Python nets.mobilenet.mobilenet.depth_multiplier() Examples

def testMultiplier(self):
    op = mobilenet.op
    new_def = copy.deepcopy(mobilenet_v2.V2_DEF)

    def inverse_multiplier(output_params, multiplier):
      output_params['num_outputs'] = int(
          output_params['num_outputs'] / multiplier)

    new_def['spec'][0] = op(
        slim.conv2d,
        kernel_size=(3, 3),
        multiplier_func=inverse_multiplier,
        num_outputs=16)
    _ = mobilenet_v2.mobilenet_base(
        tf.placeholder(tf.float32, (10, 224, 224, 16)),
        conv_defs=new_def,
        depth_multiplier=0.1)
    s = [op.outputs[0].get_shape().as_list()[-1] for op in find_ops('Conv2D')]
    # Expect first layer to be 160 (16 / 0.1), and other layers
    # their max(original size * 0.1, 8)
    self.assertEqual([160, 8, 48, 8, 48], s[:5]) 

def testFineGrained(self):
    tf.reset_default_graph()
    # Verifies that depth_multiplier arg scope actually works
    # if no default min_depth is provided.

    mobilenet_v2.mobilenet(
        tf.placeholder(tf.float32, (10, 224, 224, 2)),
        conv_defs=mobilenet_v2.V2_DEF, depth_multiplier=0.01,
        finegrain_classification_mode=True)
    s = [op.outputs[0].get_shape().as_list()[-1] for op in find_ops('Conv2D')]
    s = set(s)
    # All convolutions will be 8->48, except for the last one.
    self.assertSameElements(s, [8, 48, 1001, 1280]) 

def testDivisibleByWithArgScope(self):
    tf.reset_default_graph()
    # Verifies that depth_multiplier arg scope actually works
    # if no default min_depth is provided.
    with slim.arg_scope((mobilenet.depth_multiplier,), min_depth=32):
      mobilenet_v2.mobilenet(
          tf.placeholder(tf.float32, (10, 224, 224, 2)),
          conv_defs=mobilenet_v2.V2_DEF, depth_multiplier=0.1)
      s = [op.outputs[0].get_shape().as_list()[-1] for op in find_ops('Conv2D')]
      s = set(s)
      self.assertSameElements(s, [32, 192, 128, 1001]) 

def mobilenet_base(input_tensor, depth_multiplier=1.0, **kwargs):
  """Creates base of the mobilenet (no pooling and no logits) ."""
  return mobilenet(input_tensor,
                   depth_multiplier=depth_multiplier,
                   base_only=True, **kwargs) 

def testMobilenetBase(self):
    tf.reset_default_graph()
    # Verifies that mobilenet_base returns pre-pooling layer.
    with slim.arg_scope((mobilenet.depth_multiplier,), min_depth=32):
      net, _ = mobilenet_v2.mobilenet_base(
          tf.placeholder(tf.float32, (10, 224, 224, 16)),
          conv_defs=mobilenet_v2.V2_DEF, depth_multiplier=0.1)
      self.assertEqual(net.get_shape().as_list(), [10, 7, 7, 128]) 

def testFineGrained(self):
    tf.reset_default_graph()
    # Verifies that depth_multiplier arg scope actually works
    # if no default min_depth is provided.

    mobilenet_v2.mobilenet(
        tf.placeholder(tf.float32, (10, 224, 224, 2)),
        conv_defs=mobilenet_v2.V2_DEF, depth_multiplier=0.01,
        finegrain_classification_mode=True)
    s = [op.outputs[0].get_shape().as_list()[-1] for op in find_ops('Conv2D')]
    s = set(s)
    # All convolutions will be 8->48, except for the last one.
    self.assertSameElements(s, [8, 48, 1001, 1280]) 

def testMobilenetBase(self):
    tf.reset_default_graph()
    # Verifies that mobilenet_base returns pre-pooling layer.
    with slim.arg_scope((mobilenet.depth_multiplier,), min_depth=32):
      net, _ = mobilenet_v2.mobilenet_base(
          tf.placeholder(tf.float32, (10, 224, 224, 16)),
          conv_defs=mobilenet_v2.V2_DEF, depth_multiplier=0.1)
      self.assertEqual(net.get_shape().as_list(), [10, 7, 7, 128]) 

def mobilenet_base(input_tensor, depth_multiplier=1.0, **kwargs):
  """Creates base of the mobilenet (no pooling and no logits) ."""
  return mobilenet(
      input_tensor, depth_multiplier=depth_multiplier, base_only=True, **kwargs) 

def mobilenet_base(input_tensor, depth_multiplier=1.0, **kwargs):
  """Creates base of the mobilenet (no pooling and no logits) ."""
  return mobilenet(input_tensor,
                   depth_multiplier=depth_multiplier,
                   base_only=True, **kwargs) 

def mobilenet_base_group_norm(input_tensor, depth_multiplier=1.0, **kwargs):
  """Creates base of the mobilenet (no pooling and no logits) ."""
  kwargs['conv_defs'] = V2_DEF_GROUP_NORM
  kwargs['conv_defs']['defaults'].update({
      (slim.group_norm,): {
          'groups': kwargs.pop('groups', 8)
      }
  })
  return mobilenet(
      input_tensor, depth_multiplier=depth_multiplier, base_only=True, **kwargs) 

def testDivisibleByWithArgScope(self):
    tf.reset_default_graph()
    # Verifies that depth_multiplier arg scope actually works
    # if no default min_depth is provided.
    with slim.arg_scope((mobilenet.depth_multiplier,), min_depth=32):
      mobilenet_v2.mobilenet(
          tf.placeholder(tf.float32, (10, 224, 224, 2)),
          conv_defs=mobilenet_v2.V2_DEF,
          depth_multiplier=0.1)
      s = [op.outputs[0].get_shape().as_list()[-1] for op in find_ops('Conv2D')]
      s = set(s)
      self.assertSameElements(s, [32, 192, 128, 1001]) 

def testFineGrained(self):
    tf.reset_default_graph()
    # Verifies that depth_multiplier arg scope actually works
    # if no default min_depth is provided.

    mobilenet_v2.mobilenet(
        tf.placeholder(tf.float32, (10, 224, 224, 2)),
        conv_defs=mobilenet_v2.V2_DEF,
        depth_multiplier=0.01,
        finegrain_classification_mode=True)
    s = [op.outputs[0].get_shape().as_list()[-1] for op in find_ops('Conv2D')]
    s = set(s)
    # All convolutions will be 8->48, except for the last one.
    self.assertSameElements(s, [8, 48, 1001, 1280]) 

def _apply_multiplier(d, multiplier, min_depth):
  p = {'num_outputs': d}
  mobilenet.depth_multiplier(
      p, multiplier=multiplier, divisible_by=8, min_depth=min_depth)
  return p['num_outputs'] 

def testDivisibleByWithArgScope(self):
    tf.reset_default_graph()
    # Verifies that depth_multiplier arg scope actually works
    # if no default min_depth is provided.
    with slim.arg_scope((mobilenet.depth_multiplier,), min_depth=32):
      mobilenet_v2.mobilenet(
          tf.placeholder(tf.float32, (10, 224, 224, 2)),
          conv_defs=mobilenet_v2.V2_DEF, depth_multiplier=0.1)
      s = [op.outputs[0].get_shape().as_list()[-1] for op in find_ops('Conv2D')]
      s = set(s)
      self.assertSameElements(s, [32, 192, 128, 1001]) 

def mobilenet_base(input_tensor, depth_multiplier=1.0, **kwargs):
  """Creates base of the mobilenet (no pooling and no logits) ."""
  return mobilenet(input_tensor,
                   depth_multiplier=depth_multiplier,
                   base_only=True, **kwargs) 

def testMobilenetBase(self):
    tf.reset_default_graph()
    # Verifies that mobilenet_base returns pre-pooling layer.
    with slim.arg_scope((mobilenet.depth_multiplier,), min_depth=32):
      net, _ = mobilenet_v2.mobilenet_base(
          tf.placeholder(tf.float32, (10, 224, 224, 16)),
          conv_defs=mobilenet_v2.V2_DEF, depth_multiplier=0.1)
      self.assertEqual(net.get_shape().as_list(), [10, 7, 7, 128]) 

def testFineGrained(self):
    tf.reset_default_graph()
    # Verifies that depth_multiplier arg scope actually works
    # if no default min_depth is provided.

    mobilenet_v2.mobilenet(
        tf.placeholder(tf.float32, (10, 224, 224, 2)),
        conv_defs=mobilenet_v2.V2_DEF, depth_multiplier=0.01,
        finegrain_classification_mode=True)
    s = [op.outputs[0].get_shape().as_list()[-1] for op in find_ops('Conv2D')]
    s = set(s)
    # All convolutions will be 8->48, except for the last one.
    self.assertSameElements(s, [8, 48, 1001, 1280]) 

def testDivisibleByWithArgScope(self):
    tf.reset_default_graph()
    # Verifies that depth_multiplier arg scope actually works
    # if no default min_depth is provided.
    with slim.arg_scope((mobilenet.depth_multiplier,), min_depth=32):
      mobilenet_v2.mobilenet(
          tf.placeholder(tf.float32, (10, 224, 224, 2)),
          conv_defs=mobilenet_v2.V2_DEF, depth_multiplier=0.1)
      s = [op.outputs[0].get_shape().as_list()[-1] for op in find_ops('Conv2D')]
      s = set(s)
      self.assertSameElements(s, [32, 192, 128, 1001]) 

def mobilenet_base(input_tensor, depth_multiplier=1.0, **kwargs):
  """Creates base of the mobilenet (no pooling and no logits) ."""
  return mobilenet(input_tensor,
                   depth_multiplier=depth_multiplier,
                   base_only=True, **kwargs) 

def testMobilenetBase(self):
    tf.reset_default_graph()
    # Verifies that mobilenet_base returns pre-pooling layer.
    with slim.arg_scope((mobilenet.depth_multiplier,), min_depth=32):
      net, _ = mobilenet_v2.mobilenet_base(
          tf.placeholder(tf.float32, (10, 224, 224, 16)),
          conv_defs=mobilenet_v2.V2_DEF, depth_multiplier=0.1)
      self.assertEqual(net.get_shape().as_list(), [10, 7, 7, 128]) 

def testFineGrained(self):
    tf.reset_default_graph()
    # Verifies that depth_multiplier arg scope actually works
    # if no default min_depth is provided.

    mobilenet_v2.mobilenet(
        tf.placeholder(tf.float32, (10, 224, 224, 2)),
        conv_defs=mobilenet_v2.V2_DEF, depth_multiplier=0.01,
        finegrain_classification_mode=True)
    s = [op.outputs[0].get_shape().as_list()[-1] for op in find_ops('Conv2D')]
    s = set(s)
    # All convolutions will be 8->48, except for the last one.
    self.assertSameElements(s, [8, 48, 1001, 1280]) 

def testDivisibleByWithArgScope(self):
    tf.reset_default_graph()
    # Verifies that depth_multiplier arg scope actually works
    # if no default min_depth is provided.
    with slim.arg_scope((mobilenet.depth_multiplier,), min_depth=32):
      mobilenet_v2.mobilenet(
          tf.placeholder(tf.float32, (10, 224, 224, 2)),
          conv_defs=mobilenet_v2.V2_DEF, depth_multiplier=0.1)
      s = [op.outputs[0].get_shape().as_list()[-1] for op in find_ops('Conv2D')]
      s = set(s)
      self.assertSameElements(s, [32, 192, 128, 1001]) 

def mobilenet_base(input_tensor, depth_multiplier=1.0, **kwargs):
  """Creates base of the mobilenet (no pooling and no logits) ."""
  return mobilenet(input_tensor,
                   depth_multiplier=depth_multiplier,
                   base_only=True, **kwargs) 

def __init__(self,
               is_training,
               depth_multiplier,
               min_depth,
               pad_to_multiple,
               conv_hyperparams_fn,
               reuse_weights=None,
               use_explicit_padding=False,
               use_depthwise=False,
               override_base_feature_extractor_hyperparams=False):
    """MobileNetV2 Feature Extractor for SSD Models.

    Mobilenet v2 (experimental), designed by sandler@. More details can be found
    in //knowledge/cerebra/brain/compression/mobilenet/mobilenet_experimental.py

    Args:
      is_training: whether the network is in training mode.
      depth_multiplier: float depth multiplier for feature extractor.
      min_depth: minimum feature extractor depth.
      pad_to_multiple: the nearest multiple to zero pad the input height and
        width dimensions to.
      conv_hyperparams_fn: A function to construct tf slim arg_scope for conv2d
        and separable_conv2d ops in the layers that are added on top of the
        base feature extractor.
      reuse_weights: Whether to reuse variables. Default is None.
      use_explicit_padding: Whether to use explicit padding when extracting
        features. Default is False.
      use_depthwise: Whether to use depthwise convolutions. Default is False.
      override_base_feature_extractor_hyperparams: Whether to override
        hyperparameters of the base feature extractor with the one from
        `conv_hyperparams_fn`.
    """
    super(SSDMobileNetV2FeatureExtractor, self).__init__(
        is_training, depth_multiplier, min_depth, pad_to_multiple,
        conv_hyperparams_fn, reuse_weights, use_explicit_padding, use_depthwise,
        override_base_feature_extractor_hyperparams) 

def __init__(self,
               is_training,
               depth_multiplier,
               min_depth,
               pad_to_multiple,
               conv_hyperparams_fn,
               reuse_weights=None,
               use_explicit_padding=False,
               use_depthwise=False,
               override_base_feature_extractor_hyperparams=False):
    """MobileNetV2 Feature Extractor for SSD Models.

    Mobilenet v2 (experimental), designed by sandler@. More details can be found
    in //knowledge/cerebra/brain/compression/mobilenet/mobilenet_experimental.py

    Args:
      is_training: whether the network is in training mode.
      depth_multiplier: float depth multiplier for feature extractor.
      min_depth: minimum feature extractor depth.
      pad_to_multiple: the nearest multiple to zero pad the input height and
        width dimensions to.
      conv_hyperparams_fn: A function to construct tf slim arg_scope for conv2d
        and separable_conv2d ops in the layers that are added on top of the
        base feature extractor.
      reuse_weights: Whether to reuse variables. Default is None.
      use_explicit_padding: Whether to use explicit padding when extracting
        features. Default is False.
      use_depthwise: Whether to use depthwise convolutions. Default is False.
      override_base_feature_extractor_hyperparams: Whether to override
        hyperparameters of the base feature extractor with the one from
        `conv_hyperparams_fn`.
    """
    super(SSDMobileNetV2FeatureExtractor, self).__init__(
        is_training, depth_multiplier, min_depth, pad_to_multiple,
        conv_hyperparams_fn, reuse_weights, use_explicit_padding, use_depthwise,
        override_base_feature_extractor_hyperparams) 

def testMobilenetBase(self):
    tf.reset_default_graph()
    # Verifies that mobilenet_base returns pre-pooling layer.
    with slim.arg_scope((mobilenet.depth_multiplier,), min_depth=32):
      net, _ = mobilenet_v2.mobilenet_base(
          tf.placeholder(tf.float32, (10, 224, 224, 16)),
          conv_defs=mobilenet_v2.V2_DEF, depth_multiplier=0.1)
      self.assertEqual(net.get_shape().as_list(), [10, 7, 7, 128]) 

def testFineGrained(self):
    tf.reset_default_graph()
    # Verifies that depth_multiplier arg scope actually works
    # if no default min_depth is provided.

    mobilenet_v2.mobilenet(
        tf.placeholder(tf.float32, (10, 224, 224, 2)),
        conv_defs=mobilenet_v2.V2_DEF, depth_multiplier=0.01,
        finegrain_classification_mode=True)
    s = [op.outputs[0].get_shape().as_list()[-1] for op in find_ops('Conv2D')]
    s = set(s)
    # All convolutions will be 8->48, except for the last one.
    self.assertSameElements(s, [8, 48, 1001, 1280]) 

def testDivisibleByWithArgScope(self):
    tf.reset_default_graph()
    # Verifies that depth_multiplier arg scope actually works
    # if no default min_depth is provided.
    with slim.arg_scope((mobilenet.depth_multiplier,), min_depth=32):
      mobilenet_v2.mobilenet(
          tf.placeholder(tf.float32, (10, 224, 224, 2)),
          conv_defs=mobilenet_v2.V2_DEF, depth_multiplier=0.1)
      s = [op.outputs[0].get_shape().as_list()[-1] for op in find_ops('Conv2D')]
      s = set(s)
      self.assertSameElements(s, [32, 192, 128, 1001]) 

def mobilenet_base(input_tensor, depth_multiplier=1.0, **kwargs):
  """Creates base of the mobilenet (no pooling and no logits) ."""
  return mobilenet(input_tensor,
                   depth_multiplier=depth_multiplier,
                   base_only=True, **kwargs) 

def testMobilenetBase(self):
    tf.reset_default_graph()
    # Verifies that mobilenet_base returns pre-pooling layer.
    with slim.arg_scope((mobilenet.depth_multiplier,), min_depth=32):
      net, _ = mobilenet_v2.mobilenet_base(
          tf.placeholder(tf.float32, (10, 224, 224, 16)),
          conv_defs=mobilenet_v2.V2_DEF, depth_multiplier=0.1)
      self.assertEqual(net.get_shape().as_list(), [10, 7, 7, 128])