)dim
where it is of size 1. Otherwise,dim
is squeezed (seetorch.squeeze()
), resulting in the output tensor having 1 (orlen(dim)
) fewer dimension(s).- Args:
input (Tensor): the input tensor. dim (int or tuple of ints): the dimension or dimensions to reduce. keepdim (bool): whether the output tensor has
dim
retained or not.- Keyword args:
- dtype (
torch.dtype
, optional): the desired data type of returned tensor. If specified, the input tensor is casted to
dtype
before the operation is performed. This is useful for preventing data type overflows. Default: None.
out (Tensor, optional): the output tensor.
- dtype (
See also
torch.nanmean()
computes the mean value of non-NaN elements.Example:
>>> a = torch.randn(4, 4) >>> a tensor([[-0.3841, 0.6320, 0.4254, -0.7384], [-0.9644, 1.0131, -0.6549, -1.4279], [-0.2951, -1.3350, -0.7694, 0.5600], [ 1.0842, -0.9580, 0.3623, 0.2343]]) >>> torch.mean(a, 1) tensor([-0.0163, -0.5085, -0.4599, 0.1807]) >>> torch.mean(a, 1, True) tensor([[-0.0163], [-0.5085], [-0.4599], [ 0.1807]])