如何有效地检索Torch张量中最大值的索引

torch.topk((就是您想要的。从文档来看，

torch.topk(input，k、dim=None和maximum=True(，sorted=True，out=None(->(张量，LongTensor(

返回给定input张量的k最大元素给定的维度。

• 如果未给定dim，则选择输入的最后一个维度。

• 如果largest是False，则返回k个最小元素。

• 返回(值，索引(的命名元组，其中索引是原始输入张量中元素的索引。

• 布尔选项sorted(如果是True(将确保返回的k个元素本身是经过排序的

如果我理解正确，你不想要值，而是想要索引。不幸的是，没有现成的解决方案。有一个argmax()函数，但我不知道如何让它做你想做的事情。

所以这里有一个小的变通方法，效率应该也可以，因为我们只是在划分张量：

n = torch.tensor(4)
d = torch.tensor(4)
x = torch.rand(n, 1, d, d)
m = x.view(n, -1).argmax(1)
# since argmax() does only return the index of the flattened
# matrix block we have to calculate the indices by ourself 
# by using / and % (// would also work, but as we are dealing with
# type torch.long / works as well
indices = torch.cat(((m / d).view(-1, 1), (m % d).view(-1, 1)), dim=1)
print(x)
print(indices)

n表示第一个维度，d表示最后两个维度。我在这里取较小的数字来显示结果。但这当然也适用于n=20和d=120:

n = torch.tensor(20)
d = torch.tensor(120)
x = torch.rand(n, 1, d, d)
m = x.view(n, -1).argmax(1)
indices = torch.cat(((m / d).view(-1, 1), (m % d).view(-1, 1)), dim=1)
#print(x)
print(indices)

以下是n=4和d=4的输出：

tensor([[[[0.3699, 0.3584, 0.4940, 0.8618],
[0.6767, 0.7439, 0.5984, 0.5499],
[0.8465, 0.7276, 0.3078, 0.3882],
[0.1001, 0.0705, 0.2007, 0.4051]]],

[[[0.7520, 0.4528, 0.0525, 0.9253],
[0.6946, 0.0318, 0.5650, 0.7385],
[0.0671, 0.6493, 0.3243, 0.2383],
[0.6119, 0.7762, 0.9687, 0.0896]]],

[[[0.3504, 0.7431, 0.8336, 0.0336],
[0.8208, 0.9051, 0.1681, 0.8722],
[0.5751, 0.7903, 0.0046, 0.1471],
[0.4875, 0.1592, 0.2783, 0.6338]]],

[[[0.9398, 0.7589, 0.6645, 0.8017],
[0.9469, 0.2822, 0.9042, 0.2516],
[0.2576, 0.3852, 0.7349, 0.2806],
[0.7062, 0.1214, 0.0922, 0.1385]]]])
tensor([[0, 3],
[3, 2],
[1, 1],
[1, 0]])

我希望这就是你想要的！：(

编辑：

这里有一个稍微修改过的，可能会稍微快一点(我想不会太快：(，但它更简单、更漂亮：

而不是像以前那样：

m = x.view(n, -1).argmax(1)
indices = torch.cat(((m // d).view(-1, 1), (m % d).view(-1, 1)), dim=1)

已经对argmax值进行了必要的整形：

m = x.view(n, -1).argmax(1).view(-1, 1)
indices = torch.cat((m // d, m % d), dim=1)

但正如评论中提到的那样。我认为不可能从中得到更多。

如果真的对您来说非常重要，那么您可以做的一件事是将上述函数作为pytorch的低级扩展(如C++中(来实现。

这将只为您提供一个可以为其调用的函数，并可以避免python代码速度缓慢。

https://pytorch.org/tutorials/advanced/cpp_extension.html

以下是torch中的unravel_index实现：

def unravel_index(
indices: torch.LongTensor,
shape: Tuple[int, ...],
) -> torch.LongTensor:
r"""Converts flat indices into unraveled coordinates in a target shape.
This is a `torch` implementation of `numpy.unravel_index`.
Args:
indices: A tensor of (flat) indices, (*, N).
shape: The targeted shape, (D,).
Returns:
The unraveled coordinates, (*, N, D).
"""
coord = []
for dim in reversed(shape):
coord.append(indices % dim)
indices = indices // dim
coord = torch.stack(coord[::-1], dim=-1)
return coord

然后，您可以使用torch.argmax函数来获得"；扁平的"；张量。

y = x.view(20, -1)
indices = torch.argmax(y)
indices.shape  # (20,)

并用CCD_ 23函数对指标进行分解。

indices = unravel_index(indices, x.shape[-2:])
indices.shape  # (20, 2)

接受的答案仅适用于给定的示例。

tejasvi88的回答很有趣，但无助于回答最初的问题(正如我在评论中所解释的(。

我相信弗朗索瓦的答案是最接近的，因为它涉及一个更通用的情况(任何维度的数量(。但是，它不与argmax连接，所示的示例也没有说明该函数处理批处理的能力。

因此，我将在这里以Francois的回答为基础，添加连接到argmax的代码。我编写了一个新函数batch_argmax，它返回批处理中最大值的索引。批次可以按多个维度组织。我还包括一些测试用例以供说明：

def batch_argmax(tensor, batch_dim=1):
"""
Assumes that dimensions of tensor up to batch_dim are "batch dimensions"
and returns the indices of the max element of each "batch row".
More precisely, returns tensor `a` such that, for each index v of tensor.shape[:batch_dim], a[v] is
the indices of the max element of tensor[v].
"""
if batch_dim >= len(tensor.shape):
raise NoArgMaxIndices()
batch_shape = tensor.shape[:batch_dim]
non_batch_shape = tensor.shape[batch_dim:]
flat_non_batch_size = prod(non_batch_shape)
tensor_with_flat_non_batch_portion = tensor.reshape(*batch_shape, flat_non_batch_size)
dimension_of_indices = len(non_batch_shape)
# We now have each batch row flattened in the last dimension of tensor_with_flat_non_batch_portion,
# so we can invoke its argmax(dim=-1) method. However, that method throws an exception if the tensor
# is empty. We cover that case first.
if tensor_with_flat_non_batch_portion.numel() == 0:
# If empty, either the batch dimensions or the non-batch dimensions are empty
batch_size = prod(batch_shape)
if batch_size == 0:  # if batch dimensions are empty
# return empty tensor of appropriate shape
batch_of_unraveled_indices = torch.ones(*batch_shape, dimension_of_indices).long()  # 'ones' is irrelevant as it will be empty
else:  # non-batch dimensions are empty, so argmax indices are undefined
raise NoArgMaxIndices()
else:   # We actually have elements to maximize, so we search for them
indices_of_non_batch_portion = tensor_with_flat_non_batch_portion.argmax(dim=-1)
batch_of_unraveled_indices = unravel_indices(indices_of_non_batch_portion, non_batch_shape)
if dimension_of_indices == 1:
# above function makes each unraveled index of a n-D tensor a n-long tensor
# however indices of 1D tensors are typically represented by scalars, so we squeeze them in this case.
batch_of_unraveled_indices = batch_of_unraveled_indices.squeeze(dim=-1)
return batch_of_unraveled_indices

class NoArgMaxIndices(BaseException):
def __init__(self):
super(NoArgMaxIndices, self).__init__(
"no argmax indices: batch_argmax requires non-batch shape to be non-empty")

以下是测试：

def test_basic():
# a simple array
tensor = torch.tensor([0, 1, 2, 3, 4])
batch_dim = 0
expected = torch.tensor(4)
run_test(tensor, batch_dim, expected)
# making batch_dim = 1 renders the non-batch portion empty and argmax indices undefined
tensor = torch.tensor([0, 1, 2, 3, 4])
batch_dim = 1
check_that_exception_is_thrown(lambda: batch_argmax(tensor, batch_dim), NoArgMaxIndices)
# now a batch of arrays
tensor = torch.tensor([[1, 2, 3], [6, 5, 4]])
batch_dim = 1
expected = torch.tensor([2, 0])
run_test(tensor, batch_dim, expected)
# Now we have an empty batch with non-batch 3-dim arrays' shape (the arrays are actually non-existent)
tensor = torch.ones(0, 3)  # 'ones' is irrelevant since this is empty
batch_dim = 1
# empty batch of the right shape: just the batch dimension 0,since indices of arrays are scalar (0D)
expected = torch.ones(0)
run_test(tensor, batch_dim, expected)
# Now we have an empty batch with non-batch matrices' shape (the matrices are actually non-existent)
tensor = torch.ones(0, 3, 2)  # 'ones' is irrelevant since this is empty
batch_dim = 1
# empty batch of the right shape: the batch and two dimension for the indices since we have 2D matrices
expected = torch.ones(0, 2)
run_test(tensor, batch_dim, expected)
# a batch of 2D matrices:
tensor = torch.tensor([[[1, 2, 3], [6, 5, 4]], [[2, 3, 1], [4, 5, 6]]])
batch_dim = 1
expected = torch.tensor([[1, 0], [1, 2]])  # coordinates of two 6's, one in each 2D matrix
run_test(tensor, batch_dim, expected)
# same as before, but testing that batch_dim supports negative values
tensor = torch.tensor([[[1, 2, 3], [6, 5, 4]], [[2, 3, 1], [4, 5, 6]]])
batch_dim = -2
expected = torch.tensor([[1, 0], [1, 2]])
run_test(tensor, batch_dim, expected)
# Same data, but a 2-dimensional batch of 1D arrays!
tensor = torch.tensor([[[1, 2, 3], [6, 5, 4]], [[2, 3, 1], [4, 5, 6]]])
batch_dim = 2
expected = torch.tensor([[2, 0], [1, 2]])  # coordinates of 3, 6, 3, and 6
run_test(tensor, batch_dim, expected)
# same as before, but testing that batch_dim supports negative values
tensor = torch.tensor([[[1, 2, 3], [6, 5, 4]], [[2, 3, 1], [4, 5, 6]]])
batch_dim = -1
expected = torch.tensor([[2, 0], [1, 2]])
run_test(tensor, batch_dim, expected)

def run_test(tensor, batch_dim, expected):
actual = batch_argmax(tensor, batch_dim)
print(f"batch_argmax of {tensor} with batch_dim {batch_dim} isn{actual}nExpected:n{expected}")
assert actual.shape == expected.shape
assert actual.eq(expected).all()
def check_that_exception_is_thrown(thunk, exception_type):
if isinstance(exception_type, BaseException):
raise Exception(f"check_that_exception_is_thrown received an exception instance rather than an exception type: "
f"{exception_type}")
try:
thunk()
raise AssertionError(f"Should have thrown {exception_type}")
except exception_type:
pass
except Exception as e:
raise AssertionError(f"Should have thrown {exception_type} but instead threw {e}")

我有一个简单的解决方案，但不是批量计算每个项目的最大值的2D坐标的最佳解决方案。简单的解决方法可能是：

# suppose the tensor is of shape (3,2,2), 
>>> a = torch.randn(3, 2, 2)
>>> a
tensor([[[ 0.1450, -1.3480],
[-0.3339, -0.5133]],
[[ 0.6867, -0.2972],
[ 0.8768,  0.0844]],
[[-2.3115, -0.4549],
[-1.5074, -0.8706]]])
# then perform batch-wise max
>>> torch.stack([(a[i]==torch.max(a[i])).nonzero() for i in range(a.size(0))], dim=0)
tensor([[[0, 0]],
[[1, 0]],
[[0, 1]]])