torch.max

torch.max()

---

torch.max(input) -> Tensor

Explation:

​ Returns the maximum value of all elements in the input tensor

Example:

>>> a = torch.randn(1, 3)
>>> a
tensor([[-0.7461, -0.7730,  0.6381]])
>>> torch.max(a)
tensor(0.6381)

---

torch.max(input, dim, keepdim=False, out=None) ->(Tensor, LongTensor)

Explation:

​ Returns a namedtuple (values, indices) where values is the maximum value of each row of the input tensor in the given dimension dim. And indices is the index location of each maximum value found (argmax).

Parameters:

• input(Tensor) - the input tensor
• dim(int) - the dimension to reduce
• keepdim(bool, optional) - whether the output tensors have dim retained or not. Default: False.
• out(tuple, optional) - the result tuple of two output tensors (max, max_indices)

Example:

>>> a = torch.randn(4, 4)
tensor([[-0.7037, -0.9814, -0.2549,  0.7349],
        [-0.0937,  0.9692, -0.2475, -0.3693],
        [ 0.5427,  0.9605,  0.2246,  0.3269],
        [-0.9964,  0.6920,  0.7989, -0.2616]])
>>> torch.max(a)
torch.return_types.max(values=tensor([0.7349, 0.9692, 0.9605, 0.7989]),
					 indices=tensor([3, 1, 1, 2]))

---

torch.max(input, other, out=None) ->Tensor

Explation:

​ Each element of the tensor input is compared with the corresponding element of the tensor other and an element-wise maximum is taken. The shapes of input and other don’t need to match, but they must be broadcastable.

\[out_i = \max(tensor_i, other_i)
\]

Parameters:

• input(Tensor) - the input tensor
• other(Tensor) - the second input tensor
• out(Tensor, optional) - the output tensor

Example:

>>> a = torch.randn(4)
>>> a
tensor([ 0.2942, -0.7416,  0.2653, -0.1584])
>>> b = torch.randn(4)
>>> b
tensor([ 0.8722, -1.7421, -0.4141, -0.5055])
>>> torch.max(a, b)
tensor([ 0.8722, -0.7416,  0.2653, -0.1584])

---

同理，这些方法可推广至torch.min().