-
Notifications
You must be signed in to change notification settings - Fork 0
/
cnn.py
84 lines (68 loc) · 2.36 KB
/
cnn.py
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
import torch
import torch.nn as nn
import torch.nn.functional as F
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
# 1 input image channel, 6 output channels, 5x5 square convolution
# kernel
self.conv1 = nn.Conv2d(1, 6, (5, 5))
self.conv2 = nn.Conv2d(6, 16, (5, 5))
# an affine operation: y = Wx + b
self.fc1 = nn.Linear(16 * 5 * 5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
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 specify with a single number
x = F.max_pool2d(F.relu(self.conv2(x)), 2)
x = torch.flatten(x, 1) # flatten all dimensions except the batch dimension
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
net = Net()
print(net)
params = list(net.parameters())
print(len(params))
print('params[0].size()', params[0].size()) # conv1's .weight
input = torch.randn(1, 1, 32, 32)
print('input', input)
out = net(input)
print('out', out)
# 使用随机梯度将所有参数和反向传播的梯度缓冲区归零
net.zero_grad()
print('torch.randn(1, 10)', torch.randn(1, 10))
out.backward(torch.randn(1, 10))
output = net(input)
print('output', output)
target = torch.randn(10) # a dummy target, for example
target = target.view(1, -1) # make it the same shape as output
print('target', target)
criterion = nn.MSELoss()
loss = criterion(output, target)
print('loss', loss)
print('loss.grad_fn', loss.grad_fn) # MSELoss
print(loss.grad_fn.next_functions[0][0]) # Linear
print(loss.grad_fn.next_functions[0][0].next_functions[0][0]) # ReLU
net.zero_grad() # zeroes the gradient buffers of all parameters
print('conv1.bias.grad before backward')
print(net.conv1.bias.grad)
loss.backward()
print('conv1.bias.grad after backward')
print(net.conv1.bias.grad)
# 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)
import torch.optim as optim
# create your optimizer
optimizer = optim.SGD(net.parameters(), lr=0.01)
# in your traning loop:
optimizer.zero_grad() # zero the gradient buffers
output = net(input)
loss = criterion(output, target)
loss.backward()
optimizer.step()