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.
from __future__ import print_function import torch
Construct a 5x3 matrix, uninitialized:
x = torch.empty(5, 3) print(x)
Out:
tensor([[-5.0254e+18, 4.5609e-41, -5.0254e+18], [ 4.5609e-41, 1.6395e-43, 1.3873e-43], [ 1.4574e-43, 4.4842e-44, 1.4293e-43], [ 1.4714e-43, 1.5134e-43, 1.4153e-43], [ 4.4842e-44, 1.5554e-43, 1.5975e-43]])
Construct a randomly initialized matrix:
x = torch.rand(5, 3) print(x)
Out:
tensor([[0.3380, 0.3845, 0.3217], [0.8337, 0.9050, 0.2650], [0.2979, 0.7141, 0.9069], [0.1449, 0.1132, 0.1375], [0.4675, 0.3947, 0.1426]])
Construct a matrix filled zeros and of dtype long:
x = torch.zeros(5, 3, dtype=torch.long) print(x)
Out:
tensor([[0, 0, 0], [0, 0, 0], [0, 0, 0], [0, 0, 0], [0, 0, 0]])
Construct a tensor directly from data:
x = torch.tensor([5.5, 3]) print(x)
Out:
tensor([5.5000, 3.0000])
or create a tensor based on an existing tensor. These methods will reuse properties of the input tensor, e.g. dtype, unless new values are provided by user
x = x.new_ones(5, 3, dtype=torch.double) # new_* methods take in sizes print(x) x = torch.randn_like(x, dtype=torch.float) # override dtype! print(x) # result has the same size
Out:
tensor([[1., 1., 1.], [1., 1., 1.], [1., 1., 1.], [1., 1., 1.], [1., 1., 1.]], dtype=torch.float64) tensor([[-0.2080, 1.5288, -1.8337], [ 1.3006, 0.9401, -2.4675], [ 0.6897, -0.4666, 2.5578], [ 1.1115, 0.1749, -0.0959], [ 0.7542, -0.2380, 0.0408]])
Get its size:
print(x.size())
Out:
torch.Size([5, 3])
Note
torch.Size
is 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:
tensor([[ 0.7890, 1.9319, -1.2865], [ 1.3956, 1.4262, -2.3513], [ 0.9005, 0.4398, 3.3741], [ 1.4076, 0.3860, -0.0404], [ 0.8079, 0.0838, 0.1361]])
Addition: syntax 2
print(torch.add(x, y))
Out:
tensor([[ 0.7890, 1.9319, -1.2865], [ 1.3956, 1.4262, -2.3513], [ 0.9005, 0.4398, 3.3741], [ 1.4076, 0.3860, -0.0404], [ 0.8079, 0.0838, 0.1361]])
Addition: providing an output tensor as argument
result = torch.empty(5, 3) torch.add(x, y, out=result) print(result)
Out:
tensor([[ 0.7890, 1.9319, -1.2865], [ 1.3956, 1.4262, -2.3513], [ 0.9005, 0.4398, 3.3741], [ 1.4076, 0.3860, -0.0404], [ 0.8079, 0.0838, 0.1361]])
Addition: in-place
# adds x to y y.add_(x) print(y)
Out:
tensor([[ 0.7890, 1.9319, -1.2865], [ 1.3956, 1.4262, -2.3513], [ 0.9005, 0.4398, 3.3741], [ 1.4076, 0.3860, -0.0404], [ 0.8079, 0.0838, 0.1361]])
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!
print(x[:, 1])
Out:
tensor([ 1.5288, 0.9401, -0.4666, 0.1749, -0.2380])
Resizing: If you want to resize/reshape tensor, you can use torch.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])
If you have a one element tensor, use .item()
to get the value as a Python number
x = torch.randn(1) print(x) print(x.item())
Out:
tensor([0.5191]) 0.5191271305084229
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 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 a Torch Tensor to a NumPy Array
a = torch.ones(5) print(a)
Out:
tensor([1., 1., 1., 1., 1.])
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:
tensor([2., 2., 2., 2., 2.]) [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.] tensor([2., 2., 2., 2., 2.], dtype=torch.float64)
All the Tensors on the CPU except a CharTensor support converting to NumPy and back.
CUDA Tensors
Tensors can be moved onto any device using the .to
method.
# let us run this cell only if CUDA is available # We will use ``torch.device`` objects to move tensors in and out of GPU if torch.cuda.is_available(): device = torch.device("cuda") # a CUDA device object y = torch.ones_like(x, device=device) # directly create a tensor on GPU x = x.to(device) # or just use strings ``.to("cuda")`` z = x + y print(z) print(z.to("cpu", torch.double)) # ``.to`` can also change dtype together!
Out:
tensor([1.5191], device='cuda:0') tensor([1.5191], dtype=torch.float64)