如何摆脱棋盘文物

各位编码员大家好，

我正在使用完全卷积的自动编码器为黑白图像着色，但是，输出具有棋盘格图案，我想摆脱它。到目前为止，我所看到的棋盘状工件都比我的小得多，而摆脱它们的通常方法是用双线性上采样代替所有解池操作（有人告诉我）。

但是我不能简单地替换unpooling操作，因为我使用不同大小的图像，因此需要unpooling操作，否则输出张量的大小可能会与原始张量不同。

TLDR：

如何在不替换分拆操作的情况下消除这些棋盘工件？

class AE(nn.Module):
    def __init__(self):
        super(AE, self).__init__()
        self.leaky_reLU = nn.LeakyReLU(0.2)
        self.pool = nn.MaxPool2d(kernel_size=2, stride=2, padding=1, return_indices=True)
        self.unpool = nn.MaxUnpool2d(kernel_size=2, stride=2, padding=1)
        self.softmax = nn.Softmax2d()

        self.conv1 = nn.Conv2d(in_channels=3, out_channels=64, kernel_size=3, stride=1, padding=1)
        self.conv2 = nn.Conv2d(in_channels=64, out_channels=128, kernel_size=3, stride=1, padding=1)
        self.conv3 = nn.Conv2d(in_channels=128, out_channels=256, kernel_size=3, stride=1, padding=1)
        self.conv4 = nn.Conv2d(in_channels=256, out_channels=512, kernel_size=3, stride=1, padding=1)
        self.conv5 = nn.Conv2d(in_channels=512, out_channels=1024, kernel_size=3, stride=1, padding=1)
        self.conv6 = nn.ConvTranspose2d(in_channels=1024, out_channels=512, kernel_size=3, stride=1, padding=1)
        self.conv7 = nn.ConvTranspose2d(in_channels=512, out_channels=256, kernel_size=3, stride=1, padding=1)
        self.conv8 = nn.ConvTranspose2d(in_channels=256, out_channels=128, kernel_size=3, stride=1, padding=1)
        self.conv9 = nn.ConvTranspose2d(in_channels=128, out_channels=64, kernel_size=3, stride=1, padding=1)
        self.conv10 = nn.ConvTranspose2d(in_channels=64, out_channels=2, kernel_size=3, stride=1, padding=1)

    def forward(self, x):

        # encoder
        x = self.conv1(x)
        x = self.leaky_reLU(x)
        size1 = x.size()
        x, indices1 = self.pool(x)

        x = self.conv2(x)
        x = self.leaky_reLU(x)
        size2 = x.size()
        x, indices2 = self.pool(x)

        x = self.conv3(x)
        x = self.leaky_reLU(x)
        size3 = x.size()
        x, indices3 = self.pool(x)

        x = self.conv4(x)
        x = self.leaky_reLU(x)
        size4 = x.size()
        x, indices4 = self.pool(x)

        ######################
        x = self.conv5(x)
        x = self.leaky_reLU(x)

        x = self.conv6(x)
        x = self.leaky_reLU(x)
        ######################

        # decoder
        x = self.unpool(x, indices4, output_size=size4)
        x = self.conv7(x)
        x = self.leaky_reLU(x)

        x = self.unpool(x, indices3, output_size=size3)
        x = self.conv8(x)
        x = self.leaky_reLU(x)

        x = self.unpool(x, indices2, output_size=size2)
        x = self.conv9(x)
        x = self.leaky_reLU(x)

        x = self.unpool(x, indices1, output_size=size1)
        x = self.conv10(x)
        x = self.softmax(x)

        return x

。

编辑-解决方案：

跳过连接是必经之路！

class AE(nn.Module):
    def __init__(self):
        super(AE, self).__init__()
        self.leaky_reLU = nn.LeakyReLU(0.2)
        self.pool = nn.MaxPool2d(kernel_size=2, stride=2, padding=1, return_indices=True)
        self.unpool = nn.MaxUnpool2d(kernel_size=2, stride=2, padding=1)
        self.softmax = nn.Softmax2d()

        self.conv1 = nn.Conv2d(in_channels=3, out_channels=64, kernel_size=3, stride=1, padding=1)
        self.conv2 = nn.Conv2d(in_channels=64, out_channels=128, kernel_size=3, stride=1, padding=1)
        self.conv3 = nn.Conv2d(in_channels=128, out_channels=256, kernel_size=3, stride=1, padding=1)
        self.conv4 = nn.Conv2d(in_channels=256, out_channels=512, kernel_size=3, stride=1, padding=1)
        self.conv5 = nn.Conv2d(in_channels=512, out_channels=1024, kernel_size=3, stride=1, padding=1)
        self.conv6 = nn.Conv2d(in_channels=1024, out_channels=512, kernel_size=3, stride=1, padding=1)
        self.conv7 = nn.Conv2d(in_channels=1024, out_channels=256, kernel_size=3, stride=1, padding=1)
        self.conv8 = nn.Conv2d(in_channels=512, out_channels=128, kernel_size=3, stride=1, padding=1)
        self.conv9 = nn.Conv2d(in_channels=256, out_channels=64, kernel_size=3, stride=1, padding=1)
        self.conv10 = nn.Conv2d(in_channels=128, out_channels=2, kernel_size=3, stride=1, padding=1)

    def forward(self, x):

        # encoder
        x = self.conv1(x)
        out1 = self.leaky_reLU(x)
        x = out1
        size1 = x.size()
        x, indices1 = self.pool(x)

        x = self.conv2(x)
        out2 = self.leaky_reLU(x)
        x = out2
        size2 = x.size()
        x, indices2 = self.pool(x)

        x = self.conv3(x)
        out3 = self.leaky_reLU(x)
        x = out3
        size3 = x.size()
        x, indices3 = self.pool(x)

        x = self.conv4(x)
        out4 = self.leaky_reLU(x)
        x = out4
        size4 = x.size()
        x, indices4 = self.pool(x)

        ######################
        x = self.conv5(x)
        x = self.leaky_reLU(x)

        x = self.conv6(x)
        x = self.leaky_reLU(x)
        ######################

        # decoder
        x = self.unpool(x, indices4, output_size=size4)
        x = self.conv7(torch.cat((x, out4), 1))
        x = self.leaky_reLU(x)

        x = self.unpool(x, indices3, output_size=size3)
        x = self.conv8(torch.cat((x, out3), 1))
        x = self.leaky_reLU(x)

        x = self.unpool(x, indices2, output_size=size2)
        x = self.conv9(torch.cat((x, out2), 1))
        x = self.leaky_reLU(x)

        x = self.unpool(x, indices1, output_size=size1)
        x = self.conv10(torch.cat((x, out1), 1))
        x = self.softmax(x)

        return x