add small snippet for architectures

[talhaanwarch]

I am checking DynUNet and i am confused what values should I used for kernel_size, strides and upsample_kernel_size . can you add a small snippet with random values going on model and initialize model and output the shape.
For example in case of unet , the snippet would be like

x=torch.randn((1,1,96,96,96))
model = UNet(
                      dimensions=3,
                      in_channels=1,
                      out_channels=5,
                      channels=(16, 32, 64, 128, 256),
                      strides=(2, 2, 2, 2),
                      num_res_units=2,
                      norm=Norm.BATCH,
                  )
out=model(x)
out.shape

[talhaanwarch]

@Nic-Ma

[Nic-Ma]

Hi @talhaanwarch ,

You can take a look at the unit tests of DynUNet, it has rich examples for different inputs and args and outputs:
https://github.com/Project-MONAI/MONAI/blob/dev/tests/test_dynunet.py

Thanks.