def ResNet_prelu(stack_fn,
                 preact,
                 use_bias,
                 model_name='resnet_prelu',
                 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.PReLU(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=1.001e-5,
                                      name='post_bn')(x)
        # x = layers.Activation('relu', name='post_relu')(x)
        x = layers.PReLU(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
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):
    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,
                      3,
                      strides=1,
                      padding='SAME',
                      use_bias=use_bias,
                      kernel_initializer='glorot_normal',
                      name='conv1_conv')(img_input)

    if not preact:
        x = layers.BatchNormalization(axis=bn_axis,
                                      epsilon=2.001e-5,
                                      momentum=0.9,
                                      name='conv1_bn')(x)
        x = layers.PReLU(shared_axes=[1, 2],
                         alpha_initializer='glorot_normal',
                         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=2.001e-5,
                                      momentum=0.9,
                                      name='post_bn')(x)
        x = layers.PReLU(shared_axes=[1, 2],
                         alpha_initializer='glorot_normal',
                         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