參考博文：https://blog.csdn.net/weixin_44791964/article/details/104107271
參考代碼：https://github.com/bubbliiiing/ssd-keras
原理理解
step1 網絡結構部分
模型對應代碼如下：
import keras.backend as K
from keras.layers import Activation
from keras.layers import Conv2D
from keras.layers import Dense
from keras.layers import Flatten
from keras.layers import GlobalAveragePooling2D
from keras.layers import Input
from keras.layers import MaxPooling2D
from keras.layers import merge, concatenate
from keras.layers import Reshape
from keras.layers import ZeroPadding2D
from keras.models import Model
def VGG16(input_tensor):
#----------------------------主幹特徵提取網絡開始---------------------------#
# SSD結構,net字典
net = {}
# Block 1
net['input'] = input_tensor
# 300,300,3 -> 150,150,64
net['conv1_1'] = Conv2D(64, kernel_size=(3,3),
activation='relu',
padding='same',
name='conv1_1')(net['input'])
net['conv1_2'] = Conv2D(64, kernel_size=(3,3),
activation='relu',
padding='same',
name='conv1_2')(net['conv1_1'])
net['pool1'] = MaxPooling2D((2, 2), strides=(2, 2), padding='same',
name='pool1')(net['conv1_2'])
# Block 2
# 150,150,64 -> 75,75,128
net['conv2_1'] = Conv2D(128, kernel_size=(3,3),
activation='relu',
padding='same',
name='conv2_1')(net['pool1'])
net['conv2_2'] = Conv2D(128, kernel_size=(3,3),
activation='relu',
padding='same',
name='conv2_2')(net['conv2_1'])
net['pool2'] = MaxPooling2D((2, 2), strides=(2, 2), padding='same',
name='pool2')(net['conv2_2'])
# Block 3
# 75,75,128 -> 38,38,256
net['conv3_1'] = Conv2D(256, kernel_size=(3,3),
activation='relu',
padding='same',
name='conv3_1')(net['pool2'])
net['conv3_2'] = Conv2D(256, kernel_size=(3,3),
activation='relu',
padding='same',
name='conv3_2')(net['conv3_1'])
net['conv3_3'] = Conv2D(256, kernel_size=(3,3),
activation='relu',
padding='same',
name='conv3_3')(net['conv3_2'])
net['pool3'] = MaxPooling2D((2, 2), strides=(2, 2), padding='same',
name='pool3')(net['conv3_3'])
# Block 4
# 38,38,256 -> 19,19,512
net['conv4_1'] = Conv2D(512, kernel_size=(3,3),
activation='relu',
padding='same',
name='conv4_1')(net['pool3'])
net['conv4_2'] = Conv2D(512, kernel_size=(3,3),
activation='relu',
padding='same',
name='conv4_2')(net['conv4_1'])
net['conv4_3'] = Conv2D(512, kernel_size=(3,3),
activation='relu',
padding='same',
name='conv4_3')(net['conv4_2'])
net['pool4'] = MaxPooling2D((2, 2), strides=(2, 2), padding='same',
name='pool4')(net['conv4_3'])
# Block 5
# 19,19,512 -> 19,19,512
net['conv5_1'] = Conv2D(512, kernel_size=(3,3),
activation='relu',
padding='same',
name='conv5_1')(net['pool4'])
net['conv5_2'] = Conv2D(512, kernel_size=(3,3),
activation='relu',
padding='same',
name='conv5_2')(net['conv5_1'])
net['conv5_3'] = Conv2D(512, kernel_size=(3,3),
activation='relu',
padding='same',
name='conv5_3')(net['conv5_2'])
net['pool5'] = MaxPooling2D((3, 3), strides=(1, 1), padding='same',
name='pool5')(net['conv5_3'])
# FC6
# 19,19,512 -> 19,19,1024
net['fc6'] = Conv2D(1024, kernel_size=(3,3), dilation_rate=(6, 6),
activation='relu', padding='same',
name='fc6')(net['pool5'])
# x = Dropout(0.5, name='drop6')(x)
# FC7
# 19,19,1024 -> 19,19,1024
net['fc7'] = Conv2D(1024, kernel_size=(1,1), activation='relu',
padding='same', name='fc7')(net['fc6'])
# x = Dropout(0.5, name='drop7')(x)
# Block 6
# 19,19,512 -> 10,10,512
net['conv6_1'] = Conv2D(256, kernel_size=(1,1), activation='relu',
padding='same',
name='conv6_1')(net['fc7'])
net['conv6_2'] = ZeroPadding2D(padding=((1, 1), (1, 1)), name='conv6_padding')(net['conv6_1'])
net['conv6_2'] = Conv2D(512, kernel_size=(3,3), strides=(2, 2),
activation='relu',
name='conv6_2')(net['conv6_2'])
# Block 7
# 10,10,512 -> 5,5,256
net['conv7_1'] = Conv2D(128, kernel_size=(1,1), activation='relu',
padding='same',
name='conv7_1')(net['conv6_2'])
net['conv7_2'] = ZeroPadding2D(padding=((1, 1), (1, 1)), name='conv7_padding')(net['conv7_1'])
net['conv7_2'] = Conv2D(256, kernel_size=(3,3), strides=(2, 2),
activation='relu', padding='valid',
name='conv7_2')(net['conv7_2'])
# Block 8
# 5,5,256 -> 3,3,256
net['conv8_1'] = Conv2D(128, kernel_size=(1,1), activation='relu',
padding='same',
name='conv8_1')(net['conv7_2'])
net['conv8_2'] = Conv2D(256, kernel_size=(3,3), strides=(1, 1),
activation='relu', padding='valid',
name='conv8_2')(net['conv8_1'])
# Block 9
# 3,3,256 -> 1,1,256
net['conv9_1'] = Conv2D(128, kernel_size=(1,1), activation='relu',
padding='same',
name='conv9_1')(net['conv8_2'])
net['conv9_2'] = Conv2D(256, kernel_size=(3,3), strides=(1, 1),
activation='relu', padding='valid',
name='conv9_2')(net['conv9_1'])
#----------------------------主幹特徵提取網絡結束---------------------------#
return net
"""
__project_ = 'untitled1'
__file_name__ = 'view_ssd_model'
__author__ = 'TJM'
__time__ = '2020/2/22 16:51'
__product_name = PyCharm
"""
import keras.backend as K
from keras.layers import Activation
# from keras.layers import AtrousConvolution2D
from keras.layers import Conv2D
from keras.layers import Dense
from keras.layers import Flatten
from keras.layers import GlobalAveragePooling2D
from keras.layers import Input
from keras.layers import MaxPooling2D
from keras.layers import merge, concatenate
from keras.layers import Reshape
from keras.layers import ZeroPadding2D
from keras.models import Model
from VGG16 import VGG16
from ssd_layers import Normalize
from ssd_layers import PriorBox
from keras.utils.vis_utils import plot_model
plot = True
def SSD300(input_shape, num_classes=21):
# 300,300,3
input_tensor = Input(shape=input_shape)
img_size = (input_shape[1], input_shape[0])
# SSD結構,net字典
net = VGG16(input_tensor)
# -----------------------將提取到的主幹特徵進行處理---------------------------#
# 對conv4_3進行處理 38,38,512
net['conv4_3_norm'] = Normalize(20, name='conv4_3_norm')(net['conv4_3'])
num_priors = 4
# 預測框的處理
# num_priors表示每個網格點先驗框的數量，4是x,y,h,w的調整
net['conv4_3_norm_mbox_loc'] = Conv2D(num_priors * 4, kernel_size=(3, 3), padding='same',
name='conv4_3_norm_mbox_loc')(net['conv4_3_norm'])
net['conv4_3_norm_mbox_loc_flat'] = Flatten(name='conv4_3_norm_mbox_loc_flat')(net['conv4_3_norm_mbox_loc'])
# num_priors表示每個網格點先驗框的數量，num_classes是所分的類
net['conv4_3_norm_mbox_conf'] = Conv2D(num_priors * num_classes, kernel_size=(3, 3), padding='same',
name='conv4_3_norm_mbox_conf')(net['conv4_3_norm'])
net['conv4_3_norm_mbox_conf_flat'] = Flatten(name='conv4_3_norm_mbox_conf_flat')(net['conv4_3_norm_mbox_conf'])
priorbox = PriorBox(img_size, 30.0, max_size=60.0, 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'])
# 對fc7層進行處理
num_priors = 6
# 預測框的處理
# num_priors表示每個網格點先驗框的數量，4是x,y,h,w的調整
net['fc7_mbox_loc'] = Conv2D(num_priors * 4, kernel_size=(3, 3), padding='same', name='fc7_mbox_loc')(net['fc7'])
net['fc7_mbox_loc_flat'] = Flatten(name='fc7_mbox_loc_flat')(net['fc7_mbox_loc'])
# num_priors表示每個網格點先驗框的數量，num_classes是所分的類
net['fc7_mbox_conf'] = Conv2D(num_priors * num_classes, kernel_size=(3, 3), padding='same', name='fc7_mbox_conf')(
net['fc7'])
net['fc7_mbox_conf_flat'] = Flatten(name='fc7_mbox_conf_flat')(net['fc7_mbox_conf'])
priorbox = PriorBox(img_size, 60.0, max_size=111.0, aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='fc7_mbox_priorbox')
net['fc7_mbox_priorbox'] = priorbox(net['fc7'])
# 對conv6_2進行處理
num_priors = 6
# 預測框的處理
# num_priors表示每個網格點先驗框的數量，4是x,y,h,w的調整
x = Conv2D(num_priors * 4, kernel_size=(3, 3), padding='same', name='conv6_2_mbox_loc')(net['conv6_2'])
net['conv6_2_mbox_loc'] = x
net['conv6_2_mbox_loc_flat'] = Flatten(name='conv6_2_mbox_loc_flat')(net['conv6_2_mbox_loc'])
# num_priors表示每個網格點先驗框的數量，num_classes是所分的類
x = Conv2D(num_priors * num_classes, kernel_size=(3, 3), padding='same', name='conv6_2_mbox_conf')(net['conv6_2'])
net['conv6_2_mbox_conf'] = x
net['conv6_2_mbox_conf_flat'] = Flatten(name='conv6_2_mbox_conf_flat')(net['conv6_2_mbox_conf'])
priorbox = PriorBox(img_size, 111.0, max_size=162.0, 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'])
# 對conv7_2進行處理
num_priors = 6
# 預測框的處理
# num_priors表示每個網格點先驗框的數量，4是x,y,h,w的調整
x = Conv2D(num_priors * 4, kernel_size=(3, 3), padding='same', name='conv7_2_mbox_loc')(net['conv7_2'])
net['conv7_2_mbox_loc'] = x
net['conv7_2_mbox_loc_flat'] = Flatten(name='conv7_2_mbox_loc_flat')(net['conv7_2_mbox_loc'])
# num_priors表示每個網格點先驗框的數量，num_classes是所分的類
x = Conv2D(num_priors * num_classes, kernel_size=(3, 3), padding='same', name='conv7_2_mbox_conf')(net['conv7_2'])
net['conv7_2_mbox_conf'] = x
net['conv7_2_mbox_conf_flat'] = Flatten(name='conv7_2_mbox_conf_flat')(net['conv7_2_mbox_conf'])
priorbox = PriorBox(img_size, 162.0, max_size=213.0, 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'])
# 對conv8_2進行處理
num_priors = 4
# 預測框的處理
# num_priors表示每個網格點先驗框的數量，4是x,y,h,w的調整
x = Conv2D(num_priors * 4, kernel_size=(3, 3), padding='same', name='conv8_2_mbox_loc')(net['conv8_2'])
net['conv8_2_mbox_loc'] = x
net['conv8_2_mbox_loc_flat'] = Flatten(name='conv8_2_mbox_loc_flat')(net['conv8_2_mbox_loc'])
# num_priors表示每個網格點先驗框的數量，num_classes是所分的類
x = Conv2D(num_priors * num_classes, kernel_size=(3, 3), padding='same', name='conv8_2_mbox_conf')(net['conv8_2'])
net['conv8_2_mbox_conf'] = x
net['conv8_2_mbox_conf_flat'] = Flatten(name='conv8_2_mbox_conf_flat')(net['conv8_2_mbox_conf'])
priorbox = PriorBox(img_size, 213.0, max_size=264.0, aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv8_2_mbox_priorbox')
net['conv8_2_mbox_priorbox'] = priorbox(net['conv8_2'])
# 對conv9_2進行處理
num_priors = 4
# 預測框的處理
# num_priors表示每個網格點先驗框的數量，4是x,y,h,w的調整
x = Conv2D(num_priors * 4, kernel_size=(3, 3), padding='same', name='conv9_2_mbox_loc')(net['conv9_2'])
net['conv9_2_mbox_loc'] = x
net['conv9_2_mbox_loc_flat'] = Flatten(name='conv9_2_mbox_loc_flat')(net['conv9_2_mbox_loc'])
# num_priors表示每個網格點先驗框的數量，num_classes是所分的類
x = Conv2D(num_priors * num_classes, kernel_size=(3, 3), padding='same', name='conv9_2_mbox_conf')(net['conv9_2'])
net['conv9_2_mbox_conf'] = x
net['conv9_2_mbox_conf_flat'] = Flatten(name='conv9_2_mbox_conf_flat')(net['conv9_2_mbox_conf'])
priorbox = PriorBox(img_size, 264.0, max_size=315.0, aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv9_2_mbox_priorbox')
net['conv9_2_mbox_priorbox'] = priorbox(net['conv9_2'])
# 將所有結果進行堆疊
net['mbox_loc'] = concatenate([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['conv9_2_mbox_loc_flat']],
axis=1, name='mbox_loc')
net['mbox_conf'] = concatenate([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['conv9_2_mbox_conf_flat']],
axis=1, name='mbox_conf')
net['mbox_priorbox'] = concatenate([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['conv9_2_mbox_priorbox']],
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
# 8732,4
net['mbox_loc'] = Reshape((num_boxes, 4), name='mbox_loc_final')(net['mbox_loc'])
# 8732,21
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'] = concatenate([net['mbox_loc'],
net['mbox_conf'],
net['mbox_priorbox']],
axis=2, name='predictions')
print(net['predictions'])
model = Model(net['input'], net['predictions'])
if plot:
plot_model(model, to_file='SSD_model.png', show_shapes=True)
return model
input_shape = (300, 300, 3)
model = SSD300(input_shape, 2)
打印結構：在以上代碼基礎上加入以下一行代碼
print(model.summary())
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_1 (InputLayer) (None, 300, 300, 3) 0
__________________________________________________________________________________________________
conv1_1 (Conv2D) (None, 300, 300, 64) 1792 input_1[0][0]
__________________________________________________________________________________________________
conv1_2 (Conv2D) (None, 300, 300, 64) 36928 conv1_1[0][0]
__________________________________________________________________________________________________
pool1 (MaxPooling2D) (None, 150, 150, 64) 0 conv1_2[0][0]
__________________________________________________________________________________________________
conv2_1 (Conv2D) (None, 150, 150, 128 73856 pool1[0][0]
__________________________________________________________________________________________________
conv2_2 (Conv2D) (None, 150, 150, 128 147584 conv2_1[0][0]
__________________________________________________________________________________________________
pool2 (MaxPooling2D) (None, 75, 75, 128) 0 conv2_2[0][0]
__________________________________________________________________________________________________
conv3_1 (Conv2D) (None, 75, 75, 256) 295168 pool2[0][0]
__________________________________________________________________________________________________
conv3_2 (Conv2D) (None, 75, 75, 256) 590080 conv3_1[0][0]
__________________________________________________________________________________________________
conv3_3 (Conv2D) (None, 75, 75, 256) 590080 conv3_2[0][0]
__________________________________________________________________________________________________
pool3 (MaxPooling2D) (None, 38, 38, 256) 0 conv3_3[0][0]
__________________________________________________________________________________________________
conv4_1 (Conv2D) (None, 38, 38, 512) 1180160 pool3[0][0]
__________________________________________________________________________________________________
conv4_2 (Conv2D) (None, 38, 38, 512) 2359808 conv4_1[0][0]
__________________________________________________________________________________________________
conv4_3 (Conv2D) (None, 38, 38, 512) 2359808 conv4_2[0][0]
__________________________________________________________________________________________________
pool4 (MaxPooling2D) (None, 19, 19, 512) 0 conv4_3[0][0]
__________________________________________________________________________________________________
conv5_1 (Conv2D) (None, 19, 19, 512) 2359808 pool4[0][0]
__________________________________________________________________________________________________
conv5_2 (Conv2D) (None, 19, 19, 512) 2359808 conv5_1[0][0]
__________________________________________________________________________________________________
conv5_3 (Conv2D) (None, 19, 19, 512) 2359808 conv5_2[0][0]
__________________________________________________________________________________________________
pool5 (MaxPooling2D) (None, 19, 19, 512) 0 conv5_3[0][0]
__________________________________________________________________________________________________
fc6 (Conv2D) (None, 19, 19, 1024) 4719616 pool5[0][0]
__________________________________________________________________________________________________
fc7 (Conv2D) (None, 19, 19, 1024) 1049600 fc6[0][0]
__________________________________________________________________________________________________
conv6_1 (Conv2D) (None, 19, 19, 256) 262400 fc7[0][0]
__________________________________________________________________________________________________
conv6_padding (ZeroPadding2D) (None, 21, 21, 256) 0 conv6_1[0][0]
__________________________________________________________________________________________________
conv6_2 (Conv2D) (None, 10, 10, 512) 1180160 conv6_padding[0][0]
__________________________________________________________________________________________________
conv7_1 (Conv2D) (None, 10, 10, 128) 65664 conv6_2[0][0]
__________________________________________________________________________________________________
conv7_padding (ZeroPadding2D) (None, 12, 12, 128) 0 conv7_1[0][0]
__________________________________________________________________________________________________
conv7_2 (Conv2D) (None, 5, 5, 256) 295168 conv7_padding[0][0]
__________________________________________________________________________________________________
conv8_1 (Conv2D) (None, 5, 5, 128) 32896 conv7_2[0][0]
__________________________________________________________________________________________________
conv8_2 (Conv2D) (None, 3, 3, 256) 295168 conv8_1[0][0]
__________________________________________________________________________________________________
conv9_1 (Conv2D) (None, 3, 3, 128) 32896 conv8_2[0][0]
__________________________________________________________________________________________________
conv4_3_norm (Normalize) (None, 38, 38, 512) 512 conv4_3[0][0]
__________________________________________________________________________________________________
conv9_2 (Conv2D) (None, 1, 1, 256) 295168 conv9_1[0][0]
__________________________________________________________________________________________________
conv4_3_norm_mbox_conf (Conv2D) (None, 38, 38, 8) 36872 conv4_3_norm[0][0]
__________________________________________________________________________________________________
fc7_mbox_conf (Conv2D) (None, 19, 19, 12) 110604 fc7[0][0]
__________________________________________________________________________________________________
conv6_2_mbox_conf (Conv2D) (None, 10, 10, 12) 55308 conv6_2[0][0]
__________________________________________________________________________________________________
conv7_2_mbox_conf (Conv2D) (None, 5, 5, 12) 27660 conv7_2[0][0]
__________________________________________________________________________________________________
conv8_2_mbox_conf (Conv2D) (None, 3, 3, 8) 18440 conv8_2[0][0]
__________________________________________________________________________________________________
conv9_2_mbox_conf (Conv2D) (None, 1, 1, 8) 18440 conv9_2[0][0]
__________________________________________________________________________________________________
conv4_3_norm_mbox_loc (Conv2D) (None, 38, 38, 16) 73744 conv4_3_norm[0][0]
__________________________________________________________________________________________________
fc7_mbox_loc (Conv2D) (None, 19, 19, 24) 221208 fc7[0][0]
__________________________________________________________________________________________________
conv6_2_mbox_loc (Conv2D) (None, 10, 10, 24) 110616 conv6_2[0][0]
__________________________________________________________________________________________________
conv7_2_mbox_loc (Conv2D) (None, 5, 5, 24) 55320 conv7_2[0][0]
__________________________________________________________________________________________________
conv8_2_mbox_loc (Conv2D) (None, 3, 3, 16) 36880 conv8_2[0][0]
__________________________________________________________________________________________________
conv9_2_mbox_loc (Conv2D) (None, 1, 1, 16) 36880 conv9_2[0][0]
__________________________________________________________________________________________________
conv4_3_norm_mbox_conf_flat (Fl (None, 11552) 0 conv4_3_norm_mbox_conf[0][0]
__________________________________________________________________________________________________
fc7_mbox_conf_flat (Flatten) (None, 4332) 0 fc7_mbox_conf[0][0]
__________________________________________________________________________________________________
conv6_2_mbox_conf_flat (Flatten (None, 1200) 0 conv6_2_mbox_conf[0][0]
__________________________________________________________________________________________________
conv7_2_mbox_conf_flat (Flatten (None, 300) 0 conv7_2_mbox_conf[0][0]
__________________________________________________________________________________________________
conv8_2_mbox_conf_flat (Flatten (None, 72) 0 conv8_2_mbox_conf[0][0]
__________________________________________________________________________________________________
conv9_2_mbox_conf_flat (Flatten (None, 8) 0 conv9_2_mbox_conf[0][0]
__________________________________________________________________________________________________
conv4_3_norm_mbox_loc_flat (Fla (None, 23104) 0 conv4_3_norm_mbox_loc[0][0]
__________________________________________________________________________________________________
fc7_mbox_loc_flat (Flatten) (None, 8664) 0 fc7_mbox_loc[0][0]
__________________________________________________________________________________________________
conv6_2_mbox_loc_flat (Flatten) (None, 2400) 0 conv6_2_mbox_loc[0][0]
__________________________________________________________________________________________________
conv7_2_mbox_loc_flat (Flatten) (None, 600) 0 conv7_2_mbox_loc[0][0]
__________________________________________________________________________________________________
conv8_2_mbox_loc_flat (Flatten) (None, 144) 0 conv8_2_mbox_loc[0][0]
__________________________________________________________________________________________________
conv9_2_mbox_loc_flat (Flatten) (None, 16) 0 conv9_2_mbox_loc[0][0]
__________________________________________________________________________________________________
mbox_conf (Concatenate) (None, 17464) 0 conv4_3_norm_mbox_conf_flat[0][0]
fc7_mbox_conf_flat[0][0]
conv6_2_mbox_conf_flat[0][0]
conv7_2_mbox_conf_flat[0][0]
conv8_2_mbox_conf_flat[0][0]
conv9_2_mbox_conf_flat[0][0]
__________________________________________________________________________________________________
mbox_loc (Concatenate) (None, 34928) 0 conv4_3_norm_mbox_loc_flat[0][0]
fc7_mbox_loc_flat[0][0]
conv6_2_mbox_loc_flat[0][0]
conv7_2_mbox_loc_flat[0][0]
conv8_2_mbox_loc_flat[0][0]
conv9_2_mbox_loc_flat[0][0]
__________________________________________________________________________________________________
mbox_conf_logits (Reshape) (None, 8732, 2) 0 mbox_conf[0][0]
__________________________________________________________________________________________________
conv4_3_norm_mbox_priorbox (Pri (None, 5776, 8) 0 conv4_3_norm[0][0]
__________________________________________________________________________________________________
fc7_mbox_priorbox (PriorBox) (None, 2166, 8) 0 fc7[0][0]
__________________________________________________________________________________________________
conv6_2_mbox_priorbox (PriorBox (None, 600, 8) 0 conv6_2[0][0]
__________________________________________________________________________________________________
conv7_2_mbox_priorbox (PriorBox (None, 150, 8) 0 conv7_2[0][0]
__________________________________________________________________________________________________
conv8_2_mbox_priorbox (PriorBox (None, 36, 8) 0 conv8_2[0][0]
__________________________________________________________________________________________________
conv9_2_mbox_priorbox (PriorBox (None, 4, 8) 0 conv9_2[0][0]
__________________________________________________________________________________________________
mbox_loc_final (Reshape) (None, 8732, 4) 0 mbox_loc[0][0]
__________________________________________________________________________________________________
mbox_conf_final (Activation) (None, 8732, 2) 0 mbox_conf_logits[0][0]
__________________________________________________________________________________________________
mbox_priorbox (Concatenate) (None, 8732, 8) 0 conv4_3_norm_mbox_priorbox[0][0]
fc7_mbox_priorbox[0][0]
conv6_2_mbox_priorbox[0][0]
conv7_2_mbox_priorbox[0][0]
conv8_2_mbox_priorbox[0][0]
conv9_2_mbox_priorbox[0][0]
__________________________________________________________________________________________________
predictions (Concatenate) (None, 8732, 14) 0 mbox_loc_final[0][0]
mbox_conf_final[0][0]
mbox_priorbox[0][0]
================================================================================================
SSD模型原理框圖
