def testMultipleIteratorsOnADatasetThatUsesFunctions(self):
ds = Dataset.from_tensor_slices([1, 2, 3, 4, 5, 6]).map(math_ops.square)
got1 = [x.numpy() for x in datasets.Iterator(ds)]
self.assertAllEqual([1, 4, 9, 16, 25, 36], got1)
got2 = [x.numpy() for x in datasets.Iterator(ds)]
self.assertAllEqual(got1, got2)
def benchmarkSliceBatchCacheRepeatCallable(self):
input_size = 10000
batch_size = 100
num_epochs = 100
input_data = np.random.randn(input_size)
dataset = (
Dataset.from_tensor_slices(input_data).batch(batch_size).cache()
.repeat(num_epochs))
iterator = datasets.Iterator(dataset)
ends = [time.time()]
for _ in iterator:
ends.append(time.time())
deltas = np.ediff1d(ends)
median_wall_time = np.median(deltas)
print(
'Slice/batch/cache/repeat eager input size: %d batch size: %d Median '
'wall time per element: %f'
% (input_size, batch_size, median_wall_time))
self.report_benchmark(
iters=len(deltas),
wall_time=median_wall_time,
name='benchmark_slice_batch_cache_repeat_eager_input_%d_batch_%d' %
(input_size, batch_size))
def my_input_fn(features, targets, batch_size=1, shuffle=True, num_epochs=None):
""" Trains a linear regression model of one feature.
Args:
:param features: pandas DataFrame of features
:param targets: pandas DataFrame of targets
:param batch_size: size of batches to be passed to the model
:param shuffle: weather to shuffle the data
:param num_epochs: number of epochs for which data should be repeated. None = repeat indefinitely
:return:
Tuple of (features, labels) for next data batch
"""
# Convert pandas data into a dict of np arrays.
features = {key: np.array(value) for key, value in dict(features).items()}
# Construct a dataset, and configure batching/repeating.
ds = Dataset.from_tensor_slices((features, targets))
ds = ds.batch(batch_size).repeat(num_epochs)
# Shuffle the data, if specified.
if shuffle:
ds.shuffle(buffer_size=10000)
# Return the next batch of data.
features, labels = ds.make_one_shot_iterator().get_next()
return features, labels
def testSaveRestoreMultipleIterator(self):
checkpoint_directory = self.get_temp_dir()
checkpoint_prefix = os.path.join(checkpoint_directory, 'ckpt')
dataset = Dataset.from_tensor_slices([1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11])
dataset = dataset.map(math_ops.square).batch(2)
iterator_1 = datasets.Iterator(dataset)
iterator_2 = datasets.Iterator(dataset)
dataset_2 = Dataset.range(10)
iterator_3 = datasets.Iterator(dataset_2)
checkpoint = checkpointable_utils.Checkpoint(
iterator_1=iterator_1, iterator_2=iterator_2, iterator_3=iterator_3)
self.assertAllEqual([1, 4], iterator_1.get_next().numpy())
self.assertEqual(0, iterator_3.get_next().numpy())
self.assertEqual(1, iterator_3.get_next().numpy())
self.assertEqual(2, iterator_3.get_next().numpy())
save_path = checkpoint.save(checkpoint_prefix)
self.assertAllEqual([1, 4], iterator_2.get_next().numpy())
self.assertAllEqual([9, 16], iterator_2.get_next().numpy())
self.assertEqual(3, iterator_3.get_next().numpy())
checkpoint.restore(save_path)
self.assertAllEqual([9, 16], iterator_1.get_next().numpy())
self.assertAllEqual([1, 4], iterator_2.get_next().numpy())
self.assertEqual(3, iterator_3.get_next().numpy())
def testTensorsExplicitPrefetchToDevice(self):
ds = Dataset.from_tensor_slices([0., 1.])
ds = ds.apply(prefetching_ops.prefetch_to_device(test.gpu_device_name()))
with self.assertRaisesRegexp(TypeError, 'prefetch_to_device'):
datasets.Iterator(ds)
for i, x in enumerate(ds):
with ops.device(test.gpu_device_name()):
x = math_ops.add(x, x)
self.assertEqual(float(i) + float(i), x.numpy())
def testMapCaptureLookupTable(self):
default_val = -1
keys = constant_op.constant(['brain', 'salad', 'surgery'])
values = constant_op.constant([0, 1, 2], dtypes.int64)
table = lookup.HashTable(
lookup.KeyValueTensorInitializer(keys, values), default_val)
dataset = Dataset.from_tensor_slices(['brain', 'salad', 'surgery'])
dataset = dataset.map(table.lookup)
it = datasets.Iterator(dataset)
got = [x.numpy() for x in it]
self.assertAllEqual([0, 1, 2], got)
def testSaveRestore(self): checkpoint_directory = self.get_temp_dir() checkpoint_prefix = os.path.join(checkpoint_directory, 'ckpt') dataset = Dataset.from_tensor_slices([1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]) dataset = dataset.map(math_ops.square).batch(2) iterator = datasets.Iterator(dataset) checkpoint = checkpointable_utils.Checkpoint(iterator=iterator) self.assertAllEqual([1, 4], iterator.get_next().numpy()) save_path = checkpoint.save(checkpoint_prefix) self.assertAllEqual([9, 16], iterator.get_next().numpy()) self.assertAllEqual([25, 36], iterator.get_next().numpy()) checkpoint.restore(save_path) self.assertAllEqual([9, 16], iterator.get_next().numpy()) self.assertAllEqual([25, 36], iterator.get_next().numpy())
def my_input_fn(features, targets, batch_size=1, shuffle=True, num_epochs=None):
# 将 pandas 的 data 转换成 numpy arrays
features = {key: np.array(value) for key, value in dict(features).items()}
# 构造一个 tensorflow 的 Dataset, 并且配置 batching 和 repeating
ds = Dataset.from_tensor_slices((features, targets))
ds = ds.batch(batch_size).repeat(num_epochs)
# 按需随机打乱数据
if shuffle:
ds = ds.shuffle(buffer_size=10000)
# 返回下一批次的数据
features, labels = ds.make_one_shot_iterator().get_next()
return features, labels
def my_input_fn(features, targets, batch_size=1, shuffle=True, num_epochs=None):
# Convert pandas data into a dict of np arrays.
features = {key:np.array(value) for key,value in dict(features).items()}
# Construct a dataset, and configure batching/repeating
ds = Dataset.from_tensor_slices((features,targets)) # warning: 2GB limit
ds = ds.batch(batch_size).repeat(num_epochs)
# Shuffle the data, if specified
if shuffle:
ds = ds.shuffle(10000)
# Return the next batch of data
features, labels = ds.make_one_shot_iterator().get_next()
return features, labels
def my_input_fn(features,
targets,
batch_size=5,
shuffle=True,
num_epochs=None):
# 将Csv数据转化成一个np数组。np数组能够保证一个list中全部都是一个类型的数据。
# 接着将数据切片，不然输入数据是整个数据集
# 切片后再进行分批处理。此处size为1,代表每次输入一个数据
# repeat是指数据要被重复多少次。暂时不太理解重复的意义，可能和数据处理有关。
features = {key: np.array(value) for key, value in dict(features).items()}
ds = Dataset.from_tensor_slices((features, targets))
ds = ds.batch(batch_size).repeat(num_epochs)
# 将数据随机打乱。
if shuffle:
ds = ds.shuffle(buffer_size=10000)
features, labels = ds.make_one_shot_iterator().get_next()
return features, labels
def _input_fn(num_epochs=None, shuffle=True):
# Input pipelines are reset with each call to .train(). To ensure model
# gets a good sampling of data, even when number of steps is small, we
# shuffle all the data before creating the Dataset object
idx = np.random.permutation(features.index)
raw_features = {"pixels":features.reindex(idx)}
raw_targets = np.array(labels[idx])
ds = Dataset.from_tensor_slices((raw_features,raw_targets)) # warning: 2GB limit
ds = ds.batch(batch_size).repeat(num_epochs)
if shuffle:
ds = ds.shuffle(10000)
# Return the next batch of data.
feature_batch, label_batch = ds.make_one_shot_iterator().get_next()
return feature_batch, label_batch
def _input_fn(num_epochs=None, shuffle=True):
idx = np.random.permutation(features.index)
raw_features = {
"Pclass": features["Pclass"].values,
"Age": features["Age"].values,
"SibSp": features["SibSp"].values,
"Parch": features["Parch"].values,
"Fare": features["Fare"].values,
"SexCode": features["SexCode"].values,
"EmbarkCode": features["EmbarkCode"].values
}
raw_targets = np.array(labels)
ds = Dataset.from_tensor_slices((raw_features, raw_targets))
ds = ds.batch(batch_size)
feature_batch, label_batch = ds.make_one_shot_iterator().get_next()
return feature_batch, label_batch
def my_input_fn(features, targets, batch_size=1, shuffle=True, num_epochs=None):
# 把pandas特征数据转换成NumPy数组字典
features = {key:np.array(value) for key,value in dict(features).items()}
# 构建数据集
ds = Dataset.from_tensor_slices((features, targets))
# 配置单步的样本数量,每批次传递给模型处理的数据量为batch_size；如果将默认值num_epochs=None传递到repeat()，输入数据会无限重复下去，而没有次数限制
ds = ds.batch(batch_size).repeat(num_epochs)
# 打乱数据，缓冲大小为10000，以便数据在训练期间以随机方式传递到模型
if shuffle:
ds = ds.shuffle(buffer_size=10000)
# 为数据集构建一个迭代器，并向LinearRegressor返回下一批数据
features, labels = ds.make_one_shot_iterator().get_next()
return features, labels
def create_predict_fn():
#same as above, change data into a dictionary
featureDictionary = dict()
for i in range(0, 27):
tempArray = []
for j in range(0, len(bodyPartFeatures)):
tempArray.append(bodyPartFeatures[j][i])
tempArray = np.asarray(tempArray)
featureDictionary[bodyParts[i]] = tempArray
#same as above except there is no epoch mechanic because it is being used for predictions (dont want to repeat data being predicted)
ds = Dataset.from_tensor_slices((featureDictionary, labels))
ds = ds.batch(batch_size)
ds = ds.shuffle(int(numberTests))
feature_batch, label_batch, = ds.make_one_shot_iterator().get_next()
return feature_batch, label_batch
def my_input_fn(features,
targets,
batch_size=1,
shuffle=True,
num_epochs=None):
features = {key: np.array(value) for key, value in dict(features).items()}
ds = Dataset.from_tensor_slices((features, targets))
ds = ds.batch(batch_size).repeat(num_epochs)
if shuffle:
ds = ds.shuffle(buffer_size=10000)
# return the next batch of data
features, labels = ds.make_one_shot_iterator().get_next()
return features, labels
def _input_function_delegate(input_features,
targets,
batch_size=1,
is_shuffle=True,
epoch_count=None):
features = {
key: numpy.array(value)
for key, value in dict(input_features).items()
}
dataset = Dataset.from_tensor_slices(
(features, targets)).batch(batch_size).repeat(epoch_count)
if is_shuffle:
dataset = dataset.shuffle(10000)
return dataset.make_one_shot_iterator().get_next()
def tf_input_fn(features,
targets,
batch_size=1,
shuffle=True,
num_epochs=None):
# Convert pandas data into a dict of np arrays.
features = {key: np.array(value) for key, value in dict(features).items()}
# create a batch
ds = Dataset.from_tensor_slices((features, targets))
ds = ds.batch(batch_size).repeat(num_epochs)
if shuffle:
ds = ds.shuffle(10000)
features, labels = ds.make_one_shot_iterator().get_next()
return features, labels
def my_input_fn(features,
targets,
batch_size=1,
shuffle=True,
num_epochs=None):
features = {key: np.array(value) for key, value in dict(features).items()}
ds = Dataset.from_tensor_slices((features, targets))
# See https://www.tensorflow.org/get_started/datasets_quickstart
ds = ds.batch(batch_size).repeat(num_epochs)
if shuffle:
ds = ds.shuffle(buffer_size=10000)
features, labels = ds.make_one_shot_iterator().get_next()
# print(features, labels)
return features, labels
def my_input_fn(features,
targets,
batch_size=1,
shuffle=True,
num_epochs=None):
# Convert to dict of numpy arrays
features = {key: np.array(value) for key, value in dict(features).items()}
# Construct dataset and batching/repeating
ds = Dataset.from_tensor_slices((features, targets)) # !! 2GB limit!!
ds = ds.batch(batch_size).repeat(num_epochs)
if shuffle:
ds = ds.shuffle(buffer_size=10_000)
features, labels = ds.make_one_shot_iterator().get_next()
return features, labels
def my_input_fn(features,
targets,
batch_size=1,
shuffle=True,
num_epochs=None):
# 这里得到的features是一个dict，具体为{'total_rooms': array([ 5039.,1840., ..., 705.])}
# 其仅有一对{key，value}值，这里的value实际上是一个array对象
features = {key: np.array(value) for key, value in dict(features).items()}
# 构造一个数据集
ds = Dataset.from_tensor_slices((features, targets))
ds = ds.batch(batch_size).repeat(num_epochs)
# 若shuffle为真，则对数据进行随机处理
if shuffle:
ds = ds.shuffle(buffer_size=10000)
# 返回下一批数据
features, labels = ds.make_one_shot_iterator().get_next()
return features, labels
def my_input_fn(features,
targets,
batch_size=1,
shuffle=False,
num_epochs=None):
#targets:pd.Series
# print(';;;;;;;;;;;;;;;;;;;;;;;;;;;;;')
# print(features.head(2))
# print(dict(features.head(2)))
features = {key: np.array(value) for key, value in dict(features).items()}
ds = Dataset.from_tensor_slices((features, targets)) #这两个都是dict
ds = ds.batch(batch_size).repeat(num_epochs)
if shuffle:
ds = ds.shuffle(10000)
features, labels = ds.make_one_shot_iterator().get_next()
return features, labels
def my_input_fn(features,
targets,
batch_size=1,
shuffle=True,
num_epochs=None):
#把pandas转换为numpy数组字典
features = {key: np.array(value) for key, value in dict(features).items()}
# 构建数据集
ds = Dataset.from_tensor_slices((features, targets)) # 2GB limit
ds = ds.batch(batch_size).repeat(num_epochs)
if shuffle:
ds = ds.shuffle(buffer_size=10000)
features, labels = ds.make_one_shot_iterator().get_next()
return features, labels
def my_input_fn(features, targets, batch_size=1, shuffle=True, num_epochs=None):
# 将pandas数据转换成np数组。
features = {key: np.array(value) for key, value in dict(features).items()}
# 构建数据集，并配置批处理/重复
ds = Dataset.from_tensor_slices((features, targets)) # warning: 2GB limit
ds = ds.batch(batch_size).repeat(num_epochs)
# 如果指定洗牌数据
if shuffle:
ds = ds.shuffle(10000)
# 返回下一批数据
features, labels = ds.make_one_shot_iterator().get_next()
return features, labels
def _input_fn(num_epochs=None, shuffle=True):
# randomize all the data
idx = np.random.permutation(features.index)
# create dataset object
raw_features = {"pixels": features.reindex(idx)}
raw_targets = np.array(labels[idx])
ds = Dataset.from_tensor_slices((raw_features, raw_targets))
ds = ds.batch(batch_size).repeat(num_epochs)
# shuffle data if requested
if shuffle:
ds = ds.shuffle(10000)
# return the next batch of data.
feature_batch, label_batch = ds.make_one_shot_iterator().get_next()
return feature_batch, label_batch
def _input_fn(num_epochs=None, shuffle=True):
# Input pipelines are reset with each call to .train(). To ensure model
# gets a good sampling of data, even when number of steps is small, we
# shuffle all the data before creating the Dataset object
raw_features = {key:np.array(value) for key, value in dict(features).items()}
# print(raw_features)
raw_targets = np.array(labels)
ds = Dataset.from_tensor_slices((raw_features,raw_targets)) # warning: 2GB limit
ds = ds.batch(batch_size).repeat(num_epochs)
if shuffle:
ds = ds.shuffle(10000)
# Return the next batch of data.
feature_batch, label_batch = ds.make_one_shot_iterator().get_next()
return feature_batch, label_batch
def my_input_fn(features,
targets,
batch_size=1,
shuffle=True,
num_epochs=None):
"""Trains a linear regression model of one feature.
Args:
features: pandas DataFrame of features
targets: pandas DataFrame of targets
batch_size: Size of batches to be passed to the model
shuffle: True or False. Whether to shuffle the data.
num_epochs: Number of epochs for which data should be repeated. None = repeat indefinitely
Returns:
Tuple of (features, labels) for next data batch
"""
print("The Input Function was Called")
# Convert pandas data into a dict of np arrays.
# dict() : Convert list object to dictionary
# ex. List of Tuple, Tuple of List, List of Set
# dictionary.items() : Return List of object of tuple
# 内包表現 - Python Comprehension
features = {
key: np.array(value)
for key, value in dict(features).items()
}
# Construct a dataset, and configure batching/repeating.
# Feed Full Datas that was received to the function
ds = Dataset.from_tensor_slices(
(features, targets)) # warning: 2GB limit
# Just setting batch size and num epoch variables
# num_epocks is not important, because there are 1000 steps mean 1000 * 1 = 1000 samples will be used
# That is not even 1 epoch, so there is no meaning to set up epoch here
ds = ds.batch(batch_size).repeat(num_epochs)
# Shuffle the data, if specified.
if shuffle:
ds = ds.shuffle(buffer_size=10000)
# Return the next batch of data.
features, labels = ds.make_one_shot_iterator().get_next()
return features, labels
def my_input_fn(features,
targets,
batch_size=1,
shuffle=True,
num_epochs=None):
# 将pandas DataFrame数据转化成np array的字典
features = {key: np.array(value) for key, value in dict(features).items()}
# 建立数据集
# 数据集中每个元素是传入的数据，表示成(features, targets)形式
ds = Dataset.from_tensor_slices((features, targets))
ds = ds.batch(batch_size).repeat(num_epochs)
if shuffle:
ds = ds.shuffle(10000)
# 返回下一批数据
features, labels = ds.make_one_shot_iterator().get_next()
return features, labels
def data_func(self,
features,
targets,
batch_size=1,
shuffle=True,
num_epochs=None):
features = {
key: np.array(value)
for key, value in dict(features).items()
}
ds = Dataset.from_tensor_slices((features, targets))
ds = ds.batch(batch_size).repeat(num_epochs)
if shuffle:
ds = ds.shuffle(100)
features, labels = ds.make_one_shot_iterator().get_next()
return (features, labels)
def my_input_fn(features,
targets,
batch_size=1,
num_epochs=None,
shuffle=True):
#convert features into a dict of np arrays
features = {key: np.array(val) for key, val in dict(features).items()}
#construct dataset, configure batching/repeating
ds = Dataset.from_tensor_slices((features, targets))
ds = ds.batch(batch_size).repeat(num_epochs)
if shuffle:
ds = ds.shuffle(1000)
features, labels = ds.make_one_shot_iterator().get_next()
return features, labels
def my_input_fn(features,
targets,
batch_size=1,
shuffle=True,
num_epochs=None):
#Convert pandas data into a dict of NumPy arrays
features = {key: np.array(value) for key, value in dict(features).items}
#Create a dataset from features and configure batching and repeating
ds = Dataset.from_tensor_slices((features, targets))
ds = ds.batch(batch_size).repeat(num_epochs)
#Shuffle data if specified
if shuffle:
ds = ds.shuffle(buffer_size=10000)
#Return the next batch of data
features, labels = ds.make_one_shot_iterator().get_next()
return features, labels
def my_input_fn(features,targets,batch_size=1,shuffle=True,num_epochs=None):
features={key:np.array(value) for key,value in dict(features).items()}
print (features)
#Use DataSet API to construct a dataset
# ds=DataSet.from_tensor_slices((features,targets))
# ds=ds.batch(batch_size).repeat(num_epochs)
# Construct a dataset, and configure batching/repeating.
ds = Dataset.from_tensor_slices((features,targets)) # warning: 2GB limit
ds = ds.batch(batch_size).repeat(num_epochs)
#shuffle if shuffle is set to true
if shuffle:
ds=ds.shuffle(10000)
#return batches of data
features, labels=ds.make_one_shot_iterator().get_next()
return features,labels
def my_input_fn(features,
targets,
batch_size=1,
shuffle=True,
num_epochs=None):
#转换pandas读取到的内容为 一个 字典， 以 np arrays 的方式
features = {key: np.array(value) for key, value in dict(features).items()}
#构造数据， 然后配置 批数据处理， 比如重复次数
ds = Dataset.from_tensor_slices((features, targets)) #警告， 2GB的大小限制
ds = ds.batch(batch_size).repeat(num_epochs)
#重新打乱数据， 如果指定了要打乱的话
if shuffle:
ds = ds.shuffle(buffer_size=10000)
#返回下一个批处理的数据
features, labels = ds.make_one_shot_iterator().get_next()
return features, labels
def predict_input_fn(features):
"""Trains model of multiple features.
Args:
features: pandas DataFrame of features
Returns:
features for data batch
"""
# Convert pandas data into a dict of np arrays.
features = {key: np.array(value) for key, value in dict(features).items()}
# Construct a dataset, and configure batching/repeating.
ds = Dataset.from_tensor_slices((features)) # warning: 2GB limit
ds = ds.batch(1).repeat(1)
# Return the next batch of data.
features = ds.make_one_shot_iterator().get_next()
return features
def create_training_input_fn(features,
labels,
batch_size,
num_epochs=None,
shuffle=True):
idx = np.random.permutation(features.index)
raw_features = {"pixels": features.reindex(idx)}
raw_targets = np.array(labels[idx])
ds = Dataset.from_tensor_slices((raw_features, raw_targets))
ds = ds.batch(batch_size).repeat(num_epochs)
if shuffle:
ds = ds.shuffle(10000)
# Return the next batch of data.
feature_batch, label_batch = ds.make_one_shot_iterator().get_next()
return feature_batch, label_batch
def _input_fn(num_epochs=None, shuffle=True):
# Input pipelines are reset with each call to .train().
# 为了达到很好的数据样本，甚至当步数很小的时候。我们需要在创建Dataset前混合所有的数据，也就是permutation操作。
# reindex不是打乱，这里是打乱数据。
idx = np.random.permutation(features.index) # 取随机数
raw_features = {
"pixels": features.reindex(idx)
} # features按照随机数的索引reindex，建立dict。
raw_targets = np.array(labels[idx]) # labels按照随机数的索引简历数组
ds = Dataset.from_tensor_slices(
(raw_features, raw_targets)) # 建立Dataset
ds = ds.batch(batch_size).repeat(num_epochs)
if shuffle:
ds = ds.shuffle(10000)
# Return the next batch of data
feature_batch, label_batch = ds.make_one_shot_iterator().get_next()
return feature_batch, label_batch
def _input_fn(num_epochs=None, shuffle=True):
#permutiramo podatke da dobijemo dobar uzorak
indeks = np.random.permutation(features.index)
#kopiramo polja znacajki i oznaka koje nam trebaju
_features = {"pixels": features.reindex(indeks)}
_targets = np.array(labels[indeks])
#uzimamo random element i pretvorimo ga u tensor_slices jer tensorflow radi s takvim podacima
ds = Dataset.from_tensor_slices((_features, _targets)) # 2GB limit
#gradimo skupove podataka na kojima cemo kasnije trenirati klasifikator
ds = ds.batch(batch_size).repeat(num_epochs)
#permutiramo podatke za treniranje
if shuffle:
ds = ds.shuffle(10000)
#vraca znacajke i oznake podataka u slijedecem skupu podataka za treniranje
feature_batch, label_batch = ds.make_one_shot_iterator().get_next()
return feature_batch, label_batch
def my_input_fn(features, targets, batch_size=1, shuffle=True, num_epochs=None):
"""
:param features:
:param targets:
:param batch_size:
:param shuffle:
:param num_epochs:
:return:
"""
# 用tf的方法处理数据，在数据上设置一次梯度下降验证时所用的数据集大小（batch_size),以及数据集重复的次数（num_epchs)
# 具体怎么整的不清楚，得看tf的源码了吧
dataset = Dataset.from_tensor_slices(features, targets)
dataset = dataset.batch(batch_size).repeat(num_epochs)
if shuffle:
dataset = dataset.shuffle(buffer_size=10000)
features, labels = dataset.make_one_shot_iterator().get_next()
return features, labels
def my_input_fn(features,
targets=None,
batch_size_val=1,
shuffle=True,
num_epochs=None):
features = {key: np.array(value) for key, value in dict(features).items()}
if targets is None:
# No labels, use only features.
inputs = features
else:
inputs = (features, targets)
ds = Dataset.from_tensor_slices(inputs)
ds = ds.batch(batch_size_val).repeat(num_epochs)
if shuffle:
ds = ds.shuffle(10000)
return ds.make_one_shot_iterator().get_next()
def testSparseTensorElements(self):
components = (sparse_tensor.SparseTensorValue(
indices=np.array([[0, 0], [1, 0], [2, 0]]),
values=np.array([0, 0, 0]),
dense_shape=np.array([3, 1])),
sparse_tensor.SparseTensorValue(
indices=np.array([[0, 0], [1, 1], [2, 2]]),
values=np.array([1, 2, 3]),
dense_shape=np.array([3, 3])))
expected = [
(sparse_tensor.SparseTensorValue(
indices=np.array([[0]]),
values=np.array([0]),
dense_shape=np.array([1])),
sparse_tensor.SparseTensorValue(
indices=np.array([[0]]),
values=np.array([1]),
dense_shape=np.array([3]))),
(sparse_tensor.SparseTensorValue(
indices=np.array([[0]]),
values=np.array([0]),
dense_shape=np.array([1])),
sparse_tensor.SparseTensorValue(
indices=np.array([[1]]),
values=np.array([2]),
dense_shape=np.array([3]))),
(sparse_tensor.SparseTensorValue(
indices=np.array([[0]]),
values=np.array([0]),
dense_shape=np.array([1])),
sparse_tensor.SparseTensorValue(
indices=np.array([[2]]),
values=np.array([3]),
dense_shape=np.array([3]))),
]
for i, result in enumerate(
datasets.Iterator(Dataset.from_tensor_slices(components))):
self.assertSparseValuesEqual(expected[i][0], result[0])
self.assertSparseValuesEqual(expected[i][1], result[1])