master
/ crnn / network_torch.py

network_torch.py @da31108 — raw · history · blame 

 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
import torch.nn as nn
class BidirectionalLSTM(nn.Module):
    
    def __init__(self, nIn, nHidden, nOut):
        super(BidirectionalLSTM, self).__init__()
        self.rnn = nn.LSTM(nIn, nHidden, bidirectional=True)
        self.embedding = nn.Linear(nHidden * 2, nOut)

    def forward(self, input):
        recurrent, _ = self.rnn(input)
        T, b, h = recurrent.size()
        t_rec = recurrent.view(T * b, h)
        output = self.embedding(t_rec)  # [T * b, nOut]
        output = output.view(T, b, -1)
        return output
    


class CRNN(nn.Module):

    def __init__(self, imgH, nc, nclass, nh, n_rnn=2, leakyRelu=False,lstmFlag=True):
        """
        是否加入lstm特征层
        """
        super(CRNN, self).__init__()
        assert imgH % 16 == 0, 'imgH has to be a multiple of 16'

        ks = [3, 3, 3, 3, 3, 3, 2]
        ps = [1, 1, 1, 1, 1, 1, 0]
        ss = [1, 1, 1, 1, 1, 1, 1]
        nm = [64, 128, 256, 256, 512, 512, 512]
        self.lstmFlag = lstmFlag

        cnn = nn.Sequential()

        def convRelu(i, batchNormalization=False):
            nIn = nc if i == 0 else nm[i - 1]
            nOut = nm[i]
            cnn.add_module('conv{0}'.format(i),
                           nn.Conv2d(nIn, nOut, ks[i], ss[i], ps[i]))
            if batchNormalization:
                cnn.add_module('batchnorm{0}'.format(i), nn.BatchNorm2d(nOut))
            if leakyRelu:
                cnn.add_module('relu{0}'.format(i),
                               nn.LeakyReLU(0.2, inplace=True))
            else:
                cnn.add_module('relu{0}'.format(i), nn.ReLU(True))

        convRelu(0)
        cnn.add_module('pooling{0}'.format(0), nn.MaxPool2d(2, 2))  # 64x16x64
        convRelu(1)
        cnn.add_module('pooling{0}'.format(1), nn.MaxPool2d(2, 2))  # 128x8x32
        convRelu(2, True)
        convRelu(3)
        cnn.add_module('pooling{0}'.format(2),
                       nn.MaxPool2d((2, 2), (2, 1), (0, 1)))  # 256x4x16
        convRelu(4, True)
        convRelu(5)
        cnn.add_module('pooling{0}'.format(3),
                       nn.MaxPool2d((2, 2), (2, 1), (0, 1)))  # 512x2x16
        convRelu(6, True)  # 512x1x16
        
        self.cnn = cnn
        if self.lstmFlag:
            self.rnn = nn.Sequential(
                BidirectionalLSTM(512, nh, nh),
                BidirectionalLSTM(nh, nh, nclass))
        else:
            self.linear = nn.Linear(nh*2, nclass)
            

    def forward(self, input):
        # conv features
        conv = self.cnn(input)
        b, c, h, w = conv.size()
        
        assert h == 1, "the height of conv must be 1"
        conv = conv.squeeze(2)
        conv = conv.permute(2, 0, 1)  # [w, b, c]
        if self.lstmFlag:
           # rnn features
           output = self.rnn(conv)
        else:
             T, b, h = conv.size()
             
             t_rec = conv.contiguous().view(T * b, h)
             
             output = self.linear(t_rec)  # [T * b, nOut]
             output = output.view(T, b, -1)
             
             
        return output