torch.nn.ConvTranspose2d vs torch.nn.Upsample

vision
1

What is the difference between ConvTranspose2d and Upsample in Pytorch?
To implement UNet in Pytorch based on the model in this paper for the first upsampling layer some people used

self.upSample1 = nn.Upsample(size=(1024, 1024), scale_factor=(2, 2), mode="bilinear")

        self.up1 = nn.Sequential(
            ConvRelu2d(1024, 512, kernel_size=(3, 3), stride=1, padding=0),
            ConvRelu2d(512, 512, kernel_size=(3, 3), stride=1, padding=0)
        )

while some people used

        self.up = nn.ConvTranspose2d(in_size, out_size, 2, stride=2)
        self.conv = nn.Conv2d(in_size, out_size, kernel_size)
        self.conv2 = nn.Conv2d(out_size, out_size, kernel_size)
        self.activation = F.relu

I am confused is both Upsample and ConvTranspose2d do the same things?

10 Likes