a small bug in resnet model _make_layer() implementation

Hi guys,

I think there is a small bug in the "_make_layer(self, block, planes, blocks, stride=1)" function (in charge of generating residual blocks at certain resolution) in the ResNet model. This function will just simply discard the odd number of rows and columns in the feature maps in the identity path at the first residual block in a resolution stage when the stride=2 (the case where feature maps get downsampled by 2).

def _make_layer(self, block, planes, blocks, stride=1):
    downsample = None
    if stride != 1 or self.inplanes != planes * block.expansion:
        downsample = nn.Sequential(
            #this 1x1 conv with stride 2 will simply discard the odd number of rows and columns in the feature maps in the identity path
            conv1x1(self.inplanes, planes * block.expansion, stride), 
            nn.BatchNorm2d(planes * block.expansion),
        )

Please let me know what do you think.

Start at the ResNet _make_layer(self, block, planes, blocks, stride=1) entry point and inspect the stride-2 downsample path shown in the report. Reproduce the behavior with feature maps having odd dimensions, then determine the intended identity-path alignment and add a regression test; the issue does not specify the expected correction.