【人工智能笔记】第二十一节 efficientdet 目标检测模型，官方源码分析系列，Box与Class回归细节分析（三）

本章继续分析Efficientdet模型，Box与Class回归网络部分。

Box与Class实现代码一样，共5层共用一个卷积层，然后链接单独的BN，接激活函数swish，drop_connect方法用于drop部分卷积。Box与Class主要区别是在最后一层通道数不同，Box通道数为num_anchors*4，Class通道数为num_anchors*(num_classes+1)，这里的1为背景。

结构图如下：

代码如下：

class ClassNet(tf.keras.layers.Layer):
  """Object class prediction network."""

  def __init__(self,
               num_classes=90,
               num_anchors=9,
               num_filters=32,
               min_level=3,
               max_level=7,
               is_training_bn=False,
               act_type='swish',
               repeats=4,
               separable_conv=True,
               survival_prob=None,
               strategy=None,
               data_format='channels_last',
               name='class_net',
               **kwargs):
    """Initialize the ClassNet.

    Args:
      num_classes: number of classes.
      num_anchors: number of anchors.
      num_filters: number of filters for "intermediate" layers.
      min_level: minimum level for features.
      max_level: maximum level for features.
      is_training_bn: True if we train the BatchNorm.
      act_type: String of the activation used.
      repeats: number of intermediate layers.
      separable_conv: True to use separable_conv instead of conv2D.
      survival_prob: if a value is set then drop connect will be used.
      strategy: string to specify training strategy for TPU/GPU/CPU.
      data_format: string of 'channel_first' or 'channels_last'.
      name: the name of this layerl.
      **kwargs: other parameters.
    """

    super().__init__(name=name, **kwargs)
    self.num_classes = num_classes
    self.num_anchors = num_anchors
    self.num_filters = num_filters
    self.min_level = min_level
    self.max_level = max_level
    self.repeats = repeats
    self.separable_conv = separable_conv
    self.is_training_bn = is_training_bn
    self.survival_prob = survival_prob
    self.act_type = act_type
    self.strategy = strategy
    self.data_format = data_format
    self.conv_ops = []
    self.bns = []
    if separable_conv:
      conv2d_layer = functools.partial(
          tf.keras.layers.SeparableConv2D,
          depth_multiplier=1,
          data_format=data_format,
          pointwise_initializer=tf.initializers.VarianceScaling(),
          depthwise_initializer=tf.initializers.VarianceScaling())
    else:
      conv2d_layer = functools.partial(
          tf.keras.layers.Conv2D,
          data_format=data_format,
          kernel_initializer=tf.random_normal_initializer(stddev=0.01))
    for i in range(self.repeats):
      # If using SeparableConv2D
      self.conv_ops.append(
          conv2d_layer(
              self.num_filters,
              kernel_size=3,
              bias_initializer=tf.zeros_initializer(),
              activation=None,
              padding='same',
              name='class-%d' % i))

      bn_per_level = []
      for level in range(self.min_level, self.max_level + 1):
        bn_per_level.append(
            util_keras.build_batch_norm(
                is_training_bn=self.is_training_bn,
                strategy=self.strategy,
                data_format=self.data_format,
                name='class-%d-bn-%d' % (i, level),
            ))
      self.bns.append(bn_per_level)

    self.classes = conv2d_layer(
        num_classes * num_anchors,
        kernel_size=3,
        bias_initializer=tf.constant_initializer(-np.log((1 - 0.01) / 0.01)),
        padding='same',
        name='class-predict')

  def call(self, inputs, training, **kwargs):
    """Call ClassNet."""

    class_outputs = []
    for level_id in range(0, self.max_level - self.min_level + 1):
      image = inputs[level_id]
      for i in range(self.repeats):
        # 这里有跳层
        original_image = image
        # 所有层经过同一个卷积
        image = self.conv_ops[i](image)
        # 每层单独对应BN
        image = self.bns[i][level_id](image, training=training)
        if self.act_type:
          image = utils.activation_fn(image, self.act_type)
        if i > 0 and self.survival_prob:
          # 多于1层时，drop掉后面几层
          image = utils.drop_connect(image, training, self.survival_prob)
          image = image + original_image
      # 最后输出结果
      class_outputs.append(self.classes(image))

    return class_outputs


class BoxNet(tf.keras.layers.Layer):
  """Box regression network."""

  def __init__(self,
               num_anchors=9,
               num_filters=32,
               min_level=3,
               max_level=7,
               is_training_bn=False,
               act_type='swish',
               repeats=4,
               separable_conv=True,
               survival_prob=None,
               strategy=None,
               data_format='channels_last',
               name='box_net',
               **kwargs):
    """Initialize BoxNet.

    Args:
      num_anchors: number of  anchors used.
      num_filters: number of filters for "intermediate" layers.
      min_level: minimum level for features.
      max_level: maximum level for features.
      is_training_bn: True if we train the BatchNorm.
      act_type: String of the activation used.
      repeats: number of "intermediate" layers.
      separable_conv: True to use separable_conv instead of conv2D.
      survival_prob: if a value is set then drop connect will be used.
      strategy: string to specify training strategy for TPU/GPU/CPU.
      data_format: string of 'channel_first' or 'channels_last'.
      name: Name of the layer.
      **kwargs: other parameters.
    """

    super().__init__(name=name, **kwargs)

    self.num_anchors = num_anchors
    self.num_filters = num_filters
    self.min_level = min_level
    self.max_level = max_level
    self.repeats = repeats
    self.separable_conv = separable_conv
    self.is_training_bn = is_training_bn
    self.survival_prob = survival_prob
    self.act_type = act_type
    self.strategy = strategy
    self.data_format = data_format

    self.conv_ops = []
    self.bns = []

    for i in range(self.repeats):
      # If using SeparableConv2D
      if self.separable_conv:
        self.conv_ops.append(
            tf.keras.layers.SeparableConv2D(
                filters=self.num_filters,
                depth_multiplier=1,
                pointwise_initializer=tf.initializers.VarianceScaling(),
                depthwise_initializer=tf.initializers.VarianceScaling(),
                data_format=self.data_format,
                kernel_size=3,
                activation=None,
                bias_initializer=tf.zeros_initializer(),
                padding='same',
                name='box-%d' % i))
      # If using Conv2d
      else:
        self.conv_ops.append(
            tf.keras.layers.Conv2D(
                filters=self.num_filters,
                kernel_initializer=tf.random_normal_initializer(stddev=0.01),
                data_format=self.data_format,
                kernel_size=3,
                activation=None,
                bias_initializer=tf.zeros_initializer(),
                padding='same',
                name='box-%d' % i))

      bn_per_level = []
      for level in range(self.min_level, self.max_level + 1):
        bn_per_level.append(
            util_keras.build_batch_norm(
                is_training_bn=self.is_training_bn,
                strategy=self.strategy,
                data_format=self.data_format,
                name='box-%d-bn-%d' % (i, level)))
      self.bns.append(bn_per_level)

    if self.separable_conv:
      self.boxes = tf.keras.layers.SeparableConv2D(
          filters=4 * self.num_anchors,
          depth_multiplier=1,
          pointwise_initializer=tf.initializers.VarianceScaling(),
          depthwise_initializer=tf.initializers.VarianceScaling(),
          data_format=self.data_format,
          kernel_size=3,
          activation=None,
          bias_initializer=tf.zeros_initializer(),
          padding='same',
          name='box-predict')
    else:
      self.boxes = tf.keras.layers.Conv2D(
          filters=4 * self.num_anchors,
          kernel_initializer=tf.random_normal_initializer(stddev=0.01),
          data_format=self.data_format,
          kernel_size=3,
          activation=None,
          bias_initializer=tf.zeros_initializer(),
          padding='same',
          name='box-predict')

  def call(self, inputs, training):
    """Call boxnet."""
    # 和分类网络一样
    box_outputs = []
    for level_id in range(0, self.max_level - self.min_level + 1):
      image = inputs[level_id]
      for i in range(self.repeats):
        # 这里有跳层
        original_image = image
        # 所有层经过同一个卷积
        image = self.conv_ops[i](image)
        # 每层单独对应BN
        image = self.bns[i][level_id](image, training=training)
        if self.act_type:
          image = utils.activation_fn(image, self.act_type)
        if i > 0 and self.survival_prob:
          # 多于1层时，drop掉后面几层
          image = utils.drop_connect(image, training, self.survival_prob)
          image = image + original_image

      box_outputs.append(self.boxes(image))

    return box_outputs

到此本章内容结束，下一章，Loss计算细节分析，敬请关注！！！