fcn32s.py 文件源码

def __init__(self, num_classes, pretrained=True):
        super(FCN32VGG, self).__init__()
        vgg = models.vgg16()
        if pretrained:
            vgg.load_state_dict(torch.load(vgg16_caffe_path))
        features, classifier = list(vgg.features.children()), list(vgg.classifier.children())

        features[0].padding = (100, 100)

        for f in features:
            if 'MaxPool' in f.__class__.__name__:
                f.ceil_mode = True
            elif 'ReLU' in f.__class__.__name__:
                f.inplace = True

        self.features5 = nn.Sequential(*features)

        fc6 = nn.Conv2d(512, 4096, kernel_size=7)
        fc6.weight.data.copy_(classifier[0].weight.data.view(4096, 512, 7, 7))
        fc6.bias.data.copy_(classifier[0].bias.data)
        fc7 = nn.Conv2d(4096, 4096, kernel_size=1)
        fc7.weight.data.copy_(classifier[3].weight.data.view(4096, 4096, 1, 1))
        fc7.bias.data.copy_(classifier[3].bias.data)
        score_fr = nn.Conv2d(4096, num_classes, kernel_size=1)
        score_fr.weight.data.zero_()
        score_fr.bias.data.zero_()
        self.score_fr = nn.Sequential(
            fc6, nn.ReLU(inplace=True), nn.Dropout(), fc7, nn.ReLU(inplace=True), nn.Dropout(), score_fr
        )

        self.upscore = nn.ConvTranspose2d(num_classes, num_classes, kernel_size=64, stride=32, bias=False)
        self.upscore.weight.data.copy_(get_upsampling_weight(num_classes, num_classes, 64))