pytorch中的张量变换

Question

我有一个形状为(size, 1)的张量，我想通过移动其值将其转换为形状为(size, lookback, 1)的张量。熊猫的等价物低于

size = 7
lookback = 3
data = pd.DataFrame(np.arange(size), columns=['out'])  # input
y = np.full((len(data), lookback, 1), np.nan)          # required/output
for j in range(lookback):
y[:, j, 0] = data['out'].shift(lookback - j - 1).fillna(method="bfill")

我怎样才能在pytorch中获得类似的结果？

示例输入：

[0, 1, 2, 3, 4, 5, 6]

期望输出：

[[0. 0. 0.]
[0. 0. 1.]
[0. 1. 2.]
[1. 2. 3.]
[2. 3. 4.]
[3. 4. 5.]
[4. 5. 6.]]

Answer 1

您可以为此使用Tensor.unfold。首先，您需要填充张量的前面，为此您可以使用nn.functional.pad。例如

import torch
import torch.nn.functional as F
size = 7
loopback = 3
data = torch.arange(size, dtype=torch.float)
# pad front of data with 2 values
# replicate padding requires 3d, 4d, or 5d tensor, hence the creation of two unitary dimensions before padding
data_padded = F.pad(data[None, None, ...], (loopback - 1, 0), 'replicate')[0, 0, ...]
# unfold with window size of 3 with step size of 1
y = data_padded.unfold(dimension=0, size=loopback, step=1)

它给出的输出

tensor([[0., 0., 0.],
[0., 0., 1.],
[0., 1., 2.],
[1., 2., 3.],
[2., 3., 4.],
[3., 4., 5.],
[4., 5., 6.]])