Bottleneck block for ResNeXt. If style is "pytorch", the stride-two layer is the 3x3 conv layer, if it is "caffe", the stride-two layer is the first 1x1 conv layer.
(self,
inplanes,
planes,
groups=1,
base_width=4,
base_channels=64,
**kwargs)
source not stored for this graph (policy: none)
nothing calls this directly
no test coverage detected