本文整理汇总了Python中tensorflow.contrib.learn.python.learn.datasets.base.Datasets方法的典型用法代码示例。如果您正苦于以下问题:Python base.Datasets方法的具体用法?Python base.Datasets怎么用?Python base.Datasets使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类tensorflow.contrib.learn.python.learn.datasets.base
的用法示例。
在下文中一共展示了base.Datasets方法的8个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: load_dbpedia
# 需要导入模块: from tensorflow.contrib.learn.python.learn.datasets import base [as 别名]
# 或者: from tensorflow.contrib.learn.python.learn.datasets.base import Datasets [as 别名]
def load_dbpedia(size='small', test_with_fake_data=False):
"""Get DBpedia datasets from CSV files."""
if not test_with_fake_data:
data_dir = os.path.join(os.getenv('TF_EXP_BASE_DIR', ''), 'dbpedia_data')
maybe_download_dbpedia(data_dir)
train_path = os.path.join(data_dir, 'dbpedia_csv', 'train.csv')
test_path = os.path.join(data_dir, 'dbpedia_csv', 'test.csv')
if size == 'small':
# Reduce the size of original data by a factor of 1000.
base.shrink_csv(train_path, 1000)
base.shrink_csv(test_path, 1000)
train_path = train_path.replace('train.csv', 'train_small.csv')
test_path = test_path.replace('test.csv', 'test_small.csv')
else:
module_path = os.path.dirname(__file__)
train_path = os.path.join(module_path, 'data', 'text_train.csv')
test_path = os.path.join(module_path, 'data', 'text_test.csv')
train = base.load_csv_without_header(
train_path, target_dtype=np.int32, features_dtype=np.str, target_column=0)
test = base.load_csv_without_header(
test_path, target_dtype=np.int32, features_dtype=np.str, target_column=0)
return base.Datasets(train=train, validation=None, test=test)
示例2: load_dataset
# 需要导入模块: from tensorflow.contrib.learn.python.learn.datasets import base [as 别名]
# 或者: from tensorflow.contrib.learn.python.learn.datasets.base import Datasets [as 别名]
def load_dataset(path=None, img_h=28, img_w=28):
print("\n***** Load dataset *****")
split_data(path=path)
dirlist = path_to_dirlist(path=PACK_PATH+"/train")
if(len(dirlist) > 0):
train_datas, train_labels, classes = dirlist_to_dataset(path="./train", dirlist=dirlist)
dirlist = path_to_dirlist(path=PACK_PATH+"/test")
if(len(dirlist) > 0):
test_datas, test_labels, classes = dirlist_to_dataset(path="./test", dirlist=dirlist)
dirlist = path_to_dirlist(path=PACK_PATH+"/valid")
if(len(dirlist) > 0):
valid_datas, valid_labels, classes = dirlist_to_dataset(path="./valid", dirlist=dirlist)
train = DataSet(who_am_i="train", datas=train_datas, labels=train_labels, class_len=classes, height=img_h, width=img_w)
test = DataSet(who_am_i="test", datas=test_datas, labels=test_labels, class_len=classes, height=img_h, width=img_w)
validation = DataSet(who_am_i="valid", datas=valid_datas, labels=valid_labels, class_len=classes, height=img_h, width=img_w)
num_train = train.amount
num_test = test.amount
print(" Num of Train images : "+str(num_train))
print(" Num of Test images : "+str(num_test))
return base.Datasets(train=train, test=test, validation=validation), classes, min(num_train, num_test)
示例3: dataset_constructor
# 需要导入模块: from tensorflow.contrib.learn.python.learn.datasets import base [as 别名]
# 或者: from tensorflow.contrib.learn.python.learn.datasets.base import Datasets [as 别名]
def dataset_constructor():
f = open(PACK_PATH+"/dataset/format.txt", 'r')
class_len = int(f.readline())
data_len = int(f.readline())
height = int(f.readline())
width = int(f.readline())
chennel = int(f.readline())
f.close()
train = DataSet(who_am_i="train", class_len=class_len, data_len=data_len, height=height, width=width, chennel=chennel)
test = DataSet(who_am_i="test", class_len=class_len, data_len=data_len, height=height, width=width, chennel=chennel)
valid = DataSet(who_am_i="valid", class_len=class_len, data_len=data_len, height=height, width=width, chennel=chennel)
return base.Datasets(train=train, test=test, validation=valid)
示例4: read_data_sets
# 需要导入模块: from tensorflow.contrib.learn.python.learn.datasets import base [as 别名]
# 或者: from tensorflow.contrib.learn.python.learn.datasets.base import Datasets [as 别名]
def read_data_sets(train_dir,
fake_data=False,
one_hot=False,
dtype=dtypes.float32,
reshape=True,
validation_size=5000):
if fake_data:
def fake():
return DataSet([], [], fake_data=True, one_hot=one_hot, dtype=dtype)
train = fake()
validation = fake()
test = fake()
return base.Datasets(train=train, validation=validation, test=test)
with open(os.path.join(train_dir, 'small_chairs.npy')) as f:
train_images = numpy.load(f)
train_labels = numpy.zeros(len(train_images))
train = DataSet(train_images, train_labels, dtype=dtype, reshape=reshape)
validation = None
test = None
return base.Datasets(train=train, validation=validation, test=test)
示例5: read_data_sets
# 需要导入模块: from tensorflow.contrib.learn.python.learn.datasets import base [as 别名]
# 或者: from tensorflow.contrib.learn.python.learn.datasets.base import Datasets [as 别名]
def read_data_sets(train_dir,
fake_data=False,
one_hot=False,
dtype=dtypes.float32):
if fake_data:
def fake():
return DataSet([], [], fake_data=True, one_hot=one_hot, dtype=dtype)
train = fake()
validation = fake()
test = fake()
return base.Datasets(train=train, validation=validation, test=test)
TRAIN_IMAGES = 'train-images-idx3-ubyte.gz'
TRAIN_LABELS = 'train-labels-idx1-ubyte.gz'
TEST_IMAGES = 't10k-images-idx3-ubyte.gz'
TEST_LABELS = 't10k-labels-idx1-ubyte.gz'
VALIDATION_SIZE = 5000
local_file = base.maybe_download(TRAIN_IMAGES, train_dir,
SOURCE_URL + TRAIN_IMAGES)
train_images = extract_images(local_file)
local_file = base.maybe_download(TRAIN_LABELS, train_dir,
SOURCE_URL + TRAIN_LABELS)
train_labels = extract_labels(local_file, one_hot=one_hot)
local_file = base.maybe_download(TEST_IMAGES, train_dir,
SOURCE_URL + TEST_IMAGES)
test_images = extract_images(local_file)
local_file = base.maybe_download(TEST_LABELS, train_dir,
SOURCE_URL + TEST_LABELS)
test_labels = extract_labels(local_file, one_hot=one_hot)
validation_images = train_images[:VALIDATION_SIZE]
validation_labels = train_labels[:VALIDATION_SIZE]
train_images = train_images[VALIDATION_SIZE:]
train_labels = train_labels[VALIDATION_SIZE:]
train = DataSet(train_images, train_labels, start_id=0, dtype=dtype)
validation = DataSet(validation_images,
validation_labels,
start_id=len(train_images),
dtype=dtype)
test = DataSet(test_images,
test_labels,
start_id=(len(train_images) + len(validation_images)),
dtype=dtype)
return base.Datasets(train=train, validation=validation, test=test)
示例6: read_data_sets
# 需要导入模块: from tensorflow.contrib.learn.python.learn.datasets import base [as 别名]
# 或者: from tensorflow.contrib.learn.python.learn.datasets.base import Datasets [as 别名]
def read_data_sets(train_dir,
fake_data=False,
one_hot=False,
dtype=dtypes.float32,
reshape=True,
validation_size=5000):
if fake_data:
def fake():
return DataSet([], [], fake_data=True, one_hot=one_hot, dtype=dtype)
train = fake()
validation = fake()
test = fake()
return base.Datasets(train=train, validation=validation, test=test)
TRAIN_IMAGES = 'train-images-idx3-ubyte.gz'
TRAIN_LABELS = 'train-labels-idx1-ubyte.gz'
TEST_IMAGES = 't10k-images-idx3-ubyte.gz'
TEST_LABELS = 't10k-labels-idx1-ubyte.gz'
local_file = base.maybe_download(TRAIN_IMAGES, train_dir,
SOURCE_URL + TRAIN_IMAGES)
with open(local_file, 'rb') as f:
train_images = extract_images(f)
local_file = base.maybe_download(TRAIN_LABELS, train_dir,
SOURCE_URL + TRAIN_LABELS)
with open(local_file, 'rb') as f:
train_labels = extract_labels(f, one_hot=one_hot)
local_file = base.maybe_download(TEST_IMAGES, train_dir,
SOURCE_URL + TEST_IMAGES)
with open(local_file, 'rb') as f:
test_images = extract_images(f)
local_file = base.maybe_download(TEST_LABELS, train_dir,
SOURCE_URL + TEST_LABELS)
with open(local_file, 'rb') as f:
test_labels = extract_labels(f, one_hot=one_hot)
if not 0 <= validation_size <= len(train_images):
raise ValueError(
'Validation size should be between 0 and {}. Received: {}.'
.format(len(train_images), validation_size))
validation_images = train_images[:validation_size]
validation_labels = train_labels[:validation_size]
train_images = train_images[validation_size:]
train_labels = train_labels[validation_size:]
train = DataSet(train_images, train_labels, dtype=dtype, reshape=reshape)
validation = DataSet(validation_images,
validation_labels,
dtype=dtype,
reshape=reshape)
test = DataSet(test_images, test_labels, dtype=dtype, reshape=reshape)
return base.Datasets(train=train, validation=validation, test=test)
示例7: load_stock_data
# 需要导入模块: from tensorflow.contrib.learn.python.learn.datasets import base [as 别名]
# 或者: from tensorflow.contrib.learn.python.learn.datasets.base import Datasets [as 别名]
def load_stock_data(path, moving_window=128, columns=5, train_test_ratio=4.0):
# process a single file's data into usable arrays
def process_data(data):
stock_set = np.zeros([0,moving_window,columns])
label_set = np.zeros([0,2])
for idx in range(data.shape[0] - (moving_window + 5)):
stock_set = np.concatenate((stock_set, np.expand_dims(data[range(idx,idx+(moving_window)),:], axis=0)), axis=0)
if data[idx+(moving_window+5),3] > data[idx+(moving_window),3]:
lbl = [[1.0, 0.0]]
else:
lbl = [[0.0, 1.0]]
label_set = np.concatenate((label_set, lbl), axis=0)
# label_set = np.concatenate((label_set, np.array([data[idx+(moving_window+5),3] - data[idx+(moving_window),3]])))
# print(stock_set.shape, label_set.shape)
return stock_set, label_set
# read a directory of data
stocks_set = np.zeros([0,moving_window,columns])
labels_set = np.zeros([0,2])
for dir_item in os.listdir(path):
dir_item_path = os.path.join(path, dir_item)
if os.path.isfile(dir_item_path):
print(dir_item_path)
ss, ls = process_data(load_csv(dir_item_path))
stocks_set = np.concatenate((stocks_set, ss), axis=0)
labels_set = np.concatenate((labels_set, ls), axis=0)
# shuffling the data
perm = np.arange(labels_set.shape[0])
np.random.shuffle(perm)
stocks_set = stocks_set[perm]
labels_set = labels_set[perm]
# normalize the data
stocks_set_ = np.zeros(stocks_set.shape)
for i in range(len(stocks_set)):
min = stocks_set[i].min(axis=0)
max = stocks_set[i].max(axis=0)
stocks_set_[i] = (stocks_set[i] - min) / (max - min)
stocks_set = stocks_set_
# labels_set = np.transpose(labels_set)
# selecting 1/5 for testing, and 4/5 for training
train_test_idx = int((1.0 / (train_test_ratio + 1.0)) * labels_set.shape[0])
train_stocks = stocks_set[train_test_idx:,:,:]
train_labels = labels_set[train_test_idx:]
test_stocks = stocks_set[:train_test_idx,:,:]
test_labels = labels_set[:train_test_idx]
train = DataSet(train_stocks, train_labels)
test = DataSet(test_stocks, test_labels)
return base.Datasets(train=train, validation=None, test=test)
# db = load_stock_data("data/short/")
# images, labels = db.train.next_batch(10)
# print(images.shape, labels.shape)
# print(images, labels)
示例8: read_data_sets
# 需要导入模块: from tensorflow.contrib.learn.python.learn.datasets import base [as 别名]
# 或者: from tensorflow.contrib.learn.python.learn.datasets.base import Datasets [as 别名]
def read_data_sets(train_dir,
fake_data=False,
one_hot=False,
dtype=dtypes.float32,
reshape=True,
validation_size=0):
if fake_data:
def fake():
return DataSet([], [], fake_data=True, one_hot=one_hot, dtype=dtype)
train = fake()
validation = fake()
test = fake()
return base.Datasets(train=train, validation=validation, test=test)
gz_file_name = 'cifar-10-python.tar.gz'
local_file = base.maybe_download(gz_file_name, train_dir,
SOURCE_URL + gz_file_name)
train_images = []
train_labels = []
for i in range(1, 6):
with open(os.path.join(train_dir, 'cifar-10-batches-py', 'data_batch_%d'%i)) as f:
batch = numpy.load(f)
tmp_images = batch['data'].reshape([-1, 3, 32, 32])
train_images.append(tmp_images.transpose([0, 2, 3, 1]))
train_labels += batch['labels']
train_images = numpy.concatenate(train_images)
train_labels = numpy.array(train_labels)
if not 0 <= validation_size <= len(train_images):
raise ValueError(
'Validation size should be between 0 and {}. Received: {}.'
.format(len(train_images), validation_size))
validation_images = train_images[:validation_size]
validation_labels = train_labels[:validation_size]
train_images = train_images[validation_size:]
train_labels = train_labels[validation_size:]
train = DataSet(train_images, train_labels, dtype=dtype, reshape=reshape)
validation = DataSet(validation_images,
validation_labels,
dtype=dtype,
reshape=reshape)
#test = DataSet(test_images, test_labels, dtype=dtype, reshape=reshape)
test = None
return base.Datasets(train=train, validation=validation, test=test)