def __init__()

in models/densenet_efficient_multi_gpu.py [0:0]

• 26 lines of code
• 3 McCabe index (conditional complexity)

    def __init__(self, growth_rate=12, block_config=(16, 16, 16), compression=0.5,
                 num_init_features=24, bn_size=4, drop_rate=0., avgpool_size=8,
                 num_classes=10):

        super(DenseNetEfficientMulti, self).__init__()
        assert 0 < compression <= 1, 'compression of densenet should be between '
        self.avgpool_size = avgpool_size

        # First convolution
        self.features = nn.Sequential(OrderedDict([
            ('conv0', nn.Conv2d(3, num_init_features, kernel_size=3, stride=1, padding=1, bias=False)),
        ]))

        # Each dense block
        storage = create_multi_gpu_storage()
        num_features = num_init_features
        for i, num_layers in enumerate(block_config):
            block = _DenseBlock(num_layers=num_layers,
                                num_input_features=num_features,
                                bn_size=bn_size, growth_rate=growth_rate,
                                drop_rate=drop_rate, storage=storage)
            self.features.add_module('denseblock_%d' % (i + 1), block)
            num_features = num_features + num_layers * growth_rate
            if i != len(block_config) - 1:
                trans = TransitionBlock(in_planes=num_features,
                                    out_planes=int(num_features * compression),
                                        dropRate=drop_rate)
                self.features.add_module('transition_%d' % (i + 1), trans)
                num_features = int(num_features * compression)

        # Final batch norm
        self.features.add_module('norm_final', nn.BatchNorm2d(num_features))

        # Linear layer
        self.classifier = nn.Linear(num_features, num_classes)