Python object_detection.core.box_predictor.BoxPredictor() Examples

def __init__(self,
               is_training,
               num_classes,
               box_prediction_head,
               class_prediction_head,
               third_stage_heads):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      box_prediction_head: The head that predicts the boxes in second stage.
      class_prediction_head: The head that predicts the classes in second stage.
      third_stage_heads: A dictionary mapping head names to mask rcnn head
        classes.
    """
    super(MaskRCNNBoxPredictor, self).__init__(is_training, num_classes)
    self._box_prediction_head = box_prediction_head
    self._class_prediction_head = class_prediction_head
    self._third_stage_heads = third_stage_heads 

def __init__(self,
               is_training,
               num_classes,
               box_prediction_head,
               class_prediction_head,
               third_stage_heads):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      box_prediction_head: The head that predicts the boxes in second stage.
      class_prediction_head: The head that predicts the classes in second stage.
      third_stage_heads: A dictionary mapping head names to mask rcnn head
        classes.
    """
    super(MaskRCNNBoxPredictor, self).__init__(is_training, num_classes)
    self._box_prediction_head = box_prediction_head
    self._class_prediction_head = class_prediction_head
    self._third_stage_heads = third_stage_heads 

def __init__(self,
               is_training,
               num_classes,
               box_prediction_head,
               class_prediction_head,
               third_stage_heads):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      box_prediction_head: The head that predicts the boxes in second stage.
      class_prediction_head: The head that predicts the classes in second stage.
      third_stage_heads: A dictionary mapping head names to mask rcnn head
        classes.
    """
    super(MaskRCNNBoxPredictor, self).__init__(is_training, num_classes)
    self._box_prediction_head = box_prediction_head
    self._class_prediction_head = class_prediction_head
    self._third_stage_heads = third_stage_heads 

def __init__(self,
               is_training,
               num_classes,
               box_prediction_head,
               class_prediction_head,
               third_stage_heads):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      box_prediction_head: The head that predicts the boxes in second stage.
      class_prediction_head: The head that predicts the classes in second stage.
      third_stage_heads: A dictionary mapping head names to mask rcnn head
        classes.
    """
    super(MaskRCNNBoxPredictor, self).__init__(is_training, num_classes)
    self._box_prediction_head = box_prediction_head
    self._class_prediction_head = class_prediction_head
    self._third_stage_heads = third_stage_heads 

def __init__(self,
               is_training,
               num_classes,
               box_prediction_head,
               class_prediction_head,
               third_stage_heads):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      box_prediction_head: The head that predicts the boxes in second stage.
      class_prediction_head: The head that predicts the classes in second stage.
      third_stage_heads: A dictionary mapping head names to mask rcnn head
        classes.
    """
    super(MaskRCNNBoxPredictor, self).__init__(is_training, num_classes)
    self._box_prediction_head = box_prediction_head
    self._class_prediction_head = class_prediction_head
    self._third_stage_heads = third_stage_heads 

def __init__(self,
               is_training,
               num_classes,
               box_prediction_head,
               class_prediction_head,
               third_stage_heads):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      box_prediction_head: The head that predicts the boxes in second stage.
      class_prediction_head: The head that predicts the classes in second stage.
      third_stage_heads: A dictionary mapping head names to mask rcnn head
        classes.
    """
    super(MaskRCNNBoxPredictor, self).__init__(is_training, num_classes)
    self._box_prediction_head = box_prediction_head
    self._class_prediction_head = class_prediction_head
    self._third_stage_heads = third_stage_heads 

def __init__(self,
               is_training,
               num_classes,
               conv_hyperparams_fn,
               num_spatial_bins,
               depth,
               crop_size,
               box_code_size):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      conv_hyperparams_fn: A function to construct tf-slim arg_scope with
        hyperparameters for convolutional layers.
      num_spatial_bins: A list of two integers `[spatial_bins_y,
        spatial_bins_x]`.
      depth: Target depth to reduce the input feature maps to.
      crop_size: A list of two integers `[crop_height, crop_width]`.
      box_code_size: Size of encoding for each box.
    """
    super(RfcnBoxPredictor, self).__init__(is_training, num_classes)
    self._conv_hyperparams_fn = conv_hyperparams_fn
    self._num_spatial_bins = num_spatial_bins
    self._depth = depth
    self._crop_size = crop_size
    self._box_code_size = box_code_size 

def __init__(self,
               is_training,
               num_classes,
               conv_hyperparams_fn,
               num_spatial_bins,
               depth,
               crop_size,
               box_code_size):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      conv_hyperparams_fn: A function to construct tf-slim arg_scope with
        hyperparameters for convolutional layers.
      num_spatial_bins: A list of two integers `[spatial_bins_y,
        spatial_bins_x]`.
      depth: Target depth to reduce the input feature maps to.
      crop_size: A list of two integers `[crop_height, crop_width]`.
      box_code_size: Size of encoding for each box.
    """
    super(RfcnBoxPredictor, self).__init__(is_training, num_classes)
    self._conv_hyperparams_fn = conv_hyperparams_fn
    self._num_spatial_bins = num_spatial_bins
    self._depth = depth
    self._crop_size = crop_size
    self._box_code_size = box_code_size 

def __init__(self,
               is_training,
               num_classes,
               conv_hyperparams_fn,
               num_spatial_bins,
               depth,
               crop_size,
               box_code_size):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      conv_hyperparams_fn: A function to construct tf-slim arg_scope with
        hyperparameters for convolutional layers.
      num_spatial_bins: A list of two integers `[spatial_bins_y,
        spatial_bins_x]`.
      depth: Target depth to reduce the input feature maps to.
      crop_size: A list of two integers `[crop_height, crop_width]`.
      box_code_size: Size of encoding for each box.
    """
    super(RfcnBoxPredictor, self).__init__(is_training, num_classes)
    self._conv_hyperparams_fn = conv_hyperparams_fn
    self._num_spatial_bins = num_spatial_bins
    self._depth = depth
    self._crop_size = crop_size
    self._box_code_size = box_code_size 

def __init__(self,
               is_training,
               num_classes,
               conv_hyperparams_fn,
               num_spatial_bins,
               depth,
               crop_size,
               box_code_size):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      conv_hyperparams_fn: A function to construct tf-slim arg_scope with
        hyperparameters for convolutional layers.
      num_spatial_bins: A list of two integers `[spatial_bins_y,
        spatial_bins_x]`.
      depth: Target depth to reduce the input feature maps to.
      crop_size: A list of two integers `[crop_height, crop_width]`.
      box_code_size: Size of encoding for each box.
    """
    super(RfcnBoxPredictor, self).__init__(is_training, num_classes)
    self._conv_hyperparams_fn = conv_hyperparams_fn
    self._num_spatial_bins = num_spatial_bins
    self._depth = depth
    self._crop_size = crop_size
    self._box_code_size = box_code_size 

def __init__(self,
               is_training,
               num_classes,
               conv_hyperparams_fn,
               num_spatial_bins,
               depth,
               crop_size,
               box_code_size):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      conv_hyperparams_fn: A function to construct tf-slim arg_scope with
        hyperparameters for convolutional layers.
      num_spatial_bins: A list of two integers `[spatial_bins_y,
        spatial_bins_x]`.
      depth: Target depth to reduce the input feature maps to.
      crop_size: A list of two integers `[crop_height, crop_width]`.
      box_code_size: Size of encoding for each box.
    """
    super(RfcnBoxPredictor, self).__init__(is_training, num_classes)
    self._conv_hyperparams_fn = conv_hyperparams_fn
    self._num_spatial_bins = num_spatial_bins
    self._depth = depth
    self._crop_size = crop_size
    self._box_code_size = box_code_size 

def __init__(self,
               is_training,
               num_classes,
               conv_hyperparams_fn,
               num_spatial_bins,
               depth,
               crop_size,
               box_code_size):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      conv_hyperparams_fn: A function to construct tf-slim arg_scope with
        hyperparameters for convolutional layers.
      num_spatial_bins: A list of two integers `[spatial_bins_y,
        spatial_bins_x]`.
      depth: Target depth to reduce the input feature maps to.
      crop_size: A list of two integers `[crop_height, crop_width]`.
      box_code_size: Size of encoding for each box.
    """
    super(RfcnBoxPredictor, self).__init__(is_training, num_classes)
    self._conv_hyperparams_fn = conv_hyperparams_fn
    self._num_spatial_bins = num_spatial_bins
    self._depth = depth
    self._crop_size = crop_size
    self._box_code_size = box_code_size 

def __init__(self,
               is_training,
               num_classes,
               box_prediction_head,
               class_prediction_head,
               other_heads,
               conv_hyperparams_fn,
               num_layers_before_predictor,
               min_depth,
               max_depth):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      box_prediction_head: The head that predicts the boxes.
      class_prediction_head: The head that predicts the classes.
      other_heads: A dictionary mapping head names to convolutional
        head classes.
      conv_hyperparams_fn: A function to generate tf-slim arg_scope with
        hyperparameters for convolution ops.
      num_layers_before_predictor: Number of the additional conv layers before
        the predictor.
      min_depth: Minimum feature depth prior to predicting box encodings
        and class predictions.
      max_depth: Maximum feature depth prior to predicting box encodings
        and class predictions. If max_depth is set to 0, no additional
        feature map will be inserted before location and class predictions.

    Raises:
      ValueError: if min_depth > max_depth.
    """
    super(ConvolutionalBoxPredictor, self).__init__(is_training, num_classes)
    self._box_prediction_head = box_prediction_head
    self._class_prediction_head = class_prediction_head
    self._other_heads = other_heads
    self._conv_hyperparams_fn = conv_hyperparams_fn
    self._min_depth = min_depth
    self._max_depth = max_depth
    self._num_layers_before_predictor = num_layers_before_predictor 

def __init__(self,
               is_training,
               num_classes,
               box_prediction_head,
               class_prediction_head,
               other_heads,
               conv_hyperparams_fn,
               depth,
               num_layers_before_predictor,
               kernel_size=3,
               apply_batch_norm=False,
               share_prediction_tower=False,
               use_depthwise=False):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      box_prediction_head: The head that predicts the boxes.
      class_prediction_head: The head that predicts the classes.
      other_heads: A dictionary mapping head names to convolutional
        head classes.
      conv_hyperparams_fn: A function to generate tf-slim arg_scope with
        hyperparameters for convolution ops.
      depth: depth of conv layers.
      num_layers_before_predictor: Number of the additional conv layers before
        the predictor.
      kernel_size: Size of final convolution kernel.
      apply_batch_norm: Whether to apply batch normalization to conv layers in
        this predictor.
      share_prediction_tower: Whether to share the multi-layer tower between box
        prediction and class prediction heads.
      use_depthwise: Whether to use depthwise separable conv2d instead of
       regular conv2d.
    """
    super(WeightSharedConvolutionalBoxPredictor, self).__init__(is_training,
                                                                num_classes)
    self._box_prediction_head = box_prediction_head
    self._class_prediction_head = class_prediction_head
    self._other_heads = other_heads
    self._conv_hyperparams_fn = conv_hyperparams_fn
    self._depth = depth
    self._num_layers_before_predictor = num_layers_before_predictor
    self._kernel_size = kernel_size
    self._apply_batch_norm = apply_batch_norm
    self._share_prediction_tower = share_prediction_tower
    self._use_depthwise = use_depthwise 

def __init__(self,
               is_training,
               num_classes,
               box_prediction_head,
               class_prediction_head,
               other_heads,
               conv_hyperparams_fn,
               depth,
               num_layers_before_predictor,
               kernel_size=3,
               apply_batch_norm=False,
               share_prediction_tower=False):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      box_prediction_head: The head that predicts the boxes.
      class_prediction_head: The head that predicts the classes.
      other_heads: A dictionary mapping head names to convolutional
        head classes.
      conv_hyperparams_fn: A function to generate tf-slim arg_scope with
        hyperparameters for convolution ops.
      depth: depth of conv layers.
      num_layers_before_predictor: Number of the additional conv layers before
        the predictor.
      kernel_size: Size of final convolution kernel.
      apply_batch_norm: Whether to apply batch normalization to conv layers in
        this predictor.
      share_prediction_tower: Whether to share the multi-layer tower between box
        prediction and class prediction heads.
    """
    super(WeightSharedConvolutionalBoxPredictor, self).__init__(is_training,
                                                                num_classes)
    self._box_prediction_head = box_prediction_head
    self._class_prediction_head = class_prediction_head
    self._other_heads = other_heads
    self._conv_hyperparams_fn = conv_hyperparams_fn
    self._depth = depth
    self._num_layers_before_predictor = num_layers_before_predictor
    self._kernel_size = kernel_size
    self._apply_batch_norm = apply_batch_norm
    self._share_prediction_tower = share_prediction_tower 

def __init__(self,
               is_training,
               num_classes,
               box_prediction_head,
               class_prediction_head,
               other_heads,
               conv_hyperparams_fn,
               num_layers_before_predictor,
               min_depth,
               max_depth):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      box_prediction_head: The head that predicts the boxes.
      class_prediction_head: The head that predicts the classes.
      other_heads: A dictionary mapping head names to convolutional
        head classes.
      conv_hyperparams_fn: A function to generate tf-slim arg_scope with
        hyperparameters for convolution ops.
      num_layers_before_predictor: Number of the additional conv layers before
        the predictor.
      min_depth: Minimum feature depth prior to predicting box encodings
        and class predictions.
      max_depth: Maximum feature depth prior to predicting box encodings
        and class predictions. If max_depth is set to 0, no additional
        feature map will be inserted before location and class predictions.

    Raises:
      ValueError: if min_depth > max_depth.
    """
    super(ConvolutionalBoxPredictor, self).__init__(is_training, num_classes)
    self._box_prediction_head = box_prediction_head
    self._class_prediction_head = class_prediction_head
    self._other_heads = other_heads
    self._conv_hyperparams_fn = conv_hyperparams_fn
    self._min_depth = min_depth
    self._max_depth = max_depth
    self._num_layers_before_predictor = num_layers_before_predictor 

def __init__(self,
               is_training,
               num_classes,
               box_prediction_head,
               class_prediction_head,
               other_heads,
               conv_hyperparams_fn,
               depth,
               num_layers_before_predictor,
               kernel_size=3,
               apply_batch_norm=False,
               share_prediction_tower=False,
               use_depthwise=False):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      box_prediction_head: The head that predicts the boxes.
      class_prediction_head: The head that predicts the classes.
      other_heads: A dictionary mapping head names to convolutional
        head classes.
      conv_hyperparams_fn: A function to generate tf-slim arg_scope with
        hyperparameters for convolution ops.
      depth: depth of conv layers.
      num_layers_before_predictor: Number of the additional conv layers before
        the predictor.
      kernel_size: Size of final convolution kernel.
      apply_batch_norm: Whether to apply batch normalization to conv layers in
        this predictor.
      share_prediction_tower: Whether to share the multi-layer tower between box
        prediction and class prediction heads.
      use_depthwise: Whether to use depthwise separable conv2d instead of
       regular conv2d.
    """
    super(WeightSharedConvolutionalBoxPredictor, self).__init__(is_training,
                                                                num_classes)
    self._box_prediction_head = box_prediction_head
    self._class_prediction_head = class_prediction_head
    self._other_heads = other_heads
    self._conv_hyperparams_fn = conv_hyperparams_fn
    self._depth = depth
    self._num_layers_before_predictor = num_layers_before_predictor
    self._kernel_size = kernel_size
    self._apply_batch_norm = apply_batch_norm
    self._share_prediction_tower = share_prediction_tower
    self._use_depthwise = use_depthwise 

def __init__(self,
               is_training,
               num_classes,
               box_prediction_head,
               class_prediction_head,
               other_heads,
               conv_hyperparams_fn,
               num_layers_before_predictor,
               min_depth,
               max_depth):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      box_prediction_head: The head that predicts the boxes.
      class_prediction_head: The head that predicts the classes.
      other_heads: A dictionary mapping head names to convolutional
        head classes.
      conv_hyperparams_fn: A function to generate tf-slim arg_scope with
        hyperparameters for convolution ops.
      num_layers_before_predictor: Number of the additional conv layers before
        the predictor.
      min_depth: Minimum feature depth prior to predicting box encodings
        and class predictions.
      max_depth: Maximum feature depth prior to predicting box encodings
        and class predictions. If max_depth is set to 0, no additional
        feature map will be inserted before location and class predictions.

    Raises:
      ValueError: if min_depth > max_depth.
    """
    super(ConvolutionalBoxPredictor, self).__init__(is_training, num_classes)
    self._box_prediction_head = box_prediction_head
    self._class_prediction_head = class_prediction_head
    self._other_heads = other_heads
    self._conv_hyperparams_fn = conv_hyperparams_fn
    self._min_depth = min_depth
    self._max_depth = max_depth
    self._num_layers_before_predictor = num_layers_before_predictor 

def __init__(self,
               is_training,
               num_classes,
               box_prediction_head,
               class_prediction_head,
               other_heads,
               conv_hyperparams_fn,
               num_layers_before_predictor,
               min_depth,
               max_depth):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      box_prediction_head: The head that predicts the boxes.
      class_prediction_head: The head that predicts the classes.
      other_heads: A dictionary mapping head names to convolutional
        head classes.
      conv_hyperparams_fn: A function to generate tf-slim arg_scope with
        hyperparameters for convolution ops.
      num_layers_before_predictor: Number of the additional conv layers before
        the predictor.
      min_depth: Minimum feature depth prior to predicting box encodings
        and class predictions.
      max_depth: Maximum feature depth prior to predicting box encodings
        and class predictions. If max_depth is set to 0, no additional
        feature map will be inserted before location and class predictions.

    Raises:
      ValueError: if min_depth > max_depth.
    """
    super(ConvolutionalBoxPredictor, self).__init__(is_training, num_classes)
    self._box_prediction_head = box_prediction_head
    self._class_prediction_head = class_prediction_head
    self._other_heads = other_heads
    self._conv_hyperparams_fn = conv_hyperparams_fn
    self._min_depth = min_depth
    self._max_depth = max_depth
    self._num_layers_before_predictor = num_layers_before_predictor 

def __init__(self,
               is_training,
               num_classes,
               box_prediction_head,
               class_prediction_head,
               other_heads,
               conv_hyperparams_fn,
               depth,
               num_layers_before_predictor,
               kernel_size=3,
               apply_batch_norm=False,
               share_prediction_tower=False,
               use_depthwise=False):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      box_prediction_head: The head that predicts the boxes.
      class_prediction_head: The head that predicts the classes.
      other_heads: A dictionary mapping head names to convolutional
        head classes.
      conv_hyperparams_fn: A function to generate tf-slim arg_scope with
        hyperparameters for convolution ops.
      depth: depth of conv layers.
      num_layers_before_predictor: Number of the additional conv layers before
        the predictor.
      kernel_size: Size of final convolution kernel.
      apply_batch_norm: Whether to apply batch normalization to conv layers in
        this predictor.
      share_prediction_tower: Whether to share the multi-layer tower among box
        prediction head, class prediction head and other heads.
      use_depthwise: Whether to use depthwise separable conv2d instead of
       regular conv2d.
    """
    super(WeightSharedConvolutionalBoxPredictor, self).__init__(is_training,
                                                                num_classes)
    self._box_prediction_head = box_prediction_head
    self._class_prediction_head = class_prediction_head
    self._other_heads = other_heads
    self._conv_hyperparams_fn = conv_hyperparams_fn
    self._depth = depth
    self._num_layers_before_predictor = num_layers_before_predictor
    self._kernel_size = kernel_size
    self._apply_batch_norm = apply_batch_norm
    self._share_prediction_tower = share_prediction_tower
    self._use_depthwise = use_depthwise 

def __init__(self,
               is_training,
               num_classes,
               box_prediction_head,
               class_prediction_head,
               other_heads,
               conv_hyperparams_fn,
               depth,
               num_layers_before_predictor,
               kernel_size=3,
               apply_batch_norm=False,
               share_prediction_tower=False,
               use_depthwise=False):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      box_prediction_head: The head that predicts the boxes.
      class_prediction_head: The head that predicts the classes.
      other_heads: A dictionary mapping head names to convolutional
        head classes.
      conv_hyperparams_fn: A function to generate tf-slim arg_scope with
        hyperparameters for convolution ops.
      depth: depth of conv layers.
      num_layers_before_predictor: Number of the additional conv layers before
        the predictor.
      kernel_size: Size of final convolution kernel.
      apply_batch_norm: Whether to apply batch normalization to conv layers in
        this predictor.
      share_prediction_tower: Whether to share the multi-layer tower between box
        prediction and class prediction heads.
      use_depthwise: Whether to use depthwise separable conv2d instead of
       regular conv2d.
    """
    super(WeightSharedConvolutionalBoxPredictor, self).__init__(is_training,
                                                                num_classes)
    self._box_prediction_head = box_prediction_head
    self._class_prediction_head = class_prediction_head
    self._other_heads = other_heads
    self._conv_hyperparams_fn = conv_hyperparams_fn
    self._depth = depth
    self._num_layers_before_predictor = num_layers_before_predictor
    self._kernel_size = kernel_size
    self._apply_batch_norm = apply_batch_norm
    self._share_prediction_tower = share_prediction_tower
    self._use_depthwise = use_depthwise 

def __init__(self,
               is_training,
               num_classes,
               box_prediction_head,
               class_prediction_head,
               other_heads,
               conv_hyperparams_fn,
               num_layers_before_predictor,
               min_depth,
               max_depth):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      box_prediction_head: The head that predicts the boxes.
      class_prediction_head: The head that predicts the classes.
      other_heads: A dictionary mapping head names to convolutional
        head classes.
      conv_hyperparams_fn: A function to generate tf-slim arg_scope with
        hyperparameters for convolution ops.
      num_layers_before_predictor: Number of the additional conv layers before
        the predictor.
      min_depth: Minimum feature depth prior to predicting box encodings
        and class predictions.
      max_depth: Maximum feature depth prior to predicting box encodings
        and class predictions. If max_depth is set to 0, no additional
        feature map will be inserted before location and class predictions.

    Raises:
      ValueError: if min_depth > max_depth.
    """
    super(ConvolutionalBoxPredictor, self).__init__(is_training, num_classes)
    self._box_prediction_head = box_prediction_head
    self._class_prediction_head = class_prediction_head
    self._other_heads = other_heads
    self._conv_hyperparams_fn = conv_hyperparams_fn
    self._min_depth = min_depth
    self._max_depth = max_depth
    self._num_layers_before_predictor = num_layers_before_predictor 

def __init__(self,
               is_training,
               num_classes,
               box_prediction_head,
               class_prediction_head,
               other_heads,
               conv_hyperparams_fn,
               num_layers_before_predictor,
               min_depth,
               max_depth):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      box_prediction_head: The head that predicts the boxes.
      class_prediction_head: The head that predicts the classes.
      other_heads: A dictionary mapping head names to convolutional
        head classes.
      conv_hyperparams_fn: A function to generate tf-slim arg_scope with
        hyperparameters for convolution ops.
      num_layers_before_predictor: Number of the additional conv layers before
        the predictor.
      min_depth: Minimum feature depth prior to predicting box encodings
        and class predictions.
      max_depth: Maximum feature depth prior to predicting box encodings
        and class predictions. If max_depth is set to 0, no additional
        feature map will be inserted before location and class predictions.

    Raises:
      ValueError: if min_depth > max_depth.
    """
    super(ConvolutionalBoxPredictor, self).__init__(is_training, num_classes)
    self._box_prediction_head = box_prediction_head
    self._class_prediction_head = class_prediction_head
    self._other_heads = other_heads
    self._conv_hyperparams_fn = conv_hyperparams_fn
    self._min_depth = min_depth
    self._max_depth = max_depth
    self._num_layers_before_predictor = num_layers_before_predictor 

def __init__(self,
               is_training,
               num_classes,
               box_prediction_head,
               class_prediction_head,
               other_heads,
               conv_hyperparams_fn,
               depth,
               num_layers_before_predictor,
               kernel_size=3,
               apply_batch_norm=False,
               share_prediction_tower=False,
               use_depthwise=False):
    """Constructor.

    Args:
      is_training: Indicates whether the BoxPredictor is in training mode.
      num_classes: number of classes.  Note that num_classes *does not*
        include the background category, so if groundtruth labels take values
        in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
        assigned classification targets can range from {0,... K}).
      box_prediction_head: The head that predicts the boxes.
      class_prediction_head: The head that predicts the classes.
      other_heads: A dictionary mapping head names to convolutional
        head classes.
      conv_hyperparams_fn: A function to generate tf-slim arg_scope with
        hyperparameters for convolution ops.
      depth: depth of conv layers.
      num_layers_before_predictor: Number of the additional conv layers before
        the predictor.
      kernel_size: Size of final convolution kernel.
      apply_batch_norm: Whether to apply batch normalization to conv layers in
        this predictor.
      share_prediction_tower: Whether to share the multi-layer tower between box
        prediction and class prediction heads.
      use_depthwise: Whether to use depthwise separable conv2d instead of
       regular conv2d.
    """
    super(WeightSharedConvolutionalBoxPredictor, self).__init__(is_training,
                                                                num_classes)
    self._box_prediction_head = box_prediction_head
    self._class_prediction_head = class_prediction_head
    self._other_heads = other_heads
    self._conv_hyperparams_fn = conv_hyperparams_fn
    self._depth = depth
    self._num_layers_before_predictor = num_layers_before_predictor
    self._kernel_size = kernel_size
    self._apply_batch_norm = apply_batch_norm
    self._share_prediction_tower = share_prediction_tower
    self._use_depthwise = use_depthwise