Unet implemented by pytorch

vision
1

It is also possible to put a test image of different size into unet model which was trained by 640 * 640image.
Why is that?

this is codes(github:https://github.com/milesial/Pytorch-UNet)

class UNet(nn.Module):
    def __init__(self, n_channels, n_classes):
        super(UNet, self).__init__()
        self.inc = inconv(n_channels, 64)
        self.down1 = down(64, 128)
        self.down2 = down(128, 256)
        self.down3 = down(256, 512)
        self.down4 = down(512, 512)
        self.up1 = up(1024, 256)
        self.up2 = up(512, 128)
        self.up3 = up(256, 64)
        self.up4 = up(128, 64)
        self.outc = outconv(64, n_classes)

def forward(self, x):
    x1 = self.inc(x)
    x2 = self.down1(x1)
    x3 = self.down2(x2)
    x4 = self.down3(x3)
    x5 = self.down4(x4)
    x = self.up1(x5, x4)
    x = self.up2(x, x3)
    x = self.up3(x, x2)
    x = self.up4(x, x1)
    x = self.outc(x)
    return F.sigmoid(x)

…

class double_conv(nn.Module):
    '''(conv => BN => ReLU) * 2'''
    def __init__(self, in_ch, out_ch):
        super(double_conv, self).__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(in_ch, out_ch, 3, padding=1),
            nn.BatchNorm2d(out_ch),
            nn.ReLU(inplace=True),
            nn.Conv2d(out_ch, out_ch, 3, padding=1),
            nn.BatchNorm2d(out_ch),
            nn.ReLU(inplace=True)
        )

    def forward(self, x):
        x = self.conv(x)
        return x


class inconv(nn.Module):
    def __init__(self, in_ch, out_ch):
        super(inconv, self).__init__()
        self.conv = double_conv(in_ch, out_ch)

    def forward(self, x):
        x = self.conv(x)
        return x

...

so i found this

  • This architecture(UNET) is input image size agnostic since it does not contain fully connected layers (!);

However, when I look at the code, I use the Conv2d function provided by the existing pytorch, and I guess this function is fully-connected. I do not know how it works with different image sizes.