Python mobilenet_v2.training_scope方法代码示例

# 需要导入模块: from nets.mobilenet import mobilenet_v2 [as 别名]
# 或者: from nets.mobilenet.mobilenet_v2 import training_scope [as 别名]
def training_scope(l2_weight_decay=1e-4, is_training=None):
  """Arg scope for training MnasFPN."""
  with slim.arg_scope(
      [slim.conv2d],
      weights_initializer=tf.initializers.he_normal(),
      weights_regularizer=slim.l2_regularizer(l2_weight_decay)), \
      slim.arg_scope(
          [slim.separable_conv2d],
          weights_initializer=tf.initializers.truncated_normal(
              stddev=0.536),  # He_normal for 3x3 depthwise kernel.
          weights_regularizer=slim.l2_regularizer(l2_weight_decay)), \
      slim.arg_scope([slim.batch_norm],
                     is_training=is_training,
                     epsilon=0.01,
                     decay=0.99,
                     center=True,
                     scale=True) as s:
    return s 

# 需要导入模块: from nets.mobilenet import mobilenet_v2 [as 别名]
# 或者: from nets.mobilenet.mobilenet_v2 import training_scope [as 别名]
def MobileNet(depth_multiplier, imgs_in, weight_decay, batch_norm_momentum, is_training):
    with tf.contrib.slim.arg_scope(mobilenet_v2.training_scope(is_training=is_training, weight_decay=weight_decay, bn_decay=batch_norm_momentum)):
        features, _ = mobilenet_v2.mobilenet_base(imgs_in, depth_multiplier=depth_multiplier, finegrain_classification_mode=depth_multiplier < 1, output_stride=16)

    return features 

# 需要导入模块: from nets.mobilenet import mobilenet_v2 [as 别名]
# 或者: from nets.mobilenet.mobilenet_v2 import training_scope [as 别名]
def _image_to_head(self, is_training, reuse=None):
        with slim.arg_scope(mobilenet_v2.training_scope(is_training=is_training)):
            net, endpoints = mobilenet_v2.mobilenet_base(self._image, conv_defs=CTPN_DEF)

        self.variables_to_restore = slim.get_variables_to_restore()

        self._act_summaries.append(net)
        self._layers['head'] = net

        return net 

# 需要导入模块: from nets.mobilenet import mobilenet_v2 [as 别名]
# 或者: from nets.mobilenet.mobilenet_v2 import training_scope [as 别名]
def extract_features(self, preprocessed_inputs):
    """Extract features from preprocessed inputs.

    Args:
      preprocessed_inputs: a [batch, height, width, channels] float tensor
        representing a batch of images.

    Returns:
      feature_maps: a list of tensors where the ith tensor has shape
        [batch, height_i, width_i, depth_i]
    """
    preprocessed_inputs = shape_utils.check_min_image_dim(
        33, preprocessed_inputs)

    feature_map_layout = {
        'from_layer': ['layer_15/expansion_output', 'layer_19', '', '', '', ''],
        'layer_depth': [-1, -1, 512, 256, 256, 128],
        'use_depthwise': self._use_depthwise,
        'use_explicit_padding': self._use_explicit_padding,
    }

    with tf.variable_scope('MobilenetV2', reuse=self._reuse_weights) as scope:
      with slim.arg_scope(
          mobilenet_v2.training_scope(is_training=None, bn_decay=0.9997)), \
          slim.arg_scope(
              [mobilenet.depth_multiplier], min_depth=self._min_depth):
        with (slim.arg_scope(self._conv_hyperparams_fn())
              if self._override_base_feature_extractor_hyperparams else
              context_manager.IdentityContextManager()):
          _, image_features = mobilenet_v2.mobilenet_base(
              ops.pad_to_multiple(preprocessed_inputs, self._pad_to_multiple),
              final_endpoint='layer_19',
              depth_multiplier=self._depth_multiplier,
              use_explicit_padding=self._use_explicit_padding,
              scope=scope)
        with slim.arg_scope(self._conv_hyperparams_fn()):
          feature_maps = feature_map_generators.multi_resolution_feature_maps(
              feature_map_layout=feature_map_layout,
              depth_multiplier=self._depth_multiplier,
              min_depth=self._min_depth,
              insert_1x1_conv=True,
              image_features=image_features)

    return feature_maps.values() 

# 需要导入模块: from nets.mobilenet import mobilenet_v2 [as 别名]
# 或者: from nets.mobilenet.mobilenet_v2 import training_scope [as 别名]
def extract_features(self, preprocessed_inputs):
    """Extract features from preprocessed inputs.

    Args:
      preprocessed_inputs: a [batch, height, width, channels] float tensor
        representing a batch of images.

    Returns:
      feature_maps: a list of tensors where the ith tensor has shape
        [batch, height_i, width_i, depth_i]
    """
    preprocessed_inputs = shape_utils.check_min_image_dim(
        33, preprocessed_inputs)

    feature_map_layout = {
        'from_layer': ['layer_15/expansion_output', 'layer_19', '', '', '', ''],
        'layer_depth': [-1, -1, 512, 256, 256, 128],
        'use_depthwise': self._use_depthwise,
        'use_explicit_padding': self._use_explicit_padding,
    }

    with tf.variable_scope('MobilenetV2', reuse=self._reuse_weights) as scope:
      with slim.arg_scope(
          mobilenet_v2.training_scope(
              is_training=(self._is_training and self._batch_norm_trainable),
              bn_decay=0.9997)), \
          slim.arg_scope(
              [mobilenet.depth_multiplier], min_depth=self._min_depth):
        # TODO(b/68150321): Enable fused batch norm once quantization
        # supports it.
        with slim.arg_scope([slim.batch_norm], fused=False):
          _, image_features = mobilenet_v2.mobilenet_base(
              ops.pad_to_multiple(preprocessed_inputs, self._pad_to_multiple),
              final_endpoint='layer_19',
              depth_multiplier=self._depth_multiplier,
              use_explicit_padding=self._use_explicit_padding,
              scope=scope)
        with slim.arg_scope(self._conv_hyperparams):
          # TODO(b/68150321): Enable fused batch norm once quantization
          # supports it.
          with slim.arg_scope([slim.batch_norm], fused=False):
            feature_maps = feature_map_generators.multi_resolution_feature_maps(
                feature_map_layout=feature_map_layout,
                depth_multiplier=self._depth_multiplier,
                min_depth=self._min_depth,
                insert_1x1_conv=True,
                image_features=image_features)

    return feature_maps.values() 

# 需要导入模块: from nets.mobilenet import mobilenet_v2 [as 别名]
# 或者: from nets.mobilenet.mobilenet_v2 import training_scope [as 别名]
def extract_features(self, preprocessed_inputs):
    """Extract features from preprocessed inputs.

    Args:
      preprocessed_inputs: a [batch, height, width, channels] float tensor
        representing a batch of images.

    Returns:
      feature_maps: a list of tensors where the ith tensor has shape
        [batch, height_i, width_i, depth_i]
    """
    preprocessed_inputs = shape_utils.check_min_image_dim(
        33, preprocessed_inputs)

    feature_map_layout = {
        'from_layer': ['layer_15/expansion_output', 'layer_19', '', '', '', ''],
        'layer_depth': [-1, -1, 512, 256, 256, 128],
        'use_depthwise': self._use_depthwise,
        'use_explicit_padding': self._use_explicit_padding,
    }

    with tf.variable_scope('MobilenetV2', reuse=self._reuse_weights) as scope:
      with slim.arg_scope(
          mobilenet_v2.training_scope(is_training=None, bn_decay=0.9997)), \
          slim.arg_scope(
              [mobilenet.depth_multiplier], min_depth=self._min_depth):
        with (slim.arg_scope(self._conv_hyperparams_fn())
              if self._override_base_feature_extractor_hyperparams else
              context_manager.IdentityContextManager()):
          # TODO(b/68150321): Enable fused batch norm once quantization
          # supports it.
          with slim.arg_scope([slim.batch_norm], fused=False):
            _, image_features = mobilenet_v2.mobilenet_base(
                ops.pad_to_multiple(preprocessed_inputs, self._pad_to_multiple),
                final_endpoint='layer_19',
                depth_multiplier=self._depth_multiplier,
                use_explicit_padding=self._use_explicit_padding,
                scope=scope)
        with slim.arg_scope(self._conv_hyperparams_fn()):
          # TODO(b/68150321): Enable fused batch norm once quantization
          # supports it.
          with slim.arg_scope([slim.batch_norm], fused=False):
            feature_maps = feature_map_generators.multi_resolution_feature_maps(
                feature_map_layout=feature_map_layout,
                depth_multiplier=self._depth_multiplier,
                min_depth=self._min_depth,
                insert_1x1_conv=True,
                image_features=image_features)

    return feature_maps.values() 

# 需要导入模块: from nets.mobilenet import mobilenet_v2 [as 别名]
# 或者: from nets.mobilenet.mobilenet_v2 import training_scope [as 别名]
def extract_features(self, preprocessed_inputs):
    """Extract features from preprocessed inputs.

    Args:
      preprocessed_inputs: a [batch, height, width, channels] float tensor
        representing a batch of images.

    Returns:
      feature_maps: a list of tensors where the ith tensor has shape
        [batch, height_i, width_i, depth_i]
    """
    preprocessed_inputs = shape_utils.check_min_image_dim(
        33, preprocessed_inputs)

    feature_map_layout = {
        'from_layer': ['layer_15/expansion_output', 'layer_19', '', '', '', ''
                      ][:self._num_layers],
        'layer_depth': [-1, -1, 512, 256, 256, 128][:self._num_layers],
        'use_depthwise': self._use_depthwise,
        'use_explicit_padding': self._use_explicit_padding,
    }

    with tf.variable_scope('MobilenetV2', reuse=self._reuse_weights) as scope:
      with slim.arg_scope(
          mobilenet_v2.training_scope(is_training=None, bn_decay=0.9997)), \
          slim.arg_scope(
              [mobilenet.depth_multiplier], min_depth=self._min_depth):
        with (slim.arg_scope(self._conv_hyperparams_fn())
              if self._override_base_feature_extractor_hyperparams else
              context_manager.IdentityContextManager()):
          _, image_features = mobilenet_v2.mobilenet_base(
              ops.pad_to_multiple(preprocessed_inputs, self._pad_to_multiple),
              final_endpoint='layer_19',
              depth_multiplier=self._depth_multiplier,
              use_explicit_padding=self._use_explicit_padding,
              scope=scope)
        with slim.arg_scope(self._conv_hyperparams_fn()):
          feature_maps = feature_map_generators.multi_resolution_feature_maps(
              feature_map_layout=feature_map_layout,
              depth_multiplier=self._depth_multiplier,
              min_depth=self._min_depth,
              insert_1x1_conv=True,
              image_features=image_features)

    return feature_maps.values() 

# 需要导入模块: from nets.mobilenet import mobilenet_v2 [as 别名]
# 或者: from nets.mobilenet.mobilenet_v2 import training_scope [as 别名]
def extract_features(self, preprocessed_inputs):
    """Extract features from preprocessed inputs.

    Args:
      preprocessed_inputs: a [batch, height, width, channels] float tensor
        representing a batch of images.

    Returns:
      feature_maps: a list of tensors where the ith tensor has shape
        [batch, height_i, width_i, depth_i]
    """
    preprocessed_inputs = shape_utils.check_min_image_dim(
        33, preprocessed_inputs)

    feature_map_layout = {
        'from_layer': ['layer_15/expansion_output', 'layer_19', '', '', '', ''
                      ][:self._num_layers],
        'layer_depth': [-1, -1, 512, 256, 256, 128][:self._num_layers],
        'use_depthwise': self._use_depthwise,
        'use_explicit_padding': self._use_explicit_padding,
    }

    with tf.variable_scope('MobilenetV2', reuse=self._reuse_weights) as scope:
      with slim.arg_scope(
          mobilenet_v2.training_scope(is_training=None, bn_decay=0.9997)), \
          slim.arg_scope(
              [mobilenet.depth_multiplier], min_depth=self._min_depth):
        with (slim.arg_scope(self._conv_hyperparams_fn())
              if self._override_base_feature_extractor_hyperparams else
              context_manager.IdentityContextManager()):
          _, image_features = mobilenet_v2.mobilenet_base(
              ops.pad_to_multiple(preprocessed_inputs, self._pad_to_multiple),
              final_endpoint='layer_19',
              depth_multiplier=self._depth_multiplier,
              use_explicit_padding=self._use_explicit_padding,
              scope=scope)
        with slim.arg_scope(self._conv_hyperparams_fn()):
          feature_maps = feature_map_generators.multi_resolution_feature_maps(
              feature_map_layout=feature_map_layout,
              depth_multiplier=self._depth_multiplier,
              min_depth=self._min_depth,
              insert_1x1_conv=True,
              image_features=image_features)

    return list(feature_maps.values())