

In [1]:

    
%matplotlib inline

What is PyTorch?

It’s a Python based scientific computing package targeted at two sets of audiences:

A replacement for numpy to use the power of GPUs
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.



In [2]:

    
from __future__ import print_function
import torch

Construct a 5x3 matrix, uninitialized:



In [3]:

    
x = torch.Tensor(5, 3)
print(x)









    



1.00000e-10 *
  0.0000  4.6566  0.0000
  4.6566  0.0000  0.0000
  0.0000  4.6566  0.0000
  4.6566  0.0000  4.6566
  0.0000  0.0000  0.0000
[torch.FloatTensor of size 5x3]

Construct a randomly initialized matrix



In [4]:

    
x = torch.rand(5, 3)
print(x)









    



 0.5836  0.9306  0.4883
 0.4927  0.6504  0.7656
 0.6796  0.5058  0.4498
 0.4805  0.8398  0.3648
 0.1439  0.2373  0.8640
[torch.FloatTensor of size 5x3]

Get its size



In [5]:

    
print(x.size())









    



torch.Size([5, 3])

Note

``torch.Size`` is in fact a tuple, so it supports the same operations

Operations ^^^^^^^^^^ There are multiple syntaxes for operations. Let's see addition as an example

Addition: syntax 1



In [6]:

    
y = torch.rand(5, 3)
print(x + y)









    



 0.6433  1.6999  1.3145
 0.7993  0.9306  1.6244
 1.1707  1.3203  0.9556
 0.6730  1.0785  0.6450
 0.2143  0.7599  1.1299
[torch.FloatTensor of size 5x3]

Addition: syntax 2



In [7]:

    
print(torch.add(x, y))









    



 0.6433  1.6999  1.3145
 0.7993  0.9306  1.6244
 1.1707  1.3203  0.9556
 0.6730  1.0785  0.6450
 0.2143  0.7599  1.1299
[torch.FloatTensor of size 5x3]

Addition: giving an output tensor



In [8]:

    
result = torch.Tensor(5, 3)
torch.add(x, y, out=result)
print(result)









    



 0.6433  1.6999  1.3145
 0.7993  0.9306  1.6244
 1.1707  1.3203  0.9556
 0.6730  1.0785  0.6450
 0.2143  0.7599  1.1299
[torch.FloatTensor of size 5x3]

Addition: in-place



In [9]:

    
# adds x to y
y.add_(x)
print(y)









    



 0.6433  1.6999  1.3145
 0.7993  0.9306  1.6244
 1.1707  1.3203  0.9556
 0.6730  1.0785  0.6450
 0.2143  0.7599  1.1299
[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 change ``x``.

You can use standard numpy-like indexing with all bells and whistles!



In [10]:

    
print(x[:, 1])









    



 0.9306
 0.6504
 0.5058
 0.8398
 0.2373
[torch.FloatTensor of size 5]

Read later:

100+ Tensor operations, including transposing, indexing, slicing, mathematical operations, linear algebra, random numbers, etc are described here <http://pytorch.org/docs/torch>_

Numpy Bridge

Converting a torch Tensor to a numpy array and vice versa is a breeze.

The torch Tensor and numpy array will share their underlying memory locations, and changing one will change the other.

Converting torch Tensor to numpy Array ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^



In [11]:

    
a = torch.ones(5)
print(a)









    



 1
 1
 1
 1
 1
[torch.FloatTensor of size 5]



In [12]:

    
b = a.numpy()
print(b)









    



[ 1.  1.  1.  1.  1.]

See how the numpy array changed in value.



In [13]:

    
a.add_(1)
print(a)
print(b)









    



 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



In [14]:

    
import numpy as np
a = np.ones(5)
b = torch.from_numpy(a)
np.add(a, 1, out=a)
print(a)
print(b)









    



[ 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 using the .cuda function.



In [15]:

    
# let us run this cell only if CUDA is available
if torch.cuda.is_available():
    x = x.cuda()
    y = y.cuda()
    x + y