张量的 pytorch 张量到张量
pytorch tensor of tensors to a tensor
当我打印火炬张量时，我得到以下输出。如果没有 [] 的内部元素，我怎么能得到那个张量呢？
我打印了第一个元素的类型，它 returns <class 'torch.Tensor'> 所以这个张量似乎是张量的张量......我怎么能把它转换成数字的张量？
tensor([[-5.6117e-01],
[ 3.5726e-01],
[-2.5853e-01],
[-4.8641e-01],
[-1.0581e-01],
[-1.8322e-01],
[-1.2732e+00],
[-5.9760e-02],
[ 1.2819e-01],
[ 6.3894e-02],
[-9.1817e-01],
[-1.6539e-01],
[-1.1471e+00],
[ 1.9666e-01],
[-6.3297e-01],
[-4.0876e-01],
[-2.4590e-02],
[ 2.7065e-01],
[ 3.5308e-01],
[-4.6348e-01],
[-4.1755e-01],
[-1.1554e-01],
[-4.2062e-01],
[ 1.4067e-01],
[-2.9788e-01],
[-7.4582e-02],
[-5.3751e-01],
[ 1.1344e-01],
[-2.6100e-01],
[ 2.6951e-02],
[-5.0437e-02],
[-1.9163e-01],
[-3.3893e-02],
[-5.9640e-01],
[-1.1574e-01],
[ 1.4613e-01],
[ 1.2263e-01],
[-1.5566e-01],
[ 1.4740e-01],
[-9.9924e-01],
[ 2.0878e-01],
[-2.0074e-01],
[ 7.8383e-02],
[ 7.4679e-02],
[-5.8065e-01],
[ 6.7777e-01],
[ 5.9879e-01],
[ 6.6301e-01],
[-4.7051e-01],
[-2.5468e-01],
[-2.7382e-01],
[ 1.7585e-01],
[ 3.6151e-01],
[-9.2532e-01],
[-1.6999e-01],
[ 8.4971e-02],
[-6.6083e-01],
[-3.1204e-02],
[ 6.3712e-01],
[-5.8580e-02],
[-7.7901e-04],
[-4.6792e-01],
[ 1.0796e-01],
[ 7.8766e-01],
[ 1.6809e-01],
[-7.0058e-01],
[-2.9299e-01],
[-8.2735e-02],
[ 2.0875e-01],
[-2.9426e-01],
[-7.6748e-02],
[-1.5762e-01],
[-5.7432e-01],
[-5.2042e-01],
[-1.5152e-01],
[ 1.4119e+00],
[-1.5752e-01],
[-3.0565e-01],
[-5.1378e-01],
[-5.8924e-01],
[-1.0163e+00],
[-2.2021e-01],
[ 2.9112e-02],
[ 1.8521e-01],
[ 6.2814e-01],
[-6.8793e-01],
[ 2.1395e-02],
[ 5.7168e-01],
[ 9.0977e-01],
[ 3.8899e-01],
[ 3.0209e-01],
[ 2.4655e-01],
[-1.1688e-01],
[-5.9835e-02],
[ 3.6426e-02],
[-5.2782e-01],
[ 1.4604e+00],
[ 2.9685e-01],
[-2.4077e-01],
[ 1.0163e+00],
[ 6.9770e-01],
[-2.6183e-01],
[ 3.6770e-01],
[ 3.6535e-03],
[ 4.2364e-01],
[-5.4703e-01],
[ 8.9173e-02],
[-3.9032e-01],
[-5.9740e-01],
[ 3.7479e-02],
[ 3.0257e-01],
[ 8.2539e-02],
[-6.0559e-01],
[-4.3660e-01],
[-7.0624e-01],
[-5.0503e-01],
[-4.0929e-01],
[-2.3300e-01],
[ 2.0298e-01],
[-6.3697e-01],
[-1.2584e-01],
[ 5.6092e-02],
[ 5.0150e-02],
[-1.5358e-01],
[ 2.9248e-02],
[ 1.1180e-01],
[-1.5535e-01],
[ 1.1964e-01],
[-6.5698e-01],
[ 4.1923e-01],
[ 7.4044e-02],
[ 2.4536e-02],
[ 3.2647e-01],
[-7.7464e-01],
[ 3.9898e-01],
[-2.5777e-01],
[ 8.5569e-02],
[-4.0305e-01],
[ 5.4463e-01],
[-3.4124e-01],
[-4.0789e-01],
[ 4.2093e-01],
[-3.8487e-01],
[-4.0491e-01],
[-2.1539e-01],
[-1.7979e-02],
[ 3.2492e-01],
[-2.0894e-01],
[ 2.5629e-01],
[ 9.6046e-01]], device='cuda:0', grad_fn=<AddmmBackward0>)
该张量具有单一维度（即它的形状 [Nx1]）。只需压缩该维度或选择第 0 个元素：
In [1]: import torch
In [2]: a = torch.zeros([10,1])
In [3]: a
Out[3]:
tensor([[0.],
[0.],
[0.],
[0.],
[0.],
[0.],
[0.],
[0.],
[0.],
[0.]])
In [4]: a[:,0]
Out[4]: tensor([0., 0., 0., 0., 0., 0., 0., 0., 0., 0.])
In [5]: a.squeeze(1)
Out[5]: tensor([0., 0., 0., 0., 0., 0., 0., 0., 0., 0.])
如果我理解你的问题，你可以使用flatten方法
输入：
tvalue=torch.tensor([[-5.6117e-01],
[ 3.5726e-01],
[-2.5853e-01],
[-4.8641e-01],
[-1.0581e-01],
[-1.8322e-01],
[-1.2732e+00],
[-5.9760e-02],
[ 1.2819e-01],
[ 6.3894e-02],
[-9.1817e-01],
[-1.6539e-01],
[-1.1471e+00],
[ 1.9666e-01],
[-6.3297e-01],
[-4.0876e-01],
[-2.4590e-02],
[ 2.7065e-01],
[ 3.5308e-01],
[-4.6348e-01],
[-4.1755e-01],
[-1.1554e-01],
[-4.2062e-01],
[ 1.4067e-01],
[-2.9788e-01],
[-7.4582e-02],
[-5.3751e-01],
[ 1.1344e-01],
[-2.6100e-01],
[ 2.6951e-02],
[-5.0437e-02],
[-1.9163e-01],
[-3.3893e-02],
[-5.9640e-01],
[-1.1574e-01],
[ 1.4613e-01],
[ 1.2263e-01],
[-1.5566e-01],
[ 1.4740e-01],
[-9.9924e-01],
[ 2.0878e-01],
[-2.0074e-01],
[ 7.8383e-02],
[ 7.4679e-02],
[-5.8065e-01],
[ 6.7777e-01],
[ 5.9879e-01],
[ 6.6301e-01],
[-4.7051e-01],
[-2.5468e-01],
[-2.7382e-01],
[ 1.7585e-01],
[ 3.6151e-01],
[-9.2532e-01],
[-1.6999e-01],
[ 8.4971e-02],
[-6.6083e-01],
[-3.1204e-02],
[ 6.3712e-01],
[-5.8580e-02],
[-7.7901e-04],
[-4.6792e-01],
[ 1.0796e-01],
[ 7.8766e-01],
[ 1.6809e-01],
[-7.0058e-01],
[-2.9299e-01],
[-8.2735e-02],
[ 2.0875e-01],
[-2.9426e-01],
[-7.6748e-02],
[-1.5762e-01],
[-5.7432e-01],
[-5.2042e-01],
[-1.5152e-01],
[ 1.4119e+00],
[-1.5752e-01],
[-3.0565e-01],
[-5.1378e-01],
[-5.8924e-01],
[-1.0163e+00],
[-2.2021e-01],
[ 2.9112e-02],
[ 1.8521e-01],
[ 6.2814e-01],
[-6.8793e-01],
[ 2.1395e-02],
[ 5.7168e-01],
[ 9.0977e-01],
[ 3.8899e-01],
[ 3.0209e-01],
[ 2.4655e-01],
[-1.1688e-01],
[-5.9835e-02],
[ 3.6426e-02],
[-5.2782e-01],
[ 1.4604e+00],
[ 2.9685e-01],
[-2.4077e-01],
[ 1.0163e+00],
[ 6.9770e-01],
[-2.6183e-01],
[ 3.6770e-01],
[ 3.6535e-03],
[ 4.2364e-01],
[-5.4703e-01],
[ 8.9173e-02],
[-3.9032e-01],
[-5.9740e-01],
[ 3.7479e-02],
[ 3.0257e-01],
[ 8.2539e-02],
[-6.0559e-01],
[-4.3660e-01],
[-7.0624e-01],
[-5.0503e-01],
[-4.0929e-01],
[-2.3300e-01],
[ 2.0298e-01],
[-6.3697e-01],
[-1.2584e-01],
[ 5.6092e-02],
[ 5.0150e-02],
[-1.5358e-01],
[ 2.9248e-02],
[ 1.1180e-01],
[-1.5535e-01],
[ 1.1964e-01],
[-6.5698e-01],
[ 4.1923e-01],
[ 7.4044e-02],
[ 2.4536e-02],
[ 3.2647e-01],
[-7.7464e-01],
[ 3.9898e-01],
[-2.5777e-01],
[ 8.5569e-02],
[-4.0305e-01],
[ 5.4463e-01],
[-3.4124e-01],
[-4.0789e-01],
[ 4.2093e-01],
[-3.8487e-01],
[-4.0491e-01],
[-2.1539e-01],
[-1.7979e-02],
[ 3.2492e-01],
[-2.0894e-01],
[ 2.5629e-01],
[ 9.6046e-01]])
输出
tvalue.flatten()
tensor([-5.6117e-01, 3.5726e-01, -2.5853e-01, -4.8641e-01, -1.0581e-01,
-1.8322e-01, -1.2732e+00, -5.9760e-02, 1.2819e-01, 6.3894e-02,
-9.1817e-01, -1.6539e-01, -1.1471e+00, 1.9666e-01, -6.3297e-01,
-4.0876e-01, -2.4590e-02, 2.7065e-01, 3.5308e-01, -4.6348e-01,
-4.1755e-01, -1.1554e-01, -4.2062e-01, 1.4067e-01, -2.9788e-01,
-7.4582e-02, -5.3751e-01, 1.1344e-01, -2.6100e-01, 2.6951e-02,
-5.0437e-02, -1.9163e-01, -3.3893e-02, -5.9640e-01, -1.1574e-01,
1.4613e-01, 1.2263e-01, -1.5566e-01, 1.4740e-01, -9.9924e-01,
2.0878e-01, -2.0074e-01, 7.8383e-02, 7.4679e-02, -5.8065e-01,
6.7777e-01, 5.9879e-01, 6.6301e-01, -4.7051e-01, -2.5468e-01,
-2.7382e-01, 1.7585e-01, 3.6151e-01, -9.2532e-01, -1.6999e-01,
8.4971e-02, -6.6083e-01, -3.1204e-02, 6.3712e-01, -5.8580e-02,
-7.7901e-04, -4.6792e-01, 1.0796e-01, 7.8766e-01, 1.6809e-01,
-7.0058e-01, -2.9299e-01, -8.2735e-02, 2.0875e-01, -2.9426e-01,
-7.6748e-02, -1.5762e-01, -5.7432e-01, -5.2042e-01, -1.5152e-01,
1.4119e+00, -1.5752e-01, -3.0565e-01, -5.1378e-01, -5.8924e-01,
-1.0163e+00, -2.2021e-01, 2.9112e-02, 1.8521e-01, 6.2814e-01,
-6.8793e-01, 2.1395e-02, 5.7168e-01, 9.0977e-01, 3.8899e-01,
3.0209e-01, 2.4655e-01, -1.1688e-01, -5.9835e-02, 3.6426e-02,
-5.2782e-01, 1.4604e+00, 2.9685e-01, -2.4077e-01, 1.0163e+00,
6.9770e-01, -2.6183e-01, 3.6770e-01, 3.6535e-03, 4.2364e-01,
-5.4703e-01, 8.9173e-02, -3.9032e-01, -5.9740e-01, 3.7479e-02,
3.0257e-01, 8.2539e-02, -6.0559e-01, -4.3660e-01, -7.0624e-01,
-5.0503e-01, -4.0929e-01, -2.3300e-01, 2.0298e-01, -6.3697e-01,
-1.2584e-01, 5.6092e-02, 5.0150e-02, -1.5358e-01, 2.9248e-02,
1.1180e-01, -1.5535e-01, 1.1964e-01, -6.5698e-01, 4.1923e-01,
7.4044e-02, 2.4536e-02, 3.2647e-01, -7.7464e-01, 3.9898e-01,
-2.5777e-01, 8.5569e-02, -4.0305e-01, 5.4463e-01, -3.4124e-01,
-4.0789e-01, 4.2093e-01, -3.8487e-01, -4.0491e-01, -2.1539e-01,
-1.7979e-02, 3.2492e-01, -2.0894e-01, 2.5629e-01, 9.6046e-01])
当我打印火炬张量时，我得到以下输出。如果没有 [] 的内部元素，我怎么能得到那个张量呢？
我打印了第一个元素的类型，它 returns <class 'torch.Tensor'> 所以这个张量似乎是张量的张量......我怎么能把它转换成数字的张量？
tensor([[-5.6117e-01],
[ 3.5726e-01],
[-2.5853e-01],
[-4.8641e-01],
[-1.0581e-01],
[-1.8322e-01],
[-1.2732e+00],
[-5.9760e-02],
[ 1.2819e-01],
[ 6.3894e-02],
[-9.1817e-01],
[-1.6539e-01],
[-1.1471e+00],
[ 1.9666e-01],
[-6.3297e-01],
[-4.0876e-01],
[-2.4590e-02],
[ 2.7065e-01],
[ 3.5308e-01],
[-4.6348e-01],
[-4.1755e-01],
[-1.1554e-01],
[-4.2062e-01],
[ 1.4067e-01],
[-2.9788e-01],
[-7.4582e-02],
[-5.3751e-01],
[ 1.1344e-01],
[-2.6100e-01],
[ 2.6951e-02],
[-5.0437e-02],
[-1.9163e-01],
[-3.3893e-02],
[-5.9640e-01],
[-1.1574e-01],
[ 1.4613e-01],
[ 1.2263e-01],
[-1.5566e-01],
[ 1.4740e-01],
[-9.9924e-01],
[ 2.0878e-01],
[-2.0074e-01],
[ 7.8383e-02],
[ 7.4679e-02],
[-5.8065e-01],
[ 6.7777e-01],
[ 5.9879e-01],
[ 6.6301e-01],
[-4.7051e-01],
[-2.5468e-01],
[-2.7382e-01],
[ 1.7585e-01],
[ 3.6151e-01],
[-9.2532e-01],
[-1.6999e-01],
[ 8.4971e-02],
[-6.6083e-01],
[-3.1204e-02],
[ 6.3712e-01],
[-5.8580e-02],
[-7.7901e-04],
[-4.6792e-01],
[ 1.0796e-01],
[ 7.8766e-01],
[ 1.6809e-01],
[-7.0058e-01],
[-2.9299e-01],
[-8.2735e-02],
[ 2.0875e-01],
[-2.9426e-01],
[-7.6748e-02],
[-1.5762e-01],
[-5.7432e-01],
[-5.2042e-01],
[-1.5152e-01],
[ 1.4119e+00],
[-1.5752e-01],
[-3.0565e-01],
[-5.1378e-01],
[-5.8924e-01],
[-1.0163e+00],
[-2.2021e-01],
[ 2.9112e-02],
[ 1.8521e-01],
[ 6.2814e-01],
[-6.8793e-01],
[ 2.1395e-02],
[ 5.7168e-01],
[ 9.0977e-01],
[ 3.8899e-01],
[ 3.0209e-01],
[ 2.4655e-01],
[-1.1688e-01],
[-5.9835e-02],
[ 3.6426e-02],
[-5.2782e-01],
[ 1.4604e+00],
[ 2.9685e-01],
[-2.4077e-01],
[ 1.0163e+00],
[ 6.9770e-01],
[-2.6183e-01],
[ 3.6770e-01],
[ 3.6535e-03],
[ 4.2364e-01],
[-5.4703e-01],
[ 8.9173e-02],
[-3.9032e-01],
[-5.9740e-01],
[ 3.7479e-02],
[ 3.0257e-01],
[ 8.2539e-02],
[-6.0559e-01],
[-4.3660e-01],
[-7.0624e-01],
[-5.0503e-01],
[-4.0929e-01],
[-2.3300e-01],
[ 2.0298e-01],
[-6.3697e-01],
[-1.2584e-01],
[ 5.6092e-02],
[ 5.0150e-02],
[-1.5358e-01],
[ 2.9248e-02],
[ 1.1180e-01],
[-1.5535e-01],
[ 1.1964e-01],
[-6.5698e-01],
[ 4.1923e-01],
[ 7.4044e-02],
[ 2.4536e-02],
[ 3.2647e-01],
[-7.7464e-01],
[ 3.9898e-01],
[-2.5777e-01],
[ 8.5569e-02],
[-4.0305e-01],
[ 5.4463e-01],
[-3.4124e-01],
[-4.0789e-01],
[ 4.2093e-01],
[-3.8487e-01],
[-4.0491e-01],
[-2.1539e-01],
[-1.7979e-02],
[ 3.2492e-01],
[-2.0894e-01],
[ 2.5629e-01],
[ 9.6046e-01]], device='cuda:0', grad_fn=<AddmmBackward0>)
该张量具有单一维度（即它的形状 [Nx1]）。只需压缩该维度或选择第 0 个元素：
In [1]: import torch
In [2]: a = torch.zeros([10,1])
In [3]: a
Out[3]:
tensor([[0.],
[0.],
[0.],
[0.],
[0.],
[0.],
[0.],
[0.],
[0.],
[0.]])
In [4]: a[:,0]
Out[4]: tensor([0., 0., 0., 0., 0., 0., 0., 0., 0., 0.])
In [5]: a.squeeze(1)
Out[5]: tensor([0., 0., 0., 0., 0., 0., 0., 0., 0., 0.])
如果我理解你的问题，你可以使用flatten方法
输入：
tvalue=torch.tensor([[-5.6117e-01],
[ 3.5726e-01],
[-2.5853e-01],
[-4.8641e-01],
[-1.0581e-01],
[-1.8322e-01],
[-1.2732e+00],
[-5.9760e-02],
[ 1.2819e-01],
[ 6.3894e-02],
[-9.1817e-01],
[-1.6539e-01],
[-1.1471e+00],
[ 1.9666e-01],
[-6.3297e-01],
[-4.0876e-01],
[-2.4590e-02],
[ 2.7065e-01],
[ 3.5308e-01],
[-4.6348e-01],
[-4.1755e-01],
[-1.1554e-01],
[-4.2062e-01],
[ 1.4067e-01],
[-2.9788e-01],
[-7.4582e-02],
[-5.3751e-01],
[ 1.1344e-01],
[-2.6100e-01],
[ 2.6951e-02],
[-5.0437e-02],
[-1.9163e-01],
[-3.3893e-02],
[-5.9640e-01],
[-1.1574e-01],
[ 1.4613e-01],
[ 1.2263e-01],
[-1.5566e-01],
[ 1.4740e-01],
[-9.9924e-01],
[ 2.0878e-01],
[-2.0074e-01],
[ 7.8383e-02],
[ 7.4679e-02],
[-5.8065e-01],
[ 6.7777e-01],
[ 5.9879e-01],
[ 6.6301e-01],
[-4.7051e-01],
[-2.5468e-01],
[-2.7382e-01],
[ 1.7585e-01],
[ 3.6151e-01],
[-9.2532e-01],
[-1.6999e-01],
[ 8.4971e-02],
[-6.6083e-01],
[-3.1204e-02],
[ 6.3712e-01],
[-5.8580e-02],
[-7.7901e-04],
[-4.6792e-01],
[ 1.0796e-01],
[ 7.8766e-01],
[ 1.6809e-01],
[-7.0058e-01],
[-2.9299e-01],
[-8.2735e-02],
[ 2.0875e-01],
[-2.9426e-01],
[-7.6748e-02],
[-1.5762e-01],
[-5.7432e-01],
[-5.2042e-01],
[-1.5152e-01],
[ 1.4119e+00],
[-1.5752e-01],
[-3.0565e-01],
[-5.1378e-01],
[-5.8924e-01],
[-1.0163e+00],
[-2.2021e-01],
[ 2.9112e-02],
[ 1.8521e-01],
[ 6.2814e-01],
[-6.8793e-01],
[ 2.1395e-02],
[ 5.7168e-01],
[ 9.0977e-01],
[ 3.8899e-01],
[ 3.0209e-01],
[ 2.4655e-01],
[-1.1688e-01],
[-5.9835e-02],
[ 3.6426e-02],
[-5.2782e-01],
[ 1.4604e+00],
[ 2.9685e-01],
[-2.4077e-01],
[ 1.0163e+00],
[ 6.9770e-01],
[-2.6183e-01],
[ 3.6770e-01],
[ 3.6535e-03],
[ 4.2364e-01],
[-5.4703e-01],
[ 8.9173e-02],
[-3.9032e-01],
[-5.9740e-01],
[ 3.7479e-02],
[ 3.0257e-01],
[ 8.2539e-02],
[-6.0559e-01],
[-4.3660e-01],
[-7.0624e-01],
[-5.0503e-01],
[-4.0929e-01],
[-2.3300e-01],
[ 2.0298e-01],
[-6.3697e-01],
[-1.2584e-01],
[ 5.6092e-02],
[ 5.0150e-02],
[-1.5358e-01],
[ 2.9248e-02],
[ 1.1180e-01],
[-1.5535e-01],
[ 1.1964e-01],
[-6.5698e-01],
[ 4.1923e-01],
[ 7.4044e-02],
[ 2.4536e-02],
[ 3.2647e-01],
[-7.7464e-01],
[ 3.9898e-01],
[-2.5777e-01],
[ 8.5569e-02],
[-4.0305e-01],
[ 5.4463e-01],
[-3.4124e-01],
[-4.0789e-01],
[ 4.2093e-01],
[-3.8487e-01],
[-4.0491e-01],
[-2.1539e-01],
[-1.7979e-02],
[ 3.2492e-01],
[-2.0894e-01],
[ 2.5629e-01],
[ 9.6046e-01]])
输出
tvalue.flatten()
tensor([-5.6117e-01, 3.5726e-01, -2.5853e-01, -4.8641e-01, -1.0581e-01,
-1.8322e-01, -1.2732e+00, -5.9760e-02, 1.2819e-01, 6.3894e-02,
-9.1817e-01, -1.6539e-01, -1.1471e+00, 1.9666e-01, -6.3297e-01,
-4.0876e-01, -2.4590e-02, 2.7065e-01, 3.5308e-01, -4.6348e-01,
-4.1755e-01, -1.1554e-01, -4.2062e-01, 1.4067e-01, -2.9788e-01,
-7.4582e-02, -5.3751e-01, 1.1344e-01, -2.6100e-01, 2.6951e-02,
-5.0437e-02, -1.9163e-01, -3.3893e-02, -5.9640e-01, -1.1574e-01,
1.4613e-01, 1.2263e-01, -1.5566e-01, 1.4740e-01, -9.9924e-01,
2.0878e-01, -2.0074e-01, 7.8383e-02, 7.4679e-02, -5.8065e-01,
6.7777e-01, 5.9879e-01, 6.6301e-01, -4.7051e-01, -2.5468e-01,
-2.7382e-01, 1.7585e-01, 3.6151e-01, -9.2532e-01, -1.6999e-01,
8.4971e-02, -6.6083e-01, -3.1204e-02, 6.3712e-01, -5.8580e-02,
-7.7901e-04, -4.6792e-01, 1.0796e-01, 7.8766e-01, 1.6809e-01,
-7.0058e-01, -2.9299e-01, -8.2735e-02, 2.0875e-01, -2.9426e-01,
-7.6748e-02, -1.5762e-01, -5.7432e-01, -5.2042e-01, -1.5152e-01,
1.4119e+00, -1.5752e-01, -3.0565e-01, -5.1378e-01, -5.8924e-01,
-1.0163e+00, -2.2021e-01, 2.9112e-02, 1.8521e-01, 6.2814e-01,
-6.8793e-01, 2.1395e-02, 5.7168e-01, 9.0977e-01, 3.8899e-01,
3.0209e-01, 2.4655e-01, -1.1688e-01, -5.9835e-02, 3.6426e-02,
-5.2782e-01, 1.4604e+00, 2.9685e-01, -2.4077e-01, 1.0163e+00,
6.9770e-01, -2.6183e-01, 3.6770e-01, 3.6535e-03, 4.2364e-01,
-5.4703e-01, 8.9173e-02, -3.9032e-01, -5.9740e-01, 3.7479e-02,
3.0257e-01, 8.2539e-02, -6.0559e-01, -4.3660e-01, -7.0624e-01,
-5.0503e-01, -4.0929e-01, -2.3300e-01, 2.0298e-01, -6.3697e-01,
-1.2584e-01, 5.6092e-02, 5.0150e-02, -1.5358e-01, 2.9248e-02,
1.1180e-01, -1.5535e-01, 1.1964e-01, -6.5698e-01, 4.1923e-01,
7.4044e-02, 2.4536e-02, 3.2647e-01, -7.7464e-01, 3.9898e-01,
-2.5777e-01, 8.5569e-02, -4.0305e-01, 5.4463e-01, -3.4124e-01,
-4.0789e-01, 4.2093e-01, -3.8487e-01, -4.0491e-01, -2.1539e-01,
-1.7979e-02, 3.2492e-01, -2.0894e-01, 2.5629e-01, 9.6046e-01])