Fully Convolutional Networks for Semantic Segmentation

最新推荐文章于 2022-01-01 18:55:40 发布

seamanj

最新推荐文章于 2022-01-01 18:55:40 发布

阅读量489

点赞数

分类专栏： deep learning pytorch paper

本文链接：https://blog.csdn.net/seamanj/article/details/90709566

版权

paper 同时被 3 个专栏收录

106 篇文章 1 订阅

订阅专栏

deep learning

40 篇文章 0 订阅

订阅专栏

pytorch

29 篇文章 0 订阅

订阅专栏

在这里插入图片描述

具体实现代码见:https://github.com/wkentaro/pytorch-fcn/blob/master/torchfcn/models/fcn16s.py

class FCN16s(nn.Module):

    pretrained_model = \
        osp.expanduser('~/data/models/pytorch/fcn16s_from_caffe.pth')

    @classmethod
    def download(cls):
        return fcn.data.cached_download(
            url='http://drive.google.com/uc?id=0B9P1L--7Wd2vVGE3TkRMbWlNRms',
            path=cls.pretrained_model,
            md5='991ea45d30d632a01e5ec48002cac617',
        )

    def __init__(self, n_class=21):
        super(FCN16s, self).__init__()
        # conv1
        self.conv1_1 = nn.Conv2d(3, 64, 3, padding=100)
        self.relu1_1 = nn.ReLU(inplace=True)
        self.conv1_2 = nn.Conv2d(64, 64, 3, padding=1)
        self.relu1_2 = nn.ReLU(inplace=True)
        self.pool1 = nn.MaxPool2d(2, stride=2, ceil_mode=True)  # 1/2

        # conv2
        self.conv2_1 = nn.Conv2d(64, 128, 3, padding=1)
        self.relu2_1 = nn.ReLU(inplace=True)
        self.conv2_2 = nn.Conv2d(128, 128, 3, padding=1)
        self.relu2_2 = nn.ReLU(inplace=True)
        self.pool2 = nn.MaxPool2d(2, stride=2, ceil_mode=True)  # 1/4

        # conv3
        self.conv3_1 = nn.Conv2d(128, 256, 3, padding=1)
        self.relu3_1 = nn.ReLU(inplace=True)
        self.conv3_2 = nn.Conv2d(256, 256, 3, padding=1)
        self.relu3_2 = nn.ReLU(inplace=True)
        self.conv3_3 = nn.Conv2d(256, 256, 3, padding=1)
        self.relu3_3 = nn.ReLU(inplace=True)
        self.pool3 = nn.MaxPool2d(2, stride=2, ceil_mode=True)  # 1/8

        # conv4
        self.conv4_1 = nn.Conv2d(256, 512, 3, padding=1)
        self.relu4_1 = nn.ReLU(inplace=True)
        self.conv4_2 = nn.Conv2d(512, 512, 3, padding=1)
        self.relu4_2 = nn.ReLU(inplace=True)
        self.conv4_3 = nn.Conv2d(512, 512, 3, padding=1)
        self.relu4_3 = nn.ReLU(inplace=True)
        self.pool4 = nn.MaxPool2d(2, stride=2, ceil_mode=True)  # 1/16

        # conv5
        self.conv5_1 = nn.Conv2d(512, 512, 3, padding=1)
        self.relu5_1 = nn.ReLU(inplace=True)
        self.conv5_2 = nn.Conv2d(512, 512, 3, padding=1)
        self.relu5_2 = nn.ReLU(inplace=True)
        self.conv5_3 = nn.Conv2d(512, 512, 3, padding=1)
        self.relu5_3 = nn.ReLU(inplace=True)
        self.pool5 = nn.MaxPool2d(2, stride=2, ceil_mode=True)  # 1/32

        # fc6
        self.fc6 = nn.Conv2d(512, 4096, 7)
        self.relu6 = nn.ReLU(inplace=True)
        self.drop6 = nn.Dropout2d()

        # fc7
        self.fc7 = nn.Conv2d(4096, 4096, 1)
        self.relu7 = nn.ReLU(inplace=True)
        self.drop7 = nn.Dropout2d()

        self.score_fr = nn.Conv2d(4096, n_class, 1)
        self.score_pool4 = nn.Conv2d(512, n_class, 1)

        self.upscore2 = nn.ConvTranspose2d(
            n_class, n_class, 4, stride=2, bias=False)
        self.upscore16 = nn.ConvTranspose2d(
            n_class, n_class, 32, stride=16, bias=False)

        self._initialize_weights()