def load_data(label_mode='fine'):
"""Loads CIFAR100 dataset.
Arguments:
label_mode: one of "fine", "coarse".
Returns:
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
Raises:
ValueError: in case of invalid `label_mode`.
"""
if label_mode not in ['fine', 'coarse']:
raise ValueError('`label_mode` must be one of `"fine"`, `"coarse"`.')
dirname = 'cifar-100-python'
origin = 'https://www.cs.toronto.edu/~kriz/cifar-100-python.tar.gz'
path = get_file(dirname, origin=origin, untar=True)
fpath = os.path.join(path, 'train')
x_train, y_train = load_batch(fpath, label_key=label_mode + '_labels')
fpath = os.path.join(path, 'test')
x_test, y_test = load_batch(fpath, label_key=label_mode + '_labels')
y_train = np.reshape(y_train, (len(y_train), 1))
y_test = np.reshape(y_test, (len(y_test), 1))
if K.image_data_format() == 'channels_last':
x_train = x_train.transpose(0, 2, 3, 1)
x_test = x_test.transpose(0, 2, 3, 1)
return (x_train, y_train), (x_test, y_test)
def load_data(path='mnist.npz'):
"""Loads the MNIST dataset.
Arguments:
path: path where to cache the dataset locally
(relative to ~/.keras/datasets).
Returns:
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
License:
Yann LeCun and Corinna Cortes hold the copyright of MNIST dataset,
which is a derivative work from original NIST datasets.
MNIST dataset is made available under the terms of the
[Creative Commons Attribution-Share Alike 3.0 license.](
https://creativecommons.org/licenses/by-sa/3.0/)
"""
origin_folder = 'https://storage.googleapis.com/tensorflow/tf-keras-datasets/'
path = get_file(
path,
origin=origin_folder + 'mnist.npz',
file_hash='8a61469f7ea1b51cbae51d4f78837e45')
f = np.load(path)
x_train, y_train = f['x_train'], f['y_train']
x_test, y_test = f['x_test'], f['y_test']
f.close()
return (x_train, y_train), (x_test, y_test)
def load_data():
"""Loads CIFAR10 dataset.
Returns:
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
"""
dirname = 'cifar-10-batches-py'
origin = 'https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz'
path = get_file(dirname, origin=origin, untar=True)
num_train_samples = 50000
x_train = np.empty((num_train_samples, 3, 32, 32), dtype='uint8')
y_train = np.empty((num_train_samples,), dtype='uint8')
for i in range(1, 6):
fpath = os.path.join(path, 'data_batch_' + str(i))
(x_train[(i - 1) * 10000:i * 10000, :, :, :],
y_train[(i - 1) * 10000:i * 10000]) = load_batch(fpath)
fpath = os.path.join(path, 'test_batch')
x_test, y_test = load_batch(fpath)
y_train = np.reshape(y_train, (len(y_train), 1))
y_test = np.reshape(y_test, (len(y_test), 1))
if K.image_data_format() == 'channels_last':
x_train = x_train.transpose(0, 2, 3, 1)
x_test = x_test.transpose(0, 2, 3, 1)
return (x_train, y_train), (x_test, y_test)
def load_data():
"""Loads the Fashion-MNIST dataset.
Returns:
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
"""
dirname = os.path.join('datasets', 'fashion-mnist')
base = 'http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/'
files = [
'train-labels-idx1-ubyte.gz', 'train-images-idx3-ubyte.gz',
't10k-labels-idx1-ubyte.gz', 't10k-images-idx3-ubyte.gz'
]
paths = []
for fname in files:
paths.append(get_file(fname, origin=base + fname, cache_subdir=dirname))
with gzip.open(paths[0], 'rb') as lbpath:
y_train = np.frombuffer(lbpath.read(), np.uint8, offset=8)
with gzip.open(paths[1], 'rb') as imgpath:
x_train = np.frombuffer(
imgpath.read(), np.uint8, offset=16).reshape(len(y_train), 28, 28)
with gzip.open(paths[2], 'rb') as lbpath:
y_test = np.frombuffer(lbpath.read(), np.uint8, offset=8)
with gzip.open(paths[3], 'rb') as imgpath:
x_test = np.frombuffer(
imgpath.read(), np.uint8, offset=16).reshape(len(y_test), 28, 28)
return (x_train, y_train), (x_test, y_test)
def load_data(path='boston_housing.npz', test_split=0.2, seed=113):
"""Loads the Boston Housing dataset.
Arguments:
path: path where to cache the dataset locally
(relative to ~/.keras/datasets).
test_split: fraction of the data to reserve as test set.
seed: Random seed for shuffling the data
before computing the test split.
Returns:
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
"""
assert 0 <= test_split < 1
path = get_file(
path,
origin='https://s3.amazonaws.com/keras-datasets/boston_housing.npz',
file_hash=
'f553886a1f8d56431e820c5b82552d9d95cfcb96d1e678153f8839538947dff5')
f = np.load(path)
x = f['x']
y = f['y']
f.close()
np.random.seed(seed)
indices = np.arange(len(x))
np.random.shuffle(indices)
x = x[indices]
y = y[indices]
x_train = np.array(x[:int(len(x) * (1 - test_split))])
y_train = np.array(y[:int(len(x) * (1 - test_split))])
x_test = np.array(x[int(len(x) * (1 - test_split)):])
y_test = np.array(y[int(len(x) * (1 - test_split)):])
return (x_train, y_train), (x_test, y_test)
def _get_elephant(target_size):
# For models that don't include a Flatten step,
# the default is to accept variable-size inputs
# even when loading ImageNet weights (since it is possible).
# In this case, default to 299x299.
if target_size[0] is None:
target_size = (299, 299)
test_image = data_utils.get_file('elephant.jpg', TEST_IMAGE_PATH)
img = image.load_img(test_image, target_size=tuple(target_size))
x = image.img_to_array(img)
return np.expand_dims(x, axis=0)
def __init__(self, mapping={}) -> None:
checkpoint = data_utils.get_file(
DIR_NAME, WEIGHTS_URL, untar=True, extract=True, cache_subdir="deep_learning")
checkpoint = os.path.join(checkpoint, "variables")
checkpoint_file = os.path.join(checkpoint, "checkpoint")
if not os.path.isfile(checkpoint_file):
local_ckpt_file = os.path.join(
os.path.dirname(__file__), 'checkpoint')
copyfile(local_ckpt_file, checkpoint_file)
ckpt_path = tf.train.latest_checkpoint(checkpoint)
self.reader = py_checkpoint_reader.NewCheckpointReader(ckpt_path)
self.mapping = mapping
def __init__(self, bits=8, resolution=64):
if resolution not in {32, 64}: raise NotImplementedError("Only support resolution 32 or 64, not %i. "%resolution)
if not os.path.exists("datasets/"): os.makedirs("datasets/")
from tensorflow.python.keras.utils.data_utils import get_file
import tarfile
if resolution == 32: # 4 GB
print("Starting to download and extract imagenet32, it is 4GB, so this might take a long time. ")
print("Go grab a cup of coffee. ")
loc = get_file("imagenet32train.tar", "http://image-net.org/small/train_32x32.tar") # save this location for later use?
tarf = tarfile.open(loc)
tarf.extract_all()
if resolution == 64: # 12 GB (might take a very long time)
print("Starting to download and extract imagenet64, it is 12GB, so this might take a very long time. ")
print("Go hit the gym or go for a walk. ")
loc = get_file("imagenet32train.tar", "http://image-net.org/small/train_64x64.tar") # save this location for later use?
tarf = tarfile.open(loc)
tarf.extract_all()
def load_data(label_mode='fine'):
"""Loads [CIFAR100 dataset](https://www.cs.toronto.edu/~kriz/cifar.html).
This is a dataset of 50,000 32x32 color training images and
10,000 test images, labeled over 100 fine-grained classes that are
grouped into 20 coarse-grained classes. See more info at the
[CIFAR homepage](https://www.cs.toronto.edu/~kriz/cifar.html).
Args:
label_mode: one of "fine", "coarse". If it is "fine" the category labels
are the fine-grained labels, if it is "coarse" the output labels are the
coarse-grained superclasses.
Returns:
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
**x_train, x_test**: uint8 arrays of RGB image data with shape
`(num_samples, 3, 32, 32)` if `tf.keras.backend.image_data_format()` is
`'channels_first'`, or `(num_samples, 32, 32, 3)` if the data format
is `'channels_last'`.
**y_train, y_test**: uint8 arrays of category labels with shape
(num_samples, 1).
Raises:
ValueError: in case of invalid `label_mode`.
"""
if label_mode not in ['fine', 'coarse']:
raise ValueError('`label_mode` must be one of `"fine"`, `"coarse"`.')
dirname = 'cifar-100-python'
origin = 'https://www.cs.toronto.edu/~kriz/cifar-100-python.tar.gz'
path = get_file(
dirname,
origin=origin,
untar=True,
file_hash=
'85cd44d02ba6437773c5bbd22e183051d648de2e7d6b014e1ef29b855ba677a7')
fpath = os.path.join(path, 'train')
x_train, y_train = load_batch(fpath, label_key=label_mode + '_labels')
fpath = os.path.join(path, 'test')
x_test, y_test = load_batch(fpath, label_key=label_mode + '_labels')
y_train = np.reshape(y_train, (len(y_train), 1))
y_test = np.reshape(y_test, (len(y_test), 1))
if K.image_data_format() == 'channels_last':
x_train = x_train.transpose(0, 2, 3, 1)
x_test = x_test.transpose(0, 2, 3, 1)
return (x_train, y_train), (x_test, y_test)
def load_data(path='boston_housing.npz', test_split=0.2, seed=113):
"""Loads the Boston Housing dataset.
This is a dataset taken from the StatLib library which is maintained at
Carnegie Mellon University.
Samples contain 13 attributes of houses at different locations around the
Boston suburbs in the late 1970s. Targets are the median values of
the houses at a location (in k$).
The attributes themselves are defined in the
[StatLib website](http://lib.stat.cmu.edu/datasets/boston).
Arguments:
path: path where to cache the dataset locally
(relative to `~/.keras/datasets`).
test_split: fraction of the data to reserve as test set.
seed: Random seed for shuffling the data
before computing the test split.
Returns:
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
**x_train, x_test**: numpy arrays with shape `(num_samples, 13)`
containing either the training samples (for x_train),
or test samples (for y_train).
**y_train, y_test**: numpy arrays of shape `(num_samples,)` containing the
target scalars. The targets are float scalars typically between 10 and
50 that represent the home prices in k$.
"""
assert 0 <= test_split < 1
origin_folder = 'https://storage.googleapis.com/tensorflow/tf-keras-datasets/'
path = get_file(
path,
origin=origin_folder + 'boston_housing.npz',
file_hash=
'f553886a1f8d56431e820c5b82552d9d95cfcb96d1e678153f8839538947dff5')
with np.load(path, allow_pickle=True) as f:
x = f['x']
y = f['y']
np.random.seed(seed)
indices = np.arange(len(x))
np.random.shuffle(indices)
x = x[indices]
y = y[indices]
x_train = np.array(x[:int(len(x) * (1 - test_split))])
y_train = np.array(y[:int(len(x) * (1 - test_split))])
x_test = np.array(x[int(len(x) * (1 - test_split)):])
y_test = np.array(y[int(len(x) * (1 - test_split)):])
return (x_train, y_train), (x_test, y_test)
def load_data(image_key: str = "x",
label_key: str = "y") -> Tuple[NumpyDataset, NumpyDataset]:
"""Load and return the ciFAIR10 dataset.
This is the cifar10 dataset but with test set duplicates removed and replaced. See
https://arxiv.org/pdf/1902.00423.pdf or https://cvjena.github.io/cifair/ for details. Cite the paper if you use the
dataset.
Args:
image_key: The key for image.
label_key: The key for label.
Returns:
(train_data, test_data)
"""
dirname = 'ciFAIR-10'
archive_name = 'ciFAIR-10.zip'
origin = 'https://github.com/cvjena/cifair/releases/download/v1.0/ciFAIR-10.zip'
md5_hash = 'ca08fd390f0839693d3fc45c4e49585f'
path = get_file(archive_name,
origin=origin,
file_hash=md5_hash,
hash_algorithm='md5',
extract=True,
archive_format='zip')
path = os.path.join(os.path.dirname(path), dirname)
num_train_samples = 50000
x_train = np.empty((num_train_samples, 3, 32, 32), dtype='uint8')
y_train = np.empty((num_train_samples, ), dtype='uint8')
for i in range(1, 6):
fpath = os.path.join(path, f'data_batch_{i}')
(x_train[(i - 1) * 10000:i * 10000, :, :, :],
y_train[(i - 1) * 10000:i * 10000]) = _load_batch(fpath)
fpath = os.path.join(path, 'test_batch')
x_test, y_test = _load_batch(fpath)
y_train = np.reshape(y_train, (len(y_train), 1))
y_test = np.reshape(y_test, (len(y_test), 1))
x_train = x_train.transpose((0, 2, 3, 1))
x_test = x_test.transpose((0, 2, 3, 1))
x_test = x_test.astype(x_train.dtype)
y_test = y_test.astype(y_train.dtype)
train_data = NumpyDataset({image_key: x_train, label_key: y_train})
test_data = NumpyDataset({image_key: x_test, label_key: y_test})
return train_data, test_data
def load_data():
"""Loads [CIFAR10 dataset](https://www.cs.toronto.edu/~kriz/cifar.html).
This is a dataset of 50,000 32x32 color training images and 10,000 test
images, labeled over 10 categories. See more info at the
[CIFAR homepage](https://www.cs.toronto.edu/~kriz/cifar.html).
Returns:
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
**x_train, x_test**: uint8 arrays of RGB image data with shape
(num_samples, 3, 32, 32) if the `tf.keras.backend.image_data_format` is
'channels_first', or (num_samples, 32, 32, 3) if the data format
is 'channels_last'.
**y_train, y_test**: uint8 arrays of category labels
(integers in range 0-9) each with shape (num_samples, 1).
"""
dirname = 'cifar-10-batches-py'
origin = 'https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz'
path = get_file(
dirname,
origin=origin,
untar=True,
file_hash=
'6d958be074577803d12ecdefd02955f39262c83c16fe9348329d7fe0b5c001ce')
num_train_samples = 50000
x_train = np.empty((num_train_samples, 3, 32, 32), dtype='uint8')
y_train = np.empty((num_train_samples, ), dtype='uint8')
for i in range(1, 6):
fpath = os.path.join(path, 'data_batch_' + str(i))
(x_train[(i - 1) * 10000:i * 10000, :, :, :],
y_train[(i - 1) * 10000:i * 10000]) = load_batch(fpath)
fpath = os.path.join(path, 'test_batch')
x_test, y_test = load_batch(fpath)
y_train = np.reshape(y_train, (len(y_train), 1))
y_test = np.reshape(y_test, (len(y_test), 1))
if K.image_data_format() == 'channels_last':
x_train = x_train.transpose(0, 2, 3, 1)
x_test = x_test.transpose(0, 2, 3, 1)
x_test = x_test.astype(x_train.dtype)
y_test = y_test.astype(y_train.dtype)
return (x_train, y_train), (x_test, y_test)
def get_word_index(path='imdb_word_index.json'):
"""Retrieves a dict mapping words to their index in the IMDB dataset.
Arguments:
path: where to cache the data (relative to `~/.keras/dataset`).
Returns:
The word index dictionary. Keys are word strings, values are their index.
"""
origin_folder = 'https://storage.googleapis.com/tensorflow/tf-keras-datasets/'
path = get_file(path,
origin=origin_folder + 'imdb_word_index.json',
file_hash='bfafd718b763782e994055a2d397834f')
with open(path) as f:
return json.load(f)
def load_data(path='mnist.npz'):
origin_folder = 'https://storage.googleapis.com/tensorflow/tf-keras-datasets/'
path = get_file(
path,
origin=origin_folder + 'mnist.npz',
file_hash=
'731c5ac602752760c8e48fbffcf8c3b850d9dc2a2aedcf2cc48468fc17b673d1')
with np.load(path, allow_pickle=True) as f:
x_train, y_train = f['x_train'], f['y_train']
x_test, y_test = f['x_test'], f['y_test']
mymat_data = mymat['test_images_var0_36']
mymattrain_data = mymattrain["train_images_var0_36"]
x_train = mymattrain_data
x_test = mymat_data
return (x_train, y_train), (x_test, y_test)
def get_classes_info(self):
fpath = data_utils.get_file(
'imagenet_class_index.json',
CLASS_INDEX_PATH,
cache_subdir='models',
file_hash='c2c37ea517e94d9795004a39431a14cb')
with open(fpath) as f:
class_index = json.load(f)
class_names = []
class_titles = []
for i in range(len(class_index)):
entry = class_index[str(i)]
class_names.append(entry[0])
class_titles.append(entry[1])
return class_names, class_titles
def get_word_index(path='imdb_word_index.json'):
"""Retrieves the dictionary mapping word indices back to words.
Arguments:
path: where to cache the data (relative to `~/.keras/dataset`).
Returns:
The word index dictionary.
"""
path = get_file(
path,
origin='https://s3.amazonaws.com/text-datasets/imdb_word_index.json',
file_hash='bfafd718b763782e994055a2d397834f')
with open(path) as f:
return json.load(f)
def get_word_index(path='reuters_word_index.json'):
"""Retrieves a dict mapping words to their index in the Reuters dataset.
Args:
path: where to cache the data (relative to `~/.keras/dataset`).
Returns:
The word index dictionary. Keys are word strings, values are their index.
"""
origin_folder = 'https://storage.googleapis.com/tensorflow/tf-keras-datasets/'
path = get_file(path,
origin=origin_folder + 'reuters_word_index.json',
file_hash='4d44cc38712099c9e383dc6e5f11a921')
with open(path) as f:
return json.load(f)
def get_word_index(path='imdb_word_index.json'):
"""Retrieves the dictionary mapping word indices back to words.
Arguments:
path: where to cache the data (relative to `~/.keras/dataset`).
Returns:
The word index dictionary.
"""
path = get_file(
path,
origin='https://s3.amazonaws.com/text-datasets/imdb_word_index.json',
file_hash='bfafd718b763782e994055a2d397834f')
with open(path) as f:
return json.load(f)
def get_word_index(path='reuters_word_index.json'):
"""Retrieves the dictionary mapping word indices back to words.
Arguments:
path: where to cache the data (relative to `~/.keras/dataset`).
Returns:
The word index dictionary.
"""
origin_folder = 'https://storage.googleapis.com/tensorflow/tf-keras-datasets/'
path = get_file(
path,
origin=origin_folder + 'reuters_word_index.json',
file_hash='4d44cc38712099c9e383dc6e5f11a921')
with open(path) as f:
return json.load(f)
def get_word_index(path='imdb_word_index.json'):
"""Retrieves the dictionary mapping word indices back to words.
Arguments:
path: where to cache the data (relative to `~/.keras/dataset`).
Returns:
The word index dictionary.
"""
origin_folder = 'https://storage.googleapis.com/tensorflow/tf-keras-datasets/'
path = get_file(
path,
origin=origin_folder + 'imdb_word_index.json',
file_hash='bfafd718b763782e994055a2d397834f')
with open(path) as f:
return json.load(f)
def NuclearSegmentationModel(input_shape=(None, None, 1),
backbone='resnet50',
use_pretrained_weights=True):
"""
A RetinaMask model with a ResNet50 backbone
for nuclear segmentation trained on DAPI data.
Args:
input_shape (tuple): a 3-length tuple of the input data shape.
backbone (str): name of the backbone to use for the model.
use_pretrained_weights (bool): whether to load pre-trained weights.
Only supports the ResNet50 backbone.
"""
backbone_levels = ['C1', 'C2', 'C3', 'C4', 'C5']
pyramid_levels = ['P2', 'P3', 'P4']
anchor_size_dict = {'P2': 8, 'P3': 16, 'P4': 32}
# Set up the prediction model
anchor_params = generate_anchor_params(pyramid_levels, anchor_size_dict)
model = model_zoo.RetinaMask(
backbone=backbone,
use_imagenet=False,
panoptic=True,
num_semantic_heads=2,
num_semantic_classes=[4, 4],
input_shape=input_shape,
num_classes=1,
backbone_levels=backbone_levels,
pyramid_levels=pyramid_levels,
anchor_params=anchor_params,
norm_method='whole_image')
if use_pretrained_weights:
if backbone == 'resnet50':
# '/data/models/resnet50_panoptic_train-val_DVV_V4.h5'
weights_path = get_file(
'resnet50_panoptic_nuclear_segmentation.h5',
WEIGHTS_PATH,
cache_subdir='models',
md5_hash='6e925c49cb05a1e3b0e2210220922445')
model.load_weights(weights_path)
else:
raise ValueError('Backbone %s does not have a weights file.' %
backbone)
return model
def PhaseSegmentationModel(input_shape=(None, None, 1),
backbone='resnet50',
use_pretrained_weights=True):
"""
A RetinaMask model with a ResNet50 backbone
for cytoplasmic segmentation trained on phase data.
Args:
input_shape (tuple): a 3-length tuple of the input data shape.
backbone (str): name of the backbone to use for the model.
use_pretrained_weights (bool): whether to load pre-trained weights.
Only supports the ResNet50 backbone.
"""
backbone_levels = ['C1', 'C2', 'C3', 'C4', 'C5']
pyramid_levels = ['P3', 'P4', 'P5', 'P6']
anchor_size_dicts = {'P3': 32, 'P4': 64, 'P5': 128, 'P6': 256}
anchor_params = generate_anchor_params(pyramid_levels, anchor_size_dicts)
model = model_zoo.RetinaMask(
backbone=backbone,
use_imagenet=False,
panoptic=False,
num_semantic_heads=2,
num_semantic_classes=[4, 4],
input_shape=input_shape,
num_classes=1,
backbone_levels=backbone_levels,
pyramid_levels=pyramid_levels,
anchor_params=anchor_params,
norm_method='whole_image')
if use_pretrained_weights:
if backbone == 'resnet50':
weights_path = get_file(
'resnet50_retinanet_20190813_all_phase_512.h5',
WEIGHTS_PATH,
cache_subdir='models',
md5_hash='ce31d084fadf7b907a25ab1fcf25529a')
model.load_weights(weights_path)
else:
raise ValueError('Backbone %s does not have a weights file.' %
backbone)
return model
def read_cifar_10_data(path_data, subdir, STANDARDIZE_BOOL = True):
dirname = 'cifar-10-batches-py'
origin = 'https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz'
path = get_file(dirname, origin=origin, untar=True,
file_hash='6d958be074577803d12ecdefd02955f39262c83c16fe9348329d7fe0b5c001ce', cache_dir=path_data,
cache_subdir=subdir)
num_train_samples = 50000
x_train = onp.empty((num_train_samples, 3, 32, 32), dtype='uint8')
y_train = onp.empty((num_train_samples,), dtype='uint8')
for i in range(1, 6):
fpath = os.path.join(path, 'data_batch_' + str(i))
(x_train[(i - 1)*10000: i*10000,:,:,:], y_train[(i - 1)*10000: i*10000]) = load_batch(fpath)
fpath = os.path.join(path, 'test_batch')
x_test, y_test = load_batch(fpath)
y_train = onp.reshape(y_train, (len(y_train), 1))
y_test = onp.reshape(y_test, (len(y_test), 1))
if K.image_data_format() == 'channels_last':
x_train = x_train.transpose(0, 2, 3, 1)
x_test = x_test.transpose(0, 2, 3, 1)
x_test = x_test.astype(x_train.dtype)
y_test = y_test.astype(y_train.dtype)
# Pre-processing (normalize)
train_images = onp.divide(x_train, 255, dtype=onp.float32)
test_images = onp.divide(x_test, 255, dtype=onp.float32)
train_labels = dense_to_one_hot(y_train, num_classes=10)
test_labels = dense_to_one_hot(y_test, num_classes=10)
if STANDARDIZE_BOOL:
channel_mean = onp.mean(train_images, axis=(0,1,2), dtype=onp.float32, keepdims=True)
channel_std = onp.std(train_images, axis=(0,1,2), dtype=onp.float32, keepdims=True)
train_images = (train_images - channel_mean) / channel_std
test_images = (test_images - channel_mean) / channel_std
dataset = {
'train': {'input': train_images, 'label': train_labels},
'test': {'input': test_images, 'label': test_labels},
}
return dataset
def get_word_index(path='reuters_word_index.json'):
"""Retrieves the dictionary mapping word indices back to words.
Arguments:
path: where to cache the data (relative to `~/.keras/dataset`).
Returns:
The word index dictionary.
"""
origin_folder = 'https://storage.googleapis.com/tensorflow/tf-keras-datasets/'
path = get_file(path,
origin=origin_folder + 'reuters_word_index.json',
file_hash='4d44cc38712099c9e383dc6e5f11a921')
f = open(path)
data = json.load(f)
f.close()
return data
def get_word_index(path='reuters_word_index.json'):
"""Retrieves the dictionary mapping word indices back to words.
Arguments:
path: where to cache the data (relative to `~/.keras/dataset`).
Returns:
The word index dictionary.
"""
path = get_file(
path,
origin='https://s3.amazonaws.com/text-datasets/reuters_word_index.json',
file_hash='4d44cc38712099c9e383dc6e5f11a921')
f = open(path)
data = json.load(f)
f.close()
return data
def load_data(path='mousebrain.npz'):
"""Loads the MNIST dataset.
# Arguments
path: path where to cache the dataset locally
(relative to ~/.keras/datasets).
# Returns
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
"""
path = get_file(path,
origin='https://deepcell-data.s3.amazonaws.com/nuclei/mousebrain.npz',
file_hash='9c91304f7da7cc5559f46b2c5fc2eace')
train_dict, test_dict = get_data(path, seed=0, test_size=.2)
x_train, y_train = train_dict['X'], train_dict['y']
x_test, y_test = test_dict['X'], test_dict['y']
return (x_train, y_train), (x_test, y_test)
def get_word_index(path='reuters_word_index.json'):
"""Retrieves the dictionary mapping word indices back to words.
Arguments:
path: where to cache the data (relative to `~/.keras/dataset`).
Returns:
The word index dictionary.
"""
path = get_file(
path,
origin='https://s3.amazonaws.com/text-datasets/reuters_word_index.json',
file_hash='4d44cc38712099c9e383dc6e5f11a921')
f = open(path)
data = json.load(f)
f.close()
return data
def check_download(fname):
"""Check if you need to download the file or not.
Returns the path
"""
# check if the file has already been downloaded or not
data_file = os.path.join(ds.__path__[0], fname)
if not os.path.exists(data_file):
print("Downloading file to {}".format(data_file))
data_file = get_file(
fname=data_file,
origin=
'https://storage.googleapis.com/tensorflow/tf-keras-datasets/' +
fname)
return data_file
def load_data(self):
"""
Load data of emnist dataset using its federated version, where each data belongs to a \
specific user. It returns for each sample a 2-tuple with (id_writer, image).
# Returns:
all_data : train data, train labels, test data and test labels
"""
if not self._type in [e.name for e in Md5Hash]:
self._type = 'digits'
file_hash_ = Md5Hash[self._type].value
path_dataset = get_file(
'emnist-digits',
origin=
'https://github.com/sherpaai/federated-emnist-dataset/blob/master/datasets/emnist-'
+ self._type + '.mat?raw=true',
file_hash=file_hash_,
extract=True,
cache_dir='~/.sherpa-ai')
dataset = loadmat(path_dataset)['dataset']
writers = dataset['train'][0, 0]['writers'][0, 0]
data = np.reshape(dataset['train'][0, 0]['images'][0, 0],
(-1, 28, 28, 1),
order='F')
self._train_data = np.array([(writers[i][0], v)
for i, v in enumerate(data)])
self._train_labels = np.reshape(
np.eye(10)[dataset['train'][0, 0]['labels'][0, 0]],
(self._train_data.shape[0], 10))
self._test_data = np.reshape(dataset['test'][0, 0]['images'][0, 0],
(-1, 28, 28, 1),
order='F')
self._test_labels = np.reshape(
np.eye(10)[dataset['test'][0, 0]['labels'][0, 0]],
(self._test_data.shape[0], 10))
self.shuffle()
return self.data
def load_data(dataset_base_path, train=True, label_mode="fine"):
"""Loads CIFAR100 dataset.
Parameters
----------
dataset_base_path: str
Path to create dataset dir, a recommended choice is project root dir
train: bool
flag, return training set or test set
label_mode: str
one of "fine", "coarse".
Returns
-------
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
Raises
------
ValueError: in case of invalid `label_mode`.
"""
if label_mode not in ['fine', 'coarse']:
raise ValueError('`label_mode` must be one of `"fine"`, `"coarse"`.')
dirname = 'cifar-100-python'
origin = 'https://www.cs.toronto.edu/~kriz/cifar-100-python.tar.gz'
path = get_file(dirname,
origin=origin,
untar=True,
cache_dir=dataset_base_path)
if train:
fpath = os.path.join(path, 'train')
x_train, y_train = load_batch(fpath, label_key=label_mode + '_labels')
# y_train = np.reshape(y_train, (len(y_train), 1))
y_train = np.asarray(y_train)
if K.image_data_format() == 'channels_last':
x_train = x_train.transpose((0, 2, 3, 1))
return x_train, y_train
else:
fpath = os.path.join(path, 'test')
x_test, y_test = load_batch(fpath, label_key=label_mode + '_labels')
# y_test = np.reshape(y_test, (len(y_test), 1))
y_test = np.asarray(y_test)
if K.image_data_format() == 'channels_last':
x_test = x_test.transpose((0, 2, 3, 1))
return x_test, y_test
def load_data(path='mnist.npz'):
"""Loads the MNIST dataset.
Arguments:
path: path where to cache the dataset locally
(relative to ~/.keras/datasets).
Returns:
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
"""
path = get_file(path,
origin='https://s3.amazonaws.com/img-datasets/mnist.npz',
file_hash='8a61469f7ea1b51cbae51d4f78837e45')
f = np.load(path)
x_train, y_train = f['x_train'], f['y_train']
x_test, y_test = f['x_test'], f['y_test']
f.close()
return (x_train, y_train), (x_test, y_test)
def load_data(path='HEK293.npz'):
"""Loads the MNIST dataset.
# Arguments
path: path where to cache the dataset locally
(relative to ~/.keras/datasets).
# Returns
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
"""
path = get_file(
path,
origin='https://deepcell-data.s3.amazonaws.com/nuclei/HEK293.npz',
file_hash='c0bbfba54b90e63a2010133a198e6e63')
train_dict, test_dict = get_data(path, seed=0, test_size=.2)
x_train, y_train = train_dict['X'], train_dict['y']
x_test, y_test = test_dict['X'], test_dict['y']
return (x_train, y_train), (x_test, y_test)
def load_data(path='3T3_NIH.npz'):
"""Loads the MNIST dataset.
# Arguments
path: path where to cache the dataset locally
(relative to ~/.keras/datasets).
# Returns
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
"""
path = get_file(
path,
origin='https://deepcell-data.s3.amazonaws.com/nuclei/HeLa_S3.npz',
file_hash='42c631726713bbb180d4a0a07c2e8107')
train_dict, test_dict = get_data(path, seed=0, test_size=.2)
x_train, y_train = train_dict['X'], train_dict['y']
x_test, y_test = test_dict['X'], test_dict['y']
return (x_train, y_train), (x_test, y_test)
def load_data(path='3T3_NIH.npz'):
"""Loads the MNIST dataset.
# Arguments
path: path where to cache the dataset locally
(relative to ~/.keras/datasets).
# Returns
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
"""
path = get_file(
path,
origin='https://deepcell-data.s3.amazonaws.com/nuclei/3T3_NIH.npz',
file_hash='954b6f4ad6a71435b84c40726837e4ba')
train_dict, test_dict = get_data(path, seed=0, test_size=.2)
x_train, y_train = train_dict['X'], train_dict['y']
x_test, y_test = test_dict['X'], test_dict['y']
return (x_train, y_train), (x_test, y_test)
def load_data(path='mnist.npz'):
"""Loads the MNIST dataset.
Arguments:
path: path where to cache the dataset locally
(relative to ~/.keras/datasets).
Returns:
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
"""
path = get_file(
path,
origin='https://s3.amazonaws.com/img-datasets/mnist.npz',
file_hash='8a61469f7ea1b51cbae51d4f78837e45')
f = np.load(path)
x_train, y_train = f['x_train'], f['y_train']
x_test, y_test = f['x_test'], f['y_test']
f.close()
return (x_train, y_train), (x_test, y_test)
def load_data():
"""Loads the Fashion-MNIST dataset.
Returns:
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
License:
The copyright for Fashion-MNIST is held by Zalando SE.
Fashion-MNIST is licensed under the [MIT license](
https://github.com/zalandoresearch/fashion-mnist/blob/master/LICENSE).
"""
dirname = os.path.join('datasets', 'fashion-mnist')
# 自定义链接
base = 'http://localhost:8081/tensorflow/tf-keras-datasets/'
# 自定义链接
files = [
'train-labels-idx1-ubyte.gz', 'train-images-idx3-ubyte.gz',
't10k-labels-idx1-ubyte.gz', 't10k-images-idx3-ubyte.gz'
]
paths = []
for fname in files:
paths.append(get_file(fname, origin=base + fname,
cache_subdir=dirname))
with gzip.open(paths[0], 'rb') as lbpath:
y_train = np.frombuffer(lbpath.read(), np.uint8, offset=8)
with gzip.open(paths[1], 'rb') as imgpath:
x_train = np.frombuffer(imgpath.read(), np.uint8,
offset=16).reshape(len(y_train), 28, 28)
with gzip.open(paths[2], 'rb') as lbpath:
y_test = np.frombuffer(lbpath.read(), np.uint8, offset=8)
with gzip.open(paths[3], 'rb') as imgpath:
x_test = np.frombuffer(imgpath.read(), np.uint8,
offset=16).reshape(len(y_test), 28, 28)
return (x_train, y_train), (x_test, y_test)
def load_data(dataset_base_path, train=True):
"""Loads CIFAR10 dataset.
Parameters
----------
dataset_base_path: str
Path to create dataset dir, a recommended choice is project root dir
train: bool
flag, return training set or test set
Returns:
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
"""
dirname = 'cifar-10-batches-py'
origin = 'https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz'
path = get_file(dirname,
origin=origin,
untar=True,
cache_dir=dataset_base_path)
if train:
num_train_samples = 50000
x_train = np.empty((num_train_samples, 3, 32, 32), dtype='uint8')
y_train = np.empty((num_train_samples, ), dtype='uint8')
for i in range(1, 6):
fpath = os.path.join(path, 'data_batch_' + str(i))
(x_train[(i - 1) * 10000:i * 10000, :, :, :],
y_train[(i - 1) * 10000:i * 10000]) = load_batch(fpath)
# y_train = np.reshape(y_train, (len(y_train), 1))
y_train = np.asarray(y_train)
if K.image_data_format() == 'channels_last':
x_train = x_train.transpose((0, 2, 3, 1))
return x_train, y_train
else:
fpath = os.path.join(path, 'test_batch')
x_test, y_test = load_batch(fpath)
# y_test = np.reshape(y_test, (len(y_test), 1))
y_test = np.asarray(y_test)
if K.image_data_format() == 'channels_last':
x_test = x_test.transpose((0, 2, 3, 1))
return x_test, y_test
def load_data(download_directory):
"""Loads the Fashion-MNIST dataset.
Returns:
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
License:
The copyright for Fashion-MNIST is held by Zalando SE.
Fashion-MNIST is licensed under the [MIT license](
https://github.com/zalandoresearch/fashion-mnist/blob/master/LICENSE).
"""
dirname = os.path.join(download_directory, "fashion-mnist")
base = "https://storage.googleapis.com/tensorflow/tf-keras-datasets/"
files = [
"train-labels-idx1-ubyte.gz",
"train-images-idx3-ubyte.gz",
"t10k-labels-idx1-ubyte.gz",
"t10k-images-idx3-ubyte.gz",
]
paths = []
for fname in files:
paths.append(get_file(fname, origin=base + fname,
cache_subdir=dirname))
with gzip.open(paths[0], "rb") as lbpath:
y_train = np.frombuffer(lbpath.read(), np.uint8, offset=8)
with gzip.open(paths[1], "rb") as imgpath:
x_train = np.frombuffer(imgpath.read(), np.uint8,
offset=16).reshape(len(y_train), 28, 28)
with gzip.open(paths[2], "rb") as lbpath:
y_test = np.frombuffer(lbpath.read(), np.uint8, offset=8)
with gzip.open(paths[3], "rb") as imgpath:
x_test = np.frombuffer(imgpath.read(), np.uint8,
offset=16).reshape(len(y_test), 28, 28)
return (x_train, y_train), (x_test, y_test)
def load_data(path='mnist.npz'):
"""Loads the MNIST dataset.
Arguments:
path: path where to cache the dataset locally
(relative to ~/.keras/datasets).
Returns:
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
License:
Yann LeCun and Corinna Cortes hold the copyright of MNIST dataset,
which is a derivative work from original NIST datasets.
MNIST dataset is made available under the terms of the
[Creative Commons Attribution-Share Alike 3.0 license.](
https://creativecommons.org/licenses/by-sa/3.0/)
"""
origin_folder = 'https://storage.googleapis.com/tensorflow/tf-keras-datasets/'
path = get_file(path,
origin=origin_folder + 'mnist.npz',
file_hash='8a61469f7ea1b51cbae51d4f78837e45')
with np.load(path) as f:
x_train, y_train = f['x_train'], f['y_train']
x_test, y_test = f['x_test'], f['y_test']
def load_data(path='mnist.npz'):
"""Loads the [MNIST dataset](http://yann.lecun.com/exdb/mnist/).
This is a dataset of 60,000 28x28 grayscale images of the 10 digits,
along with a test set of 10,000 images.
More info can be found at the
[MNIST homepage](http://yann.lecun.com/exdb/mnist/).
Arguments:
path: path where to cache the dataset locally
(relative to `~/.keras/datasets`).
Returns:
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
**x_train, x_test**: uint8 arrays of grayscale image data with shapes
(num_samples, 28, 28).
**y_train, y_test**: uint8 arrays of digit labels (integers in range 0-9)
with shapes (num_samples,).
License:
Yann LeCun and Corinna Cortes hold the copyright of MNIST dataset,
which is a derivative work from original NIST datasets.
MNIST dataset is made available under the terms of the
[Creative Commons Attribution-Share Alike 3.0 license.](
https://creativecommons.org/licenses/by-sa/3.0/)
"""
origin_folder = 'https://storage.googleapis.com/tensorflow/tf-keras-datasets/'
path = get_file(
path,
origin=origin_folder + 'mnist.npz',
file_hash=
'731c5ac602752760c8e48fbffcf8c3b850d9dc2a2aedcf2cc48468fc17b673d1')
with np.load(path, allow_pickle=True) as f:
x_train, y_train = f['x_train'], f['y_train']
x_test, y_test = f['x_test'], f['y_test']
return (x_train, y_train), (x_test, y_test)
def load_data():
"""Loads the Fashion-MNIST dataset.
Returns:
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
License:
The copyright for Fashion-MNIST is held by Zalando SE.
Fashion-MNIST is licensed under the [MIT license](
https://github.com/zalandoresearch/fashion-mnist/blob/master/LICENSE).
"""
dirname = os.path.join('datasets', 'fashion-mnist')
base = 'https://storage.googleapis.com/tensorflow/tf-keras-datasets/'
files = [
'train-labels-idx1-ubyte.gz', 'train-images-idx3-ubyte.gz',
't10k-labels-idx1-ubyte.gz', 't10k-images-idx3-ubyte.gz'
]
paths = []
for fname in files:
paths.append(get_file(fname, origin=base + fname, cache_subdir=dirname))
with gzip.open(paths[0], 'rb') as lbpath:
y_train = np.frombuffer(lbpath.read(), np.uint8, offset=8)
with gzip.open(paths[1], 'rb') as imgpath:
x_train = np.frombuffer(
imgpath.read(), np.uint8, offset=16).reshape(len(y_train), 28, 28)
with gzip.open(paths[2], 'rb') as lbpath:
y_test = np.frombuffer(lbpath.read(), np.uint8, offset=8)
with gzip.open(paths[3], 'rb') as imgpath:
x_test = np.frombuffer(
imgpath.read(), np.uint8, offset=16).reshape(len(y_test), 28, 28)
return (x_train, y_train), (x_test, y_test)
def decode_predictions(preds, top=5):
"""Decodes the prediction of an ImageNet model.
Arguments:
preds: Numpy tensor encoding a batch of predictions.
top: Integer, how many top-guesses to return.
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).
"""
global CLASS_INDEX
if len(preds.shape) != 2 or preds.shape[1] != 1000:
raise ValueError('`decode_predictions` expects '
'a batch of predictions '
'(i.e. a 2D array of shape (samples, 1000)). '
'Found array with shape: ' + str(preds.shape))
if CLASS_INDEX is None:
fpath = get_file(
'imagenet_class_index.json',
CLASS_INDEX_PATH,
cache_subdir='models',
file_hash='c2c37ea517e94d9795004a39431a14cb')
with open(fpath) as f:
CLASS_INDEX = json.load(f)
results = []
for pred in preds:
top_indices = pred.argsort()[-top:][::-1]
result = [tuple(CLASS_INDEX[str(i)]) + (pred[i],) for i in top_indices]
result.sort(key=lambda x: x[2], reverse=True)
results.append(result)
return results
def InceptionResNetV2(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the Inception-ResNet v2 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 TensorFlow, Theano and
CNTK backends. The data format convention used by the model is
the one specified in your Keras config file.
Note that the default input image size for this model is 299x299, instead
of 224x224 as in the VGG16 and ResNet models. Also, the input preprocessing
function is different (i.e., do not use `imagenet_utils.preprocess_input()`
with this model. Use `preprocess_input()` defined in this module instead).
Arguments:
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 `(299, 299, 3)` (with `'channels_last'` data format)
or `(3, 299, 299)` (with `'channels_first'` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 139.
E.g. `(150, 150, 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 not (weights in {'imagenet', None} or os.path.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 = _obtain_input_shape(
input_shape,
default_size=299,
min_size=139,
data_format=K.image_data_format(),
require_flatten=False,
weights=weights)
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
# Stem block: 35 x 35 x 192
x = conv2d_bn(img_input, 32, 3, strides=2, padding='valid')
x = conv2d_bn(x, 32, 3, padding='valid')
x = conv2d_bn(x, 64, 3)
x = MaxPooling2D(3, strides=2)(x)
x = conv2d_bn(x, 80, 1, padding='valid')
x = conv2d_bn(x, 192, 3, padding='valid')
x = MaxPooling2D(3, strides=2)(x)
# Mixed 5b (Inception-A block): 35 x 35 x 320
branch_0 = conv2d_bn(x, 96, 1)
branch_1 = conv2d_bn(x, 48, 1)
branch_1 = conv2d_bn(branch_1, 64, 5)
branch_2 = conv2d_bn(x, 64, 1)
branch_2 = conv2d_bn(branch_2, 96, 3)
branch_2 = conv2d_bn(branch_2, 96, 3)
branch_pool = AveragePooling2D(3, strides=1, padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1)
branches = [branch_0, branch_1, branch_2, branch_pool]
channel_axis = 1 if K.image_data_format() == 'channels_first' else 3
x = Concatenate(axis=channel_axis, name='mixed_5b')(branches)
# 10x block35 (Inception-ResNet-A block): 35 x 35 x 320
for block_idx in range(1, 11):
x = inception_resnet_block(
x, scale=0.17, block_type='block35', block_idx=block_idx)
# Mixed 6a (Reduction-A block): 17 x 17 x 1088
branch_0 = conv2d_bn(x, 384, 3, strides=2, padding='valid')
branch_1 = conv2d_bn(x, 256, 1)
branch_1 = conv2d_bn(branch_1, 256, 3)
branch_1 = conv2d_bn(branch_1, 384, 3, strides=2, padding='valid')
branch_pool = MaxPooling2D(3, strides=2, padding='valid')(x)
branches = [branch_0, branch_1, branch_pool]
x = Concatenate(axis=channel_axis, name='mixed_6a')(branches)
# 20x block17 (Inception-ResNet-B block): 17 x 17 x 1088
for block_idx in range(1, 21):
x = inception_resnet_block(
x, scale=0.1, block_type='block17', block_idx=block_idx)
# Mixed 7a (Reduction-B block): 8 x 8 x 2080
branch_0 = conv2d_bn(x, 256, 1)
branch_0 = conv2d_bn(branch_0, 384, 3, strides=2, padding='valid')
branch_1 = conv2d_bn(x, 256, 1)
branch_1 = conv2d_bn(branch_1, 288, 3, strides=2, padding='valid')
branch_2 = conv2d_bn(x, 256, 1)
branch_2 = conv2d_bn(branch_2, 288, 3)
branch_2 = conv2d_bn(branch_2, 320, 3, strides=2, padding='valid')
branch_pool = MaxPooling2D(3, strides=2, padding='valid')(x)
branches = [branch_0, branch_1, branch_2, branch_pool]
x = Concatenate(axis=channel_axis, name='mixed_7a')(branches)
# 10x block8 (Inception-ResNet-C block): 8 x 8 x 2080
for block_idx in range(1, 10):
x = inception_resnet_block(
x, scale=0.2, block_type='block8', block_idx=block_idx)
x = inception_resnet_block(
x, scale=1., activation=None, block_type='block8', block_idx=10)
# Final convolution block: 8 x 8 x 1536
x = conv2d_bn(x, 1536, 1, name='conv_7b')
if include_top:
# Classification block
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='predictions')(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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model
model = Model(inputs, x, name='inception_resnet_v2')
# Load weights
if weights == 'imagenet':
if include_top:
fname = 'inception_resnet_v2_weights_tf_dim_ordering_tf_kernels.h5'
weights_path = get_file(
fname,
BASE_WEIGHT_URL + fname,
cache_subdir='models',
file_hash='e693bd0210a403b3192acc6073ad2e96')
else:
fname = 'inception_resnet_v2_weights_tf_dim_ordering_tf_kernels_notop.h5'
weights_path = get_file(
fname,
BASE_WEIGHT_URL + fname,
cache_subdir='models',
file_hash='d19885ff4a710c122648d3b5c3b684e4')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
def load_data(path='imdb.npz',
num_words=None,
skip_top=0,
maxlen=None,
seed=113,
start_char=1,
oov_char=2,
index_from=3,
**kwargs):
"""Loads the IMDB dataset.
Arguments:
path: where to cache the data (relative to `~/.keras/dataset`).
num_words: max number of words to include. Words are ranked
by how often they occur (in the training set) and only
the most frequent words are kept
skip_top: skip the top N most frequently occurring words
(which may not be informative).
maxlen: sequences longer than this will be filtered out.
seed: random seed for sample shuffling.
start_char: The start of a sequence will be marked with this character.
Set to 1 because 0 is usually the padding character.
oov_char: words that were cut out because of the `num_words`
or `skip_top` limit will be replaced with this character.
index_from: index actual words with this index and higher.
**kwargs: Used for backwards compatibility.
Returns:
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
Raises:
ValueError: in case `maxlen` is so low
that no input sequence could be kept.
Note that the 'out of vocabulary' character is only used for
words that were present in the training set but are not included
because they're not making the `num_words` cut here.
Words that were not seen in the training set but are in the test set
have simply been skipped.
"""
# Legacy support
if 'nb_words' in kwargs:
logging.warning('The `nb_words` argument in `load_data` '
'has been renamed `num_words`.')
num_words = kwargs.pop('nb_words')
if kwargs:
raise TypeError('Unrecognized keyword arguments: ' + str(kwargs))
origin_folder = 'https://storage.googleapis.com/tensorflow/tf-keras-datasets/'
path = get_file(
path,
origin=origin_folder + 'imdb.npz',
file_hash='599dadb1135973df5b59232a0e9a887c')
with np.load(path) as f:
x_train, labels_train = f['x_train'], f['y_train']
x_test, labels_test = f['x_test'], f['y_test']
np.random.seed(seed)
indices = np.arange(len(x_train))
np.random.shuffle(indices)
x_train = x_train[indices]
labels_train = labels_train[indices]
indices = np.arange(len(x_test))
np.random.shuffle(indices)
x_test = x_test[indices]
labels_test = labels_test[indices]
xs = np.concatenate([x_train, x_test])
labels = np.concatenate([labels_train, labels_test])
if start_char is not None:
xs = [[start_char] + [w + index_from for w in x] for x in xs]
elif index_from:
xs = [[w + index_from for w in x] for x in xs]
if maxlen:
xs, labels = _remove_long_seq(maxlen, xs, labels)
if not xs:
raise ValueError('After filtering for sequences shorter than maxlen=' +
str(maxlen) + ', no sequence was kept. '
'Increase maxlen.')
if not num_words:
num_words = max([max(x) for x in xs])
# by convention, use 2 as OOV word
# reserve 'index_from' (=3 by default) characters:
# 0 (padding), 1 (start), 2 (OOV)
if oov_char is not None:
xs = [
[w if (skip_top <= w < num_words) else oov_char for w in x] for x in xs
]
else:
xs = [[w for w in x if skip_top <= w < num_words] for x in xs]
idx = len(x_train)
x_train, y_train = np.array(xs[:idx]), np.array(labels[:idx])
x_test, y_test = np.array(xs[idx:]), np.array(labels[idx:])
return (x_train, y_train), (x_test, y_test)
def NASNet(input_shape=None,
penultimate_filters=4032,
num_blocks=6,
stem_block_filters=96,
skip_reduction=True,
filter_multiplier=2,
include_top=True,
weights=None,
input_tensor=None,
pooling=None,
classes=1000,
default_size=None):
"""Instantiates a NASNet model.
Note that only TensorFlow is supported for now,
therefore it only works with the data format
`image_data_format='channels_last'` in your Keras config
at `~/.keras/keras.json`.
Arguments:
input_shape: Optional shape tuple, the input shape
is by default `(331, 331, 3)` for NASNetLarge and
`(224, 224, 3)` for NASNetMobile.
It should have exactly 3 inputs channels,
and width and height should be no smaller than 32.
E.g. `(224, 224, 3)` would be one valid value.
penultimate_filters: Number of filters in the penultimate layer.
NASNet models use the notation `NASNet (N @ P)`, where:
- N is the number of blocks
- P is the number of penultimate filters
num_blocks: Number of repeated blocks of the NASNet model.
NASNet models use the notation `NASNet (N @ P)`, where:
- N is the number of blocks
- P is the number of penultimate filters
stem_block_filters: Number of filters in the initial stem block
skip_reduction: Whether to skip the reduction step at the tail
end of the network. Set to `False` for CIFAR models.
filter_multiplier: Controls the width of the network.
- If `filter_multiplier` < 1.0, proportionally decreases the number
of filters in each layer.
- If `filter_multiplier` > 1.0, proportionally increases the number
of filters in each layer.
- If `filter_multiplier` = 1, default number of filters from the
paper are used at each layer.
include_top: Whether to include the fully-connected
layer at the top of the network.
weights: `None` (random initialization) or
`imagenet` (ImageNet weights)
input_tensor: Optional Keras tensor (i.e. output of
`layers.Input()`)
to use as image input for the model.
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.
default_size: Specifies the default image size of the model
Returns:
A Keras model instance.
Raises:
ValueError: In case of invalid argument for `weights`,
invalid input shape or invalid `penultimate_filters` value.
RuntimeError: If attempting to run this model with a
backend that does not support separable convolutions.
"""
if K.backend() != 'tensorflow':
raise RuntimeError('Only Tensorflow backend is currently supported, '
'as other backends do not support '
'separable convolution.')
if not (weights in {'imagenet', None} or os.path.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')
if (isinstance(input_shape, tuple) and None in input_shape and
weights == 'imagenet'):
raise ValueError('When specifying the input shape of a NASNet'
' and loading `ImageNet` weights, '
'the input_shape argument must be static '
'(no None entries). Got: `input_shape=' +
str(input_shape) + '`.')
if default_size is None:
default_size = 331
# Determine proper input shape and default size.
input_shape = _obtain_input_shape(
input_shape,
default_size=default_size,
min_size=32,
data_format=K.image_data_format(),
require_flatten=False,
weights=weights)
if K.image_data_format() != 'channels_last':
logging.warning('The NASNet family of models is only available '
'for the input data format "channels_last" '
'(width, height, channels). '
'However your settings specify the default '
'data format "channels_first" (channels, width, height).'
' You should set `image_data_format="channels_last"` '
'in your Keras config located at ~/.keras/keras.json. '
'The model being returned right now will expect inputs '
'to follow the "channels_last" data format.')
K.set_image_data_format('channels_last')
old_data_format = 'channels_first'
else:
old_data_format = None
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 penultimate_filters % 24 != 0:
raise ValueError(
'For NASNet-A models, the value of `penultimate_filters` '
'needs to be divisible by 24. Current value: %d' % penultimate_filters)
channel_dim = 1 if K.image_data_format() == 'channels_first' else -1
filters = penultimate_filters // 24
if not skip_reduction:
x = Conv2D(
stem_block_filters, (3, 3),
strides=(2, 2),
padding='valid',
use_bias=False,
name='stem_conv1',
kernel_initializer='he_normal')(
img_input)
else:
x = Conv2D(
stem_block_filters, (3, 3),
strides=(1, 1),
padding='same',
use_bias=False,
name='stem_conv1',
kernel_initializer='he_normal')(
img_input)
x = BatchNormalization(
axis=channel_dim, momentum=0.9997, epsilon=1e-3, name='stem_bn1')(
x)
p = None
if not skip_reduction: # imagenet / mobile mode
x, p = _reduction_a_cell(
x, p, filters // (filter_multiplier**2), block_id='stem_1')
x, p = _reduction_a_cell(
x, p, filters // filter_multiplier, block_id='stem_2')
for i in range(num_blocks):
x, p = _normal_a_cell(x, p, filters, block_id='%d' % (i))
x, p0 = _reduction_a_cell(
x, p, filters * filter_multiplier, block_id='reduce_%d' % (num_blocks))
p = p0 if not skip_reduction else p
for i in range(num_blocks):
x, p = _normal_a_cell(
x, p, filters * filter_multiplier, block_id='%d' % (num_blocks + i + 1))
x, p0 = _reduction_a_cell(
x,
p,
filters * filter_multiplier**2,
block_id='reduce_%d' % (2 * num_blocks))
p = p0 if not skip_reduction else p
for i in range(num_blocks):
x, p = _normal_a_cell(
x,
p,
filters * filter_multiplier**2,
block_id='%d' % (2 * num_blocks + i + 1))
x = Activation('relu')(x)
if include_top:
x = GlobalAveragePooling2D()(x)
x = Dense(classes, activation='softmax', name='predictions')(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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
model = Model(inputs, x, name='NASNet')
# load weights
if weights == 'imagenet':
if default_size == 224: # mobile version
if include_top:
weight_path = NASNET_MOBILE_WEIGHT_PATH
model_name = 'nasnet_mobile.h5'
else:
weight_path = NASNET_MOBILE_WEIGHT_PATH_NO_TOP
model_name = 'nasnet_mobile_no_top.h5'
weights_file = get_file(model_name, weight_path, cache_subdir='models')
model.load_weights(weights_file)
elif default_size == 331: # large version
if include_top:
weight_path = NASNET_LARGE_WEIGHT_PATH
model_name = 'nasnet_large.h5'
else:
weight_path = NASNET_LARGE_WEIGHT_PATH_NO_TOP
model_name = 'nasnet_large_no_top.h5'
weights_file = get_file(model_name, weight_path, cache_subdir='models')
model.load_weights(weights_file)
else:
raise ValueError('ImageNet weights can only be loaded with NASNetLarge'
' or NASNetMobile')
elif weights is not None:
model.load_weights(weights)
if old_data_format:
K.set_image_data_format(old_data_format)
return model
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):
"""Instantiates the MobileNet architecture.
To load a MobileNet model via `load_model`, import the custom
objects `relu6` and pass them to the `custom_objects` parameter.
E.g.
model = load_model('mobilenet.h5', custom_objects={
'relu6': mobilenet.relu6})
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.
alpha: controls the width of the network.
- 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.
depth_multiplier: depth multiplier for depthwise convolution
(also called the resolution multiplier)
dropout: dropout rate
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.
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.
RuntimeError: If attempting to run this model with a
backend that does not support separable convolutions.
"""
if not (weights in {'imagenet', None} or os.path.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 K.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 = _obtain_input_shape(
input_shape,
default_size=default_size,
min_size=32,
data_format=K.image_data_format(),
require_flatten=include_top,
weights=weights)
if K.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]:
if rows is None:
rows = 224
logging.warning('MobileNet shape is undefined.'
' Weights for input shape (224, 224) will be loaded.')
else:
raise ValueError('If imagenet weights are being loaded, '
'input must have a static square shape (one of '
'(128, 128), (160, 160), (192, 192), or (224, 224)).'
' Input shape provided = %s' % (input_shape,))
if K.image_data_format() != 'channels_last':
logging.warning('The MobileNet family of models is only available '
'for the input data format "channels_last" '
'(width, height, channels). '
'However your settings specify the default '
'data format "channels_first" (channels, width, height).'
' You should set `image_data_format="channels_last"` '
'in your Keras config located at ~/.keras/keras.json. '
'The model being returned right now will expect inputs '
'to follow the "channels_last" data format.')
K.set_image_data_format('channels_last')
old_data_format = 'channels_first'
else:
old_data_format = None
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
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 K.image_data_format() == 'channels_first':
shape = (int(1024 * alpha), 1, 1)
else:
shape = (1, 1, int(1024 * alpha))
x = GlobalAveragePooling2D()(x)
x = Reshape(shape, name='reshape_1')(x)
x = Dropout(dropout, name='dropout')(x)
x = Conv2D(classes, (1, 1), padding='same', name='conv_preds')(x)
x = Activation('softmax', name='act_softmax')(x)
x = Reshape((classes,), name='reshape_2')(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='mobilenet_%0.2f_%s' % (alpha, rows))
# load weights
if weights == 'imagenet':
if K.image_data_format() == 'channels_first':
raise ValueError('Weights for "channels_first" format '
'are not available.')
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)
weigh_path = BASE_WEIGHT_PATH + model_name
weights_path = get_file(model_name, weigh_path, cache_subdir='models')
else:
model_name = 'mobilenet_%s_%d_tf_no_top.h5' % (alpha_text, rows)
weigh_path = BASE_WEIGHT_PATH + model_name
weights_path = get_file(model_name, weigh_path, cache_subdir='models')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
if old_data_format:
K.set_image_data_format(old_data_format)
return model
def DenseNet(blocks,
include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the DenseNet 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
TensorFlow, Theano, and CNTK. The data format
convention used by the model is the one
specified in your Keras config file.
Arguments:
blocks: numbers of building blocks for the four dense layers.
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.
Returns:
A Keras model instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if not (weights in {'imagenet', None} or os.path.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 = _obtain_input_shape(
input_shape,
default_size=224,
min_size=221,
data_format=K.image_data_format(),
require_flatten=include_top,
weights=weights)
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
bn_axis = 3 if K.image_data_format() == 'channels_last' else 1
x = ZeroPadding2D(padding=((3, 3), (3, 3)))(img_input)
x = Conv2D(64, 7, strides=2, use_bias=False, name='conv1/conv')(x)
x = BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='conv1/bn')(x)
x = Activation('relu', name='conv1/relu')(x)
x = ZeroPadding2D(padding=((1, 1), (1, 1)))(x)
x = MaxPooling2D(3, strides=2, name='pool1')(x)
x = dense_block(x, blocks[0], name='conv2')
x = transition_block(x, 0.5, name='pool2')
x = dense_block(x, blocks[1], name='conv3')
x = transition_block(x, 0.5, name='pool3')
x = dense_block(x, blocks[2], name='conv4')
x = transition_block(x, 0.5, name='pool4')
x = dense_block(x, blocks[3], name='conv5')
x = BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='bn')(x)
if include_top:
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='fc1000')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D(name='avg_pool')(x)
elif pooling == 'max':
x = 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.
if blocks == [6, 12, 24, 16]:
model = Model(inputs, x, name='densenet121')
elif blocks == [6, 12, 32, 32]:
model = Model(inputs, x, name='densenet169')
elif blocks == [6, 12, 48, 32]:
model = Model(inputs, x, name='densenet201')
else:
model = Model(inputs, x, name='densenet')
# Load weights.
if weights == 'imagenet':
if include_top:
if blocks == [6, 12, 24, 16]:
weights_path = get_file(
'densenet121_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET121_WEIGHT_PATH,
cache_subdir='models',
file_hash='0962ca643bae20f9b6771cb844dca3b0')
elif blocks == [6, 12, 32, 32]:
weights_path = get_file(
'densenet169_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET169_WEIGHT_PATH,
cache_subdir='models',
file_hash='bcf9965cf5064a5f9eb6d7dc69386f43')
elif blocks == [6, 12, 48, 32]:
weights_path = get_file(
'densenet201_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET201_WEIGHT_PATH,
cache_subdir='models',
file_hash='7bb75edd58cb43163be7e0005fbe95ef')
else:
if blocks == [6, 12, 24, 16]:
weights_path = get_file(
'densenet121_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET121_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='4912a53fbd2a69346e7f2c0b5ec8c6d3')
elif blocks == [6, 12, 32, 32]:
weights_path = get_file(
'densenet169_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET169_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='50662582284e4cf834ce40ab4dfa58c6')
elif blocks == [6, 12, 48, 32]:
weights_path = get_file(
'densenet201_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET201_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='1c2de60ee40562448dbac34a0737e798')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
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),
'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 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 not (weights in {'imagenet', None} or os.path.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 = _obtain_input_shape(
input_shape,
default_size=224,
min_size=197,
data_format=K.image_data_format(),
require_flatten=include_top,
weights=weights)
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 = Conv2D(
64, (7, 7), strides=(2, 2), padding='same', name='conv1')(img_input)
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')
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')
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')
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')
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)
elif weights is not None:
model.load_weights(weights)
return model
def load_data(path='reuters.npz',
num_words=None,
skip_top=0,
maxlen=None,
test_split=0.2,
seed=113,
start_char=1,
oov_char=2,
index_from=3,
**kwargs):
"""Loads the Reuters newswire classification dataset.
Arguments:
path: where to cache the data (relative to `~/.keras/dataset`).
num_words: max number of words to include. Words are ranked
by how often they occur (in the training set) and only
the most frequent words are kept
skip_top: skip the top N most frequently occurring words
(which may not be informative).
maxlen: truncate sequences after this length.
test_split: Fraction of the dataset to be used as test data.
seed: random seed for sample shuffling.
start_char: The start of a sequence will be marked with this character.
Set to 1 because 0 is usually the padding character.
oov_char: words that were cut out because of the `num_words`
or `skip_top` limit will be replaced with this character.
index_from: index actual words with this index and higher.
**kwargs: Used for backwards compatibility.
Returns:
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
Note that the 'out of vocabulary' character is only used for
words that were present in the training set but are not included
because they're not making the `num_words` cut here.
Words that were not seen in the training set but are in the test set
have simply been skipped.
"""
# Legacy support
if 'nb_words' in kwargs:
logging.warning('The `nb_words` argument in `load_data` '
'has been renamed `num_words`.')
num_words = kwargs.pop('nb_words')
if kwargs:
raise TypeError('Unrecognized keyword arguments: ' + str(kwargs))
origin_folder = 'https://storage.googleapis.com/tensorflow/tf-keras-datasets/'
path = get_file(
path,
origin=origin_folder + 'reuters.npz',
file_hash='87aedbeb0cb229e378797a632c1997b6')
with np.load(path) as f:
xs, labels = f['x'], f['y']
np.random.seed(seed)
indices = np.arange(len(xs))
np.random.shuffle(indices)
xs = xs[indices]
labels = labels[indices]
if start_char is not None:
xs = [[start_char] + [w + index_from for w in x] for x in xs]
elif index_from:
xs = [[w + index_from for w in x] for x in xs]
if maxlen:
xs, labels = _remove_long_seq(maxlen, xs, labels)
if not num_words:
num_words = max([max(x) for x in xs])
# by convention, use 2 as OOV word
# reserve 'index_from' (=3 by default) characters:
# 0 (padding), 1 (start), 2 (OOV)
if oov_char is not None:
xs = [[w if skip_top <= w < num_words else oov_char for w in x] for x in xs]
else:
xs = [[w for w in x if skip_top <= w < num_words] for x in xs]
idx = int(len(xs) * (1 - test_split))
x_train, y_train = np.array(xs[:idx]), np.array(labels[:idx])
x_test, y_test = np.array(xs[idx:]), np.array(labels[idx:])
return (x_train, y_train), (x_test, y_test)
def InceptionV3(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the Inception v3 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.
Note that the default input image size for this model is 299x299.
Arguments:
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 `(299, 299, 3)` (with `channels_last` data format)
or `(3, 299, 299)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 139.
E.g. `(150, 150, 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 not (weights in {'imagenet', None} or os.path.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 = _obtain_input_shape(
input_shape,
default_size=299,
min_size=139,
data_format=K.image_data_format(),
require_flatten=False,
weights=weights)
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_first':
channel_axis = 1
else:
channel_axis = 3
x = conv2d_bn(img_input, 32, 3, 3, strides=(2, 2), padding='valid')
x = conv2d_bn(x, 32, 3, 3, padding='valid')
x = conv2d_bn(x, 64, 3, 3)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv2d_bn(x, 80, 1, 1, padding='valid')
x = conv2d_bn(x, 192, 3, 3, padding='valid')
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
# mixed 0, 1, 2: 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 32, 1, 1)
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed0')
# mixed 1: 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1, 1)
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed1')
# mixed 2: 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1, 1)
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed2')
# mixed 3: 17 x 17 x 768
branch3x3 = conv2d_bn(x, 384, 3, 3, strides=(2, 2), padding='valid')
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(
branch3x3dbl, 96, 3, 3, strides=(2, 2), padding='valid')
branch_pool = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = layers.concatenate(
[branch3x3, branch3x3dbl, branch_pool], axis=channel_axis, name='mixed3')
# mixed 4: 17 x 17 x 768
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 128, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 128, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 128, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed4')
# mixed 5, 6: 17 x 17 x 768
for i in range(2):
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 160, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 160, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 160, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed' + str(5 + i))
# mixed 7: 17 x 17 x 768
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 192, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 192, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed7')
# mixed 8: 8 x 8 x 1280
branch3x3 = conv2d_bn(x, 192, 1, 1)
branch3x3 = conv2d_bn(branch3x3, 320, 3, 3, strides=(2, 2), padding='valid')
branch7x7x3 = conv2d_bn(x, 192, 1, 1)
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 1, 7)
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 7, 1)
branch7x7x3 = conv2d_bn(
branch7x7x3, 192, 3, 3, strides=(2, 2), padding='valid')
branch_pool = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = layers.concatenate(
[branch3x3, branch7x7x3, branch_pool], axis=channel_axis, name='mixed8')
# mixed 9: 8 x 8 x 2048
for i in range(2):
branch1x1 = conv2d_bn(x, 320, 1, 1)
branch3x3 = conv2d_bn(x, 384, 1, 1)
branch3x3_1 = conv2d_bn(branch3x3, 384, 1, 3)
branch3x3_2 = conv2d_bn(branch3x3, 384, 3, 1)
branch3x3 = layers.concatenate(
[branch3x3_1, branch3x3_2], axis=channel_axis, name='mixed9_' + str(i))
branch3x3dbl = conv2d_bn(x, 448, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 384, 3, 3)
branch3x3dbl_1 = conv2d_bn(branch3x3dbl, 384, 1, 3)
branch3x3dbl_2 = conv2d_bn(branch3x3dbl, 384, 3, 1)
branch3x3dbl = layers.concatenate(
[branch3x3dbl_1, branch3x3dbl_2], axis=channel_axis)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch3x3, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed' + str(9 + i))
if include_top:
# Classification block
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='predictions')(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 = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='inception_v3')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file(
'inception_v3_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
file_hash='9a0d58056eeedaa3f26cb7ebd46da564')
else:
weights_path = get_file(
'inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
file_hash='bcbd6486424b2319ff4ef7d526e38f63')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
def Xception(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the Xception architecture.
Optionally loads weights pre-trained
on ImageNet. This model is available for TensorFlow only,
and can only be used with inputs following the TensorFlow
data format `(width, height, channels)`.
You should set `image_data_format='channels_last'` in your Keras config
located at ~/.keras/keras.json.
Note that the default input image size for this model is 299x299.
Arguments:
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 `(299, 299, 3)`.
It should have exactly 3 inputs channels,
and width and height should be no smaller than 71.
E.g. `(150, 150, 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.
RuntimeError: If attempting to run this model with a
backend that does not support separable convolutions.
"""
if not (weights in {'imagenet', None} or os.path.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')
if K.image_data_format() != 'channels_last':
logging.warning(
'The Xception model is only available for the '
'input data format "channels_last" '
'(width, height, channels). '
'However your settings specify the default '
'data format "channels_first" (channels, width, height). '
'You should set `image_data_format="channels_last"` in your Keras '
'config located at ~/.keras/keras.json. '
'The model being returned right now will expect inputs '
'to follow the "channels_last" data format.')
K.set_image_data_format('channels_last')
old_data_format = 'channels_first'
else:
old_data_format = None
# Determine proper input shape
input_shape = _obtain_input_shape(
input_shape,
default_size=299,
min_size=71,
data_format=K.image_data_format(),
require_flatten=False,
weights=weights)
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
x = Conv2D(
32, (3, 3), strides=(2, 2), use_bias=False, name='block1_conv1')(
img_input)
x = BatchNormalization(name='block1_conv1_bn')(x)
x = Activation('relu', name='block1_conv1_act')(x)
x = Conv2D(64, (3, 3), use_bias=False, name='block1_conv2')(x)
x = BatchNormalization(name='block1_conv2_bn')(x)
x = Activation('relu', name='block1_conv2_act')(x)
residual = Conv2D(
128, (1, 1), strides=(2, 2), padding='same', use_bias=False)(
x)
residual = BatchNormalization()(residual)
x = SeparableConv2D(
128, (3, 3), padding='same', use_bias=False, name='block2_sepconv1')(
x)
x = BatchNormalization(name='block2_sepconv1_bn')(x)
x = Activation('relu', name='block2_sepconv2_act')(x)
x = SeparableConv2D(
128, (3, 3), padding='same', use_bias=False, name='block2_sepconv2')(
x)
x = BatchNormalization(name='block2_sepconv2_bn')(x)
x = MaxPooling2D(
(3, 3), strides=(2, 2), padding='same', name='block2_pool')(
x)
x = layers.add([x, residual])
residual = Conv2D(
256, (1, 1), strides=(2, 2), padding='same', use_bias=False)(
x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block3_sepconv1_act')(x)
x = SeparableConv2D(
256, (3, 3), padding='same', use_bias=False, name='block3_sepconv1')(
x)
x = BatchNormalization(name='block3_sepconv1_bn')(x)
x = Activation('relu', name='block3_sepconv2_act')(x)
x = SeparableConv2D(
256, (3, 3), padding='same', use_bias=False, name='block3_sepconv2')(
x)
x = BatchNormalization(name='block3_sepconv2_bn')(x)
x = MaxPooling2D(
(3, 3), strides=(2, 2), padding='same', name='block3_pool')(
x)
x = layers.add([x, residual])
residual = Conv2D(
728, (1, 1), strides=(2, 2), padding='same', use_bias=False)(
x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block4_sepconv1_act')(x)
x = SeparableConv2D(
728, (3, 3), padding='same', use_bias=False, name='block4_sepconv1')(
x)
x = BatchNormalization(name='block4_sepconv1_bn')(x)
x = Activation('relu', name='block4_sepconv2_act')(x)
x = SeparableConv2D(
728, (3, 3), padding='same', use_bias=False, name='block4_sepconv2')(
x)
x = BatchNormalization(name='block4_sepconv2_bn')(x)
x = MaxPooling2D(
(3, 3), strides=(2, 2), padding='same', name='block4_pool')(
x)
x = layers.add([x, residual])
for i in range(8):
residual = x
prefix = 'block' + str(i + 5)
x = Activation('relu', name=prefix + '_sepconv1_act')(x)
x = SeparableConv2D(
728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv1')(
x)
x = BatchNormalization(name=prefix + '_sepconv1_bn')(x)
x = Activation('relu', name=prefix + '_sepconv2_act')(x)
x = SeparableConv2D(
728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv2')(
x)
x = BatchNormalization(name=prefix + '_sepconv2_bn')(x)
x = Activation('relu', name=prefix + '_sepconv3_act')(x)
x = SeparableConv2D(
728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv3')(
x)
x = BatchNormalization(name=prefix + '_sepconv3_bn')(x)
x = layers.add([x, residual])
residual = Conv2D(
1024, (1, 1), strides=(2, 2), padding='same', use_bias=False)(
x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block13_sepconv1_act')(x)
x = SeparableConv2D(
728, (3, 3), padding='same', use_bias=False, name='block13_sepconv1')(
x)
x = BatchNormalization(name='block13_sepconv1_bn')(x)
x = Activation('relu', name='block13_sepconv2_act')(x)
x = SeparableConv2D(
1024, (3, 3), padding='same', use_bias=False, name='block13_sepconv2')(
x)
x = BatchNormalization(name='block13_sepconv2_bn')(x)
x = MaxPooling2D(
(3, 3), strides=(2, 2), padding='same', name='block13_pool')(
x)
x = layers.add([x, residual])
x = SeparableConv2D(
1536, (3, 3), padding='same', use_bias=False, name='block14_sepconv1')(
x)
x = BatchNormalization(name='block14_sepconv1_bn')(x)
x = Activation('relu', name='block14_sepconv1_act')(x)
x = SeparableConv2D(
2048, (3, 3), padding='same', use_bias=False, name='block14_sepconv2')(
x)
x = BatchNormalization(name='block14_sepconv2_bn')(x)
x = Activation('relu', name='block14_sepconv2_act')(x)
if include_top:
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='predictions')(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='xception')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file(
'xception_weights_tf_dim_ordering_tf_kernels.h5',
TF_WEIGHTS_PATH,
cache_subdir='models',
file_hash='0a58e3b7378bc2990ea3b43d5981f1f6')
else:
weights_path = get_file(
'xception_weights_tf_dim_ordering_tf_kernels_notop.h5',
TF_WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
file_hash='b0042744bf5b25fce3cb969f33bebb97')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
if old_data_format:
K.set_image_data_format(old_data_format)
return model
def VGG19(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
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),
'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 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 not (weights in {'imagenet', None} or os.path.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 = _obtain_input_shape(
input_shape,
default_size=224,
min_size=48,
data_format=K.image_data_format(),
require_flatten=include_top,
weights=weights)
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(
64, (3, 3), activation='relu', padding='same', name='block1_conv1')(
img_input)
x = Conv2D(
64, (3, 3), activation='relu', padding='same', name='block1_conv2')(
x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
# Block 2
x = Conv2D(
128, (3, 3), activation='relu', padding='same', name='block2_conv1')(
x)
x = Conv2D(
128, (3, 3), activation='relu', padding='same', name='block2_conv2')(
x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
# Block 3
x = Conv2D(
256, (3, 3), activation='relu', padding='same', name='block3_conv1')(
x)
x = Conv2D(
256, (3, 3), activation='relu', padding='same', name='block3_conv2')(
x)
x = Conv2D(
256, (3, 3), activation='relu', padding='same', name='block3_conv3')(
x)
x = Conv2D(
256, (3, 3), activation='relu', padding='same', name='block3_conv4')(
x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
# Block 4
x = Conv2D(
512, (3, 3), activation='relu', padding='same', name='block4_conv1')(
x)
x = Conv2D(
512, (3, 3), activation='relu', padding='same', name='block4_conv2')(
x)
x = Conv2D(
512, (3, 3), activation='relu', padding='same', name='block4_conv3')(
x)
x = Conv2D(
512, (3, 3), activation='relu', padding='same', name='block4_conv4')(
x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
# Block 5
x = Conv2D(
512, (3, 3), activation='relu', padding='same', name='block5_conv1')(
x)
x = Conv2D(
512, (3, 3), activation='relu', padding='same', name='block5_conv2')(
x)
x = Conv2D(
512, (3, 3), activation='relu', padding='same', name='block5_conv3')(
x)
x = Conv2D(
512, (3, 3), activation='relu', padding='same', name='block5_conv4')(
x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
if include_top:
# 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)
# 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='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',
file_hash='cbe5617147190e668d6c5d5026f83318')
else:
weights_path = 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
