这里的网络架构和论文中插图中的网络架构是相一致的。
对了，忘了说了，这里使用的keras版本是1.2.2，等源码读完之后，我自己改一个2.0.6版本上传到github上面。
可别直接粘贴复制，里面有些中文的解释，不一定可行的。
#defint input shape
input_shape = (300,300,3)
#defint the number of classes
num_classes = 21
#Here the network is wrapped in to a dictory because it more easy to make some operations.
net = {}
# Block 1
input_tensor = Input(shape=input_shape)
#defint the image hight and wight
img_size = (input_shape[1], input_shape[0])
net['input'] = input_tensor
net['conv1_1'] = Convolution2D(64, 3, 3,
activation='relu',
border_mode='same',
name='conv1_1')(net['input'])
net['conv1_2'] = Convolution2D(64, 3, 3,
activation='relu',
border_mode='same',
name='conv1_2')(net['conv1_1'])
net['pool1'] = MaxPooling2D((2, 2), strides=(2, 2), border_mode='same',
name='pool1')(net['conv1_2'])
# Block 2
net['conv2_1'] = Convolution2D(128, 3, 3,
activation='relu',
border_mode='same',
name='conv2_1')(net['pool1'])
net['conv2_2'] = Convolution2D(128, 3, 3,
activation='relu',
border_mode='same',
name='conv2_2')(net['conv2_1'])
net['pool2'] = MaxPooling2D((2, 2), strides=(2, 2), border_mode='same',
name='pool2')(net['conv2_2'])
# Block 3
net['conv3_1'] = Convolution2D(256, 3, 3,
activation='relu',
border_mode='same',
name='conv3_1')(net['pool2'])
net['conv3_2'] = Convolution2D(256, 3, 3,
activation='relu',
border_mode='same',
name='conv3_2')(net['conv3_1'])
net['conv3_3'] = Convolution2D(256, 3, 3,
activation='relu',
border_mode='same',
name='conv3_3')(net['conv3_2'])
net['pool3'] = MaxPooling2D((2, 2), strides=(2, 2), border_mode='same',
name='pool3')(net['conv3_3'])
# Block 4
net['conv4_1'] = Convolution2D(512, 3, 3,
activation='relu',
border_mode='same',
name='conv4_1')(net['pool3'])
net['conv4_2'] = Convolution2D(512, 3, 3,
activation='relu',
border_mode='same',
name='conv4_2')(net['conv4_1'])
#the first layer be operated
net['conv4_3'] = Convolution2D(512, 3, 3,
activation='relu',
border_mode='same',
name='conv4_3')(net['conv4_2'])
net['pool4'] = MaxPooling2D((2, 2), strides=(2, 2), border_mode='same',
name='pool4')(net['conv4_3'])
# Block 5
net['conv5_1'] = Convolution2D(512, 3, 3,
activation='relu',
border_mode='same',
name='conv5_1')(net['pool4'])
net['conv5_2'] = Convolution2D(512, 3, 3,
activation='relu',
border_mode='same',
name='conv5_2')(net['conv5_1'])
net['conv5_3'] = Convolution2D(512, 3, 3,
activation='relu',
border_mode='same',
name='conv5_3')(net['conv5_2'])
net['pool5'] = MaxPooling2D((3, 3), strides=(1, 1), border_mode='same',
name='pool5')(net['conv5_3'])
#here is the FC6 in the orginal VGG16 Network，There move to Atrous Convolution for the reason i don't know.
# FC6
net['fc6'] = AtrousConvolution2D(1024, 3, 3, atrous_rate=(6, 6),
activation='relu', border_mode='same',
name='fc6')(net['pool5'])
#the second layer to be operated
# FC7
net['fc7'] = Convolution2D(1024, 1, 1, activation='relu',
border_mode='same', name='fc7')(net['fc6'])
# x = Dropout(0.5, name='drop7')(x)
# Block 6
net['conv6_1'] = Convolution2D(256, 1, 1, activation='relu',
border_mode='same',
name='conv6_1')(net['fc7'])
#the third layer to be opreated
net['conv6_2'] = Convolution2D(512, 3, 3, subsample=(2, 2),
activation='relu', border_mode='same',
name='conv6_2')(net['conv6_1'])
# Block 7
net['conv7_1'] = Convolution2D(128, 1, 1, activation='relu',
border_mode='same',
name='conv7_1')(net['conv6_2'])
net['conv7_2'] = ZeroPadding2D()(net['conv7_1'])
#the forth layer to be operated
net['conv7_2'] = Convolution2D(256, 3, 3, subsample=(2, 2),
activation='relu', border_mode='valid',
name='conv7_2')(net['conv7_2'])
# Block 8
net['conv8_1'] = Convolution2D(128, 1, 1, activation='relu',
border_mode='same',
name='conv8_1')(net['conv7_2'])
#the fifth layer to be operated
net['conv8_2'] = Convolution2D(256, 3, 3, subsample=(2, 2),
activation='relu', border_mode='same',
name='conv8_2')(net['conv8_1'])
# the last layer to be operated
# Last Pool
net['pool6'] = GlobalAveragePooling2D(name='pool6')(net['conv8_2'])
# Prediction from conv4_3
# net['conv4_3']._shape = (?, 38, 38, 512)
# 算了还是说中文吧，这个层是用来对输入数据进行正则化的层，有参数需要学习，输出的数据形式和输入输入形式是一致的。
net['conv4_3_norm'] = Normalize(20, name='conv4_3_norm')(net['conv4_3'])
num_priors = 3
#here is *4 because the box need 4 number to define，here is only predice the box coordinate
x = Convolution2D(num_priors * 4, 3, 3, border_mode='same',
name='conv4_3_norm_mbox_loc')(net['conv4_3_norm'])
net['conv4_3_norm_mbox_loc'] = x
flatten = Flatten(name='conv4_3_norm_mbox_loc_flat')
net['conv4_3_norm_mbox_loc_flat'] = flatten(net['conv4_3_norm_mbox_loc'])
#the box coordinate is finished now it will perdice the classes
name = 'conv4_3_norm_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
# here is start predict the classes
x = Convolution2D(num_priors * num_classes, 3, 3, border_mode='same',
name=name)(net['conv4_3_norm'])
net['conv4_3_norm_mbox_conf'] = x
flatten = Flatten(name='conv4_3_norm_mbox_conf_flat')
net['conv4_3_norm_mbox_conf_flat'] = flatten(net['conv4_3_norm_mbox_conf'])
#这里是用来对conv4_3层的feature map生成论文中所说的default box，对没错，就是直接使用Feature map来进行default box的生成
#当然这里要指定一些参数，这些参数是需要好好斟酌的。
priorbox = PriorBox(img_size, 30.0, aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv4_3_norm_mbox_priorbox')
net['conv4_3_norm_mbox_priorbox'] = priorbox(net['conv4_3_norm'])
#好了，到这里第一个层的操作就完成了，下面其他层的操作都是相类似的啦。
# Prediction from fc7
num_priors = 6
net['fc7_mbox_loc'] = Convolution2D(num_priors * 4, 3, 3,
border_mode='same',
name='fc7_mbox_loc')(net['fc7'])
flatten = Flatten(name='fc7_mbox_loc_flat')
net['fc7_mbox_loc_flat'] = flatten(net['fc7_mbox_loc'])
name = 'fc7_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
net['fc7_mbox_conf'] = Convolution2D(num_priors * num_classes, 3, 3,
border_mode='same',
name=name)(net['fc7'])
flatten = Flatten(name='fc7_mbox_conf_flat')
net['fc7_mbox_conf_flat'] = flatten(net['fc7_mbox_conf'])
priorbox = PriorBox(img_size, 60.0, max_size=114.0, aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='fc7_mbox_priorbox')
net['fc7_mbox_priorbox'] = priorbox(net['fc7'])
# Prediction from conv6_2
num_priors = 6
x = Convolution2D(num_priors * 4, 3, 3, border_mode='same',
name='conv6_2_mbox_loc')(net['conv6_2'])
net['conv6_2_mbox_loc'] = x
flatten = Flatten(name='conv6_2_mbox_loc_flat')
net['conv6_2_mbox_loc_flat'] = flatten(net['conv6_2_mbox_loc'])
name = 'conv6_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes, 3, 3, border_mode='same',
name=name)(net['conv6_2'])
net['conv6_2_mbox_conf'] = x
flatten = Flatten(name='conv6_2_mbox_conf_flat')
net['conv6_2_mbox_conf_flat'] = flatten(net['conv6_2_mbox_conf'])
priorbox = PriorBox(img_size, 114.0, max_size=168.0, aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv6_2_mbox_priorbox')
net['conv6_2_mbox_priorbox'] = priorbox(net['conv6_2'])
# Prediction from conv7_2
num_priors = 6
x = Convolution2D(num_priors * 4, 3, 3, border_mode='same',
name='conv7_2_mbox_loc')(net['conv7_2'])
net['conv7_2_mbox_loc'] = x
flatten = Flatten(name='conv7_2_mbox_loc_flat')
net['conv7_2_mbox_loc_flat'] = flatten(net['conv7_2_mbox_loc'])
name = 'conv7_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes, 3, 3, border_mode='same',
name=name)(net['conv7_2'])
net['conv7_2_mbox_conf'] = x
flatten = Flatten(name='conv7_2_mbox_conf_flat')
net['conv7_2_mbox_conf_flat'] = flatten(net['conv7_2_mbox_conf'])
priorbox = PriorBox(img_size, 168.0, max_size=222.0, aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv7_2_mbox_priorbox')
net['conv7_2_mbox_priorbox'] = priorbox(net['conv7_2'])
# Prediction from conv8_2
num_priors = 6
x = Convolution2D(num_priors * 4, 3, 3, border_mode='same',
name='conv8_2_mbox_loc')(net['conv8_2'])
net['conv8_2_mbox_loc'] = x
flatten = Flatten(name='conv8_2_mbox_loc_flat')
net['conv8_2_mbox_loc_flat'] = flatten(net['conv8_2_mbox_loc'])
name = 'conv8_2_mbox_conf'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Convolution2D(num_priors * num_classes, 3, 3, border_mode='same',
name=name)(net['conv8_2'])
net['conv8_2_mbox_conf'] = x
flatten = Flatten(name='conv8_2_mbox_conf_flat')
net['conv8_2_mbox_conf_flat'] = flatten(net['conv8_2_mbox_conf'])
priorbox = PriorBox(img_size, 222.0, max_size=276.0, aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv8_2_mbox_priorbox')
net['conv8_2_mbox_priorbox'] = priorbox(net['conv8_2'])
# Prediction from pool6
num_priors = 6
x = Dense(num_priors * 4, name='pool6_mbox_loc_flat')(net['pool6'])
net['pool6_mbox_loc_flat'] = x
name = 'pool6_mbox_conf_flat'
if num_classes != 21:
name += '_{}'.format(num_classes)
x = Dense(num_priors * num_classes, name=name)(net['pool6'])
net['pool6_mbox_conf_flat'] = x
priorbox = PriorBox(img_size, 276.0, max_size=330.0, aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='pool6_mbox_priorbox')
#由于这里的维数不对，因此要修改Feature map层对应的维数信息
if K.image_dim_ordering() == 'tf':
target_shape = (1, 1, 256)
else:
target_shape = (256, 1, 1)
net['pool6_reshaped'] = Reshape(target_shape,
name='pool6_reshaped')(net['pool6'])
net['pool6_mbox_priorbox'] = priorbox(net['pool6_reshaped'])
#好啦，到这里位置，所有的信息都已经生成了，下一步就是根据这些信息来进行训练或者是预测了。
# Gather all predictions
net['mbox_loc'] = merge([net['conv4_3_norm_mbox_loc_flat'],
net['fc7_mbox_loc_flat'],
net['conv6_2_mbox_loc_flat'],
net['conv7_2_mbox_loc_flat'],
net['conv8_2_mbox_loc_flat'],
net['pool6_mbox_loc_flat']],
mode='concat', concat_axis=1, name='mbox_loc')
net['mbox_conf'] = merge([net['conv4_3_norm_mbox_conf_flat'],
net['fc7_mbox_conf_flat'],
net['conv6_2_mbox_conf_flat'],
net['conv7_2_mbox_conf_flat'],
net['conv8_2_mbox_conf_flat'],
net['pool6_mbox_conf_flat']],
mode='concat', concat_axis=1, name='mbox_conf')
net['mbox_priorbox'] = merge([net['conv4_3_norm_mbox_priorbox'],
net['fc7_mbox_priorbox'],
net['conv6_2_mbox_priorbox'],
net['conv7_2_mbox_priorbox'],
net['conv8_2_mbox_priorbox'],
net['pool6_mbox_priorbox']],
mode='concat', concat_axis=1,
name='mbox_priorbox')
if hasattr(net['mbox_loc'], '_keras_shape'):
num_boxes = net['mbox_loc']._keras_shape[-1] // 4
elif hasattr(net['mbox_loc'], 'int_shape'):
num_boxes = K.int_shape(net['mbox_loc'])[-1] // 4
net['mbox_loc'] = Reshape((num_boxes, 4),
name='mbox_loc_final')(net['mbox_loc'])
net['mbox_conf'] = Reshape((num_boxes, num_classes),
name='mbox_conf_logits')(net['mbox_conf'])
net['mbox_conf'] = Activation('softmax',
name='mbox_conf_final')(net['mbox_conf'])
net['predictions'] = merge([net['mbox_loc'],
net['mbox_conf'],
net['mbox_priorbox']],
mode='concat', concat_axis=2,
name='predictions')
model = Model(net['input'], net['predictions'])