SSD的英文全名是Single Shot MultiBox Detector，Single shot说明SSD算法属于one-stage方法，MultiBox说明SSD算法基于多框预测。
SSD是一种非常优秀的one-stage目标检测方法，one-stage算法就是目标检测和分类是同时完成的，其主要思路是利用CNN提取特征后，物体分类与框的回归同时进行，整个过程只需要一步，所以其优势是速度快。但是一个缺点是训练比较困难，这主要是因为正样本与负样本（背景）极其不均衡（一般训练的时候取负样本与正样本的比例维3：1），导致模型准确度稍低。
1.主干网络
SSD选用的主干网络是VGG，并且对VGG进行一定的修改，修改的地方为：
1.将fc6，fc7的全连接层改成全卷积层。
2.去点fc8层和dropout层。
3.增加conv6，conv7，conv8以及conv9.
本次实现一个5个类别的分类，所以简化了主干网络，此模型包含 7 个卷积层, 其中 4 个预测层, 预测层从第 4, 5, 6, 和 7 层做预测，keras代码如下：
conv1=Conv2D(32,(5,5),strides=(1,1),padding='same',kernel_initializer='he_normal',kernel_regularizer=l2(l2_reg),name='conv1')(x1)
conv1=BatchNormalization(axis=3,momentum=0.99,name='bn1')(conv1)
conv1=ELU(name='elu1')(conv1)
pool1=MaxPooling2D(pool_size=(2,2),name='pool1')(conv1)
conv2=Conv2D(48,(3,3),strides=(1,1),padding='same',kernel_initializer='he_normal',kernel_regularizer=l2(l2_reg),name='conv2')(pool1)
conv2=BatchNormalization(axis=3,momentum=0.99,name='bn2')(conv2)
conv2=ELU(name='elu2')(conv2)
pool2=MaxPooling2D(pool_size=(2,2),name='pool2')(conv2)
conv3=Conv2D(64,(3,3),strides=(1,1),padding='same',kernel_initializer='he_normal',kernel_regularizer=l2(l2_reg),name='conv3')(pool2)
conv3=BatchNormalization(axis=3,momentum=0.99,name='bn3')(conv3)
conv3=ELU(name='elu3')(conv3)
pool3=MaxPooling2D(pool_size=(2,2),name='pool3')(conv3)
conv4=Conv2D(64,(3,3),strides=(1,1),padding='same',kernel_initializer='he_normal',kernel_regularizer=l2(l2_reg),name='conv4')(pool3)
conv4=BatchNormalization(axis=3,momentum=0.99,name='bn4')(conv4)
conv4=ELU(name='elu4')(conv4)
pool4=MaxPooling2D(pool_size=(2,2),name='pool4')(conv4)
conv5=Conv2D(48,(3,3),strides=(1,1),padding='same',kernel_initializer='he_normal',kernel_regularizer=l2(l2_reg),name='conv5')(pool4)
conv5=BatchNormalization(axis=3,momentum=0.99,name='bn5')(conv5)
conv5=ELU(name='elu5')(conv5)
pool5=MaxPooling2D(pool_size=(2,2),name='pool5')(conv5)
conv6=Conv2D(48,(3,3),strides=(1,1),padding='same',kernel_initializer='he_normal',kernel_regularizer=l2(l2_reg),name='conv6')(pool5)
conv6=BatchNormalization(axis=3,momentum=0.99,name='bn6')(conv4)
conv6=ELU(name='elu6')(conv6)
pool6=MaxPooling2D(pool_size=(2,2),name='pool6')(conv6)
conv7=Conv2D(32,(3,3),strides=(1,1),padding='same',kernel_initializer='he_normal',kernel_regularizer=l2(l2_reg),name='conv7')(pool6)
conv7=BatchNormalization(axis=3,momentum=0.99,name='bn7')(conv7)
conv7=ELU(name='elu7')(conv7)
#输出classes形状（batch，height,width,n_boxes*n_classes）
classes4=Conv2D(n_boxes[0]*n_classes,(3,3),strides=(1,1),padding='same',kernel_initializer='he_normal',kernel_regularizer=l2(l2_reg),name='classes4')(conv4)
classes5=Conv2D(n_boxes[1]*n_classes,(3,3),strides=(1,1),padding='same',kernel_initializer='he_normal',kernel_regularizer=l2(l2_reg),name='classes5')(conv5)
classes6=Conv2D(n_boxes[2]*n_classes,(3,3),strides=(1,1),padding='same',kernel_initializer='he_normal',kernel_regularizer=l2(l2_reg),name='classes6')(conv6)
classes7=Conv2D(n_boxes[3]*n_classes,(3,3),strides=(1,1),padding='same',kernel_initializer='he_normal',kernel_regularizer=l2(l2_reg),name='classes7')(conv7)
#输出box形状（batch，height,width,n_boxes*4）
boxes4=Conv2D(n_boxes[0]*4,(3,3),strides=(1,1),padding='same',kernel_initializer='he_normal',kernel_regularizer=l2(l2_reg))(conv4)
boxes5=Conv2D(n_boxes[1]*4,(3,3),strides=(1,1),padding='same',kernel_initializer='he_normal',kernel_regularizer=l2(l2_reg))(conv5)
boxes6=Conv2D(n_boxes[2]*4,(3,3),strides=(1,1),padding='same',kernel_initializer='he_normal',kernel_regularizer=l2(l2_reg))(conv6)
boxes7=Conv2D(n_boxes[3]*4,(3,3),strides=(1,1),padding='same',kernel_initializer='he_normal',kernel_regularizer=l2(l2_reg))(conv7)
#产生anchor box
#输出anchor的形状 （batch，height,width,n_boxes,8）
anchors4=AnchorBoxes(img_height,img_width,this_scale=scales[0],next_scale=scales[1],aspect_ratios=aspect_ratios[0],
two_boxes_for_ar1=two_boxes_for_ar1,this_steps=steps[0],this_offsets=offsets[0],
clip_boxes=clip_boxes,variances=variances,coords=coords,normalize_coords=normalize_coords,name='anchors4')(boxes4)
anchors5=AnchorBoxes(img_height,img_width,this_scale=scales[1],next_scale=scales[2],aspect_ratios=aspect_ratios[1],
two_boxes_for_ar1=two_boxes_for_ar1,this_steps=steps[1],this_offsets=offsets[1],
clip_boxes=clip_boxes,variances=variances,coords=coords,normalize_coords=normalize_coords,name='anchors5')(boxes5)
anchors6=AnchorBoxes(img_height,img_width,this_scale=scales[2],next_scale=scales[3],aspect_ratios=aspect_ratios[2],
two_boxes_for_ar1=two_boxes_for_ar1,this_steps=steps[2],this_offsets=offsets[2],
clip_boxes=clip_boxes,variances=variances,coords=coords,normalize_coords=normalize_coords,name='anchors6')(boxes6)
anchors7=AnchorBoxes(img_height,img_width,this_scale=scales[3],next_scale=scales[4],aspect_ratios=aspect_ratios[3],
two_boxes_for_ar1=two_boxes_for_ar1,this_steps=steps[3],this_offsets=offsets[3],
clip_boxes=clip_boxes,variances=variances,coords=coords,normalize_coords=normalize_coords,name='anchors7')(boxes7)
classes4_reshaped=Reshape((-1,n_classes),name='classes4_reshape')(classes4)
classes5_reshaped=Reshape((-1,n_classes),name='classes5_reshape')(classes5)
classes6_reshaped=Reshape((-1,n_classes),name='classes6_reshape')(classes6)
classes7_reshaped=Reshape((-1,n_classes),name='classes7_reshape')(classes7)
boxes4_reshaped=Reshape((-1,4),name='boxes4_reshape')(boxes4)
boxes5_reshaped=Reshape((-1,4),name='boxes5_reshape')(boxes5)
boxes6_reshaped=Reshape((-1,4),name='boxes6_reshape')(boxes6)
boxes7_reshaped=Reshape((-1,4),name='boxes7_reshape')(boxes7)
anchors4_reshaped=Reshape((-1,8),name='anchors4_reshape')(anchors4)
anchors5_reshaped=Reshape((-1,8),name='anchors5_reshape')(anchors5)
anchors6_reshaped=Reshape((-1,8),name='anchors6_reshape')(anchors6)
anchors7_reshaped=Reshape((-1,8),name='anchors7_reshape')(anchors7)
#classes_concat 形状 （batch,n_boxes_total,n_classes）
classes_concat=Concatenate(axis=1,name='classes_concat')([classes4_reshaped,
classes5_reshaped,
classes6_reshaped,
classes7_reshaped])
#boxes_concat 形状 （batch,n_boxes_total,4）
boxes_concat=Concatenate(axis=1,name='boxes_concat')([boxes4_reshaped,
boxes5_reshaped,
boxes6_reshaped,
boxes7_reshaped])
#anchors_concat 形状 （batch,n_boxes_total,8）
anchors_concat=Concatenate(axis=1,name='anchors_concat')([anchors4_reshaped,
anchors5_reshaped,
anchors6_reshaped,
anchors7_reshaped])
classes_softmax=Activation('softmax',name='classes_softmax')(classes_concat)
predictions=Concatenate(axis=2,name='predictions')([classes_softmax,boxes_concat,anchors_concat])
model = Model(inputs=x, outputs=decoded_predictions)
