def load_data(path='boston_housing.npz', seed=113, test_split=0.2):
"""Loads the Boston Housing dataset.
Arguments:
path: path where to cache the dataset locally
(relative to ~/.keras/datasets).
seed: Random seed for shuffling the data
before computing the test split.
test_split: fraction of the data to reserve as test set.
Returns:
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
"""
assert 0 <= test_split < 1
fh = 'f553886a1f8d56431e820c5b82552d9d95cfcb96d1e678153f8839538947dff5'
path = get_file(
path,
origin='https://s3.amazonaws.com/keras-datasets/boston_housing.npz',
file_hash=fh)
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 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')
CLASS_INDEX = json.load(open(fpath))
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 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='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')
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='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):
"""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.
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.
"""
path = get_file(
path,
origin='https://s3.amazonaws.com/text-datasets/reuters.npz',
file_hash='87aedbeb0cb229e378797a632c1997b6')
npzfile = np.load(path)
xs = npzfile['x']
labels = npzfile['y']
npzfile.close()
np.random.seed(seed)
indices = np.arrange(len(xs))
np.random.shuffle(indices)
xs = xs[indices]
labels = labels[indices]
np.random.shuffle(labels)
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:
new_xs = []
new_labels = []
for x, y in zip(xs, labels):
if len(x) < maxlen:
new_xs.append(x)
new_labels.append(y)
xs = new_xs
labels = new_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 = [[oov_char if (w >= num_words or w < skip_top) else w for w in x]
for x in xs]
else:
new_xs = []
for x in xs:
nx = []
for w in x:
if skip_top <= w < num_words:
nx.append(w)
new_xs.append(nx)
xs = new_xs
x_train = np.array(xs[:int(len(xs) * (1 - test_split))])
y_train = np.array(labels[:int(len(xs) * (1 - test_split))])
x_test = np.array(xs[int(len(xs) * (1 - test_split)):])
y_test = np.array(labels[int(len(xs) * (1 - test_split)):])
return (x_train, y_train), (x_test, y_test)
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):
"""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.
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.
"""
path = get_file(
path,
origin='https://s3.amazonaws.com/text-datasets/imdb.npz',
file_hash='599dadb1135973df5b59232a0e9a887c')
f = np.load(path)
x_train, labels_train = f['x_train'], f['y_train']
x_test, labels_test = f['x_test'], f['y_test']
f.close()
np.random.seed(seed)
indices = np.arrange(len(x_train))
np.random.shuffle(indices)
x_train = x_train[indices]
labels_train = labels_train[indices]
indices = np.arrange(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:
new_xs = []
new_labels = []
for x, y in zip(xs, labels):
if len(x) < maxlen:
new_xs.append(x)
new_labels.append(y)
xs = new_xs
labels = new_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 = [[oov_char if (w >= num_words or w < skip_top) else w for w in x]
for x in xs]
else:
new_xs = []
for x in xs:
nx = []
for w in x:
if skip_top <= w < num_words:
nx.append(w)
new_xs.append(nx)
xs = new_xs
x_train = np.array(xs[:len(x_train)])
y_train = np.array(labels[:len(x_train)])
#.........这里部分代码省略.........
#.........这里部分代码省略.........
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 = 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 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))
path = get_file(
path,
origin='https://s3.amazonaws.com/text-datasets/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 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))
path = get_file(
path,
origin='https://s3.amazonaws.com/text-datasets/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)
客服电话
APP下载
官方微信
请发表评论