10 5月

xhy 分类 Pytorch 无评论

PyTorch中的学习率衰减

为什么要学习率衰减🤔 　　PyTorch中的学习率并不总是一成不变的，而是可以随着epoch或者迭代次数的变化阅读更多PyTorch中的学习率衰减[…]

05 9月

xhy 分类 Pytorch、Tensorflow 无评论

TensorFlow与PyTorch：区别及函数习惯的对比

　　TensorFlow与PyTorch的区别在网上有很多的分析，主要可以总结为以下几点：动态与静态　　P阅读更多TensorFlow与PyTorch：区别及函数习惯的对比[…]

04 9月

xhy 分类 AI、Pytorch 无评论

PyTorch – 神经网络

训练神经网络的各个步骤

import torch
import torch.nn as nn
import torch.nn.functional as F

# 定义网络
class Net(nn.Module):

    def __init__(self):
        super(Net, self).__init__()
        # 1 input image channel, 6 output channels, 3x3 square convolution
        # kernel
        self.conv1 = nn.Conv2d(1, 6, 3)
        self.conv2 = nn.Conv2d(6, 16, 3)
        # an affine operation: y = Wx + b
        self.fc1 = nn.Linear(16 * 6 * 6, 120)  # 6*6 from image dimension
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    # 前向传播
    def forward(self, x):
        # Max pooling over a (2, 2) window
        x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
        # If the size is a square you can only specify a single number
        x = F.max_pool2d(F.relu(self.conv2(x)), 2)
        x = x.view(-1, self.num_flat_features(x))
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

    def num_flat_features(self, x):
        size = x.size()[1:]  # all dimensions except the batch dimension
        num_features = 1
        for s in size:
            num_features *= s
        return num_features


net = Net()
print(net)

# 显示参数的个数 
params = list(net.parameters())
print(len(params))
print(params[0].size())  # conv1's .weight

# 正向传播
input = torch.randn(1, 1, 32, 32)
out = net(input)
print(out)

# 损失函数
output = net(input)
target = torch.randn(10)  # a dummy target, for example
target = target.view(1, -1)  # make it the same shape as output
criterion = nn.MSELoss()

loss = criterion(output, target)
print(loss)

# 反向传播
net.zero_grad()     # zeroes the gradient buffers of all parameters
loss.backward()

'''
更新权重
weight = weight - learning_rate * gradient
'''
learning_rate = 0.01
for f in net.parameters():
    f.data.sub_(f.grad.data * learning_rate)

# 使用优化器
import torch.optim as optim

# create your optimizer
optimizer = optim.SGD(net.parameters(), lr=0.01)

# in your training loop:
optimizer.zero_grad()   # zero the gradient buffers
output = net(input)
loss = criterion(output, target)
loss.backward()
optimizer.step()    # Does the update

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

61

62

63

64

65

66

67

68

69

70

71

72

73

74

75

76

77

78

79

80

81

82

83

84

85

import torch

import torch.nn as nn

import torch.nn.functional as F

# 定义网络

class Net(nn.Module):

def __init__(self):

super(Net, self).__init__()

# 1 input image channel, 6 output channels, 3x3 square convolution

# kernel

self.conv1 = nn.Conv2d(1, 6, 3)

self.conv2 = nn.Conv2d(6, 16, 3)

# an affine operation: y = Wx + b

self.fc1 = nn.Linear(16 * 6 * 6, 120) # 6*6 from image dimension

self.fc2 = nn.Linear(120, 84)

self.fc3 = nn.Linear(84, 10)

# 前向传播

def forward(self, x):

# Max pooling over a (2, 2) window

x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))

# If the size is a square you can only specify a single number

x = F.max_pool2d(F.relu(self.conv2(x)), 2)

x = x.view(-1, self.num_flat_features(x))

x = F.relu(self.fc1(x))

x = F.relu(self.fc2(x))

x = self.fc3(x)

return x

def num_flat_features(self, x):

size = x.size()[1:] # all dimensions except the batch dimension

num_features = 1

for s in size:

num_features *= s

return num_features

net = Net()

print(net)

# 显示参数的个数

params = list(net.parameters())

print(len(params))

print(params[0].size()) # conv1's .weight

# 正向传播

input = torch.randn(1, 1, 32, 32)

out = net(input)

print(out)

# 损失函数

output = net(input)

target = torch.randn(10) # a dummy target, for example

target = target.view(1, -1) # make it the same shape as output

criterion = nn.MSELoss()

loss = criterion(output, target)

print(loss)

# 反向传播

net.zero_grad() # zeroes the gradient buffers of all parameters

loss.backward()

'''

更新权重

weight = weight - learning_rate * gradient

'''

learning_rate = 0.01

for f in net.parameters():

f.data.sub_(f.grad.data * learning_rate)

# 使用优化器

import torch.optim as optim

# create your optimizer

optimizer = optim.SGD(net.parameters(), lr=0.01)

# in your training loop:

optimizer.zero_grad() # zero the gradient buffers

output = net(input)

loss = criterion(output, target)

loss.backward()

optimizer.step() # Does the update

识别MNIST的一个阅读更多PyTorch – 神经网络[…]

04 9月

xhy 分类 AI、Pytorch 无评论

PyTorch – Autograd库的使用

自动求梯度

import torch
from torch.autograd import Variable

N, D = 3, 4

x = Variable(torch.randn(N, D)),
         requires_grad=True)
y = Variable(torch.randn(N, D)),
         requires_grad=True)
z = Variable(torch.randn(N, D)),
         requires_grad=True)

a = x * y
b = a + z
c = torch.sum(b)

c.backward()

print(x.grad.data)  # 求梯度
print(y.grad.data)
print(z.grad.data)

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

import torch

from torch.autograd import Variable

N, D = 3, 4

x = Variable(torch.randn(N, D)),

requires_grad=True)

y = Variable(torch.randn(N, D)),

requires_grad=True)

z = Variable(torch.randn(N, D)),

requires_grad=True)

a = x * y

b = a + z

c = torch.sum(b)

c.backward()

print(x.grad.data) # 求梯度

print(y.grad.data)

print(z.grad.data)

03 9月

xhy 分类 AI、Pytorch 1 评论

PyTorch – 安装和入门

安装PyTorch 官网的安装方式 https://pytorch.org/get-started/local阅读更多PyTorch – 安装和入门[…]

X.YU

分类：Pytorch

PyTorch中的学习率衰减

TensorFlow与PyTorch：区别及函数习惯的对比

PyTorch – 神经网络

PyTorch – Autograd库的使用

PyTorch – 安装和入门