예제 #1
0
def VGG19(include_top=None, weights='imagenet',
          input_tensor=None, input_shape=None,
          pooling=None, filter_size=64, dropout=0.2,
          classes=1000):
    """Instantiates the VGG19 architecture.
    Optionally loads weights pre-trained
    on ImageNet. Note that when using TensorFlow,
    for best performance you should set
    `image_data_format="channels_last"` in your Keras config
    at ~/.keras/keras.json.
    The model and the weights are compatible with both
    TensorFlow and Theano. The data format
    convention used by the model is the one
    specified in your Keras config file.
    # Arguments
        include_top: whether to include the 3 fully-connected
            layers at the top of the network.
        weights: one of `None` (random initialization)
            or "imagenet" (pre-training on ImageNet).
        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, 244)` (with `channels_first` data format).
            It should have exactly 3 inputs channels,
            and width and height should be no smaller than 48.
            E.g. `(200, 200, 3)` would be one valid value.
        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.
    # Returns
        A Keras model instance.
    # Raises
        ValueError: in case of invalid argument for `weights`,
            or invalid input shape.
    """
    if weights not in {'imagenet', None}:
        raise ValueError('The `weights` argument should be either '
                         '`None` (random initialization) or `imagenet` '
                         '(pre-training on ImageNet).')

    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 = _obtain_input_shape(input_shape,
                                      default_size=224,
                                      min_size=32,
                                      data_format=K.image_data_format(),
                                      include_top=include_top)

    if input_tensor is None:
        img_input = Input(shape=input_shape)
    else:
        if not K.is_keras_tensor(input_tensor):
            img_input = Input(tensor=input_tensor, shape=input_shape)
        else:
            img_input = input_tensor
    # Block 1
    x = Conv2D(filter_size, (3, 3), activation='relu', padding='same', name='block1_conv1')(img_input)
    x = Conv2D(filter_size, (3, 3), activation='relu', padding='same', name='block1_conv2')(x)
    x = SpatialDropout2D(rate=dropout) (x)
    x = MaxPooling2D((2, 2), name='block1_pool')(x)

    # Block 2
    x = Conv2D(filter_size*2, (3, 3), activation='relu', padding='same', name='block2_conv1')(x)
    dn_feat1 = x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv2')(x)
    x = SpatialDropout2D(rate=dropout) (x)
    x = MaxPooling2D((2, 2), name='block2_pool')(x)

    # Block 3
    x = Conv2D(filter_size*4, (3, 3), activation='relu', padding='same', name='block3_conv1')(x)
    x = Conv2D(filter_size*4, (3, 3), activation='relu', padding='same', name='block3_conv2')(x)
    x = Conv2D(filter_size*4, (3, 3), activation='relu', padding='same', name='block3_conv3')(x)
    dn_feat2 = x = Conv2D(filter_size*4, (3, 3), dilation_rate=4, activation='relu', padding='same', name='block3_conv4')(x)
    x = Dropout(rate=dropout) (x)
    x = MaxPooling2D((2, 2), name='block3_pool')(x)

    # Block 4
    x = Conv2D(filter_size*8, (3, 3), activation='relu', padding='same', name='block4_conv1')(x)
    x = Conv2D(filter_size*8, (3, 3), activation='relu', padding='same', name='block4_conv2')(x)
    x = Conv2D(filter_size*8, (3, 3), activation='relu', padding='same', name='block4_conv3')(x)
    dn_feat3 = x = Conv2D(filter_size*8, (3, 3), activation='relu', padding='same', name='block4_conv4')(x)
    x = Dropout(rate=dropout) (x)
    x = MaxPooling2D((2, 2), name='block4_pool')(x)

    # Block 5
    x = Conv2D(filter_size*8, (3, 3), activation='relu', padding='same', name='block5_conv1')(x)
    x = Conv2D(filter_size*4, (3, 3), activation='relu', padding='same', name='block5_conv2')(x)
    x = Conv2D(filter_size*4, (3, 3), activation='relu', padding='same', name='block5_conv3')(x)
    dn_feat4 = x = Conv2D(filter_size*2, (3, 3), activation='sigmoid', padding='same', name='block5_conv4')(x)
    x = Dropout(rate=dropout) (x)
    x = MaxPooling2D((2, 2), name='block5_pool')(x)

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

    if weights == None and classes != 1000:
        output_shape = Model(inputs, x).output_shape
        if pooling == 'avg':
            x = AveragePooling2D((output_shape[1], output_shape[2]))(x)
        elif pooling == 'max':
            x = MaxPooling2D((output_shape[1], output_shape[2]))(x)
        x = Conv2D(classes, (1, 1), activation='softmax', padding='same', name='output') (x)

    elif include_top and classes == 1000:
        # Classification block
        x = Flatten(name='flatten')(x)
        x = Dense(4096, activation='relu', name='fc1')(x)
        x = Dense(4096, activation='relu', name='fc2')(x)
        x = Dense(classes, activation='softmax', name='predictions')(x)
    else:
        if pooling == 'avg':
            x = GlobalAveragePooling2D()(x)
        elif pooling == 'max':
            x = GlobalMaxPooling2D()(x)

    # Create model.
    model = Model(inputs, x, name='vgg19')

    # load weights
    if weights == 'imagenet':
        if include_top:
            weights_path = get_file('vgg19_weights_tf_dim_ordering_tf_kernels.h5',
                                    WEIGHTS_PATH,
                                    cache_subdir='models')
        else:
            weights_path = get_file('vgg19_weights_tf_dim_ordering_tf_kernels_notop.h5',
                                    WEIGHTS_PATH_NO_TOP,
                                    cache_subdir='models')
        model.load_weights(weights_path)
        if K.backend() == 'theano':
            layer_utils.convert_all_kernels_in_model(model)

        if K.image_data_format() == 'channels_first':
            if include_top:
                maxpool = model.get_layer(name='block5_pool')
                shape = maxpool.output_shape[1:]
                dense = model.get_layer(name='fc1')
                layer_utils.convert_dense_weights_data_format(dense, shape, 'channels_first')

            if K.backend() == 'tensorflow':
                warnings.warn('You are using the TensorFlow backend, yet you '
                              'are using the Theano '
                              'image data format convention '
                              '(`image_data_format="channels_first"`). '
                              'For best performance, set '
                              '`image_data_format="channels_last"` in '
                              'your Keras config '
                              'at ~/.keras/keras.json.')

    model.input_tensor_fcn = inputs
    model.tensor_hooks_fcn = [dn_feat1, dn_feat2, dn_feat3, dn_feat4, x]
    return model
예제 #2
0
def ResNet50(include_top=True, weights='imagenet',
             input_tensor=None, input_shape=None,
             pooling=None,
             classes=1000):
    """Instantiates the ResNet50 architecture.
    Optionally loads weights pre-trained
    on ImageNet. Note that when using TensorFlow,
    for best performance you should set
    `image_data_format="channels_last"` in your Keras config
    at ~/.keras/keras.json.
    The model and the weights are compatible with both
    TensorFlow and Theano. The data format
    convention used by the model is the one
    specified in your Keras config file.
    # Arguments
        include_top: whether to include the fully-connected
            layer at the top of the network.
        weights: one of `None` (random initialization)
            or "imagenet" (pre-training on ImageNet).
        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, 244)` (with `channels_first` data format).
            It should have exactly 3 inputs channels,
            and width and height should be no smaller than 197.
            E.g. `(200, 200, 3)` would be one valid value.
        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.
    # Returns
        A Keras model instance.
    # Raises
        ValueError: in case of invalid argument for `weights`,
            or invalid input shape.
    """
    if weights not in {'imagenet', None}:
        raise ValueError('The `weights` argument should be either '
                         '`None` (random initialization) or `imagenet` '
                         '(pre-training on ImageNet).')

    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 = _obtain_input_shape(input_shape,
                                      default_size=224,
                                      min_size=197,
                                      data_format=K.image_data_format(),
                                      include_top=include_top)

    if input_tensor is None:
        img_input = Input(shape=input_shape)
    else:
        if not K.is_keras_tensor(input_tensor):
            img_input = Input(tensor=input_tensor, shape=input_shape)
        else:
            img_input = input_tensor
    if K.image_data_format() == 'channels_last':
        bn_axis = 3
    else:
        bn_axis = 1

    x = ZeroPadding2D((3, 3))(img_input)
    x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(x)
    x = BatchNormalization(axis=bn_axis, name='bn_conv1')(x)
    x = Activation('relu')(x)
    x = MaxPooling2D((3, 3), strides=(2, 2))(x)

    x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
    x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
    dn_feat1 = x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')

    x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
    x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
    dn_feat2 = x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')

    x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d')
    x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e')
    dn_feat3 = x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f')

    x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
    x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
    dn_feat4 = x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')

    x = AveragePooling2D((7, 7), name='avg_pool')(x)

    if include_top:
        x = Flatten()(x)
        x = Dense(classes, activation='softmax', name='fc1000')(x)
    else:
        if pooling == 'avg':
            x = GlobalAveragePooling2D()(x)
        elif pooling == 'max':
            x = GlobalMaxPooling2D()(x)

    # Ensure that the model takes into account
    # any potential predecessors of `input_tensor`.
    if input_tensor is not None:
        inputs = get_source_inputs(input_tensor)
    else:
        inputs = img_input
    # Create model.
    model = Model(inputs, x, name='resnet50')

    # load weights
    if weights == 'imagenet':
        if include_top:
            weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels.h5',
                                    WEIGHTS_PATH,
                                    cache_subdir='models',
                                    md5_hash='a7b3fe01876f51b976af0dea6bc144eb')
        else:
            weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
                                    WEIGHTS_PATH_NO_TOP,
                                    cache_subdir='models',
                                    md5_hash='a268eb855778b3df3c7506639542a6af')
        model.load_weights(weights_path)
        #if K.backend() == 'theano':
        #    layer_utils.convert_all_kernels_in_model(model)

        if K.image_data_format() == 'channels_first':
            if include_top:
                maxpool = model.get_layer(name='avg_pool')
                shape = maxpool.output_shape[1:]
                dense = model.get_layer(name='fc1000')
                layer_utils.convert_dense_weights_data_format(dense, shape, 'channels_first')

            if K.backend() == 'tensorflow':
                warnings.warn('You are using the TensorFlow backend, yet you '
                              'are using the Theano '
                              'image data format convention '
                              '(`image_data_format="channels_first"`). '
                              'For best performance, set '
                              '`image_data_format="channels_last"` in '
                              'your Keras config '
                              'at ~/.keras/keras.json.')

    model.input_tensor_fcn = inputs
    model.tensor_hooks_fcn = [dn_feat1, dn_feat2, dn_feat3, dn_feat4, x]
    return model