参考自https://github.com/titu1994/DenseNet/blob/master/densenet.py
先来一张图，便于理解网络结构，推荐的dense_block一般是3。两个dense_block之间的就是过渡层。每个dense_block内部都使用密集连接。
Conv_block:
卷积操作，按照论文的说法，这里应该是一个组合函数，分别为：BatchNormalization、ReLU和3x3 Conv。
def conv_block(ip, nb_filter, bottleneck=False, dropout_rate=None, weight_decay=1e-4):
''' Apply BatchNorm, Relu, 3x3 Conv2D, optional bottleneck block and dropout
Args:
ip: Input keras tensor
nb_filter: number of filters
bottleneck: add bottleneck block
dropout_rate: dropout rate
weight_decay: weight decay factor
Returns: keras tensor with batch_norm, relu and convolution2d added (optional bottleneck)
'''
concat_axis = 1 if K.image_data_format() == 'channel_first' else -1
x = BatchNormalization(axis=concat_axis, epsilon=1.1e-5)(ip)
x = Activation('relu')(x)
if bottleneck:
inter_channel = nb_filter * 4
x = Conv2D(inter_channel, (1, 1), kernel_initializer='he_normal', padding='same', use_bias=False,
kernel_regularizer=l2(weight_decay))(x)
x = BatchNormalization(axis=concat_axis, epsilon=1.1e-5)(x)
x = Activation('relu')(x)
x = Conv2D(nb_filter, (3, 3), kernel_initializer='he_normal', padding='same', use_bias=False)(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
return x
其中的concat_axis表示特征轴，因为连接和BN都是对特征轴而言的。bottleneck表示是否使用瓶颈层，也就是使用1x1的卷继层将特征图的通道数进行压缩。
Transition_block:
过渡层，用来连接两个dense_block。同时在最后一个dense_block的尾部不需要使用过渡层。按照论文的说法，过渡层由四部分组成：BatchNormalization、ReLU、1x1Conv和2x2Maxpooling。
def transition_block(ip, nb_filter, compression=1.0, weight_decay=1e-4):
'''Apply BatchNorm, ReLU, Conv2d, optional compressoin, dropout and Maxpooling2D
Args:
ip: keras tensor
nb_filter: number of filters
compression: caculated as 1 - reduction. Reduces the number of features maps in the transition block
dropout_rate: dropout rate
weight_decay: weight decay factor
Returns:
keras tensor, after applying batch_norm, relu-conv, dropout, maxpool
'''
concat_axis = 1 if K.image_data_format() == 'channels_first' else -1
x = BatchNormalization(axis=concat_axis, epsilon=1.1e-5)(ip)
x = Activation('relu')(x)
x = Conv2D(int(nb_filter * compression), (1, 1), kernel_initializer='he_normal', padding='same', use_bias=False,
kernel_regularizer=l2(weight_decay))(x)
x = AveragePooling2D((2, 2), strides=(2, 2))(x)
return x
其中的Conv2D操作实现了1x1的卷积操作，同时使用了compression_rate，也就是论文中说的压缩率，将通道数进行调整。
Dense_block:
此处使用循环实现了dense_block的密集连接。
def dense_block(x, nb_layers, nb_filter, growth_rate, bottleneck=False, dropout_rate=None, weight_decay=1e-4,
grow_nb_filters=True, return_concat_list=False):
'''Build a dense_block where the output of ench conv_block is fed t subsequent ones
Args:
x: keras tensor
nb_layser: the number of layers of conv_block to append to the model
nb_filter: number of filters
growth_rate: growth rate
bottleneck: bottleneck block
dropout_rate: dropout rate
weight_decay: weight decay factor
grow_nb_filters: flag to decide to allow number of filters to grow
return_concat_list: return the list of feature maps along with the actual output
Returns:
keras tensor with nb_layers of conv_block appened
'''
concat_axis = 1 if K.image_data_format() == 'channels_first' else -1
x_list = [x]
for i in range(nb_layers):
cb = conv_block(x, growth_rate, bottleneck, dropout_rate, weight_decay)
x_list.append(cb)
x = concatenate([x, cb], axis=concat_axis)
if grow_nb_filters:
nb_filter += growth_rate
if return_concat_list:
return x, nb_filter, x_list
else:
return x, nb_filter
其中的x = concatenate([x, cb], axis=concat_axis)操作使得x在每次循环中始终维护一个全局状态，第一次循环输入为x，输出为cb1，第二的输入为cb=[x, cb1]，输出为cb2，第三次的输入为cb=[x, cb1, cb2]，输出为cb3，以此类推。增长率growth_rate其实就是每次卷积时使用的卷积核个数，也就是最后输出的通道数。
Create_dense_net:
构建网络模型：
def create_dense_net(nb_classes, img_input, include_top, depth=40, nb_dense_block=3, growth_rate=12, nb_filter=-1,
nb_layers_per_block=[1], bottleneck=False, reduction=0.0, dropout_rate=None, weight_decay=1e-4,
subsample_initial_block=False, activation='softmax'):
''' Build the DenseNet model
Args:
nb_classes: number of classes
img_input: tuple of shape (channels, rows, columns) or (rows, columns, channels)
include_top: flag to include the final Dense layer
depth: number or layers
nb_dense_block: number of dense blocks to add to end (generally = 3)
growth_rate: number of filters to add per dense block
nb_filter: initial number of filters. Default -1 indicates initial number of filters is 2 * growth_rate
nb_layers_per_block: list, number of layers in each dense block
bottleneck: add bottleneck blocks
reduction: reduction factor of transition blocks. Note : reduction value is inverted to compute compression
dropout_rate: dropout rate
weight_decay: weight decay rate
subsample_initial_block: Set to True to subsample the initial convolution and
add a MaxPool2D before the dense blocks are added.
subsample_initial:
activation: Type of activation at the top layer. Can be one of 'softmax' or 'sigmoid'.
Note that if sigmoid is used, classes must be 1.
Returns: keras tensor with nb_layers of conv_block appended
'''
concat_axis = 1 if K.image_data_format() == 'channel_first' else -1
if type(nb_layers_per_block) is not list:
print('nb_layers_per_block should be a list!!!')
return 0
final_nb_layer = nb_layers_per_block[-1]
nb_layers = nb_layers_per_block[:-1]
if nb_filter <= 0:
nb_filter = 2 * growth_rate
compression = 1.0 - reduction
if subsample_initial_block:
initial_kernel = (7, 7)
initial_strides = (2, 2)
else:
initial_kernel = (3, 3)
initial_strides = (1, 1)
x = Conv2D(nb_filter, initial_kernel, kernel_initializer='he_normal', padding='same',
strides=initial_strides, use_bias=False, kernel_regularizer=l2(weight_decay))(img_input)
if subsample_initial_block:
x = BatchNormalization(axis=concat_axis, epsilon=1.1e-5)(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x)
for block_index in range(nb_dense_block - 1):
x, nb_filter = dense_block(x, nb_layers[block_index], nb_filter, growth_rate, bottleneck=bottleneck,
dropout_rate=dropout_rate, weight_decay=weight_decay)
x = transition_block(x, nb_filter, compression=compression, weight_decay=weight_decay)
nb_filter = int(nb_filter * compression)
# 最后一个block没有transition_block
x, nb_filter = dense_block(x, final_nb_layer, nb_filter, growth_rate, bottleneck=bottleneck,
dropout_rate=dropout_rate, weight_decay=weight_decay)
x = BatchNormalization(axis=concat_axis, epsilon=1.1e-5)(x)
x = Activation('relu')(x)
x = GlobalAveragePooling2D()(x)
if include_top:
x = Dense(nb_classes, activation=activation)(x)
return x
生成Model：
inputs = Input(tensor=img_input, shape=input_shape)
x = create_dense_net(classes=1000, img_input, include_top=True, depth=169, nb_dense_block=4,
growth_rate=32, nb_filter=64, nb_layers_per_block=[6, 12, 32, 32], bottleneck=True, reduction=0.5,
dropout_rate=0.0, weight_decay=1e-4, subsample_initial_blockTrue, activation='softmax')
model = Model(inputs, x, name='densenet169')