Python object_detection.meta_architectures.ssd_meta_arch.SSDFeatureExtractor() Examples

The following are 28 code examples of object_detection.meta_architectures.ssd_meta_arch.SSDFeatureExtractor(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module object_detection.meta_architectures.ssd_meta_arch , or try the search function .
Example #1
Source File: ssd_pnasnet_feature_extractor.py    From multilabel-image-classification-tensorflow with MIT License 6 votes vote down vote up
def restore_from_classification_checkpoint_fn(self, feature_extractor_scope):
    """Returns a map of variables to load from a foreign checkpoint.

    Note that this overrides the default implementation in
    ssd_meta_arch.SSDFeatureExtractor which does not work for PNASNet
    checkpoints.

    Args:
      feature_extractor_scope: A scope name for the first stage feature
        extractor.

    Returns:
      A dict mapping variable names (to load from a checkpoint) to variables in
      the model graph.
    """
    variables_to_restore = {}
    for variable in tf.global_variables():
      if variable.op.name.startswith(feature_extractor_scope):
        var_name = variable.op.name.replace(feature_extractor_scope + '/', '')
        var_name += '/ExponentialMovingAverage'
        variables_to_restore[var_name] = variable
    return variables_to_restore 
Example #2
Source File: ssd_pnasnet_feature_extractor.py    From vehicle_counting_tensorflow with MIT License 6 votes vote down vote up
def restore_from_classification_checkpoint_fn(self, feature_extractor_scope):
    """Returns a map of variables to load from a foreign checkpoint.

    Note that this overrides the default implementation in
    ssd_meta_arch.SSDFeatureExtractor which does not work for PNASNet
    checkpoints.

    Args:
      feature_extractor_scope: A scope name for the first stage feature
        extractor.

    Returns:
      A dict mapping variable names (to load from a checkpoint) to variables in
      the model graph.
    """
    variables_to_restore = {}
    for variable in tf.global_variables():
      if variable.op.name.startswith(feature_extractor_scope):
        var_name = variable.op.name.replace(feature_extractor_scope + '/', '')
        var_name += '/ExponentialMovingAverage'
        variables_to_restore[var_name] = variable
    return variables_to_restore 
Example #3
Source File: ssd_pnasnet_feature_extractor.py    From models with Apache License 2.0 6 votes vote down vote up
def restore_from_classification_checkpoint_fn(self, feature_extractor_scope):
    """Returns a map of variables to load from a foreign checkpoint.

    Note that this overrides the default implementation in
    ssd_meta_arch.SSDFeatureExtractor which does not work for PNASNet
    checkpoints.

    Args:
      feature_extractor_scope: A scope name for the first stage feature
        extractor.

    Returns:
      A dict mapping variable names (to load from a checkpoint) to variables in
      the model graph.
    """
    variables_to_restore = {}
    for variable in variables_helper.get_global_variables_safely():
      if variable.op.name.startswith(feature_extractor_scope):
        var_name = variable.op.name.replace(feature_extractor_scope + '/', '')
        var_name += '/ExponentialMovingAverage'
        variables_to_restore[var_name] = variable
    return variables_to_restore 
Example #4
Source File: ssd_pnasnet_feature_extractor.py    From g-tensorflow-models with Apache License 2.0 6 votes vote down vote up
def restore_from_classification_checkpoint_fn(self, feature_extractor_scope):
    """Returns a map of variables to load from a foreign checkpoint.

    Note that this overrides the default implementation in
    ssd_meta_arch.SSDFeatureExtractor which does not work for PNASNet
    checkpoints.

    Args:
      feature_extractor_scope: A scope name for the first stage feature
        extractor.

    Returns:
      A dict mapping variable names (to load from a checkpoint) to variables in
      the model graph.
    """
    variables_to_restore = {}
    for variable in tf.global_variables():
      if variable.op.name.startswith(feature_extractor_scope):
        var_name = variable.op.name.replace(feature_extractor_scope + '/', '')
        var_name += '/ExponentialMovingAverage'
        variables_to_restore[var_name] = variable
    return variables_to_restore 
Example #5
Source File: ssd_pnasnet_feature_extractor.py    From MAX-Object-Detector with Apache License 2.0 6 votes vote down vote up
def restore_from_classification_checkpoint_fn(self, feature_extractor_scope):
    """Returns a map of variables to load from a foreign checkpoint.

    Note that this overrides the default implementation in
    ssd_meta_arch.SSDFeatureExtractor which does not work for PNASNet
    checkpoints.

    Args:
      feature_extractor_scope: A scope name for the first stage feature
        extractor.

    Returns:
      A dict mapping variable names (to load from a checkpoint) to variables in
      the model graph.
    """
    variables_to_restore = {}
    for variable in tf.global_variables():
      if variable.op.name.startswith(feature_extractor_scope):
        var_name = variable.op.name.replace(feature_extractor_scope + '/', '')
        var_name += '/ExponentialMovingAverage'
        variables_to_restore[var_name] = variable
    return variables_to_restore 
Example #6
Source File: ssd_pnasnet_feature_extractor.py    From Live-feed-object-device-identification-using-Tensorflow-and-OpenCV with Apache License 2.0 6 votes vote down vote up
def restore_from_classification_checkpoint_fn(self, feature_extractor_scope):
    """Returns a map of variables to load from a foreign checkpoint.

    Note that this overrides the default implementation in
    ssd_meta_arch.SSDFeatureExtractor which does not work for PNASNet
    checkpoints.

    Args:
      feature_extractor_scope: A scope name for the first stage feature
        extractor.

    Returns:
      A dict mapping variable names (to load from a checkpoint) to variables in
      the model graph.
    """
    variables_to_restore = {}
    for variable in variables_helper.get_global_variables_safely():
      if variable.op.name.startswith(feature_extractor_scope):
        var_name = variable.op.name.replace(feature_extractor_scope + '/', '')
        var_name += '/ExponentialMovingAverage'
        variables_to_restore[var_name] = variable
    return variables_to_restore 
Example #7
Source File: model_builder.py    From moveo_ros with MIT License 5 votes vote down vote up
def _build_ssd_feature_extractor(feature_extractor_config, is_training,
                                 reuse_weights=None):
  """Builds a ssd_meta_arch.SSDFeatureExtractor based on config.

  Args:
    feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
    is_training: True if this feature extractor is being built for training.
    reuse_weights: if the feature extractor should reuse weights.

  Returns:
    ssd_meta_arch.SSDFeatureExtractor based on config.

  Raises:
    ValueError: On invalid feature extractor type.
  """
  feature_type = feature_extractor_config.type
  depth_multiplier = feature_extractor_config.depth_multiplier
  min_depth = feature_extractor_config.min_depth
  conv_hyperparams = hyperparams_builder.build(
      feature_extractor_config.conv_hyperparams, is_training)

  if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP:
    raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type))

  feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
  return feature_extractor_class(depth_multiplier, min_depth, conv_hyperparams,
                                 reuse_weights) 
Example #8
Source File: model_builder.py    From mtl-ssl with Apache License 2.0 5 votes vote down vote up
def _build_ssd_feature_extractor(feature_extractor_config, is_training,
                                 reuse_weights=None):
  """Builds a ssd_meta_arch.SSDFeatureExtractor based on config.

  Args:
    feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
    is_training: True if this feature extractor is being built for training.
    reuse_weights: if the feature extractor should reuse weights.

  Returns:
    ssd_meta_arch.SSDFeatureExtractor based on config.

  Raises:
    ValueError: On invalid feature extractor type.
  """
  feature_type = feature_extractor_config.type
  depth_multiplier = feature_extractor_config.depth_multiplier
  min_depth = feature_extractor_config.min_depth
  conv_hyperparams = hyperparams_builder.build(
      feature_extractor_config.conv_hyperparams, is_training)

  if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP:
    raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type))

  feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
  return feature_extractor_class(depth_multiplier, min_depth, conv_hyperparams,
                                 reuse_weights) 
Example #9
Source File: model_builder.py    From AniSeg with Apache License 2.0 5 votes vote down vote up
def _build_ssd_feature_extractor(feature_extractor_config, is_training,
                                 reuse_weights=None):
  """Builds a ssd_meta_arch.SSDFeatureExtractor based on config.

  Args:
    feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
    is_training: True if this feature extractor is being built for training.
    reuse_weights: if the feature extractor should reuse weights.

  Returns:
    ssd_meta_arch.SSDFeatureExtractor based on config.

  Raises:
    ValueError: On invalid feature extractor type.
  """
  feature_type = feature_extractor_config.type
  depth_multiplier = feature_extractor_config.depth_multiplier
  min_depth = feature_extractor_config.min_depth
  pad_to_multiple = feature_extractor_config.pad_to_multiple
  batch_norm_trainable = feature_extractor_config.batch_norm_trainable
  use_explicit_padding = feature_extractor_config.use_explicit_padding
  use_depthwise = feature_extractor_config.use_depthwise
  conv_hyperparams = hyperparams_builder.build(
      feature_extractor_config.conv_hyperparams, is_training)

  if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP:
    raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type))

  feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
  return feature_extractor_class(is_training, depth_multiplier, min_depth,
                                 pad_to_multiple, conv_hyperparams,
                                 batch_norm_trainable, reuse_weights,
                                 use_explicit_padding, use_depthwise) 
Example #10
Source File: model_builder.py    From object_detection_with_tensorflow with MIT License 5 votes vote down vote up
def _build_ssd_feature_extractor(feature_extractor_config, is_training,
                                 reuse_weights=None):
  """Builds a ssd_meta_arch.SSDFeatureExtractor based on config.

  Args:
    feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
    is_training: True if this feature extractor is being built for training.
    reuse_weights: if the feature extractor should reuse weights.

  Returns:
    ssd_meta_arch.SSDFeatureExtractor based on config.

  Raises:
    ValueError: On invalid feature extractor type.
  """
  feature_type = feature_extractor_config.type
  depth_multiplier = feature_extractor_config.depth_multiplier
  min_depth = feature_extractor_config.min_depth
  pad_to_multiple = feature_extractor_config.pad_to_multiple
  batch_norm_trainable = feature_extractor_config.batch_norm_trainable
  conv_hyperparams = hyperparams_builder.build(
      feature_extractor_config.conv_hyperparams, is_training)

  if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP:
    raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type))

  feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
  return feature_extractor_class(is_training, depth_multiplier, min_depth,
                                 pad_to_multiple, conv_hyperparams,
                                 batch_norm_trainable, reuse_weights) 
Example #11
Source File: model_builder.py    From object_detection_with_tensorflow with MIT License 5 votes vote down vote up
def _build_ssd_feature_extractor(feature_extractor_config, is_training,
                                 reuse_weights=None):
  """Builds a ssd_meta_arch.SSDFeatureExtractor based on config.

  Args:
    feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
    is_training: True if this feature extractor is being built for training.
    reuse_weights: if the feature extractor should reuse weights.

  Returns:
    ssd_meta_arch.SSDFeatureExtractor based on config.

  Raises:
    ValueError: On invalid feature extractor type.
  """
  feature_type = feature_extractor_config.type
  depth_multiplier = feature_extractor_config.depth_multiplier
  min_depth = feature_extractor_config.min_depth
  pad_to_multiple = feature_extractor_config.pad_to_multiple
  batch_norm_trainable = feature_extractor_config.batch_norm_trainable
  conv_hyperparams = hyperparams_builder.build(
      feature_extractor_config.conv_hyperparams, is_training)

  if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP:
    raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type))

  feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
  return feature_extractor_class(is_training, depth_multiplier, min_depth,
                                 pad_to_multiple, conv_hyperparams,
                                 batch_norm_trainable, reuse_weights) 
Example #12
Source File: model_builder.py    From Elphas with Apache License 2.0 5 votes vote down vote up
def _build_ssd_feature_extractor(feature_extractor_config, is_training,
                                 reuse_weights=None):
  """Builds a ssd_meta_arch.SSDFeatureExtractor based on config.

  Args:
    feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
    is_training: True if this feature extractor is being built for training.
    reuse_weights: if the feature extractor should reuse weights.

  Returns:
    ssd_meta_arch.SSDFeatureExtractor based on config.

  Raises:
    ValueError: On invalid feature extractor type.
  """
  feature_type = feature_extractor_config.type
  depth_multiplier = feature_extractor_config.depth_multiplier
  min_depth = feature_extractor_config.min_depth
  pad_to_multiple = feature_extractor_config.pad_to_multiple
  batch_norm_trainable = feature_extractor_config.batch_norm_trainable
  use_explicit_padding = feature_extractor_config.use_explicit_padding
  use_depthwise = feature_extractor_config.use_depthwise
  conv_hyperparams = hyperparams_builder.build(
      feature_extractor_config.conv_hyperparams, is_training)

  if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP:
    raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type))

  feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
  return feature_extractor_class(is_training, depth_multiplier, min_depth,
                                 pad_to_multiple, conv_hyperparams,
                                 batch_norm_trainable, reuse_weights,
                                 use_explicit_padding, use_depthwise) 
Example #13
Source File: model_builder.py    From MBMD with MIT License 5 votes vote down vote up
def _build_ssd_feature_extractor(feature_extractor_config, is_training,
                                 reuse_weights=None):
  """Builds a ssd_meta_arch.SSDFeatureExtractor based on config.

  Args:
    feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
    is_training: True if this feature extractor is being built for training.
    reuse_weights: if the feature extractor should reuse weights.

  Returns:
    ssd_meta_arch.SSDFeatureExtractor based on config.

  Raises:
    ValueError: On invalid feature extractor type.
  """
  feature_type = feature_extractor_config.type
  depth_multiplier = feature_extractor_config.depth_multiplier
  min_depth = feature_extractor_config.min_depth
  conv_hyperparams = hyperparams_builder.build(
      feature_extractor_config.conv_hyperparams, is_training)

  if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP:
    raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type))

  feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
  return feature_extractor_class(depth_multiplier, min_depth, conv_hyperparams,
                                 reuse_weights) 
Example #14
Source File: model_builder.py    From object_detection_kitti with Apache License 2.0 5 votes vote down vote up
def _build_ssd_feature_extractor(feature_extractor_config, is_training,
                                 reuse_weights=None):
  """Builds a ssd_meta_arch.SSDFeatureExtractor based on config.

  Args:
    feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
    is_training: True if this feature extractor is being built for training.
    reuse_weights: if the feature extractor should reuse weights.

  Returns:
    ssd_meta_arch.SSDFeatureExtractor based on config.

  Raises:
    ValueError: On invalid feature extractor type.
  """
  feature_type = feature_extractor_config.type
  depth_multiplier = feature_extractor_config.depth_multiplier
  min_depth = feature_extractor_config.min_depth
  conv_hyperparams = hyperparams_builder.build(
      feature_extractor_config.conv_hyperparams, is_training)

  if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP:
    raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type))

  feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
  return feature_extractor_class(depth_multiplier, min_depth, conv_hyperparams,
                                 reuse_weights) 
Example #15
Source File: model_builder.py    From hands-detection with MIT License 5 votes vote down vote up
def _build_ssd_feature_extractor(feature_extractor_config, is_training,
                                 reuse_weights=None):
  """Builds a ssd_meta_arch.SSDFeatureExtractor based on config.

  Args:
    feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
    is_training: True if this feature extractor is being built for training.
    reuse_weights: if the feature extractor should reuse weights.

  Returns:
    ssd_meta_arch.SSDFeatureExtractor based on config.

  Raises:
    ValueError: On invalid feature extractor type.
  """
  feature_type = feature_extractor_config.type
  depth_multiplier = feature_extractor_config.depth_multiplier
  min_depth = feature_extractor_config.min_depth
  conv_hyperparams = hyperparams_builder.build(
      feature_extractor_config.conv_hyperparams, is_training)

  if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP:
    raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type))

  feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
  return feature_extractor_class(depth_multiplier, min_depth, conv_hyperparams,
                                 reuse_weights) 
Example #16
Source File: model_builder.py    From DOTA_models with Apache License 2.0 5 votes vote down vote up
def _build_ssd_feature_extractor(feature_extractor_config, is_training,
                                 reuse_weights=None):
  """Builds a ssd_meta_arch.SSDFeatureExtractor based on config.

  Args:
    feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
    is_training: True if this feature extractor is being built for training.
    reuse_weights: if the feature extractor should reuse weights.

  Returns:
    ssd_meta_arch.SSDFeatureExtractor based on config.

  Raises:
    ValueError: On invalid feature extractor type.
  """
  feature_type = feature_extractor_config.type
  depth_multiplier = feature_extractor_config.depth_multiplier
  min_depth = feature_extractor_config.min_depth
  conv_hyperparams = hyperparams_builder.build(
      feature_extractor_config.conv_hyperparams, is_training)

  if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP:
    raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type))

  feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
  return feature_extractor_class(depth_multiplier, min_depth, conv_hyperparams,
                                 reuse_weights) 
Example #17
Source File: model_builder.py    From ros_tensorflow with Apache License 2.0 5 votes vote down vote up
def _build_ssd_feature_extractor(feature_extractor_config, is_training,
                                 reuse_weights=None):
  """Builds a ssd_meta_arch.SSDFeatureExtractor based on config.

  Args:
    feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
    is_training: True if this feature extractor is being built for training.
    reuse_weights: if the feature extractor should reuse weights.

  Returns:
    ssd_meta_arch.SSDFeatureExtractor based on config.

  Raises:
    ValueError: On invalid feature extractor type.
  """
  feature_type = feature_extractor_config.type
  depth_multiplier = feature_extractor_config.depth_multiplier
  min_depth = feature_extractor_config.min_depth
  pad_to_multiple = feature_extractor_config.pad_to_multiple
  use_explicit_padding = feature_extractor_config.use_explicit_padding
  use_depthwise = feature_extractor_config.use_depthwise
  conv_hyperparams = hyperparams_builder.build(
      feature_extractor_config.conv_hyperparams, is_training)
  override_base_feature_extractor_hyperparams = (
      feature_extractor_config.override_base_feature_extractor_hyperparams)

  if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP:
    raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type))

  feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
  return feature_extractor_class(
      is_training, depth_multiplier, min_depth, pad_to_multiple,
      conv_hyperparams, reuse_weights, use_explicit_padding, use_depthwise,
      override_base_feature_extractor_hyperparams) 
Example #18
Source File: model_builder.py    From Gun-Detector with Apache License 2.0 5 votes vote down vote up
def _build_ssd_feature_extractor(feature_extractor_config, is_training,
                                 reuse_weights=None):
  """Builds a ssd_meta_arch.SSDFeatureExtractor based on config.

  Args:
    feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
    is_training: True if this feature extractor is being built for training.
    reuse_weights: if the feature extractor should reuse weights.

  Returns:
    ssd_meta_arch.SSDFeatureExtractor based on config.

  Raises:
    ValueError: On invalid feature extractor type.
  """
  feature_type = feature_extractor_config.type
  depth_multiplier = feature_extractor_config.depth_multiplier
  min_depth = feature_extractor_config.min_depth
  pad_to_multiple = feature_extractor_config.pad_to_multiple
  use_explicit_padding = feature_extractor_config.use_explicit_padding
  use_depthwise = feature_extractor_config.use_depthwise
  conv_hyperparams = hyperparams_builder.build(
      feature_extractor_config.conv_hyperparams, is_training)
  override_base_feature_extractor_hyperparams = (
      feature_extractor_config.override_base_feature_extractor_hyperparams)

  if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP:
    raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type))

  feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
  return feature_extractor_class(
      is_training, depth_multiplier, min_depth, pad_to_multiple,
      conv_hyperparams, reuse_weights, use_explicit_padding, use_depthwise,
      override_base_feature_extractor_hyperparams) 
Example #19
Source File: model_builder.py    From tensorflow with BSD 2-Clause "Simplified" License 5 votes vote down vote up
def _build_ssd_feature_extractor(feature_extractor_config, is_training,
                                 reuse_weights=None):
  """Builds a ssd_meta_arch.SSDFeatureExtractor based on config.

  Args:
    feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
    is_training: True if this feature extractor is being built for training.
    reuse_weights: if the feature extractor should reuse weights.

  Returns:
    ssd_meta_arch.SSDFeatureExtractor based on config.

  Raises:
    ValueError: On invalid feature extractor type.
  """
  feature_type = feature_extractor_config.type
  depth_multiplier = feature_extractor_config.depth_multiplier
  min_depth = feature_extractor_config.min_depth
  conv_hyperparams = hyperparams_builder.build(
      feature_extractor_config.conv_hyperparams, is_training)

  if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP:
    raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type))

  feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
  return feature_extractor_class(depth_multiplier, min_depth, conv_hyperparams,
                                 reuse_weights) 
Example #20
Source File: model_builder.py    From Hands-On-Machine-Learning-with-OpenCV-4 with MIT License 5 votes vote down vote up
def _build_ssd_feature_extractor(feature_extractor_config, is_training,
                                 reuse_weights=None):
  """Builds a ssd_meta_arch.SSDFeatureExtractor based on config.

  Args:
    feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
    is_training: True if this feature extractor is being built for training.
    reuse_weights: if the feature extractor should reuse weights.

  Returns:
    ssd_meta_arch.SSDFeatureExtractor based on config.

  Raises:
    ValueError: On invalid feature extractor type.
  """
  feature_type = feature_extractor_config.type
  depth_multiplier = feature_extractor_config.depth_multiplier
  min_depth = feature_extractor_config.min_depth
  conv_hyperparams = hyperparams_builder.build(
      feature_extractor_config.conv_hyperparams, is_training)

  if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP:
    raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type))

  feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
  return feature_extractor_class(depth_multiplier, min_depth, conv_hyperparams,
                                 reuse_weights) 
Example #21
Source File: model_builder.py    From Traffic-Rule-Violation-Detection-System with MIT License 5 votes vote down vote up
def _build_ssd_feature_extractor(feature_extractor_config, is_training,
                                 reuse_weights=None):
  """Builds a ssd_meta_arch.SSDFeatureExtractor based on config.

  Args:
    feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
    is_training: True if this feature extractor is being built for training.
    reuse_weights: if the feature extractor should reuse weights.

  Returns:
    ssd_meta_arch.SSDFeatureExtractor based on config.

  Raises:
    ValueError: On invalid feature extractor type.
  """
  feature_type = feature_extractor_config.type
  depth_multiplier = feature_extractor_config.depth_multiplier
  min_depth = feature_extractor_config.min_depth
  pad_to_multiple = feature_extractor_config.pad_to_multiple
  batch_norm_trainable = feature_extractor_config.batch_norm_trainable
  use_explicit_padding = feature_extractor_config.use_explicit_padding
  use_depthwise = feature_extractor_config.use_depthwise
  conv_hyperparams = hyperparams_builder.build(
      feature_extractor_config.conv_hyperparams, is_training)

  if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP:
    raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type))

  feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
  return feature_extractor_class(is_training, depth_multiplier, min_depth,
                                 pad_to_multiple, conv_hyperparams,
                                 batch_norm_trainable, reuse_weights,
                                 use_explicit_padding, use_depthwise) 
Example #22
Source File: model_builder.py    From yolo_v2 with Apache License 2.0 5 votes vote down vote up
def _build_ssd_feature_extractor(feature_extractor_config, is_training,
                                 reuse_weights=None):
  """Builds a ssd_meta_arch.SSDFeatureExtractor based on config.

  Args:
    feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
    is_training: True if this feature extractor is being built for training.
    reuse_weights: if the feature extractor should reuse weights.

  Returns:
    ssd_meta_arch.SSDFeatureExtractor based on config.

  Raises:
    ValueError: On invalid feature extractor type.
  """
  feature_type = feature_extractor_config.type
  depth_multiplier = feature_extractor_config.depth_multiplier
  min_depth = feature_extractor_config.min_depth
  pad_to_multiple = feature_extractor_config.pad_to_multiple
  batch_norm_trainable = feature_extractor_config.batch_norm_trainable
  conv_hyperparams = hyperparams_builder.build(
      feature_extractor_config.conv_hyperparams, is_training)

  if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP:
    raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type))

  feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
  return feature_extractor_class(is_training, depth_multiplier, min_depth,
                                 pad_to_multiple, conv_hyperparams,
                                 batch_norm_trainable, reuse_weights) 
Example #23
Source File: model_builder.py    From HereIsWally with MIT License 5 votes vote down vote up
def _build_ssd_feature_extractor(feature_extractor_config, is_training,
                                 reuse_weights=None):
  """Builds a ssd_meta_arch.SSDFeatureExtractor based on config.

  Args:
    feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
    is_training: True if this feature extractor is being built for training.
    reuse_weights: if the feature extractor should reuse weights.

  Returns:
    ssd_meta_arch.SSDFeatureExtractor based on config.

  Raises:
    ValueError: On invalid feature extractor type.
  """
  feature_type = feature_extractor_config.type
  depth_multiplier = feature_extractor_config.depth_multiplier
  min_depth = feature_extractor_config.min_depth
  conv_hyperparams = hyperparams_builder.build(
      feature_extractor_config.conv_hyperparams, is_training)

  if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP:
    raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type))

  feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
  return feature_extractor_class(depth_multiplier, min_depth, conv_hyperparams,
                                 reuse_weights) 
Example #24
Source File: model_builder.py    From garbage-object-detection-tensorflow with MIT License 5 votes vote down vote up
def _build_ssd_feature_extractor(feature_extractor_config, is_training,
                                 reuse_weights=None):
  """Builds a ssd_meta_arch.SSDFeatureExtractor based on config.

  Args:
    feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
    is_training: True if this feature extractor is being built for training.
    reuse_weights: if the feature extractor should reuse weights.

  Returns:
    ssd_meta_arch.SSDFeatureExtractor based on config.

  Raises:
    ValueError: On invalid feature extractor type.
  """
  feature_type = feature_extractor_config.type
  depth_multiplier = feature_extractor_config.depth_multiplier
  min_depth = feature_extractor_config.min_depth
  conv_hyperparams = hyperparams_builder.build(
      feature_extractor_config.conv_hyperparams, is_training)

  if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP:
    raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type))

  feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
  return feature_extractor_class(depth_multiplier, min_depth, conv_hyperparams,
                                 reuse_weights) 
Example #25
Source File: model_builder.py    From Person-Detection-and-Tracking with MIT License 5 votes vote down vote up
def _build_ssd_feature_extractor(feature_extractor_config, is_training,
                                 reuse_weights=None):
  """Builds a ssd_meta_arch.SSDFeatureExtractor based on config.

  Args:
    feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
    is_training: True if this feature extractor is being built for training.
    reuse_weights: if the feature extractor should reuse weights.

  Returns:
    ssd_meta_arch.SSDFeatureExtractor based on config.

  Raises:
    ValueError: On invalid feature extractor type.
  """
  feature_type = feature_extractor_config.type
  depth_multiplier = feature_extractor_config.depth_multiplier
  min_depth = feature_extractor_config.min_depth
  pad_to_multiple = feature_extractor_config.pad_to_multiple
  use_explicit_padding = feature_extractor_config.use_explicit_padding
  use_depthwise = feature_extractor_config.use_depthwise
  conv_hyperparams = hyperparams_builder.build(
      feature_extractor_config.conv_hyperparams, is_training)
  override_base_feature_extractor_hyperparams = (
      feature_extractor_config.override_base_feature_extractor_hyperparams)

  if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP:
    raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type))

  feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
  return feature_extractor_class(
      is_training, depth_multiplier, min_depth, pad_to_multiple,
      conv_hyperparams, reuse_weights, use_explicit_padding, use_depthwise,
      override_base_feature_extractor_hyperparams) 
Example #26
Source File: model_builder.py    From ros_people_object_detection_tensorflow with Apache License 2.0 5 votes vote down vote up
def _build_ssd_feature_extractor(feature_extractor_config, is_training,
                                 reuse_weights=None):
  """Builds a ssd_meta_arch.SSDFeatureExtractor based on config.

  Args:
    feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
    is_training: True if this feature extractor is being built for training.
    reuse_weights: if the feature extractor should reuse weights.

  Returns:
    ssd_meta_arch.SSDFeatureExtractor based on config.

  Raises:
    ValueError: On invalid feature extractor type.
  """
  feature_type = feature_extractor_config.type
  depth_multiplier = feature_extractor_config.depth_multiplier
  min_depth = feature_extractor_config.min_depth
  pad_to_multiple = feature_extractor_config.pad_to_multiple
  batch_norm_trainable = feature_extractor_config.batch_norm_trainable
  use_explicit_padding = feature_extractor_config.use_explicit_padding
  use_depthwise = feature_extractor_config.use_depthwise
  conv_hyperparams = hyperparams_builder.build(
      feature_extractor_config.conv_hyperparams, is_training)

  if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP:
    raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type))

  feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
  return feature_extractor_class(is_training, depth_multiplier, min_depth,
                                 pad_to_multiple, conv_hyperparams,
                                 batch_norm_trainable, reuse_weights,
                                 use_explicit_padding, use_depthwise) 
Example #27
Source File: model_builder.py    From object_detector_app with MIT License 5 votes vote down vote up
def _build_ssd_feature_extractor(feature_extractor_config, is_training,
                                 reuse_weights=None):
  """Builds a ssd_meta_arch.SSDFeatureExtractor based on config.

  Args:
    feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
    is_training: True if this feature extractor is being built for training.
    reuse_weights: if the feature extractor should reuse weights.

  Returns:
    ssd_meta_arch.SSDFeatureExtractor based on config.

  Raises:
    ValueError: On invalid feature extractor type.
  """
  feature_type = feature_extractor_config.type
  depth_multiplier = feature_extractor_config.depth_multiplier
  min_depth = feature_extractor_config.min_depth
  conv_hyperparams = hyperparams_builder.build(
      feature_extractor_config.conv_hyperparams, is_training)

  if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP:
    raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type))

  feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
  return feature_extractor_class(depth_multiplier, min_depth, conv_hyperparams,
                                 reuse_weights) 
Example #28
Source File: model_builder.py    From BMW-TensorFlow-Training-GUI with Apache License 2.0 4 votes vote down vote up
def _build_ssd_feature_extractor(feature_extractor_config, is_training,
                                 reuse_weights=None):
  """Builds a ssd_meta_arch.SSDFeatureExtractor based on config.

  Args:
    feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
    is_training: True if this feature extractor is being built for training.
    reuse_weights: if the feature extractor should reuse weights.

  Returns:
    ssd_meta_arch.SSDFeatureExtractor based on config.

  Raises:
    ValueError: On invalid feature extractor type.
  """
  feature_type = feature_extractor_config.type
  depth_multiplier = feature_extractor_config.depth_multiplier
  min_depth = feature_extractor_config.min_depth
  pad_to_multiple = feature_extractor_config.pad_to_multiple
  use_explicit_padding = feature_extractor_config.use_explicit_padding
  use_depthwise = feature_extractor_config.use_depthwise
  conv_hyperparams = hyperparams_builder.build(
      feature_extractor_config.conv_hyperparams, is_training)
  override_base_feature_extractor_hyperparams = (
      feature_extractor_config.override_base_feature_extractor_hyperparams)

  if feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP:
    raise ValueError('Unknown ssd feature_extractor: {}'.format(feature_type))

  feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
  kwargs = {
      'is_training':
          is_training,
      'depth_multiplier':
          depth_multiplier,
      'min_depth':
          min_depth,
      'pad_to_multiple':
          pad_to_multiple,
      'conv_hyperparams_fn':
          conv_hyperparams,
      'reuse_weights':
          reuse_weights,
      'use_explicit_padding':
          use_explicit_padding,
      'use_depthwise':
          use_depthwise,
      'override_base_feature_extractor_hyperparams':
          override_base_feature_extractor_hyperparams
  }

  if feature_extractor_config.HasField('fpn'):
    kwargs.update({
        'fpn_min_level': feature_extractor_config.fpn.min_level,
        'fpn_max_level': feature_extractor_config.fpn.max_level,
    })

  return feature_extractor_class(**kwargs)