Assert image resolution has to be divisible by 32 for resnet

[bkowshik]

With this fix, getting predictions with overlap % 32 != 0 will result in the following assertion.

Traceback (most recent call last):
  File "/usr/lib/python3.5/runpy.py", line 184, in _run_module_as_main
    "__main__", mod_spec)
  File "/usr/lib/python3.5/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/app/robosat/robosat/tools/__main__.py", line 57, in <module>
    args.func(args)
  File "/app/robosat/robosat/tools/predict.py", line 82, in main
    outputs = net(images)
  File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/module.py", line 491, in __call__
    result = self.forward(*input, **kwargs)
  File "/usr/local/lib/python3.5/dist-packages/torch/nn/parallel/data_parallel.py", line 112, in forward
    return self.module(*inputs[0], **kwargs[0])
  File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/module.py", line 491, in __call__
    result = self.forward(*input, **kwargs)
  File "/app/robosat/robosat/unet.py", line 120, in forward
    assert size[-1] % 32 == 0 and size[-2] % 32 == 0, "image resolution has to be divisible by 32 for resnet"
AssertionError: image resolution has to be divisible by 32 for resnet

@daniel-j-h how do you want to get a similar fix to #75

[daniel-j-h]

👍 looks good!

You can merge this into master, then checkout the branch for #75 and do the same there for the fpn (you can then also rebase against master).