What to learn PyTorch?
Some people always choose, choose the most people's frame, to use as their beginner's frame, such asTensorflow, but most of the papers' implementations are based on thePyTorchIf we want to go into the details of the thesis, we must choose to learn the introductoryPyTorch
Installing PyTorch
One line of command.official website
pip install torch===1.6.0 torchvision===0.7.0 - /whl/torch_stable.html
It's taking a while. Be patient.
Test yourself to see if the installation was successful
Run the command test
import torch x = (5,3) print(x)
exports
tensor([[0.5096, 0.1209, 0.7721],
[0.9486, 0.8676, 0.2157],
[0.0586, 0.3467, 0.5015],
[0.9470, 0.5654, 0.9317],
[0.2127, 0.2386, 0.0629]])
Start learning PyTorch
Creation without initializationtensor (math.)
import torch x = ([5,5]) print(x)
exports
tensor([[0., 0., 0.],
[0., 0., 0.],
[0., 0., 0.],
[0., 0., 0.],
[0., 0., 0.]])
Randomly create a 0-1tensor (math.)
import torch x = (5,5) print(x)
exports
tensor([[0.3369, 0.5339, 0.8419, 0.6857, 0.6241],
[0.4991, 0.1691, 0.8356, 0.4574, 0.0395],
[0.9714, 0.2975, 0.9322, 0.5213, 0.8509],
[0.3037, 0.8690, 0.3481, 0.2538, 0.9513],
[0.0156, 0.9516, 0.3674, 0.1831, 0.6466]])
Creates an all-zerotensor (math.)
import torch x = (5,5, dtype=torch.float32) print(x)
The creation can be done with thedtypeSpecify the data type
exports
tensor([[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.],
[0., 0., 0., 0., 0.]])
Use the data to directly createtensor (math.)
import torch x = ([5,5], dtype=torch.float32) print(x)
exports
tensor([5., 5.])
Using the originaltensorCreate a newtensor
import torch x = ([5,5], dtype=torch.float32) x = x.new_zeros(5, 3) y = torch.rand_like(x) print(x) print(y)
exports
tensor([[0., 0., 0.],
[0., 0., 0.],
[0., 0., 0.],
[0., 0., 0.],
[0., 0., 0.]])
tensor([[0.5552, 0.3333, 0.0426],
[0.3861, 0.3945, 0.6658],
[0.6978, 0.3508, 0.4813],
[0.8193, 0.2274, 0.8384],
[0.9360, 0.9226, 0.1453]])
heedtensorThe dimensional information of the
x = (3,3) ()
exports
([3, 3])
Some simple arithmetic
x = ([1]) y = ([3]) ''' Mode 1 ''' z = x + y ''' Mode 2 ''' z = (x, y) ''' Mode 3 ''' result = (1) # No initialization of data (x, y, out=result) # Return the results to result ''' Mode 4 ''' x.add_(y)
exports
tensor([4])
indexing operation
x = (5,5) x[:,:] x[1,:] x[:,1] x[1,1]
Separate outputs
tensor([[0.4012, 0.2604, 0.1720, 0.0996, 0.7806],
[0.8734, 0.9087, 0.4828, 0.3543, 0.2375],
[0.0924, 0.9040, 0.4408, 0.9758, 0.2250],
[0.7179, 0.7244, 0.6165, 0.1142, 0.7363],
[0.8504, 0.0391, 0.0753, 0.4530, 0.7372]])
tensor([0.8734, 0.9087, 0.4828, 0.3543, 0.2375])
tensor([0.2604, 0.9087, 0.9040, 0.7244, 0.0391])
tensor(0.9087)
(math.) a dimensional transformation
x = (4,4) (16) (8,2) (-1,8)
Separate outputs
tensor([0.9277, 0.9547, 0.9487, 0.9841, 0.4114, 0.1693, 0.8691, 0.3954, 0.4679,
0.7914, 0.7456, 0.0522, 0.0043, 0.2097, 0.5932, 0.9797])
tensor([[0.9277, 0.9547],
[0.9487, 0.9841],
[0.4114, 0.1693],
[0.8691, 0.3954],
[0.4679, 0.7914],
[0.7456, 0.0522],
[0.0043, 0.2097],
[0.5932, 0.9797]])
tensor([[0.9277, 0.9547, 0.9487, 0.9841, 0.4114, 0.1693, 0.8691, 0.3954],
[0.4679, 0.7914, 0.7456, 0.0522, 0.0043, 0.2097, 0.5932, 0.9797]])
Note: The number of dimensionally transformed data must be consistent.
This article on PyTorch installation and basic use of the article is introduced to this, more related to the installation and use of PyTorch content, please search for my previous articles or continue to browse the following related articles I hope you will support me in the future!