Exemplo n.º 1
0
def MobileNet(input_shape=None,
              alpha=1.0,
              depth_multiplier=1,
              dropout=1e-3,
              include_top=True,
              weights='imagenet',
              input_tensor=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 and default size.
    if input_shape is None:
        default_size = 224
    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 [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 depth_multiplier != 1:
            raise ValueError('If imagenet weights are being loaded, '
                             'depth multiplier must be 1')

        if alpha not in [0.25, 0.50, 0.75, 1.0]:
            raise ValueError('If imagenet weights are being loaded, '
                             'alpha can be one of'
                             '`0.25`, `0.50`, `0.75` or `1.0` only.')

        if rows != cols or rows not in [128, 160, 192, 224]:
            rows = 224
            logging.warning('`input_shape` is undefined or non-square, '
                            'or `rows` is not in [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

    x = _conv_block(img_input, 32, strides=(2, 2), block_id=0)

    x = _conv_block(x, 64, block_id=1)

    x = _conv_block(x, 128, strides=(2, 2), block_id=2)

    x = _conv_block(x, 128, block_id=3)

    x = _conv_block(x, 256, strides=(2, 2), block_id=4)

    x = _conv_block(x, 256, block_id=5)

    x = _conv_block(x, 512, strides=(2, 2), block_id=6)
    x = _conv_block(x, 512, block_id=7)
    x = _conv_block(x, 512, block_id=8)
    x = _conv_block(x, 512, block_id=9)
    x = _conv_block(x, 512, block_id=10)

    x = _conv_block(x, 512, block_id=11)

    x = _conv_block(x, 1024, strides=(2, 2), block_id=12)

    x = _conv_block(x, 1024, block_id=13)

    if include_top:
        if backend.image_data_format() == 'channels_first':
            shape = (int(1024 * alpha), 1, 1)
        else:
            shape = (1, 1, int(1024 * alpha))

        x = layers.GlobalAveragePooling2D()(x)
        x = layers.Reshape(shape, name='reshape_1')(x)
        x = layers.Dropout(dropout, name='dropout')(x)
        x = layers.Conv2D(classes, (1, 1), padding='same',
                          name='conv_preds')(x)
        x = layers.Reshape((classes, ), name='reshape_2')(x)
        imagenet_utils.validate_activation(classifier_activation, weights)
        x = layers.Activation(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='mobilenet_%0.2f_%s' % (alpha, rows))

    # Load weights.
    if weights == 'imagenet':
        if alpha == 1.0:
            alpha_text = '1_0'
        elif alpha == 0.75:
            alpha_text = '7_5'
        elif alpha == 0.50:
            alpha_text = '5_0'
        else:
            alpha_text = '2_5'

        if include_top:
            model_name = 'mobilenet_%s_%d_tf.h5' % (alpha_text, rows)
            weight_path = BASE_WEIGHT_PATH + model_name
            weights_path = data_utils.get_file(model_name,
                                               weight_path,
                                               cache_subdir='models')
        else:
            model_name = 'mobilenet_%s_%d_tf_no_top.h5' % (alpha_text, rows)
            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
Exemplo n.º 2
0
def MobileNet(input_shape=None,
              alpha=1.0,
              depth_multiplier=1,
              dropout=1e-3,
              include_top=True,
              weights='imagenet',
              input_tensor=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 and default size.
    if input_shape is None:
        default_size = 224
    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 [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 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

    x = _conv_block(img_input, 32, alpha, strides=(8, 8))

    #x = _depthwise_conv_block(
    #       x, 128, alpha, depth_multiplier, strides=(2,2), block_id=2)

    #x = _depthwise_conv_block(
    #       x, 1024, alpha, depth_multiplier, strides=(2,2))

    x = _depthwise_conv_block(x, 1024, alpha, depth_multiplier, block_id=13)

    if include_top:
        if backend.image_data_format() == 'channels_first':
            shape = (int(1024 * alpha), 1, 1)
        else:
            shape = (1, 1, int(1024 * alpha))

        x = layers.GlobalAveragePooling2D()(x)
        x = layers.Reshape(shape, name='reshape_1')(x)
        x = layers.Conv2D(classes, (1, 1), padding='same',
                          name='conv_preds')(x)
        x = layers.Reshape((classes, ), name='reshape_2')(x)
        imagenet_utils.validate_activation(classifier_activation, weights)
        x = layers.Activation(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='mobilenet_%0.2f_%s' % (alpha, rows))

    return model
Exemplo n.º 3
0
def MobileNet(input_shape=None,
              alpha=1.0,
              depth_multiplier=1,
              dropout=1e-3,
              include_top=True,
              weights='imagenet',
              input_tensor=None,
              pooling=None,
              classes=1000,
              classifier_activation='softmax',
              **kwargs):
    """Instantiates the MobileNet architecture.
  Reference:
  - [MobileNets: Efficient Convolutional Neural Networks
     for Mobile Vision Applications](
      https://arxiv.org/abs/1704.04861)
  Optionally loads weights pre-trained on ImageNet.
  Note that the data format convention used by the model is
  the one specified in the `tf.keras.backend.image_data_format()`.
  Note: each Keras Application expects a specific kind of input preprocessing.
  For MobileNet, call `tf.keras.applications.mobilenet.preprocess_input`
  on your inputs before passing them to the model.
  Arguments:
    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, and width and
      height should be no smaller than 32. E.g. `(200, 200, 3)` would be one
      valid value. Default to `None`.
      `input_shape` will be ignored if the `input_tensor` is provided.
    alpha: Controls the width of the network. This is known as the width
      multiplier in the MobileNet paper. - 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. Default to 1.0.
    depth_multiplier: Depth multiplier for depthwise convolution. This is
      called the resolution multiplier in the MobileNet paper. Default to 1.0.
    dropout: Dropout rate. Default to 0.001.
    include_top: Boolean, whether to include the fully-connected layer at the
      top of the network. Default to `True`.
    weights: One of `None` (random initialization), 'imagenet' (pre-training
      on ImageNet), or the path to the weights file to be loaded. Default to
      `imagenet`.
    input_tensor: Optional Keras tensor (i.e. output of `layers.Input()`) to
      use as image input for the model. `input_tensor` is useful for sharing
      inputs between multiple different networks. Default to None.
    pooling: Optional pooling mode for feature extraction when `include_top`
      is `False`.
      - `None` (default) 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: Optional number of classes to classify images into, only to be
      specified if `include_top` is True, and if no `weights` argument is
      specified. Defaults to 1000.
    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_v2(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 input_shape is None:
        default_size = 224
    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 [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 depth_multiplier != 1:
            raise ValueError('If imagenet weights are being loaded, '
                             'depth multiplier must be 1')

        if alpha not in [0.25, 0.50, 0.75, 1.0]:
            raise ValueError('If imagenet weights are being loaded, '
                             'alpha can be one of'
                             '`0.25`, `0.50`, `0.75` or `1.0` only.')

        if rows != cols or rows not in [128, 160, 192, 224]:
            rows = 224
            logging.warning('`input_shape` is undefined or non-square, '
                            'or `rows` is not in [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

    x = _conv_block(img_input, 32, alpha, strides=(2, 2))
    x = _depthwise_conv_block(x, 64, alpha, depth_multiplier, block_id=1)

    x = _depthwise_conv_block(x,
                              128,
                              alpha,
                              depth_multiplier,
                              strides=(2, 2),
                              block_id=2)
    x = _depthwise_conv_block(x, 128, alpha, depth_multiplier, block_id=3)

    x = _depthwise_conv_block(x,
                              256,
                              alpha,
                              depth_multiplier,
                              strides=(2, 2),
                              block_id=4)
    x = _depthwise_conv_block(x, 256, alpha, depth_multiplier, block_id=5)

    x = _depthwise_conv_block(x,
                              512,
                              alpha,
                              depth_multiplier,
                              strides=(2, 2),
                              block_id=6)
    x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=7)
    x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=8)
    x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=9)
    x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=10)
    x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=11)

    x = _depthwise_conv_block(x,
                              1024,
                              alpha,
                              depth_multiplier,
                              strides=(2, 2),
                              block_id=12)
    x = _depthwise_conv_block(x, 1024, alpha, depth_multiplier, block_id=13)

    if include_top:
        if backend.image_data_format() == 'channels_first':
            shape = (int(1024 * alpha), 1, 1)
        else:
            shape = (1, 1, int(1024 * alpha))

        x = layers.GlobalAveragePooling2D()(x)
        x = layers.Reshape(shape, name='reshape_1')(x)
        x = layers.Dropout(dropout, name='dropout')(x)
        x = layers.Conv2D(classes, (1, 1), padding='same',
                          name='conv_preds')(x)
        x = layers.Reshape((classes, ), name='reshape_2')(x)
        imagenet_utils.validate_activation(classifier_activation, weights)
        x = layers.Activation(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='mobilenet_%0.2f_%s' % (alpha, rows))

    # Load weights.
    if weights == 'imagenet':
        if alpha == 1.0:
            alpha_text = '1_0'
        elif alpha == 0.75:
            alpha_text = '7_5'
        elif alpha == 0.50:
            alpha_text = '5_0'
        else:
            alpha_text = '2_5'

        if include_top:
            model_name = 'mobilenet_%s_%d_tf.h5' % (alpha_text, rows)
            weight_path = BASE_WEIGHT_PATH + model_name
            weights_path = data_utils.get_file(model_name,
                                               weight_path,
                                               cache_subdir='models')
        else:
            model_name = 'mobilenet_%s_%d_tf_no_top.h5' % (alpha_text, rows)
            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
Exemplo n.º 4
0
def LeNet(input_shape=None,
          alpha=1.0,
          depth_multiplier=1,
          dropout=1e-3,
          include_top=True,
          weights='None',
          input_tensor=None,
          pooling=None,
          classes=10,
          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_v2(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 input_shape is None:
        default_size = 224
    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 [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 depth_multiplier != 1:
            raise ValueError('If imagenet weights are being loaded, '
                             'depth multiplier must be 1')

        if alpha not in [0.25, 0.50, 0.75, 1.0]:
            raise ValueError('If imagenet weights are being loaded, '
                             'alpha can be one of'
                             '`0.25`, `0.50`, `0.75` or `1.0` only.')

        if rows != cols or rows not in [128, 160, 192, 224]:
            rows = 224
            logging.warning('`input_shape` is undefined or non-square, '
                            'or `rows` is not in [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

    x = layers.Convolution2D(filters=20,
                             kernel_size=(5, 5),
                             padding="same",
                             input_shape=(28, 28, 1),
                             activation="relu",
                             name="Conv1")(img_input)
    x = layers.MaxPooling2D(pool_size=(2, 2), strides=(2, 2),
                            name="MaxPool1")(x)
    x = layers.Convolution2D(filters=50,
                             kernel_size=(5, 5),
                             padding="same",
                             activation="relu",
                             name="Conv2")(x)
    x = layers.MaxPooling2D(pool_size=(2, 2), strides=(2, 2),
                            name="MaxPool2")(x)
    #y = x.shape
    #shape = np.prod(x.shape[1:])
    #reshaper=keras.layers.Lambda(lambda x: keras.backend.reshape(x, shape=(y, shape)))
    #x = reshaper(x)
    if backend.image_data_format() == 'channels_first':
        shape = (int(800 * alpha), 1, 1)
    else:
        shape = (1, 1, int(800 * alpha))

    x = layers.Reshape(shape, name='reshape_1')(x)
    x = layers.Dense(500, activation="relu", name="Dense3")(x)
    x = layers.Dense(10, activation="softmax", name="Dense4")(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='mobilenet_%0.2f_%s' % (alpha, rows))

    # Load weights.
    if weights == 'imagenet':
        if alpha == 1.0:
            alpha_text = '1_0'
        elif alpha == 0.75:
            alpha_text = '7_5'
        elif alpha == 0.50:
            alpha_text = '5_0'
        else:
            alpha_text = '2_5'

        if include_top:
            model_name = 'mobilenet_%s_%d_tf.h5' % (alpha_text, rows)
            weight_path = BASE_WEIGHT_PATH + model_name
            weights_path = data_utils.get_file(model_name,
                                               weight_path,
                                               cache_subdir='models')
        else:
            model_name = 'mobilenet_%s_%d_tf_no_top.h5' % (alpha_text, rows)
            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