ResNext optimized for the ImageNet dataset, as specified in https://arxiv.org/pdf/1611.05431.pdf

Set the learning rate of each parameter group using a cosine annealing schedule, where :math:`\eta_{max}` is set to the initial lr and :math:`

Base class for bottlenecks that implements `forward()` method.

RexNeXt bottleneck type C

Bottleneck for SENet154.

ResNeXt bottleneck type C with a Squeeze-and-Excitation module.

ResNet bottleneck with a Squeeze-and-Excitation module. It follows Caffe implementation and uses `stride=stride` in `conv1` and not in `conv2