代码如下，U我认为对于新手来说最重要的是学会rnn读取数据的格式。
|
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
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
|
# -*- coding: utf-8 -*-"""Created on Tue Oct 9 08:53:25 2018@author: www""" import syssys.path.append('..') import torchimport datetimefrom torch.autograd import Variablefrom torch import nnfrom torch.utils.data import DataLoader from torchvision import transforms as tfsfrom torchvision.datasets import MNIST #定义数据data_tf = tfs.Compose([ tfs.ToTensor(), tfs.Normalize([0.5], [0.5])])train_set = MNIST('E:/data', train=True, transform=data_tf, download=True)test_set = MNIST('E:/data', train=False, transform=data_tf, download=True) train_data = DataLoader(train_set, 64, True, num_workers=4)test_data = DataLoader(test_set, 128, False, num_workers=4) #定义模型class rnn_classify(nn.Module): def __init__(self, in_feature=28, hidden_feature=100, num_class=10, num_layers=2): super(rnn_classify, self).__init__() self.classifier = nn.Linear(hidden_feature, num_class)#将最后一个的rnn使用全连接的到最后的输出结果 def forward(self, x): #x的大小为（batch，1，28,28），所以我们需要将其转化为rnn的输入格式（28，batch，28） x = x.squeeze() #去掉（batch，1,28,28）中的1，变成（batch， 28,28） x = x.permute(2, 0, 1)#将最后一维放到第一维，变成（batch，28,28） out, _ = self.rnn(x) #使用默认的隐藏状态，得到的out是（28， batch， hidden_feature） out = out[-1,:,:]#取序列中的最后一个，大小是（batch， hidden_feature) out = self.classifier(out) #得到分类结果 return out net = rnn_classify()criterion = nn.CrossEntropyLoss()optimizer = torch.optim.Adadelta(net.parameters(), 1e-1) #定义训练过程def get_acc(output, label): total = output.shape[0] _, pred_label = output.max(1) num_correct = (pred_label == label).sum().item() return num_correct / total def train(net, train_data, valid_data, num_epochs, optimizer, criterion): if torch.cuda.is_available(): net = net.cuda() prev_time = datetime.datetime.now() for epoch in range(num_epochs): train_loss = 0 train_acc = 0 net = net.train() for im, label in train_data: if torch.cuda.is_available(): im = Variable(im.cuda()) # (bs, 3, h, w) label = Variable(label.cuda()) # (bs, h, w) else: im = Variable(im) label = Variable(label) # forward output = net(im) loss = criterion(output, label) # backward optimizer.zero_grad() loss.backward() optimizer.step() train_loss += loss.item() train_acc += get_acc(output, label) cur_time = datetime.datetime.now() h, remainder = divmod((cur_time - prev_time).seconds, 3600) m, s = divmod(remainder, 60) time_str = "Time %02d:%02d:%02d" % (h, m, s) if valid_data is not None: valid_loss = 0 valid_acc = 0 net = net.eval() for im, label in valid_data: if torch.cuda.is_available(): im = Variable(im.cuda()) label = Variable(label.cuda()) else: im = Variable(im) label = Variable(label) output = net(im) loss = criterion(output, label) valid_loss += loss.item() valid_acc += get_acc(output, label) epoch_str = ( "Epoch %d. Train Loss: %f, Train Acc: %f, Valid Loss: %f, Valid Acc: %f, " % (epoch, train_loss / len(train_data), train_acc / len(train_data), valid_loss / len(valid_data), valid_acc / len(valid_data))) else: epoch_str = ("Epoch %d. Train Loss: %f, Train Acc: %f, " % (epoch, train_loss / len(train_data), train_acc / len(train_data))) prev_time = cur_time print(epoch_str + time_str) train(net, train_data, test_data, 10, optimizer, criterion) |
以上这篇pytorch 利用lstm做mnist手写数字识别分类的实例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/xckkcxxck/article/details/82978942
