예제 #1
0
def MobileNetV2(input_shape=None,
                alpha=1.0,
                include_top=True,
                weights='imagenet',
                input_tensor=None,
                pooling=None,
                classes=1000,
                classifier_activation='softmax',
                **kwargs):
  """Instantiates the MobileNetV2 architecture.

  Reference:
  - [MobileNetV2: Inverted Residuals and Linear Bottlenecks](
      https://arxiv.org/abs/1801.04381) (CVPR 2018)

  Optionally loads weights pre-trained on ImageNet.

  Caution: Be sure to properly pre-process your inputs to the application.
  Please see `applications.mobilenet_v2.preprocess_input` for an example.

  Arguments:
    input_shape: Optional shape tuple, to be specified if you would
      like to use a model with an input image resolution that is not
      (224, 224, 3).
      It should have exactly 3 inputs channels (224, 224, 3).
      You can also omit this option if you would like
      to infer input_shape from an input_tensor.
      If you choose to include both input_tensor and input_shape then
      input_shape will be used if they match, if the shapes
      do not match then we will throw an error.
      E.g. `(160, 160, 3)` would be one valid value.
    alpha: Float between 0 and 1. controls the width of the network.
      This is known as the width multiplier in the MobileNetV2 paper,
      but the name is kept for consistency with `applications.MobileNetV1`
      model in Keras.
      - If `alpha` < 1.0, proportionally decreases the number
          of filters in each layer.
      - If `alpha` > 1.0, proportionally increases the number
          of filters in each layer.
      - If `alpha` = 1, default number of filters from the paper
          are used at each layer.
    include_top: Boolean, whether to include the fully-connected
      layer at the top of the network. Defaults to `True`.
    weights: String, one of `None` (random initialization),
      'imagenet' (pre-training on ImageNet),
      or the path to the weights file to be loaded.
    input_tensor: Optional Keras tensor (i.e. output of
      `layers.Input()`)
      to use as image input for the model.
    pooling: String, optional pooling mode for feature extraction
      when `include_top` is `False`.
      - `None` means that the output of the model
          will be the 4D tensor output of the
          last convolutional block.
      - `avg` means that global average pooling
          will be applied to the output of the
          last convolutional block, and thus
          the output of the model will be a
          2D tensor.
      - `max` means that global max pooling will
          be applied.
    classes: Integer, optional number of classes to classify images
      into, only to be specified if `include_top` is True, and
      if no `weights` argument is specified.
    classifier_activation: A `str` or callable. The activation function to use
      on the "top" layer. Ignored unless `include_top=True`. Set
      `classifier_activation=None` to return the logits of the "top" layer.
    **kwargs: For backwards compatibility only.

  Returns:
    A `keras.Model` instance.

  Raises:
    ValueError: in case of invalid argument for `weights`,
      or invalid input shape or invalid alpha, rows when
      weights='imagenet'
    ValueError: if `classifier_activation` is not `softmax` or `None` when
      using a pretrained top layer.
  """
  global layers
  if 'layers' in kwargs:
    layers = kwargs.pop('layers')
  else:
    layers = VersionAwareLayers()
  if kwargs:
    raise ValueError('Unknown argument(s): %s' % (kwargs,))
  if not (weights in {'imagenet', None} or file_io.file_exists(weights)):
    raise ValueError('The `weights` argument should be either '
                     '`None` (random initialization), `imagenet` '
                     '(pre-training on ImageNet), '
                     'or the path to the weights file to be loaded.')

  if weights == 'imagenet' and include_top and classes != 1000:
    raise ValueError('If using `weights` as `"imagenet"` with `include_top` '
                     'as true, `classes` should be 1000')

  # Determine proper input shape and default size.
  # If both input_shape and input_tensor are used, they should match
  if input_shape is not None and input_tensor is not None:
    try:
      is_input_t_tensor = backend.is_keras_tensor(input_tensor)
    except ValueError:
      try:
        is_input_t_tensor = backend.is_keras_tensor(
            layer_utils.get_source_inputs(input_tensor))
      except ValueError:
        raise ValueError('input_tensor: ', input_tensor,
                         'is not type input_tensor')
    if is_input_t_tensor:
      if backend.image_data_format == 'channels_first':
        if backend.int_shape(input_tensor)[1] != input_shape[1]:
          raise ValueError('input_shape: ', input_shape, 'and input_tensor: ',
                           input_tensor,
                           'do not meet the same shape requirements')
      else:
        if backend.int_shape(input_tensor)[2] != input_shape[1]:
          raise ValueError('input_shape: ', input_shape, 'and input_tensor: ',
                           input_tensor,
                           'do not meet the same shape requirements')
    else:
      raise ValueError('input_tensor specified: ', input_tensor,
                       'is not a keras tensor')

  # If input_shape is None, infer shape from input_tensor
  if input_shape is None and input_tensor is not None:

    try:
      backend.is_keras_tensor(input_tensor)
    except ValueError:
      raise ValueError('input_tensor: ', input_tensor, 'is type: ',
                       type(input_tensor), 'which is not a valid type')

    if input_shape is None and not backend.is_keras_tensor(input_tensor):
      default_size = 224
    elif input_shape is None and backend.is_keras_tensor(input_tensor):
      if backend.image_data_format() == 'channels_first':
        rows = backend.int_shape(input_tensor)[2]
        cols = backend.int_shape(input_tensor)[3]
      else:
        rows = backend.int_shape(input_tensor)[1]
        cols = backend.int_shape(input_tensor)[2]

      if rows == cols and rows in [96, 128, 160, 192, 224]:
        default_size = rows
      else:
        default_size = 224

  # If input_shape is None and no input_tensor
  elif input_shape is None:
    default_size = 224

  # If input_shape is not None, assume default size
  else:
    if backend.image_data_format() == 'channels_first':
      rows = input_shape[1]
      cols = input_shape[2]
    else:
      rows = input_shape[0]
      cols = input_shape[1]

    if rows == cols and rows in [96, 128, 160, 192, 224]:
      default_size = rows
    else:
      default_size = 224

  input_shape = imagenet_utils.obtain_input_shape(
      input_shape,
      default_size=default_size,
      min_size=32,
      data_format=backend.image_data_format(),
      require_flatten=include_top,
      weights=weights)

  if backend.image_data_format() == 'channels_last':
    row_axis, col_axis = (0, 1)
  else:
    row_axis, col_axis = (1, 2)
  rows = input_shape[row_axis]
  cols = input_shape[col_axis]

  if weights == 'imagenet':
    if alpha not in [0.35, 0.50, 0.75, 1.0, 1.3, 1.4]:
      raise ValueError('If imagenet weights are being loaded, '
                       'alpha can be one of `0.35`, `0.50`, `0.75`, '
                       '`1.0`, `1.3` or `1.4` only.')

    if rows != cols or rows not in [96, 128, 160, 192, 224]:
      rows = 224
      logging.warning('`input_shape` is undefined or non-square, '
                      'or `rows` is not in [96, 128, 160, 192, 224].'
                      ' Weights for input shape (224, 224) will be'
                      ' loaded as the default.')

  if input_tensor is None:
    img_input = layers.Input(shape=input_shape)
  else:
    if not backend.is_keras_tensor(input_tensor):
      img_input = layers.Input(tensor=input_tensor, shape=input_shape)
    else:
      img_input = input_tensor

  channel_axis = 1 if backend.image_data_format() == 'channels_first' else -1

  first_block_filters = _make_divisible(32 * alpha, 8)
  x = layers.ZeroPadding2D(
      padding=imagenet_utils.correct_pad(img_input, 3),
      name='Conv1_pad')(img_input)
  x = layers.Conv2D(
      first_block_filters,
      kernel_size=3,
      strides=(2, 2),
      padding='valid',
      use_bias=False,
      name='Conv1')(
          x)
  x = layers.BatchNormalization(
      axis=channel_axis, epsilon=1e-3, momentum=0.999, name='bn_Conv1')(
          x)
  x = layers.ReLU(6., name='Conv1_relu')(x)

  x = _inverted_res_block(
      x, filters=16, alpha=alpha, stride=1, expansion=1, block_id=0)

  x = _inverted_res_block(
      x, filters=24, alpha=alpha, stride=2, expansion=6, block_id=1)
  x = _inverted_res_block(
      x, filters=24, alpha=alpha, stride=1, expansion=6, block_id=2)

  x = _inverted_res_block(
      x, filters=32, alpha=alpha, stride=2, expansion=6, block_id=3)
  x = _inverted_res_block(
      x, filters=32, alpha=alpha, stride=1, expansion=6, block_id=4)
  x = _inverted_res_block(
      x, filters=32, alpha=alpha, stride=1, expansion=6, block_id=5)

  x = _inverted_res_block(
      x, filters=64, alpha=alpha, stride=2, expansion=6, block_id=6)
  x = _inverted_res_block(
      x, filters=64, alpha=alpha, stride=1, expansion=6, block_id=7)
  x = _inverted_res_block(
      x, filters=64, alpha=alpha, stride=1, expansion=6, block_id=8)
  x = _inverted_res_block(
      x, filters=64, alpha=alpha, stride=1, expansion=6, block_id=9)

  x = _inverted_res_block(
      x, filters=96, alpha=alpha, stride=1, expansion=6, block_id=10)
  x = _inverted_res_block(
      x, filters=96, alpha=alpha, stride=1, expansion=6, block_id=11)
  x = _inverted_res_block(
      x, filters=96, alpha=alpha, stride=1, expansion=6, block_id=12)

  x = _inverted_res_block(
      x, filters=160, alpha=alpha, stride=2, expansion=6, block_id=13)
  x = _inverted_res_block(
      x, filters=160, alpha=alpha, stride=1, expansion=6, block_id=14)
  x = _inverted_res_block(
      x, filters=160, alpha=alpha, stride=1, expansion=6, block_id=15)

  x = _inverted_res_block(
      x, filters=320, alpha=alpha, stride=1, expansion=6, block_id=16)

  # no alpha applied to last Conv as stated in the paper:
  # if the width multiplier is greater than 1 we
  # increase the number of output channels
  if alpha > 1.0:
    last_block_filters = _make_divisible(1280 * alpha, 8)
  else:
    last_block_filters = 1280

  x = layers.Conv2D(
      last_block_filters, kernel_size=1, use_bias=False, name='Conv_1')(
          x)
  x = layers.BatchNormalization(
      axis=channel_axis, epsilon=1e-3, momentum=0.999, name='Conv_1_bn')(
          x)
  x = layers.ReLU(6., name='out_relu')(x)

  if include_top:
    x = layers.GlobalAveragePooling2D()(x)
    imagenet_utils.validate_activation(classifier_activation, weights)
    x = layers.Dense(classes, activation=classifier_activation,
                     name='predictions')(x)

  else:
    if pooling == 'avg':
      x = layers.GlobalAveragePooling2D()(x)
    elif pooling == 'max':
      x = layers.GlobalMaxPooling2D()(x)

  # Ensure that the model takes into account
  # any potential predecessors of `input_tensor`.
  if input_tensor is not None:
    inputs = layer_utils.get_source_inputs(input_tensor)
  else:
    inputs = img_input

  # Create model.
  model = training.Model(inputs, x, name='mobilenetv2_%0.2f_%s' % (alpha, rows))

  # Load weights.
  if weights == 'imagenet':
    if include_top:
      model_name = ('mobilenet_v2_weights_tf_dim_ordering_tf_kernels_' +
                    str(alpha) + '_' + str(rows) + '.h5')
      weight_path = BASE_WEIGHT_PATH + model_name
      weights_path = data_utils.get_file(
          model_name, weight_path, cache_subdir='models')
    else:
      model_name = ('mobilenet_v2_weights_tf_dim_ordering_tf_kernels_' +
                    str(alpha) + '_' + str(rows) + '_no_top' + '.h5')
      weight_path = BASE_WEIGHT_PATH + model_name
      weights_path = data_utils.get_file(
          model_name, weight_path, cache_subdir='models')
    model.load_weights(weights_path)
  elif weights is not None:
    model.load_weights(weights)

  return model
예제 #2
0
def ResNet(stack_fn,
           preact,
           use_bias,
           model_name='resnet',
           include_top=True,
           weights='imagenet',
           input_tensor=None,
           input_shape=None,
           pooling=None,
           classes=1000,
           classifier_activation='softmax',
           **kwargs):
    """Instantiates the ResNet, ResNetV2, and ResNeXt architecture.

  Reference:
  - [Deep Residual Learning for Image Recognition](
      https://arxiv.org/abs/1512.03385) (CVPR 2015)

  Optionally loads weights pre-trained on ImageNet.
  Note that the data format convention used by the model is
  the one specified in your Keras config at `~/.keras/keras.json`.

  Caution: Be sure to properly pre-process your inputs to the application.
  Please see `applications.resnet.preprocess_input` for an example.

  Arguments:
    stack_fn: a function that returns output tensor for the
      stacked residual blocks.
    preact: whether to use pre-activation or not
      (True for ResNetV2, False for ResNet and ResNeXt).
    use_bias: whether to use biases for convolutional layers or not
      (True for ResNet and ResNetV2, False for ResNeXt).
    model_name: string, model name.
    include_top: whether to include the fully-connected
      layer at the top of the network.
    weights: one of `None` (random initialization),
      'imagenet' (pre-training on ImageNet),
      or the path to the weights file to be loaded.
    input_tensor: optional Keras tensor
      (i.e. output of `layers.Input()`)
      to use as image input for the model.
    input_shape: optional shape tuple, only to be specified
      if `include_top` is False (otherwise the input shape
      has to be `(224, 224, 3)` (with `channels_last` data format)
      or `(3, 224, 224)` (with `channels_first` data format).
      It should have exactly 3 inputs channels.
    pooling: optional pooling mode for feature extraction
      when `include_top` is `False`.
      - `None` means that the output of the model will be
          the 4D tensor output of the
          last convolutional layer.
      - `avg` means that global average pooling
          will be applied to the output of the
          last convolutional layer, and thus
          the output of the model will be a 2D tensor.
      - `max` means that global max pooling will
          be applied.
    classes: optional number of classes to classify images
      into, only to be specified if `include_top` is True, and
      if no `weights` argument is specified.
    classifier_activation: A `str` or callable. The activation function to use
      on the "top" layer. Ignored unless `include_top=True`. Set
      `classifier_activation=None` to return the logits of the "top" layer.
    **kwargs: For backwards compatibility only.
  Returns:
    A `keras.Model` instance.

  Raises:
    ValueError: in case of invalid argument for `weights`,
      or invalid input shape.
    ValueError: if `classifier_activation` is not `softmax` or `None` when
      using a pretrained top layer.
  """
    global layers
    if 'layers' in kwargs:
        layers = kwargs.pop('layers')
    else:
        layers = VersionAwareLayers()
    if kwargs:
        raise ValueError('Unknown argument(s): %s' % (kwargs, ))
    if not (weights in {'imagenet', None} or file_io.file_exists(weights)):
        raise ValueError('The `weights` argument should be either '
                         '`None` (random initialization), `imagenet` '
                         '(pre-training on ImageNet), '
                         'or the path to the weights file to be loaded.')

    if weights == 'imagenet' and include_top and classes != 1000:
        raise ValueError(
            'If using `weights` as `"imagenet"` with `include_top`'
            ' as true, `classes` should be 1000')

    # Determine proper input shape
    input_shape = imagenet_utils.obtain_input_shape(
        input_shape,
        default_size=224,
        min_size=32,
        data_format=backend.image_data_format(),
        require_flatten=include_top,
        weights=weights)

    if input_tensor is None:
        img_input = layers.Input(shape=input_shape)
    else:
        if not backend.is_keras_tensor(input_tensor):
            img_input = layers.Input(tensor=input_tensor, shape=input_shape)
        else:
            img_input = input_tensor

    bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1

    x = layers.ZeroPadding2D(padding=((3, 3), (3, 3)),
                             name='conv1_pad')(img_input)
    x = layers.Conv2D(64, 7, strides=2, use_bias=use_bias,
                      name='conv1_conv')(x)

    if not preact:
        x = layers.BatchNormalization(axis=bn_axis,
                                      epsilon=1.001e-5,
                                      name='conv1_bn')(x)
        x = layers.Activation('relu', name='conv1_relu')(x)

    x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)), name='pool1_pad')(x)
    x = layers.MaxPooling2D(3, strides=2, name='pool1_pool')(x)

    x = stack_fn(x)

    if preact:
        x = layers.BatchNormalization(axis=bn_axis,
                                      epsilon=1.001e-5,
                                      name='post_bn')(x)
        x = layers.Activation('relu', name='post_relu')(x)

    if include_top:
        x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
        imagenet_utils.validate_activation(classifier_activation, weights)
        x = layers.Dense(classes,
                         activation=classifier_activation,
                         name='predictions')(x)
    else:
        if pooling == 'avg':
            x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
        elif pooling == 'max':
            x = layers.GlobalMaxPooling2D(name='max_pool')(x)

    # Ensure that the model takes into account
    # any potential predecessors of `input_tensor`.
    if input_tensor is not None:
        inputs = layer_utils.get_source_inputs(input_tensor)
    else:
        inputs = img_input

    # Create model.
    model = training.Model(inputs, x, name=model_name)

    # Load weights.
    if (weights == 'imagenet') and (model_name in WEIGHTS_HASHES):
        if include_top:
            file_name = model_name + '_weights_tf_dim_ordering_tf_kernels.h5'
            file_hash = WEIGHTS_HASHES[model_name][0]
        else:
            file_name = model_name + '_weights_tf_dim_ordering_tf_kernels_notop.h5'
            file_hash = WEIGHTS_HASHES[model_name][1]
        weights_path = data_utils.get_file(file_name,
                                           BASE_WEIGHTS_PATH + file_name,
                                           cache_subdir='models',
                                           file_hash=file_hash)
        model.load_weights(weights_path)
    elif weights is not None:
        model.load_weights(weights)

    return model
예제 #3
0
def ResNet(stack_fn,
           preact,
           use_bias,
           model_name='resnet',
           include_top=True,
           weights='imagenet',
           input_tensor=None,
           input_shape=None,
           pooling=None,
           classes=1000,
           classifier_activation='softmax',
           **kwargs):
    global layers
    if 'layers' in kwargs:
        layers = kwargs.pop('layers')
    else:
        layers = VersionAwareLayers()
    if kwargs:
        raise ValueError('Unknown argument(s): %s' % (kwargs, ))
    if not (weights in {'imagenet', None} or file_io.file_exists(weights)):
        raise ValueError('The `weights` argument should be either '
                         '`None` (random initialization), `imagenet` '
                         '(pre-training on ImageNet), '
                         'or the path to the weights file to be loaded.')

    if weights == 'imagenet' and include_top and classes != 1000:
        raise ValueError(
            'If using `weights` as `"imagenet"` with `include_top`'
            ' as true, `classes` should be 1000')

    # Determine proper input shape
    input_shape = imagenet_utils.obtain_input_shape(
        input_shape,
        default_size=224,
        min_size=32,
        data_format=backend.image_data_format(),
        require_flatten=include_top,
        weights=weights)

    if input_tensor is None:
        img_input = layers.Input(shape=input_shape)
    else:
        if not backend.is_keras_tensor(input_tensor):
            img_input = layers.Input(tensor=input_tensor, shape=input_shape)
        else:
            img_input = input_tensor

    bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1

    x = layers.ZeroPadding2D(padding=1, name='conv1_pad')(img_input)
    x = layers.Conv2D(64,
                      3,
                      strides=1,
                      use_bias=use_bias,
                      kernel_initializer='glorot_normal',
                      name='conv1_conv')(x)

    if not preact:
        x = layers.BatchNormalization(axis=bn_axis,
                                      epsilon=2e-5,
                                      momentum=0.9,
                                      name='conv1_bn')(x)
        x = layers.PReLU(shared_axes=[1, 2], name='conv1_prelu')(x)

    # x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)), name='pool1_pad')(x)
    # x = layers.MaxPooling2D(3, strides=2, name='pool1_pool')(x)

    x = stack_fn(x)

    if preact:
        x = layers.BatchNormalization(axis=bn_axis,
                                      epsilon=2e-5,
                                      momentum=0.9,
                                      name='post_bn')(x)
        x = layers.PReLU(shared_axes=[1, 2], name='post_prelu')(x)

    if include_top:
        x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
        imagenet_utils.validate_activation(classifier_activation, weights)
        x = layers.Dense(classes,
                         activation=classifier_activation,
                         name='predictions')(x)
    else:
        if pooling == 'avg':
            x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
        elif pooling == 'max':
            x = layers.GlobalMaxPooling2D(name='max_pool')(x)

    # Ensure that the model takes into account
    # any potential predecessors of `input_tensor`.
    if input_tensor is not None:
        inputs = layer_utils.get_source_inputs(input_tensor)
    else:
        inputs = img_input

    # Create model.
    model = training.Model(inputs, x, name=model_name)

    # Load weights.
    if (weights == 'imagenet') and (model_name in WEIGHTS_HASHES):
        if include_top:
            file_name = model_name + '_weights_tf_dim_ordering_tf_kernels.h5'
            file_hash = WEIGHTS_HASHES[model_name][0]
        else:
            file_name = model_name + '_weights_tf_dim_ordering_tf_kernels_notop.h5'
            file_hash = WEIGHTS_HASHES[model_name][1]
        weights_path = data_utils.get_file(file_name,
                                           BASE_WEIGHTS_PATH + file_name,
                                           cache_subdir='models',
                                           file_hash=file_hash)
        model.load_weights(weights_path)
    elif weights is not None:
        model.load_weights(weights)

    return model