Website: http://pytorch.org/tutorials/beginner/blitz/tensor\_tutorial.html\#sphx-glr-beginner-blitz-tensor-tutorial-py
What is PyTorch?
PyTorch is a Python based scientific computing package targeted at two sets of audiences:
- The audience is a replacement for NumPy to use the power of GPUs
- The audience is a deep learning research platform that provides maximum flexibility and speed
Getting Started
Tensors
Tensors are similar to NumPy’s ndarrays with the addition being that Tensors can also be used on a GPU to accelerate computing.
from__future__import print_function
import torch
Construct a 5x3 matrix, uninitialized:
x= torch.Tensor(5, 3)
print(x)
Out:
0.0000e+00 0.0000e+00 5.1715e+36
4.5759e-41 5.1720e+36 4.5759e-41
1.6410e+38 4.5759e-41 1.6410e+38
4.5759e-41 2.0297e+38 4.5759e-41
1.9567e+38 4.5759e-41 -2.9502e-12
[torch.FloatTensor of size 5x3]
Construct a randomly initialized matrix:
x=torch.rand(5,3)
print(x)
Out:
0.0678 0.3477 0.8519
0.1702 0.1063 0.1622
0.3628 0.9545 0.9967
0.3112 0.8519 0.2486
0.4186 0.6778 0.4960
[torch.FloatTensor of size 5x3]
Get its size:
print(x.size())
Out:
torch.Size([5,3])
Note
torch.Sizeis in fact a tuple, so it supports all tuple operations.
Operations
There are multiple syntaxes for operations. In the following example, we will take a look at the addition operation.
Addition: syntax 1
y=torch.rand(5,3)
print(x+y)
Out:
0.0940 0.7706 1.5622
0.1752 0.6163 0.2284
0.9932 1.4596 1.6300
0.9993 1.3482 1.2210
0.6945 0.7995 0.7464
[torch.FloatTensor of size 5x3]
Addition: syntax 2
print(torch.add(x,y))
Out:
0.0940 0.7706 1.5622
0.1752 0.6163 0.2284
0.9932 1.4596 1.6300
0.9993 1.3482 1.2210
0.6945 0.7995 0.7464
[torch.FloatTensor of size 5x3]
Addition: providing an output tensor as argument
result=torch.Tensor(5,3)
torch.add(x,y,out=result)
print(result)
Out:
0.0940 0.7706 1.5622
0.1752 0.6163 0.2284
0.9932 1.4596 1.6300
0.9993 1.3482 1.2210
0.6945 0.7995 0.7464
[torch.FloatTensor of size 5x3]
Addition: in-place
# adds x to y
y.add_(x)
print(y)
Out:
0.0940 0.7706 1.5622
0.1752 0.6163 0.2284
0.9932 1.4596 1.6300
0.9993 1.3482 1.2210
0.6945 0.7995 0.7464
[torch.FloatTensor of size 5x3]
Note
Any operation that mutates a tensor in-place is post-fixed with an_. For example:x.copy_(y),x.t_(), will changex.
You can use standard NumPy-like indexing with all bells and whistles!
print(x[:,1])
Out:
0.3477
0.1063
0.9545
0.8519
0.6778
[torch.FloatTensor of size 5]
Resizing: If you want to resize/reshape tensor, you can usetorch.view:
x=torch.randn(4,4)
y = x.view(16)
z = x.view(-1, 8) # the size -1 is inferred from other dimensions
print(x.size(), y.size(), z.size())
Out:
torch.Size([4,4])torch.Size([16])torch.Size([2,8])
Read later:
100+ Tensor operations, including transposing, indexing, slicing, mathematical operations, linear algebra, random numbers, etc., are described here.
NumPy Bridge
Converting a Torch Tensor to a NumPy array or converting a NumPy array to a Torch Tensor is easy.
The Torch Tensor and NumPy array will share their underlying memory locations, and changing one will change the other.
Converting a Torch Tensor to a NumPy Array
a=torch.ones(5)
print(a)
Out:
1
1
1
1
1
[torch.FloatTensor of size 5]
b=a.numpy()
print(b)
Out:
[1.1.1.1.1.]
See how the numpy array changed in value.
a.add_(1)
print(a)
print(b)
Out:
2
2
2
2
2
[torch.FloatTensor of size 5]
[2. 2. 2. 2. 2.]
Converting NumPy Array to Torch Tensor
See how changing the np array changed the Torch Tensor automatically
import numpy as np
a = np.ones(5)
b = torch.from_numpy(a)
np.add(a, 1, out=a)
print(a)
print(b)
Out:
[2.2.2.2.2.]
2
2
2
2
2
[torch.DoubleTensor of size 5]
All the Tensors on the CPU except a CharTensor support converting to NumPy and back.
CUDA Tensors
Tensors can be moved onto GPU with using the.cudamethod.
# let us run this cell only if CUDA is available
if torch.cuda.is_available():
x = x.cuda()
y = y.cuda()
x + y
Total running time of the script: ( 0 minutes 0.071 seconds)