Function denseblock_altern

DenseNet/densenet.py:102–128

Build a denseblock where the output of each conv_factory is fed to subsequent ones. (Alternative of a above) :param x: keras model :param concat_axis: int -- index of contatenate axis :param nb_layers: int -- the number of layers of conv_ factory to append t

(x, concat_axis, nb_layers, nb_filter, growth_rate,
                      dropout_rate=None, weight_decay=1E-4)

def denseblock_altern(x, concat_axis, nb_layers, nb_filter, growth_rate,
                      dropout_rate=None, weight_decay=1E-4):
    """Build a denseblock where the output of each conv_factory
       is fed to subsequent ones. (Alternative of a above)

    :param x: keras model
    :param concat_axis: int -- index of contatenate axis
    :param nb_layers: int -- the number of layers of conv_
                      factory to append to the model.
    :param nb_filter: int -- number of filters
    :param dropout_rate: int -- dropout rate
    :param weight_decay: int -- weight decay factor

    :returns: keras model with nb_layers of conv_factory appended
    :rtype: keras model

    * The main difference between this implementation and the implementation
    above is that the one above
    """

    for i in range(nb_layers):
        merge_tensor = conv_factory(x, concat_axis, growth_rate,
                                    dropout_rate, weight_decay)
        x = Concatenate(axis=concat_axis)([merge_tensor, x])
        nb_filter += growth_rate

    return x, nb_filter


def DenseNet(nb_classes, img_dim, depth, nb_dense_block, growth_rate,