DenseNet transition block from https://github.com/gpleiss/efficient_densenet_pytorch/blob/master/models/densenet.py

dense-net_transition_block.py

class _Transition(nn.Sequential):
    
    def __init__(self, num_input_features, num_output_features):
        
        super(_Transition, self).__init__()
        
        self.add_module('norm', nn.BatchNorm2d(num_input_features))
        self.add_module('relu', nn.ReLU(inplace=True))
        self.add_module('conv', nn.Conv2d(num_input_features, num_output_features,
                                          kernel_size=1, stride=1, bias=False))
        self.add_module('pool', nn.AvgPool2d(kernel_size=2, stride=2))