Pytorch中Tensor的一些操作
1 a = torch.rand(1,10,4)，生成的Tensor在0-1之间，且tensor的shape为（1,10,4）
2 torch.cat(tensors, dim=0, out=None) → Tensor
>>> x = torch.randn(2, 3)
>>> x
tensor([[ 0.6580, -1.0969, -0.4614],
[-0.1034, -0.5790, 0.1497]])
>>> torch.cat((x, x, x), 0)
tensor([[ 0.6580, -1.0969, -0.4614],
[-0.1034, -0.5790, 0.1497],
[ 0.6580, -1.0969, -0.4614],
[-0.1034, -0.5790, 0.1497],
[ 0.6580, -1.0969, -0.4614],
[-0.1034, -0.5790, 0.1497]])
>>> torch.cat((x, x, x), 1)
tensor([[ 0.6580, -1.0969, -0.4614, 0.6580, -1.0969, -0.4614, 0.6580,
-1.0969, -0.4614],
[-0.1034, -0.5790, 0.1497, -0.1034, -0.5790, 0.1497, -0.1034,
-0.5790, 0.1497]])
3 torch.index_select(input, dim, index, out=None) → Tensor
>>> x = torch.randn(3, 4)
>>> x
tensor([[ 0.1427, 0.0231, -0.5414, -1.0009],
[-0.4664, 0.2647, -0.1228, -1.1068],
[-1.1734, -0.6571, 0.7230, -0.6004]])
>>> indices = torch.tensor([0, 2])
>>> torch.index_select(x, 0, indices)
tensor([[ 0.1427, 0.0231, -0.5414, -1.0009],
[-1.1734, -0.6571, 0.7230, -0.6004]])
>>> torch.index_select(x, 1, indices)
tensor([[ 0.1427, -0.5414],
[-0.4664, -0.1228],
[-1.1734, 0.7230]])
4 torch.masked_select(input, mask, out=None) → Tensor
Returns a new 1-D tensor which indexes the input tensor according to the binary mask mask which is a ByteTensor.
>>> x = torch.randn(3, 4)
>>> x
tensor([[ 0.3552, -2.3825, -0.8297, 0.3477],
[-1.2035, 1.2252, 0.5002, 0.6248],
[ 0.1307, -2.0608, 0.1244, 2.0139]])
>>> mask = x.ge(0.5)
>>> mask
tensor([[ 0, 0, 0, 0],
[ 0, 1, 1, 1],
[ 0, 0, 0, 1]], dtype=torch.uint8)
>>> torch.masked_select(x, mask)
tensor([ 1.2252, 0.5002, 0.6248, 2.0139])
5 torch.squeeze(input, dim=None, out=None) → Tensor
Returns a tensor with all the dimensions of input of size 1 removed.
>>> x = torch.zeros(2, 1, 2, 1, 2)
>>> x.size()
torch.Size([2, 1, 2, 1, 2])
>>> y = torch.squeeze(x)
>>> y.size()
torch.Size([2, 2, 2])
>>> y = torch.squeeze(x, 0)
>>> y.size()
torch.Size([2, 1, 2, 1, 2])
>>> y = torch.squeeze(x, 1)
>>> y.size()
torch.Size([2, 2, 1, 2])
6 torch.transpose(input, dim0, dim1) → Tensor
Returns a tensor that is a transposed version of input. The given dimensions dim0 and dim1 are swapped.
The resulting out tensor shares it’s underlying storage with the input tensor, so changing the content of one would change the content of the other.
>>> x = torch.randn(2, 3)
>>> x
tensor([[ 1.0028, -0.9893, 0.5809],
[-0.1669, 0.7299, 0.4942]])
>>> torch.transpose(x, 0, 1)
tensor([[ 1.0028, -0.1669],
[-0.9893, 0.7299],
[ 0.5809, 0.4942]])
7 torch.unsqueeze(input, dim, out=None) → Tensor
Returns a new tensor with a dimension of size one inserted at the specified position.
>>> x = torch.tensor([1, 2, 3, 4])
>>> torch.unsqueeze(x, 0)
tensor([[ 1, 2, 3, 4]])
>>> torch.unsqueeze(x, 1)
tensor([[ 1],
[ 2],
[ 3],
[ 4]])
8 torch.where(condition, x, y) → Tensor
Return a tensor of elements selected from either x or y, depending on condition.
>>> x = torch.randn(3, 2)
>>> y = torch.ones(3, 2)
>>> x
tensor([[-0.4620, 0.3139],
[ 0.3898, -0.7197],
[ 0.0478, -0.1657]])
>>> torch.where(x > 0, x, y)
tensor([[ 1.0000, 0.3139],
[ 0.3898, 1.0000],
[ 0.0478, 1.0000]])
9 torch.rand(*sizes, out=None, dtype=None, layout=torch.strided, device=None, requires_grad=False) → Tensor
>>> torch.rand(4)
tensor([ 0.5204, 0.2503, 0.3525, 0.5673])
>>> torch.rand(2, 3)
tensor([[ 0.8237, 0.5781, 0.6879],
[ 0.3816, 0.7249, 0.0998]])
10 torch.randint(low=0, high, size, out=None, dtype=None, layout=torch.strided, device=None, requires_grad=False) → Tensor
>>> torch.randint(3, 5, (3,))
tensor([4, 3, 4])
>>> torch.randint(10, (2, 2))
tensor([[0, 2],
[5, 5]])
>>> torch.randint(3, 10, (2, 2))
tensor([[4, 5],
[6, 7]])
10 torch.randn(*sizes, out=None, dtype=None, layout=torch.strided, device=None, requires_grad=False) → Tensor
Returns a tensor filled with random numbers from a normal distribution with mean 0 and variance 1 (also called the standard normal distribution).
>>> torch.randn(4)
tensor([-2.1436, 0.9966, 2.3426, -0.6366])
>>> torch.randn(2, 3)
tensor([[ 1.5954, 2.8929, -1.0923],
[ 1.1719, -0.4709, -0.1996]])
11 torch.clamp(input, min, max, out=None) → Tensor
>>> a = torch.randn(4)
>>> a
tensor([-1.7120, 0.1734, -0.0478, -0.0922])
>>> torch.clamp(a, min=-0.5, max=0.5)
tensor([-0.5000, 0.1734, -0.0478, -0.0922])
12 torch.argmax(input, dim, keepdim=False) → LongTensor
torch.argmin(input, dim, keepdim=False, out=None) → LongTensor
>>> a = torch.randn(4, 4)
>>> a
tensor([[ 0.1139, 0.2254, -0.1381, 0.3687],
[ 1.0100, -1.1975, -0.0102, -0.4732],
[-0.9240, 0.1207, -0.7506, -1.0213],
[ 1.7809, -1.2960, 0.9384, 0.1438]])
>>> torch.argmin(a, dim=1)
tensor([ 2, 1, 3, 1])
13 torch.unique(input, sorted=True, return_inverse=False, return_counts=False, dim=None)
>>> output = torch.unique(torch.tensor([1, 3, 2, 3], dtype=torch.long))
>>> output
tensor([ 2, 3, 1])
>>> output, inverse_indices = torch.unique(
torch.tensor([1, 3, 2, 3], dtype=torch.long), sorted=True, return_inverse=True)
>>> output
tensor([ 1, 2, 3])
>>> inverse_indices
tensor([ 0, 2, 1, 2])
>>> output, inverse_indices = torch.unique(
torch.tensor([[1, 3], [2, 3]], dtype=torch.long), sorted=True, return_inverse=True)
>>> output
tensor([ 1, 2, 3])
>>> inverse_indices
tensor([[ 0, 2],
[ 1, 2]])
14 torch.argsort(input, dim=-1, descending=False, out=None) → LongTensor
>>> a = torch.randn(4, 4)
>>> a
tensor([[ 0.0785, 1.5267, -0.8521, 0.4065],
[ 0.1598, 0.0788, -0.0745, -1.2700],
[ 1.2208, 1.0722, -0.7064, 1.2564],
[ 0.0669, -0.2318, -0.8229, -0.9280]])
>>> torch.argsort(a, dim=1)
tensor([[2, 0, 3, 1],
[3, 2, 1, 0],
[2, 1, 0, 3],
[3, 2, 1, 0]])
15 torch.eq(input, other, out=None) → Tensor（ByteTensor）
Computes element-wise equality
The second argument can be a number or a tensor whose shape is broadcastable with the first argument.
>>> torch.eq(torch.tensor([[1, 2], [3, 4]]), torch.tensor([[1, 1], [4, 4]]))
tensor([[ 1, 0],
[ 0, 1]], dtype=torch.uint8)
16 torch.ge(input, other, out=None) → Tensor（ByteTensor）
Computes \text{input} \geq \text{other}input≥other element-wise.
The second argument can be a number or a tensor whose shape is broadcastable with the first argument.
>>> torch.ge(torch.tensor([[1, 2], [3, 4]]), torch.tensor([[1, 1], [4, 4]]))
tensor([[ 1, 1],
[ 0, 1]], dtype=torch.uint8)
17 torch.le(input, other, out=None) → Tensor（ByteTensor）
>>> torch.le(torch.tensor([[1, 2], [3, 4]]), torch.tensor([[1, 1], [4, 4]]))
tensor([[ 1, 0],
[ 1, 1]], dtype=torch.uint8)
18 torch.max(input, dim, keepdim=False, out=None) -> (Tensor, LongTensor)（同torch.min(), torch.ne()）
>>> a = torch.randn(4, 4)
>>> a
tensor([[-1.2360, -0.2942, -0.1222, 0.8475],
[ 1.1949, -1.1127, -2.2379, -0.6702],
[ 1.5717, -0.9207, 0.1297, -1.8768],
[-0.6172, 1.0036, -0.6060, -0.2432]])
>>> torch.max(a, 1)
torch.return_types.max(values=tensor([0.8475, 1.1949, 1.5717, 1.0036]), indices=tensor([3, 0, 0, 1]))
19 torch.sort(input, dim=-1, descending=False, out=None) -> (Tensor, LongTensor)
>>> x = torch.randn(3, 4)
>>> sorted, indices = torch.sort(x)
>>> sorted
tensor([[-0.2162, 0.0608, 0.6719, 2.3332],
[-0.5793, 0.0061, 0.6058, 0.9497],
[-0.5071, 0.3343, 0.9553, 1.0960]])
>>> indices
tensor([[ 1, 0, 2, 3],
[ 3, 1, 0, 2],
[ 0, 3, 1, 2]])
>>> sorted, indices = torch.sort(x, 0)
>>> sorted
tensor([[-0.5071, -0.2162, 0.6719, -0.5793],
[ 0.0608, 0.0061, 0.9497, 0.3343],
[ 0.6058, 0.9553, 1.0960, 2.3332]])
>>> indices
tensor([[ 2, 0, 0, 1],
[ 0, 1, 1, 2],
[ 1, 2, 2, 0]])
20 torch.topk(input, k, dim=None, largest=True, sorted=True, out=None) -> (Tensor, LongTensor)
>>> x = torch.arange(1., 6.)
>>> x
tensor([ 1., 2., 3., 4., 5.])
>>> torch.topk(x, 3)
torch.return_types.topk(values=tensor([5., 4., 3.]), indices=tensor([4, 3, 2]))
21 torch.diag(input, diagonal=0, out=None) → Tensor
If input is a vector (1-D tensor), then returns a 2-D square tensor with the elements of input as the diagonal.
If input is a matrix (2-D tensor), then returns a 1-D tensor with the diagonal elements of input.
>>> a = torch.randn(3)
>>> a
tensor([ 0.5950,-0.0872, 2.3298])
>>> torch.diag(a)
tensor([[ 0.5950, 0.0000, 0.0000],
[ 0.0000,-0.0872, 0.0000],
[ 0.0000, 0.0000, 2.3298]])
>>> torch.diag(a, 1)
tensor([[ 0.0000, 0.5950, 0.0000, 0.0000],
[ 0.0000, 0.0000,-0.0872, 0.0000],
[ 0.0000, 0.0000, 0.0000, 2.3298],
[ 0.0000, 0.0000, 0.0000, 0.0000]])
# ******************
>>> a = torch.randn(3, 3)
>>> a
tensor([[-0.4264, 0.0255,-0.1064],
[ 0.8795,-0.2429, 0.1374],
[ 0.1029,-0.6482,-1.6300]])
>>> torch.diag(a, 0)
tensor([-0.4264,-0.2429,-1.6300])
>>> torch.diag(a, 1)
tensor([ 0.0255, 0.1374])
就是对tensor根据index进行选择，例子如下，这里需要保证a是long，byte，bool类型
In [26]: a = a.long()
In [27]: b[a]
Out[27]:
tensor([[0.2214, 0.9189, 0.2356, 0.0580],
[0.2214, 0.9189, 0.2356, 0.0580],
[0.2214, 0.9189, 0.2356, 0.0580],
[0.2214, 0.9189, 0.2356, 0.0580]])
In [28]: a = torch.ones(4).long()
In [29]: b = torch.rand(2,4)
In [30]: b
Out[30]:
tensor([[0.5651, 0.5041, 0.2411, 0.9585],
[0.0191, 0.7716, 0.2444, 0.5113]])
In [31]: b[a]
Out[31]:
tensor([[0.0191, 0.7716, 0.2444, 0.5113],
[0.0191, 0.7716, 0.2444, 0.5113],
[0.0191, 0.7716, 0.2444, 0.5113],
[0.0191, 0.7716, 0.2444, 0.5113]])