Module keras.applications.vgg19

VGG19 model for Keras.

Reference

Expand source code
# Copyright 2015 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
# pylint: disable=invalid-name
"""VGG19 model for Keras.

Reference:
  - [Very Deep Convolutional Networks for Large-Scale Image Recognition](
      https://arxiv.org/abs/1409.1556) (ICLR 2015)
"""

import tensorflow.compat.v2 as tf

from keras import backend
from keras.applications import imagenet_utils
from keras.engine import training
from keras.layers import VersionAwareLayers
from keras.utils import data_utils
from keras.utils import layer_utils
from tensorflow.python.util.tf_export import keras_export


WEIGHTS_PATH = ('https://storage.googleapis.com/tensorflow/keras-applications/'
                'vgg19/vgg19_weights_tf_dim_ordering_tf_kernels.h5')
WEIGHTS_PATH_NO_TOP = ('https://storage.googleapis.com/tensorflow/'
                       'keras-applications/vgg19/'
                       'vgg19_weights_tf_dim_ordering_tf_kernels_notop.h5')

layers = VersionAwareLayers()


@keras_export('keras.applications.vgg19.VGG19', 'keras.applications.VGG19')
def VGG19(
    include_top=True,
    weights='imagenet',
    input_tensor=None,
    input_shape=None,
    pooling=None,
    classes=1000,
    classifier_activation='softmax'):
  """Instantiates the VGG19 architecture.

  Reference:
  - [Very Deep Convolutional Networks for Large-Scale Image Recognition](
      https://arxiv.org/abs/1409.1556) (ICLR 2015)

  For image classification use cases, see
  [this page for detailed examples](
    https://keras.io/api/applications/#usage-examples-for-image-classification-models).

  For transfer learning use cases, make sure to read the
  [guide to transfer learning & fine-tuning](
    https://keras.io/guides/transfer_learning/).

  The default input size for this model is 224x224.

  Note: each Keras Application expects a specific kind of input preprocessing.
  For VGG19, call `tf.keras.applications.vgg19.preprocess_input` on your
  inputs before passing them to the model.
  `vgg19.preprocess_input` will convert the input images from RGB to BGR,
  then will zero-center each color channel with respect to the ImageNet dataset,
  without scaling.

  Args:
    include_top: whether to include the 3 fully-connected
      layers 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,
      and width and height should be no smaller than 32.
      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 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.
    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.
      When loading pretrained weights, `classifier_activation` can only
      be `None` or `"softmax"`.

  Returns:
    A `keras.Model` instance.
  """
  if not (weights in {'imagenet', None} or tf.io.gfile.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
  # Block 1
  x = layers.Conv2D(
      64, (3, 3), activation='relu', padding='same', name='block1_conv1')(
          img_input)
  x = layers.Conv2D(
      64, (3, 3), activation='relu', padding='same', name='block1_conv2')(x)
  x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)

  # Block 2
  x = layers.Conv2D(
      128, (3, 3), activation='relu', padding='same', name='block2_conv1')(x)
  x = layers.Conv2D(
      128, (3, 3), activation='relu', padding='same', name='block2_conv2')(x)
  x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)

  # Block 3
  x = layers.Conv2D(
      256, (3, 3), activation='relu', padding='same', name='block3_conv1')(x)
  x = layers.Conv2D(
      256, (3, 3), activation='relu', padding='same', name='block3_conv2')(x)
  x = layers.Conv2D(
      256, (3, 3), activation='relu', padding='same', name='block3_conv3')(x)
  x = layers.Conv2D(
      256, (3, 3), activation='relu', padding='same', name='block3_conv4')(x)
  x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)

  # Block 4
  x = layers.Conv2D(
      512, (3, 3), activation='relu', padding='same', name='block4_conv1')(x)
  x = layers.Conv2D(
      512, (3, 3), activation='relu', padding='same', name='block4_conv2')(x)
  x = layers.Conv2D(
      512, (3, 3), activation='relu', padding='same', name='block4_conv3')(x)
  x = layers.Conv2D(
      512, (3, 3), activation='relu', padding='same', name='block4_conv4')(x)
  x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)

  # Block 5
  x = layers.Conv2D(
      512, (3, 3), activation='relu', padding='same', name='block5_conv1')(x)
  x = layers.Conv2D(
      512, (3, 3), activation='relu', padding='same', name='block5_conv2')(x)
  x = layers.Conv2D(
      512, (3, 3), activation='relu', padding='same', name='block5_conv3')(x)
  x = layers.Conv2D(
      512, (3, 3), activation='relu', padding='same', name='block5_conv4')(x)
  x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)

  if include_top:
    # Classification block
    x = layers.Flatten(name='flatten')(x)
    x = layers.Dense(4096, activation='relu', name='fc1')(x)
    x = layers.Dense(4096, activation='relu', name='fc2')(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='vgg19')

  # Load weights.
  if weights == 'imagenet':
    if include_top:
      weights_path = data_utils.get_file(
          'vgg19_weights_tf_dim_ordering_tf_kernels.h5',
          WEIGHTS_PATH,
          cache_subdir='models',
          file_hash='cbe5617147190e668d6c5d5026f83318')
    else:
      weights_path = data_utils.get_file(
          'vgg19_weights_tf_dim_ordering_tf_kernels_notop.h5',
          WEIGHTS_PATH_NO_TOP,
          cache_subdir='models',
          file_hash='253f8cb515780f3b799900260a226db6')
    model.load_weights(weights_path)
  elif weights is not None:
    model.load_weights(weights)

  return model


@keras_export('keras.applications.vgg19.preprocess_input')
def preprocess_input(x, data_format=None):
  return imagenet_utils.preprocess_input(
      x, data_format=data_format, mode='caffe')


@keras_export('keras.applications.vgg19.decode_predictions')
def decode_predictions(preds, top=5):
  return imagenet_utils.decode_predictions(preds, top=top)


preprocess_input.__doc__ = imagenet_utils.PREPROCESS_INPUT_DOC.format(
    mode='',
    ret=imagenet_utils.PREPROCESS_INPUT_RET_DOC_CAFFE,
    error=imagenet_utils.PREPROCESS_INPUT_ERROR_DOC)
decode_predictions.__doc__ = imagenet_utils.decode_predictions.__doc__

Functions

def VGG19(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000, classifier_activation='softmax')

Instantiates the VGG19 architecture.

Reference: - Very Deep Convolutional Networks for Large-Scale Image Recognition (ICLR 2015)

For image classification use cases, see this page for detailed examples.

For transfer learning use cases, make sure to read the guide to transfer learning & fine-tuning.

The default input size for this model is 224x224.

Note: each Keras Application expects a specific kind of input preprocessing. For VGG19, call tf.keras.applications.vgg19.preprocess_input on your inputs before passing them to the model. vgg19.preprocess_input will convert the input images from RGB to BGR, then will zero-center each color channel with respect to the ImageNet dataset, without scaling.

Args

include_top
whether to include the 3 fully-connected layers 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, and width and height should be no smaller than 32. 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 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.
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. When loading pretrained weights, classifier_activation can only be None or "softmax".

Returns

A keras.Model instance.

Expand source code
@keras_export('keras.applications.vgg19.VGG19', 'keras.applications.VGG19')
def VGG19(
    include_top=True,
    weights='imagenet',
    input_tensor=None,
    input_shape=None,
    pooling=None,
    classes=1000,
    classifier_activation='softmax'):
  """Instantiates the VGG19 architecture.

  Reference:
  - [Very Deep Convolutional Networks for Large-Scale Image Recognition](
      https://arxiv.org/abs/1409.1556) (ICLR 2015)

  For image classification use cases, see
  [this page for detailed examples](
    https://keras.io/api/applications/#usage-examples-for-image-classification-models).

  For transfer learning use cases, make sure to read the
  [guide to transfer learning & fine-tuning](
    https://keras.io/guides/transfer_learning/).

  The default input size for this model is 224x224.

  Note: each Keras Application expects a specific kind of input preprocessing.
  For VGG19, call `tf.keras.applications.vgg19.preprocess_input` on your
  inputs before passing them to the model.
  `vgg19.preprocess_input` will convert the input images from RGB to BGR,
  then will zero-center each color channel with respect to the ImageNet dataset,
  without scaling.

  Args:
    include_top: whether to include the 3 fully-connected
      layers 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,
      and width and height should be no smaller than 32.
      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 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.
    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.
      When loading pretrained weights, `classifier_activation` can only
      be `None` or `"softmax"`.

  Returns:
    A `keras.Model` instance.
  """
  if not (weights in {'imagenet', None} or tf.io.gfile.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
  # Block 1
  x = layers.Conv2D(
      64, (3, 3), activation='relu', padding='same', name='block1_conv1')(
          img_input)
  x = layers.Conv2D(
      64, (3, 3), activation='relu', padding='same', name='block1_conv2')(x)
  x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)

  # Block 2
  x = layers.Conv2D(
      128, (3, 3), activation='relu', padding='same', name='block2_conv1')(x)
  x = layers.Conv2D(
      128, (3, 3), activation='relu', padding='same', name='block2_conv2')(x)
  x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)

  # Block 3
  x = layers.Conv2D(
      256, (3, 3), activation='relu', padding='same', name='block3_conv1')(x)
  x = layers.Conv2D(
      256, (3, 3), activation='relu', padding='same', name='block3_conv2')(x)
  x = layers.Conv2D(
      256, (3, 3), activation='relu', padding='same', name='block3_conv3')(x)
  x = layers.Conv2D(
      256, (3, 3), activation='relu', padding='same', name='block3_conv4')(x)
  x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)

  # Block 4
  x = layers.Conv2D(
      512, (3, 3), activation='relu', padding='same', name='block4_conv1')(x)
  x = layers.Conv2D(
      512, (3, 3), activation='relu', padding='same', name='block4_conv2')(x)
  x = layers.Conv2D(
      512, (3, 3), activation='relu', padding='same', name='block4_conv3')(x)
  x = layers.Conv2D(
      512, (3, 3), activation='relu', padding='same', name='block4_conv4')(x)
  x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)

  # Block 5
  x = layers.Conv2D(
      512, (3, 3), activation='relu', padding='same', name='block5_conv1')(x)
  x = layers.Conv2D(
      512, (3, 3), activation='relu', padding='same', name='block5_conv2')(x)
  x = layers.Conv2D(
      512, (3, 3), activation='relu', padding='same', name='block5_conv3')(x)
  x = layers.Conv2D(
      512, (3, 3), activation='relu', padding='same', name='block5_conv4')(x)
  x = layers.MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)

  if include_top:
    # Classification block
    x = layers.Flatten(name='flatten')(x)
    x = layers.Dense(4096, activation='relu', name='fc1')(x)
    x = layers.Dense(4096, activation='relu', name='fc2')(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='vgg19')

  # Load weights.
  if weights == 'imagenet':
    if include_top:
      weights_path = data_utils.get_file(
          'vgg19_weights_tf_dim_ordering_tf_kernels.h5',
          WEIGHTS_PATH,
          cache_subdir='models',
          file_hash='cbe5617147190e668d6c5d5026f83318')
    else:
      weights_path = data_utils.get_file(
          'vgg19_weights_tf_dim_ordering_tf_kernels_notop.h5',
          WEIGHTS_PATH_NO_TOP,
          cache_subdir='models',
          file_hash='253f8cb515780f3b799900260a226db6')
    model.load_weights(weights_path)
  elif weights is not None:
    model.load_weights(weights)

  return model
def decode_predictions(preds, top=5)

Decodes the prediction of an ImageNet model.

Args

preds
Numpy array encoding a batch of predictions.
top
Integer, how many top-guesses to return. Defaults to 5.

Returns

A list of lists of top class prediction tuples (class_name, class_description, score). One list of tuples per sample in batch input.

Raises

ValueError
In case of invalid shape of the pred array (must be 2D).
Expand source code
@keras_export('keras.applications.vgg19.decode_predictions')
def decode_predictions(preds, top=5):
  return imagenet_utils.decode_predictions(preds, top=top)
def preprocess_input(x, data_format=None)

Preprocesses a tensor or Numpy array encoding a batch of images.

Usage example with applications.MobileNet:

i = tf.keras.layers.Input([None, None, 3], dtype = tf.uint8)
x = tf.cast(i, tf.float32)
x = tf.keras.applications.mobilenet.preprocess_input(x)
core = tf.keras.applications.MobileNet()
x = core(x)
model = tf.keras.Model(inputs=[i], outputs=[x])

image = tf.image.decode_png(tf.io.read_file('file.png'))
result = model(image)

Args

x
A floating point numpy.array or a tf.Tensor, 3D or 4D with 3 color channels, with values in the range [0, 255]. The preprocessed data are written over the input data if the data types are compatible. To avoid this behaviour, numpy.copy(x) can be used.
data_format
Optional data format of the image tensor/array. Defaults to None, in which case the global setting tf.keras.backend.image_data_format() is used (unless you changed it, it defaults to "channels_last").

Returns

Preprocessed numpy.array or a tf.Tensor with type float32.

The images are converted from RGB to BGR, then each color channel is zero-centered with respect to the ImageNet dataset, without scaling.

Raises

ValueError
In case of unknown data_format argument.
Expand source code
@keras_export('keras.applications.vgg19.preprocess_input')
def preprocess_input(x, data_format=None):
  return imagenet_utils.preprocess_input(
      x, data_format=data_format, mode='caffe')