Notebook

In [ ]:

%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 [ ]:

from__future__importprint_functionimporttorch

Construct a 5x3 matrix, uninitialized:

In [ ]:

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

Construct a randomly initialized matrix

In [ ]:

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

Get its size

In [ ]:

print(x.size())

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 [ ]:

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

Addition: syntax 2

In [ ]:

print(torch.add(x,y))

Addition: giving an output tensor

In [ ]:

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

Addition: in-place

In [ ]:

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

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 [ ]:

print(x[:,1])

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 [ ]:

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

In [ ]:

b=a.numpy()print(b)

See how the numpy array changed in value.

In [ ]:

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

Converting numpy Array to torch Tensor ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ See how changing the np array changed the torch Tensor automatically

In [ ]:

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

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 [ ]:

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