评价此页

torch.gradient#

torch.gradient(input, *, spacing=1, dim=None, edge_order=1) List of Tensors#

使用 二阶精度中心差分法 估算函数 g:RnRg : \mathbb{R}^n \rightarrow \mathbb{R} 的梯度,并使用一阶或二阶边界估计。

使用样本估计gg的梯度。默认情况下,当未指定spacing时,样本完全由input描述,输入坐标到输出的映射与张量索引到值的映射相同。例如,对于一个三维input,描述的函数是g:R3Rg : \mathbb{R}^3 \rightarrow \mathbb{R},并且g(1,2,3) ==input[1,2,3]g(1, 2, 3)\ == input[1, 2, 3]

当指定spacing时,它会修改input与输入坐标之间的关系。这将在下面的“关键字参数”部分详细说明。

梯度是通过独立估计gg的每个偏导数来估计的。如果gg属于C3C^3(即至少有3个连续导数),则该估计是准确的,并且可以通过提供更接近的样本来改进估计。从数学上讲,每个内部点的偏导数使用带余项的泰勒定理进行估计。令xx为内部点,其左侧和右侧邻近点分别为xhlx-h_lx+hrx+h_rf(x+hr)f(x+h_r)f(xhl)f(x-h_l)可以这样估计:

f(x+hr)=f(x)+hrf(x)+hr2f(x)2+hr3f(ξ1)6,ξ1(x,x+hr)f(xhl)=f(x)hlf(x)+hl2f(x)2hl3f(ξ2)6,ξ2(x,xhl)\begin{aligned} f(x+h_r) = f(x) + h_r f'(x) + {h_r}^2 \frac{f''(x)}{2} + {h_r}^3 \frac{f'''(\xi_1)}{6}, \xi_1 \in (x, x+h_r) \\ f(x-h_l) = f(x) - h_l f'(x) + {h_l}^2 \frac{f''(x)}{2} - {h_l}^3 \frac{f'''(\xi_2)}{6}, \xi_2 \in (x, x-h_l) \\ \end{aligned}

利用fC3f \in C^3这一事实,并求解线性方程组,我们推导出:

f(x)hl2f(x+hr)hr2f(xhl)+(hr2hl2)f(x)hrhl2+hr2hlf'(x) \approx \frac{ {h_l}^2 f(x+h_r) - {h_r}^2 f(x-h_l) + ({h_r}^2-{h_l}^2 ) f(x) }{ {h_r} {h_l}^2 + {h_r}^2 {h_l} }

注意

我们以同样的方式估计复域g:CnCg : \mathbb{C}^n \rightarrow \mathbb{C}中函数的梯度。

边界点处每个偏导数的值的计算方式不同。请参阅下面的 edge_order。

参数

input (Tensor) – 表示函数值的张量

关键字参数
  • spacing (scalar, list of scalar, list of Tensor, optional) – spacing可用于修改input张量的索引与样本坐标之间的关系。如果spacing是一个标量,则索引乘以该标量以生成坐标。例如,如果spacing=2,则索引(1, 2, 3)变为坐标(2, 4, 6)。如果spacing是标量列表,则相应的索引会被乘以。例如,如果spacing=(2, -1, 3),则索引(1, 2, 3)变为坐标(2, -2, 9)。最后,如果spacing是包含一维张量的列表,则每个张量指定对应维度的坐标。例如,如果索引是(1, 2, 3),张量是(t0, t1, t2),则坐标是(t0[1], t1[2], t2[3])。

  • dim (int, list of int, optional) – 要近似梯度的维度或维度。默认情况下,将计算每个维度的部分梯度。请注意,当指定dim时,spacing参数的元素必须与指定的维度对应。

  • edge_order (int, optional) – 1或2,分别用于边界(“edge”)值的一阶二阶估计。

示例

>>> # Estimates the gradient of f(x)=x^2 at points [-2, -1, 2, 4]
>>> coordinates = (torch.tensor([-2., -1., 1., 4.]),)
>>> values = torch.tensor([4., 1., 1., 16.], )
>>> torch.gradient(values, spacing = coordinates)
(tensor([-3., -2., 2., 5.]),)

>>> # Estimates the gradient of the R^2 -> R function whose samples are
>>> # described by the tensor t. Implicit coordinates are [0, 1] for the outermost
>>> # dimension and [0, 1, 2, 3] for the innermost dimension, and function estimates
>>> # partial derivative for both dimensions.
>>> t = torch.tensor([[1, 2, 4, 8], [10, 20, 40, 80]])
>>> torch.gradient(t)
(tensor([[ 9., 18., 36., 72.],
         [ 9., 18., 36., 72.]]),
 tensor([[ 1.0000, 1.5000, 3.0000, 4.0000],
         [10.0000, 15.0000, 30.0000, 40.0000]]))

>>> # A scalar value for spacing modifies the relationship between tensor indices
>>> # and input coordinates by multiplying the indices to find the
>>> # coordinates. For example, below the indices of the innermost
>>> # 0, 1, 2, 3 translate to coordinates of [0, 2, 4, 6], and the indices of
>>> # the outermost dimension 0, 1 translate to coordinates of [0, 2].
>>> torch.gradient(t, spacing = 2.0) # dim = None (implicitly [0, 1])
(tensor([[ 4.5000, 9.0000, 18.0000, 36.0000],
          [ 4.5000, 9.0000, 18.0000, 36.0000]]),
 tensor([[ 0.5000, 0.7500, 1.5000, 2.0000],
          [ 5.0000, 7.5000, 15.0000, 20.0000]]))
>>> # doubling the spacing between samples halves the estimated partial gradients.

>>>
>>> # Estimates only the partial derivative for dimension 1
>>> torch.gradient(t, dim = 1) # spacing = None (implicitly 1.)
(tensor([[ 1.0000, 1.5000, 3.0000, 4.0000],
         [10.0000, 15.0000, 30.0000, 40.0000]]),)

>>> # When spacing is a list of scalars, the relationship between the tensor
>>> # indices and input coordinates changes based on dimension.
>>> # For example, below, the indices of the innermost dimension 0, 1, 2, 3 translate
>>> # to coordinates of [0, 3, 6, 9], and the indices of the outermost dimension
>>> # 0, 1 translate to coordinates of [0, 2].
>>> torch.gradient(t, spacing = [3., 2.])
(tensor([[ 4.5000, 9.0000, 18.0000, 36.0000],
         [ 4.5000, 9.0000, 18.0000, 36.0000]]),
 tensor([[ 0.3333, 0.5000, 1.0000, 1.3333],
         [ 3.3333, 5.0000, 10.0000, 13.3333]]))

>>> # The following example is a replication of the previous one with explicit
>>> # coordinates.
>>> coords = (torch.tensor([0, 2]), torch.tensor([0, 3, 6, 9]))
>>> torch.gradient(t, spacing = coords)
(tensor([[ 4.5000, 9.0000, 18.0000, 36.0000],
         [ 4.5000, 9.0000, 18.0000, 36.0000]]),
 tensor([[ 0.3333, 0.5000, 1.0000, 1.3333],
         [ 3.3333, 5.0000, 10.0000, 13.3333]]))