tf.data.TextLineDataset

tf.data.TextLineDataset(
    filenames, compression_type=None, buffer_size=None, num_parallel_reads=None
)

apply(
    transformation_func
)

dataset = tf.data.Dataset.range(100)
def dataset_fn(ds):
  return ds.filter(lambda x: x < 5)
dataset = dataset.apply(dataset_fn)
list(dataset.as_numpy_iterator())
[0, 1, 2, 3, 4]

as_numpy_iterator()

dataset = tf.data.Dataset.from_tensor_slices([1, 2, 3])
for element in dataset:
  print(element)
tf.Tensor(1, shape=(), dtype=int32)
tf.Tensor(2, shape=(), dtype=int32)
tf.Tensor(3, shape=(), dtype=int32)

dataset = tf.data.Dataset.from_tensor_slices([1, 2, 3])
for element in dataset.as_numpy_iterator():
  print(element)
1
2
3

dataset = tf.data.Dataset.from_tensor_slices([1, 2, 3])
print(list(dataset.as_numpy_iterator()))
[1, 2, 3]

dataset = tf.data.Dataset.from_tensor_slices({'a': ([1, 2], [3, 4]),
                                              'b': [5, 6]})
list(dataset.as_numpy_iterator()) == [{'a': (1, 3), 'b': 5},
                                      {'a': (2, 4), 'b': 6}]
True

batch(
    batch_size, drop_remainder=False
)

dataset = tf.data.Dataset.range(8)
dataset = dataset.batch(3)
list(dataset.as_numpy_iterator())
[array([0, 1, 2]), array([3, 4, 5]), array([6, 7])]

dataset = tf.data.Dataset.range(8)
dataset = dataset.batch(3, drop_remainder=True)
list(dataset.as_numpy_iterator())
[array([0, 1, 2]), array([3, 4, 5])]

cache(
    filename=''
)

dataset = tf.data.Dataset.range(5)
dataset = dataset.map(lambda x: x**2)
dataset = dataset.cache()
# The first time reading through the data will generate the data using
# `range` and `map`.
list(dataset.as_numpy_iterator())
[0, 1, 4, 9, 16]
# Subsequent iterations read from the cache.
list(dataset.as_numpy_iterator())
[0, 1, 4, 9, 16]

dataset = tf.data.Dataset.range(5)
dataset = dataset.cache("/path/to/file)  # doctest: +SKIP
list(dataset.as_numpy_iterator())  # doctest: +SKIP
[0, 1, 2, 3, 4]
dataset = tf.data.Dataset.range(10)
dataset = dataset.cache("/path/to/file")  # Same file! # doctest: +SKIP
list(dataset.as_numpy_iterator())  # doctest: +SKIP
[0, 1, 2, 3, 4]

concatenate(
    dataset
)

a = tf.data.Dataset.range(1, 4)  # ==> [ 1, 2, 3 ]
b = tf.data.Dataset.range(4, 8)  # ==> [ 4, 5, 6, 7 ]
ds = a.concatenate(b)
list(ds.as_numpy_iterator())
[1, 2, 3, 4, 5, 6, 7]
# The input dataset and dataset to be concatenated should have the same
# nested structures and output types.
c = tf.data.Dataset.zip((a, b))
a.concatenate(c)
Traceback (most recent call last):
TypeError: Two datasets to concatenate have different types
<dtype: 'int64'> and (tf.int64, tf.int64)
d = tf.data.Dataset.from_tensor_slices(["a", "b", "c"])
a.concatenate(d)
Traceback (most recent call last):
TypeError: Two datasets to concatenate have different types
<dtype: 'int64'> and <dtype: 'string'>

enumerate(
    start=0
)

dataset = tf.data.Dataset.from_tensor_slices([1, 2, 3])
dataset = dataset.enumerate(start=5)
for element in dataset.as_numpy_iterator():
  print(element)
(5, 1)
(6, 2)
(7, 3)

# The nested structure of the input dataset determines the structure of
# elements in the resulting dataset.
dataset = tf.data.Dataset.from_tensor_slices([(7, 8), (9, 10)])
dataset = dataset.enumerate()
for element in dataset.as_numpy_iterator():
  print(element)
(0, array([7, 8], dtype=int32))
(1, array([ 9, 10], dtype=int32))

filter(
    predicate
)

dataset = tf.data.Dataset.from_tensor_slices([1, 2, 3])
dataset = dataset.filter(lambda x: x < 3)
list(dataset.as_numpy_iterator())
[1, 2]
# `tf.math.equal(x, y)` is required for equality comparison
def filter_fn(x):
  return tf.math.equal(x, 1)
dataset = dataset.filter(filter_fn)
list(dataset.as_numpy_iterator())
[1]

flat_map(
    map_func
)

dataset = Dataset.from_tensor_slices([[1, 2, 3], [4, 5, 6], [7, 8, 9]])
dataset = dataset.flat_map(lambda x: Dataset.from_tensor_slices(x))
list(dataset.as_numpy_iterator())
[1, 2, 3, 4, 5, 6, 7, 8, 9]

@staticmethod
from_generator(
    generator, output_types, output_shapes=None, args=None
)

import itertools

def gen():
  for i in itertools.count(1):
    yield (i, [1] * i)

dataset = tf.data.Dataset.from_generator(
     gen,
     (tf.int64, tf.int64),
     (tf.TensorShape([]), tf.TensorShape([None])))

list(dataset.take(3).as_numpy_iterator())
[(1, array([1])), (2, array([1, 1])), (3, array([1, 1, 1]))]

@staticmethod
from_tensor_slices(
    tensors
)

# Slicing a 1D tensor produces scalar tensor elements.
dataset = tf.data.Dataset.from_tensor_slices([1, 2, 3])
list(dataset.as_numpy_iterator())
[1, 2, 3]

# Slicing a 2D tensor produces 1D tensor elements.
dataset = tf.data.Dataset.from_tensor_slices([[1, 2], [3, 4]])
list(dataset.as_numpy_iterator())
[array([1, 2], dtype=int32), array([3, 4], dtype=int32)]

# Slicing a tuple of 1D tensors produces tuple elements containing
# scalar tensors.
dataset = tf.data.Dataset.from_tensor_slices(([1, 2], [3, 4], [5, 6]))
list(dataset.as_numpy_iterator())
[(1, 3, 5), (2, 4, 6)]

# Dictionary structure is also preserved.
dataset = tf.data.Dataset.from_tensor_slices({"a": [1, 2], "b": [3, 4]})
list(dataset.as_numpy_iterator()) == [{'a': 1, 'b': 3},
                                      {'a': 2, 'b': 4}]
True

# Two tensors can be combined into one Dataset object.
features = tf.constant([[1, 3], [2, 1], [3, 3]]) # ==> 3x2 tensor
labels = tf.constant(['A', 'B', 'A']) # ==> 3x1 tensor
dataset = Dataset.from_tensor_slices((features, labels))
# Both the features and the labels tensors can be converted
# to a Dataset object separately and combined after.
features_dataset = Dataset.from_tensor_slices(features)
labels_dataset = Dataset.from_tensor_slices(labels)
dataset = Dataset.zip((features_dataset, labels_dataset))
# A batched feature and label set can be converted to a Dataset
# in similar fashion.
batched_features = tf.constant([[[1, 3], [2, 3]],
                                [[2, 1], [1, 2]],
                                [[3, 3], [3, 2]]], shape=(3, 2, 2))
batched_labels = tf.constant([['A', 'A'],
                              ['B', 'B'],
                              ['A', 'B']], shape=(3, 2, 1))
dataset = Dataset.from_tensor_slices((batched_features, batched_labels))
for element in dataset.as_numpy_iterator():
  print(element)
(array([[1, 3],
       [2, 3]], dtype=int32), array([[b'A'],
       [b'A']], dtype=object))
(array([[2, 1],
       [1, 2]], dtype=int32), array([[b'B'],
       [b'B']], dtype=object))
(array([[3, 3],
       [3, 2]], dtype=int32), array([[b'A'],
       [b'B']], dtype=object))

@staticmethod
from_tensors(
    tensors
)

dataset = tf.data.Dataset.from_tensors([1, 2, 3])
list(dataset.as_numpy_iterator())
[array([1, 2, 3], dtype=int32)]
dataset = tf.data.Dataset.from_tensors(([1, 2, 3], 'A'))
list(dataset.as_numpy_iterator())
[(array([1, 2, 3], dtype=int32), b'A')]

interleave(
    map_func, cycle_length=-1, block_length=1, num_parallel_calls=None
)

# Preprocess 4 files concurrently, and interleave blocks of 16 records
# from each file.
filenames = ["/var/data/file1.txt", "/var/data/file2.txt",
             "/var/data/file3.txt", "/var/data/file4.txt"]
dataset = tf.data.Dataset.from_tensor_slices(filenames)
def parse_fn(filename):
  return tf.data.Dataset.range(10)
dataset = dataset.interleave(lambda x:
    tf.data.TextLineDataset(x).map(parse_fn, num_parallel_calls=1),
    cycle_length=4, block_length=16)

dataset = Dataset.range(1, 6)  # ==> [ 1, 2, 3, 4, 5 ]
# NOTE: New lines indicate "block" boundaries.
dataset = dataset.interleave(
    lambda x: Dataset.from_tensors(x).repeat(6),
    cycle_length=2, block_length=4)
list(dataset.as_numpy_iterator())
[1, 1, 1, 1, 2, 2, 2, 2, 1, 1, 2, 2, 3, 3, 3, 3, 4, 4, 4, 4, 3, 3, 4, 4, 5, 5, 5, 5, 5, 5]

@staticmethod
list_files(
    file_pattern, shuffle=None, seed=None
)

map(
    map_func, num_parallel_calls=None
)

dataset = Dataset.range(1, 6)  # ==> [ 1, 2, 3, 4, 5 ]
dataset = dataset.map(lambda x: x + 1)
list(dataset.as_numpy_iterator())
[2, 3, 4, 5, 6]

dataset = Dataset.range(5)
# `map_func` takes a single argument of type `tf.Tensor` with the same
# shape and dtype.
result = dataset.map(lambda x: x + 1)

# Each element is a tuple containing two `tf.Tensor` objects.
elements = [(1, "foo"), (2, "bar"), (3, "baz)")]
dataset = tf.data.Dataset.from_generator(
    lambda: elements, (tf.int32, tf.string))
# `map_func` takes two arguments of type `tf.Tensor`. This function
# projects out just the first component.
result = dataset.map(lambda x_int, y_str: x_int)
list(result.as_numpy_iterator())
[1, 2, 3]

# Each element is a dictionary mapping strings to `tf.Tensor` objects.
elements =  ([{"a": 1, "b": "foo"},
              {"a": 2, "b": "bar"},
              {"a": 3, "b": "baz"}])
dataset = tf.data.Dataset.from_generator(
    lambda: elements, {"a": tf.int32, "b": tf.string})
# `map_func` takes a single argument of type `dict` with the same keys
# as the elements.
result = dataset.map(lambda d: str(d["a"]) + d["b"])

dataset = tf.data.Dataset.range(3)
# `map_func` returns two `tf.Tensor` objects.
def g(x):
  return tf.constant(37.0), tf.constant(["Foo", "Bar", "Baz"])
result = dataset.map(g)
result.element_spec
(TensorSpec(shape=(), dtype=tf.float32, name=None), TensorSpec(shape=(3,), dtype=tf.string, name=None))
# Python primitives, lists, and NumPy arrays are implicitly converted to
# `tf.Tensor`.
def h(x):
  return 37.0, ["Foo", "Bar"], np.array([1.0, 2.0], dtype=np.float64)
result = dataset.map(h)
result.element_spec
(TensorSpec(shape=(), dtype=tf.float32, name=None), TensorSpec(shape=(2,), dtype=tf.string, name=None), TensorSpec(shape=(2,), dtype=tf.float64, name=None))
# `map_func` can return nested structures.
def i(x):
  return (37.0, [42, 16]), "foo"
result = dataset.map(i)
result.element_spec
((TensorSpec(shape=(), dtype=tf.float32, name=None),
  TensorSpec(shape=(2,), dtype=tf.int32, name=None)),
 TensorSpec(shape=(), dtype=tf.string, name=None))

d = tf.data.Dataset.from_tensor_slices(['hello', 'world'])
# transform a string tensor to upper case string using a Python function
def upper_case_fn(t: tf.Tensor):
  return t.numpy().decode('utf-8').upper()
d = d.map(lambda x: tf.py_function(func=upper_case_fn,
          inp=[x], Tout=tf.string))
list(d.as_numpy_iterator())
[b'HELLO', b'WORLD']

options()

padded_batch(
    batch_size, padded_shapes, padding_values=None, drop_remainder=False
)

elements = [[1, 2],
            [3, 4, 5],
            [6, 7],
            [8]]
A = tf.data.Dataset.from_generator(lambda: iter(elements), tf.int32)
# Pad to the smallest per-batch size that fits all elements.
B = A.padded_batch(2, padded_shapes=[None])
for element in B.as_numpy_iterator():
  print(element)
[[1 2 0]
 [3 4 5]]
[[6 7]
 [8 0]]
# Pad to a fixed size.
C = A.padded_batch(2, padded_shapes=3)
for element in C.as_numpy_iterator():
  print(element)
[[1 2 0]
 [3 4 5]]
[[6 7 0]
 [8 0 0]]
# Pad with a custom value.
D = A.padded_batch(2, padded_shapes=3, padding_values=-1)
for element in D.as_numpy_iterator():
  print(element)
[[ 1  2 -1]
 [ 3  4  5]]
[[ 6  7 -1]
 [ 8 -1 -1]]
# Components of nested elements can be padded independently.
elements = [([1, 2, 3], [10]),
            ([4, 5], [11, 12])]
dataset = tf.data.Dataset.from_generator(
    lambda: iter(elements), (tf.int32, tf.int32))
# Pad the first component of the tuple to length 4, and the second
# component to the smallest size that fits.
dataset = dataset.padded_batch(2,
    padded_shapes=([4], [None]),
    padding_values=(-1, 100))
list(dataset.as_numpy_iterator())
[(array([[ 1,  2,  3, -1], [ 4,  5, -1, -1]], dtype=int32),
  array([[ 10, 100], [ 11,  12]], dtype=int32))]

prefetch(
    buffer_size
)

dataset = tf.data.Dataset.range(3)
dataset = dataset.prefetch(2)
list(dataset.as_numpy_iterator())
[0, 1, 2]

@staticmethod
range(
    *args
)

list(Dataset.range(5).as_numpy_iterator())
[0, 1, 2, 3, 4]
list(Dataset.range(2, 5).as_numpy_iterator())
[2, 3, 4]
list(Dataset.range(1, 5, 2).as_numpy_iterator())
[1, 3]
list(Dataset.range(1, 5, -2).as_numpy_iterator())
[]
list(Dataset.range(5, 1).as_numpy_iterator())
[]
list(Dataset.range(5, 1, -2).as_numpy_iterator())
[5, 3]

reduce(
    initial_state, reduce_func
)

tf.data.Dataset.range(5).reduce(np.int64(0), lambda x, _: x + 1).numpy()
5
tf.data.Dataset.range(5).reduce(np.int64(0), lambda x, y: x + y).numpy()
10

repeat(
    count=None
)

dataset = tf.data.Dataset.from_tensor_slices([1, 2, 3])
dataset = dataset.repeat(3)
list(dataset.as_numpy_iterator())
[1, 2, 3, 1, 2, 3, 1, 2, 3]

shard(
    num_shards, index
)

A = tf.data.Dataset.range(10)
B = A.shard(num_shards=3, index=0)
list(B.as_numpy_iterator())
[0, 3, 6, 9]
C = A.shard(num_shards=3, index=1)
list(C.as_numpy_iterator())
[1, 4, 7]
D = A.shard(num_shards=3, index=2)
list(D.as_numpy_iterator())
[2, 5, 8]

d = tf.data.TFRecordDataset(input_file)
d = d.shard(num_workers, worker_index)
d = d.repeat(num_epochs)
d = d.shuffle(shuffle_buffer_size)
d = d.map(parser_fn, num_parallel_calls=num_map_threads)

d = Dataset.list_files(pattern)
d = d.shard(num_workers, worker_index)
d = d.repeat(num_epochs)
d = d.shuffle(shuffle_buffer_size)
d = d.interleave(tf.data.TFRecordDataset,
                 cycle_length=num_readers, block_length=1)
d = d.map(parser_fn, num_parallel_calls=num_map_threads)

shuffle(
    buffer_size, seed=None, reshuffle_each_iteration=None
)

dataset = tf.data.Dataset.range(3)
dataset = dataset.shuffle(3, reshuffle_each_iteration=True)
dataset = dataset.repeat(2)  # doctest: +SKIP
[1, 0, 2, 1, 2, 0]

dataset = tf.data.Dataset.range(3)
dataset = dataset.shuffle(3, reshuffle_each_iteration=False)
dataset = dataset.repeat(2)  # doctest: +SKIP
[1, 0, 2, 1, 0, 2]

dataset = tf.data.Dataset.range(3)
dataset = dataset.shuffle(3, reshuffle_each_iteration=True)
list(dataset.as_numpy_iterator())  # doctest: +SKIP
[1, 0, 2]
list(dataset.as_numpy_iterator())  # doctest: +SKIP
[1, 2, 0]

dataset = tf.data.Dataset.range(3)
dataset = dataset.shuffle(3, reshuffle_each_iteration=False)
list(dataset.as_numpy_iterator())  # doctest: +SKIP
[1, 0, 2]
list(dataset.as_numpy_iterator())  # doctest: +SKIP
[1, 0, 2]

skip(
    count
)

dataset = tf.data.Dataset.range(10)
dataset = dataset.skip(7)
list(dataset.as_numpy_iterator())
[7, 8, 9]

take(
    count
)

dataset = tf.data.Dataset.range(10)
dataset = dataset.take(3)
list(dataset.as_numpy_iterator())
[0, 1, 2]

unbatch()

elements = [ [1, 2, 3], [1, 2], [1, 2, 3, 4] ]
dataset = tf.data.Dataset.from_generator(lambda: elements, tf.int64)
dataset = dataset.unbatch()
list(dataset.as_numpy_iterator())
[1, 2, 3, 1, 2, 1, 2, 3, 4]

window(
    size, shift=None, stride=1, drop_remainder=False
)

dataset = tf.data.Dataset.range(7).window(2)
for window in dataset:
  print(list(window.as_numpy_iterator()))
[0, 1]
[2, 3]
[4, 5]
[6]
dataset = tf.data.Dataset.range(7).window(3, 2, 1, True)
for window in dataset:
  print(list(window.as_numpy_iterator()))
[0, 1, 2]
[2, 3, 4]
[4, 5, 6]
dataset = tf.data.Dataset.range(7).window(3, 1, 2, True)
for window in dataset:
  print(list(window.as_numpy_iterator()))
[0, 2, 4]
[1, 3, 5]
[2, 4, 6]

nested = ([1, 2, 3, 4], [5, 6, 7, 8])
dataset = tf.data.Dataset.from_tensor_slices(nested).window(2)
for window in dataset:
  def to_numpy(ds):
    return list(ds.as_numpy_iterator())
  print(tuple(to_numpy(component) for component in window))
([1, 2], [5, 6])
([3, 4], [7, 8])

dataset = tf.data.Dataset.from_tensor_slices({'a': [1, 2, 3, 4]})
dataset = dataset.window(2)
for window in dataset:
  def to_numpy(ds):
    return list(ds.as_numpy_iterator())
  print({'a': to_numpy(window['a'])})
{'a': [1, 2]}
{'a': [3, 4]}

with_options(
    options
)

ds = tf.data.Dataset.range(5)
ds = ds.interleave(lambda x: tf.data.Dataset.range(5),
                   cycle_length=3,
                   num_parallel_calls=3)
options = tf.data.Options()
# This will make the interleave order non-deterministic.
options.experimental_deterministic = False
ds = ds.with_options(options)

@staticmethod
zip(
    datasets
)

# The nested structure of the `datasets` argument determines the
# structure of elements in the resulting dataset.
a = tf.data.Dataset.range(1, 4)  # ==> [ 1, 2, 3 ]
b = tf.data.Dataset.range(4, 7)  # ==> [ 4, 5, 6 ]
ds = tf.data.Dataset.zip((a, b))
list(ds.as_numpy_iterator())
[(1, 4), (2, 5), (3, 6)]
ds = tf.data.Dataset.zip((b, a))
list(ds.as_numpy_iterator())
[(4, 1), (5, 2), (6, 3)]

# The `datasets` argument may contain an arbitrary number of datasets.
c = tf.data.Dataset.range(7, 13).batch(2)  # ==> [ [7, 8],
                                           #       [9, 10],
                                           #       [11, 12] ]
ds = tf.data.Dataset.zip((a, b, c))
for element in ds.as_numpy_iterator():
  print(element)
(1, 4, array([7, 8]))
(2, 5, array([ 9, 10]))
(3, 6, array([11, 12]))

# The number of elements in the resulting dataset is the same as
# the size of the smallest dataset in `datasets`.
d = tf.data.Dataset.range(13, 15)  # ==> [ 13, 14 ]
ds = tf.data.Dataset.zip((a, d))
list(ds.as_numpy_iterator())
[(1, 13), (2, 14)]

__iter__()