File size: 4,745 Bytes
7734d5b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
import torch
import torch.nn as nn
import torch.nn.functional as F
import numpy as np
import cv2
import logging
import torchvision.transforms as transforms


class BasicBlock(nn.Module):
    def __init__(self, c_in, c_out, is_downsample=False):
        super(BasicBlock, self).__init__()
        self.is_downsample = is_downsample
        if is_downsample:
            self.conv1 = nn.Conv2d(
                c_in, c_out, 3, stride=2, padding=1, bias=False)
        else:
            self.conv1 = nn.Conv2d(
                c_in, c_out, 3, stride=1, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(c_out)
        self.relu = nn.ReLU(True)
        self.conv2 = nn.Conv2d(c_out, c_out, 3, stride=1,
                               padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(c_out)
        if is_downsample:
            self.downsample = nn.Sequential(
                nn.Conv2d(c_in, c_out, 1, stride=2, bias=False),
                nn.BatchNorm2d(c_out)
            )
        elif c_in != c_out:
            self.downsample = nn.Sequential(
                nn.Conv2d(c_in, c_out, 1, stride=1, bias=False),
                nn.BatchNorm2d(c_out)
            )
            self.is_downsample = True

    def forward(self, x):
        y = self.conv1(x)
        y = self.bn1(y)
        y = self.relu(y)
        y = self.conv2(y)
        y = self.bn2(y)
        if self.is_downsample:
            x = self.downsample(x)
        return F.relu(x.add(y), True)


def make_layers(c_in, c_out, repeat_times, is_downsample=False):
    blocks = []
    for i in range(repeat_times):
        if i == 0:
            blocks += [BasicBlock(c_in, c_out, is_downsample=is_downsample), ]
        else:
            blocks += [BasicBlock(c_out, c_out), ]
    return nn.Sequential(*blocks)


class Net(nn.Module):
    def __init__(self, num_classes=751, reid=False):
        super(Net, self).__init__()
        # 3 128 64
        self.conv = nn.Sequential(
            nn.Conv2d(3, 64, 3, stride=1, padding=1),
            nn.BatchNorm2d(64),
            nn.ReLU(inplace=True),
            # nn.Conv2d(32,32,3,stride=1,padding=1),
            # nn.BatchNorm2d(32),
            # nn.ReLU(inplace=True),
            nn.MaxPool2d(3, 2, padding=1),
        )
        # 32 64 32
        self.layer1 = make_layers(64, 64, 2, False)
        # 32 64 32
        self.layer2 = make_layers(64, 128, 2, True)
        # 64 32 16
        self.layer3 = make_layers(128, 256, 2, True)
        # 128 16 8
        self.layer4 = make_layers(256, 512, 2, True)
        # 256 8 4
        self.avgpool = nn.AvgPool2d((8, 4), 1)
        # 256 1 1
        self.reid = reid
        self.classifier = nn.Sequential(
            nn.Linear(512, 256),
            nn.BatchNorm1d(256),
            nn.ReLU(inplace=True),
            nn.Dropout(),
            nn.Linear(256, num_classes),
        )

    def forward(self, x):
        x = self.conv(x)
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        # B x 128
        if self.reid:
            x = x.div(x.norm(p=2, dim=1, keepdim=True))
            return x
        # classifier
        x = self.classifier(x)
        return x


class Extractor(object):
    def __init__(self, model_path, use_cuda=True):
        self.net = Net(reid=True)
        self.device = "cuda" if torch.cuda.is_available() and use_cuda else "cpu"
        state_dict = torch.load(model_path, map_location=torch.device(self.device))[
            'net_dict']
        self.net.load_state_dict(state_dict)
        logger = logging.getLogger("root.tracker")
        logger.info("Loading weights from {}... Done!".format(model_path))
        self.net.to(self.device)
        self.size = (64, 128)
        self.norm = transforms.Compose([
            transforms.ToTensor(),
            transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
        ])

    def _preprocess(self, im_crops):
        """
        TODO:
            1. to float with scale from 0 to 1
            2. resize to (64, 128) as Market1501 dataset did
            3. concatenate to a numpy array
            3. to torch Tensor
            4. normalize
        """
        def _resize(im, size):
            return cv2.resize(im.astype(np.float32)/255., size)

        im_batch = torch.cat([self.norm(_resize(im, self.size)).unsqueeze(
            0) for im in im_crops], dim=0).float()
        return im_batch

    def __call__(self, im_crops):
        im_batch = self._preprocess(im_crops)
        with torch.no_grad():
            im_batch = im_batch.to(self.device)
            features = self.net(im_batch)
        return features.cpu().numpy()