目标检测系列4—yolo1、yolo2、yolo3和SSD的网络结构对比

1、yolo1

1.1、yolo1网络结构

由图可见，其进行了二十多次卷积还有四次最大池化，其中3x3卷积用于提取特征，1x1卷积用于压缩特征，最后将图像压缩到7x7xfilter的大小，相当于将整个图像划分为7x7的网格，每个网格负责自己这一块区域的目标检测。
整个网络最后利用全连接层使其结果的size为(7x7x30)，其中7x7代表的是7x7的网格，30前20个代表的是预测的种类，后10代表两个预测框及其置信度(5x2)。

1.2、yolo1网络代码

网络部分代码如下：

# relu的改进版
def leak_relu(self,x, alpha=0.1):
    return tf.maximum(alpha * x, x)


# 建立网络部分
def _build_net(self):
    x = tf.placeholder(tf.float32, [None, 448, 448, 3])
    with tf.variable_scope('yolo'):
        # _conv_layer(self, x, num_filters, filter_size, stride,scope)
        with tf.variable_scope('conv_2'):
            # (448,448,3)->(224,224,64)
            net = self._conv_layer(x, 64, 7, 2,'conv_2')
        # (224,224,64)->(112,112,64)
        net = self._maxpool_layer(net, 2, 2)
        with tf.variable_scope('conv_4'):
            # (112,112,64)->(112,112,192)
            net = self._conv_layer(net,  192, 3, 1,'conv_4')
        # (112,112,192)->(56,56,192)
        net = self._maxpool_layer(net, 2, 2)
        with tf.variable_scope('conv_6'):
            # (56,56,128)
            net = self._conv_layer(net, 128, 1, 1,'conv_6')
        with tf.variable_scope('conv_7'):
            # (56,56,256)
            net = self._conv_layer(net, 256, 3, 1,'conv_7')
        with tf.variable_scope('conv_8'):
            # (56,56,256)
            net = self._conv_layer(net, 256, 1, 1,'conv_8')
        with tf.variable_scope('conv_9'):
            # (56,56,512)
            net = self._conv_layer(net, 512, 3, 1,'conv_9')
        # (28,28,512)
        net = self._maxpool_layer(net, 2, 2)
        with tf.variable_scope('conv_11'):
            net = self._conv_layer(net, 256, 1, 1,'conv_11')
        with tf.variable_scope('conv_12'):
            net = self._conv_layer(net, 512, 3, 1,'conv_12')
        with tf.variable_scope('conv_13'):
            net = self._conv_layer(net, 256, 1, 1,'conv_13')
        with tf.variable_scope('conv_14'):
            net = self._conv_layer(net, 512, 3, 1,'conv_14')
        with tf.variable_scope('conv_15'):
            net = self._conv_layer(net, 256, 1, 1,'conv_15')
        with tf.variable_scope('conv_16'):
            net = self._conv_layer(net, 512, 3, 1,'conv_16')
        with tf.variable_scope('conv_17'):
            net = self._conv_layer(net, 256, 1, 1,'conv_17')
        with tf.variable_scope('conv_18'):
            net = self._conv_layer(net, 512, 3, 1,'conv_18')
        with tf.variable_scope('conv_19'):
            net = self._conv_layer(net, 512, 1, 1,'conv_19')
        with tf.variable_scope('conv_20'):
            net = self._conv_layer(net, 1024, 3, 1,'conv_20')
        # (14,14,512)
        net = self._maxpool_layer(net, 2, 2)
        with tf.variable_scope('conv_22'):
            net = self._conv_layer(net,  512, 1, 1,'conv_22')
        with tf.variable_scope('conv_23'):
            net = self._conv_layer(net,  1024, 3, 1,'conv_23')
        with tf.variable_scope('conv_24'):
            net = self._conv_layer(net,  512, 1, 1,'conv_24')
        with tf.variable_scope('conv_25'):
            net = self._conv_layer(net,  1024, 3, 1,'conv_25')
        with tf.variable_scope('conv_26'):
            net = self._conv_layer(net,  1024, 3, 1,'conv_26')
        with tf.variable_scope('conv_28'):
            # (7,7,1024)
            net = self._conv_layer(net,  1024, 3, 2,'conv_28')
        with tf.variable_scope('conv_29'):
            net = self._conv_layer(net,  1024, 3, 1,'conv_29')
        with tf.variable_scope('conv_30'):
            net = self._conv_layer(net,  1024, 3, 1,'conv_30')
        net = self._flatten(net)
        # (7x7x512,512)
        with tf.variable_scope('fc_33'):
            net = self._fc_layer(net,  512, activation=self.leak_relu,scope='fc_33')
        with tf.variable_scope('fc_34'):
            net = self._fc_layer(net, 4096, activation=self.leak_relu,scope='fc_34')
        with tf.variable_scope('fc_36'):
            net = self._fc_layer(net, 7*7*30,scope='fc_36')
    # 其返回了placeholder_x和(7,7,30)net
    return net,x

# 生成卷积层
def _conv_layer(self, x, num_filters, filter_size, stride,scope):
    # 生成卷积层的weights
    in_channels = x.get_shape().as_list()[-1]
    weight = tf.Variable(tf.truncated_normal([filter_size, filter_size,
                                                in_channels, num_filters], stddev=0.1),name='weights')
    # 生成卷积层的bias
    bias = tf.Variable(tf.zeros([num_filters,]),name='biases')

    # 计算要padding的量，
    pad_size = filter_size // 2
    pad_mat = np.array([[0, 0], [pad_size, pad_size], [pad_size, pad_size], [0, 0]])
    x_pad = tf.pad(x, pad_mat)
    
    # 卷积
    conv = tf.nn.conv2d(x_pad, weight, strides=[1, stride, stride, 1], padding="VALID",name=scope)
    # 经过优化后的relu
    output = self.leak_relu(tf.nn.bias_add(conv, bias))

    return output

def _fc_layer(self, x,  num_out, activation=None,scope=None):
    # 全连接层
    num_in = x.get_shape(