先用最简单的三层全连接神经网络,然后添加激活层查看实验结果,最后加上批标准化验证是否有效
首先根据已有的模板定义网络结构SimpleNet,命名为net.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
|
import torch from torch.autograd import Variable import numpy as np import matplotlib.pyplot as plt from torch import nn,optim from torch.utils.data import DataLoader from torchvision import datasets,transforms #定义三层全连接神经网络 class simpleNet(nn.Module): def __init__( self ,in_dim,n_hidden_1,n_hidden_2,out_dim): #输入维度,第一层的神经元个数、第二层的神经元个数,以及第三层的神经元个数 super (simpleNet, self ).__init__() self .layer1 = nn.Linear(in_dim,n_hidden_1) self .layer2 = nn.Linear(n_hidden_1,n_hidden_2) self .layer3 = nn.Linear(n_hidden_2,out_dim) def forward( self ,x): x = self .layer1(x) x = self .layer2(x) x = self .layer3(x) return x #添加激活函数 class Activation_Net(nn.Module): def __init__( self ,in_dim,n_hidden_1,n_hidden_2,out_dim): super (NeutalNetwork, self ).__init__() self .layer1 = nn.Sequential( #Sequential组合结构 nn.Linear(in_dim,n_hidden_1),nn.ReLU( True )) self .layer2 = nn.Sequential( nn.Linear(n_hidden_1,n_hidden_2),nn.ReLU( True )) self .layer3 = nn.Sequential( nn.Linear(n_hidden_2,out_dim)) def forward( self ,x): x = self .layer1(x) x = self .layer2(x) x = self .layer3(x) return x #添加批标准化处理模块,皮标准化放在全连接的后面,非线性的前面 class Batch_Net(nn.Module): def _init__( self ,in_dim,n_hidden_1,n_hidden_2,out_dim): super (Batch_net, self ).__init__() self .layer1 = nn.Sequential(nn.Linear(in_dim,n_hidden_1),nn.BatchNormld(n_hidden_1),nn.ReLU( True )) self .layer2 = nn.Sequential(nn.Linear(n_hidden_1,n_hidden_2),nn.BatchNormld(n_hidden_2),nn.ReLU( True )) self .layer3 = nn.Sequential(nn.Linear(n_hidden_2,out_dim)) def forword( self ,x): x = self .layer1(x) x = self .layer2(x) x = self .layer3(x) return x |
训练网络,
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
|
import torch from torch.autograd import Variable import numpy as np import matplotlib.pyplot as plt % matplotlib inline from torch import nn,optim from torch.utils.data import DataLoader from torchvision import datasets,transforms #定义一些超参数 import net batch_size = 64 learning_rate = 1e - 2 num_epoches = 20 #预处理 data_tf = transforms.Compose( [transforms.ToTensor(),transforms.Normalize([ 0.5 ],[ 0.5 ])]) #将图像转化成tensor,然后继续标准化,就是减均值,除以方差 #读取数据集 train_dataset = datasets.MNIST(root = './data' ,train = True ,transform = data_tf,download = True ) test_dataset = datasets.MNIST(root = './data' ,train = False ,transform = data_tf) #使用内置的函数导入数据集 train_loader = DataLoader(train_dataset,batch_size = batch_size,shuffle = True ) test_loader = DataLoader(test_dataset,batch_size = batch_size,shuffle = False ) #导入网络,定义损失函数和优化方法 model = net.simpleNet( 28 * 28 , 300 , 100 , 10 ) if torch.cuda.is_available(): #是否使用cuda加速 model = model.cuda() criterion = nn.CrossEntropyLoss() optimizer = optim.SGD(model.parameters(),lr = learning_rate) import net n_epochs = 5 for epoch in range (n_epochs): running_loss = 0.0 running_correct = 0 print ( "epoch {}/{}" . format (epoch,n_epochs)) print ( "-" * 10 ) for data in train_loader: img,label = data img = img.view(img.size( 0 ), - 1 ) if torch.cuda.is_available(): img = img.cuda() label = label.cuda() else : img = Variable(img) label = Variable(label) out = model(img) #得到前向传播的结果 loss = criterion(out,label) #得到损失函数 print_loss = loss.data.item() optimizer.zero_grad() #归0梯度 loss.backward() #反向传播 optimizer.step() #优化 running_loss + = loss.item() epoch + = 1 if epoch % 50 = = 0 : print ( 'epoch:{},loss:{:.4f}' . format (epoch,loss.data.item())) |
训练的结果截图如下:
测试网络
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
|
#测试网络 model. eval () #将模型变成测试模式 eval_loss = 0 eval_acc = 0 for data in test_loader: img,label = data img = img.view(img.size( 0 ), - 1 ) #测试集不需要反向传播,所以可以在前项传播的时候释放内存,节约内存空间 if torch.cuda.is_available(): img = Variable(img,volatile = True ).cuda() label = Variable(label,volatile = True ).cuda() else : img = Variable(img,volatile = True ) label = Variable(label,volatile = True ) out = model(img) loss = criterion(out,label) eval_loss + = loss.item() * label.size( 0 ) _,pred = torch. max (out, 1 ) num_correct = (pred = = label). sum () eval_acc + = num_correct.item() print ( 'test loss:{:.6f},ac:{:.6f}' . format (eval_loss / ( len (test_dataset)),eval_acc / ( len (test_dataset)))) |
训练的时候,还可以加入一些dropout,正则化,修改隐藏层神经元的个数,增加隐藏层数,可以自己添加。
以上这篇pytorch三层全连接层实现手写字母识别方式就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持服务器之家。
原文链接:https://blog.csdn.net/yychentracy/article/details/89787507