tf.data.TFRecordDataset

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

import tempfile
example_path = os.path.join(tempfile.gettempdir(), "example.tfrecords")
np.random.seed(0)

# Write the records to a file.
with tf.io.TFRecordWriter(example_path) as file_writer:
  for _ in range(4):
    x, y = np.random.random(), np.random.random()

    record_bytes = tf.train.Example(features=tf.train.Features(feature={
        "x": tf.train.Feature(float_list=tf.train.FloatList(value=[x])),
        "y": tf.train.Feature(float_list=tf.train.FloatList(value=[y])),
    })).SerializeToString()
    file_writer.write(record_bytes)

# Read the data back out.
def decode_fn(record_bytes):
  return tf.io.parse_single_example(
      # Data
      record_bytes,

      # Schema
      {"x": tf.io.FixedLenFeature([], dtype=tf.float32),
       "y": tf.io.FixedLenFeature([], dtype=tf.float32)}
  )

for batch in tf.data.TFRecordDataset([example_path]).map(decode_fn):
  print("x = {x:.4f},  y = {y:.4f}".format(**batch))
x = 0.5488,  y = 0.7152
x = 0.6028,  y = 0.5449
x = 0.4237,  y = 0.6459
x = 0.4376,  y = 0.8918

apply(
    transformation_func
) -> 'DatasetV2'

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,
    num_parallel_calls=None,
    deterministic=None,
    name=None
) -> 'DatasetV2'

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])]

bucket_by_sequence_length(
    element_length_func,
    bucket_boundaries,
    bucket_batch_sizes,
    padded_shapes=None,
    padding_values=None,
    pad_to_bucket_boundary=False,
    no_padding=False,
    drop_remainder=False,
    name=None
) -> 'DatasetV2'

elements = [
  [0], [1, 2, 3, 4], [5, 6, 7],
  [7, 8, 9, 10, 11], [13, 14, 15, 16, 19, 20], [21, 22]]
dataset = tf.data.Dataset.from_generator(
    lambda: elements, tf.int64, output_shapes=[None])
dataset = dataset.bucket_by_sequence_length(
        element_length_func=lambda elem: tf.shape(elem)[0],
        bucket_boundaries=[3, 5],
        bucket_batch_sizes=[2, 2, 2])
for elem in dataset.as_numpy_iterator():
  print(elem)
[[1 2 3 4]
[5 6 7 0]]
[[ 7  8  9 10 11  0]
[13 14 15 16 19 20]]
[[ 0  0]
[21 22]]

cache(
    filename='', name=None
) -> 'DatasetV2'

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

cardinality()

dataset = tf.data.Dataset.range(42)
print(dataset.cardinality().numpy())
42
dataset = dataset.repeat()
cardinality = dataset.cardinality()
print((cardinality == tf.data.INFINITE_CARDINALITY).numpy())
True
dataset = dataset.filter(lambda x: True)
cardinality = dataset.cardinality()
print((cardinality == tf.data.UNKNOWN_CARDINALITY).numpy())
True

@staticmethod
choose_from_datasets(
    datasets, choice_dataset, stop_on_empty_dataset=True
) -> 'DatasetV2'

datasets = [tf.data.Dataset.from_tensors("foo").repeat(),
            tf.data.Dataset.from_tensors("bar").repeat(),
            tf.data.Dataset.from_tensors("baz").repeat()]

# Define a dataset containing `[0, 1, 2, 0, 1, 2, 0, 1, 2]`.
choice_dataset = tf.data.Dataset.range(3).repeat(3)

result = tf.data.Dataset.choose_from_datasets(datasets, choice_dataset)

"foo", "bar", "baz", "foo", "bar", "baz", "foo", "bar", "baz"

concatenate(
    dataset, name=None
) -> 'DatasetV2'

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
# compatible element specs.
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'>

@staticmethod
counter(
    start=0,
    step=1,
    dtype=tf.dtypes.int64,
    name=None
) -> 'DatasetV2'

dataset = tf.data.experimental.Counter().take(5)
list(dataset.as_numpy_iterator())
[0, 1, 2, 3, 4]
dataset.element_spec
TensorSpec(shape=(), dtype=tf.int64, name=None)
dataset = tf.data.experimental.Counter(dtype=tf.int32)
dataset.element_spec
TensorSpec(shape=(), dtype=tf.int32, name=None)
dataset = tf.data.experimental.Counter(start=2).take(5)
list(dataset.as_numpy_iterator())
[2, 3, 4, 5, 6]
dataset = tf.data.experimental.Counter(start=2, step=5).take(5)
list(dataset.as_numpy_iterator())
[2, 7, 12, 17, 22]
dataset = tf.data.experimental.Counter(start=10, step=-1).take(5)
list(dataset.as_numpy_iterator())
[10, 9, 8, 7, 6]

enumerate(
    start=0, name=None
) -> 'DatasetV2'

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, name=None
) -> 'DatasetV2'

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]

fingerprint()

flat_map(
    map_func, name=None
) -> 'DatasetV2'

def flat_map(
  self: Dataset[T],
  map_func: Callable[[T], Dataset[S]]
) -> Dataset[S]

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

@staticmethod
from_generator(
    generator,
    output_types=None,
    output_shapes=None,
    args=None,
    output_signature=None,
    name=None
) -> 'DatasetV2'

def gen():
  ragged_tensor = tf.ragged.constant([[1, 2], [3]])
  yield 42, ragged_tensor

dataset = tf.data.Dataset.from_generator(
     gen,
     output_signature=(
         tf.TensorSpec(shape=(), dtype=tf.int32),
         tf.RaggedTensorSpec(shape=(2, None), dtype=tf.int32)))

list(dataset.take(1))
[(<tf.Tensor: shape=(), dtype=int32, numpy=42>,
<tf.RaggedTensor [[1, 2], [3]]>)]

@staticmethod
from_tensor_slices(
    tensors, name=None
) -> 'DatasetV2'

# 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, name=None
) -> 'DatasetV2'

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')]

# You can use `from_tensors` to produce a dataset which repeats
# the same example many times.
example = tf.constant([1,2,3])
dataset = tf.data.Dataset.from_tensors(example).repeat(2)
list(dataset.as_numpy_iterator())
[array([1, 2, 3], dtype=int32), array([1, 2, 3], dtype=int32)]

get_single_element(
    name=None
)

def preprocessing_fn(raw_feature):
  # ... the raw_feature is preprocessed as per the use-case
  return feature

raw_features = ...  # input batch of BATCH_SIZE elements.
dataset = (tf.data.Dataset.from_tensor_slices(raw_features)
          .map(preprocessing_fn, num_parallel_calls=BATCH_SIZE)
          .batch(BATCH_SIZE))

processed_features = dataset.get_single_element()

model = ... # A pre-built or custom model

class PreprocessingModel(tf.keras.Model):
  def __init__(self, model):
    super().__init__(self)
    self.model = model

  @tf.function(input_signature=[...])
  def serving_fn(self, data):
    ds = tf.data.Dataset.from_tensor_slices(data)
    ds = ds.map(preprocessing_fn, num_parallel_calls=BATCH_SIZE)
    ds = ds.batch(batch_size=BATCH_SIZE)
    return tf.argmax(self.model(ds.get_single_element()), axis=-1)

preprocessing_model = PreprocessingModel(model)
your_exported_model_dir = ... # save the model to this path.
tf.saved_model.save(preprocessing_model, your_exported_model_dir,
              signatures={'serving_default': preprocessing_model.serving_fn}
              )

group_by_window(
    key_func, reduce_func, window_size=None, window_size_func=None, name=None
) -> 'DatasetV2'

dataset = tf.data.Dataset.range(10)
window_size = 5
key_func = lambda x: x%2
reduce_func = lambda key, dataset: dataset.batch(window_size)
dataset = dataset.group_by_window(
          key_func=key_func,
          reduce_func=reduce_func,
          window_size=window_size)
for elem in dataset.as_numpy_iterator():
  print(elem)
[0 2 4 6 8]
[1 3 5 7 9]

ignore_errors(
    log_warning=False, name=None
) -> 'DatasetV2'

dataset = tf.data.Dataset.from_tensor_slices([1., 2., 0., 4.])
dataset = dataset.map(lambda x: tf.debugging.check_numerics(1. / x, ""))
list(dataset.as_numpy_iterator())
Traceback (most recent call last):

InvalidArgumentError: ... Tensor had Inf values
dataset = dataset.ignore_errors()
list(dataset.as_numpy_iterator())
[1.0, 0.5, 0.25]

interleave(
    map_func,
    cycle_length=None,
    block_length=None,
    num_parallel_calls=None,
    deterministic=None,
    name=None
) -> 'DatasetV2'

def interleave(
  self: Dataset[T],
  map_func: Callable[[T], Dataset[S]]
) -> Dataset[S]

# 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]

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)
dataset = dataset.interleave(lambda x: tf.data.TFRecordDataset(x),
    cycle_length=4, num_parallel_calls=tf.data.AUTOTUNE,
    deterministic=False)

@staticmethod
list_files(
    file_pattern, shuffle=None, seed=None, name=None
) -> 'DatasetV2'

@staticmethod
load(
    path, element_spec=None, compression=None, reader_func=None
) -> 'DatasetV2'

import tempfile
path = os.path.join(tempfile.gettempdir(), "saved_data")
# Save a dataset
dataset = tf.data.Dataset.range(2)
tf.data.Dataset.save(dataset, path)
new_dataset = tf.data.Dataset.load(path)
for elem in new_dataset:
  print(elem)
tf.Tensor(0, shape=(), dtype=int64)
tf.Tensor(1, shape=(), dtype=int64)

def custom_reader_func(datasets):
  datasets = datasets.shuffle(NUM_SHARDS)
  return datasets.interleave(lambda x: x, num_parallel_calls=AUTOTUNE)

dataset = tf.data.Dataset.load(
    path="/path/to/data", ..., reader_func=custom_reader_func)

map(
    map_func, num_parallel_calls=None, deterministic=None, name=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']

d = tf.data.Dataset.from_tensor_slices(['hello', 'world'])
def upper_case_fn(t: np.ndarray):
  return t.decode('utf-8').upper()
d = d.map(lambda x: tf.numpy_function(func=upper_case_fn,
          inp=[x], Tout=tf.string))
list(d.as_numpy_iterator())
[b'HELLO', b'WORLD']

dataset = Dataset.range(1, 6)  # ==> [ 1, 2, 3, 4, 5 ]
dataset = dataset.map(lambda x: x + 1,
    num_parallel_calls=tf.data.AUTOTUNE,
    deterministic=False)

options()

padded_batch(
    batch_size,
    padded_shapes=None,
    padding_values=None,
    drop_remainder=False,
    name=None
) -> 'DatasetV2'

A = (tf.data.Dataset
     .range(1, 5, output_type=tf.int32)
     .map(lambda x: tf.fill([x], x)))
# Pad to the smallest per-batch size that fits all elements.
B = A.padded_batch(2)
for element in B.as_numpy_iterator():
  print(element)
[[1 0]
 [2 2]]
[[3 3 3 0]
 [4 4 4 4]]
# Pad to a fixed size.
C = A.padded_batch(2, padded_shapes=5)
for element in C.as_numpy_iterator():
  print(element)
[[1 0 0 0 0]
 [2 2 0 0 0]]
[[3 3 3 0 0]
 [4 4 4 4 0]]
# Pad with a custom value.
D = A.padded_batch(2, padded_shapes=5, padding_values=-1)
for element in D.as_numpy_iterator():
  print(element)
[[ 1 -1 -1 -1 -1]
 [ 2  2 -1 -1 -1]]
[[ 3  3  3 -1 -1]
 [ 4  4  4  4 -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))]
# Pad with a single value and multiple components.
E = tf.data.Dataset.zip((A, A)).padded_batch(2, padding_values=-1)
for element in E.as_numpy_iterator():
  print(element)
(array([[ 1, -1],
       [ 2,  2]], dtype=int32), array([[ 1, -1],
       [ 2,  2]], dtype=int32))
(array([[ 3,  3,  3, -1],
       [ 4,  4,  4,  4]], dtype=int32), array([[ 3,  3,  3, -1],
       [ 4,  4,  4,  4]], dtype=int32))

prefetch(
    buffer_size, name=None
) -> 'DatasetV2'

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

ragged_batch(
    batch_size,
    drop_remainder=False,
    row_splits_dtype=tf.dtypes.int64,
    name=None
) -> 'DatasetV2'

dataset = tf.data.Dataset.range(6)
dataset = dataset.map(lambda x: tf.range(x))
dataset.element_spec.shape
TensorShape([None])
dataset = dataset.ragged_batch(2)
for batch in dataset:
  print(batch)
<tf.RaggedTensor [[], [0]]>
<tf.RaggedTensor [[0, 1], [0, 1, 2]]>
<tf.RaggedTensor [[0, 1, 2, 3], [0, 1, 2, 3, 4]]>

@staticmethod
random(
    seed=None, rerandomize_each_iteration=None, name=None
) -> 'DatasetV2'

ds1 = tf.data.Dataset.random(seed=4).take(10)
ds2 = tf.data.Dataset.random(seed=4).take(10)
print(list(ds1.as_numpy_iterator())==list(ds2.as_numpy_iterator()))
True

ds3 = tf.data.Dataset.random(seed=4).take(10)
ds3_first_epoch = list(ds3.as_numpy_iterator())
ds3_second_epoch = list(ds3.as_numpy_iterator())
print(ds3_first_epoch == ds3_second_epoch)
True

ds4 = tf.data.Dataset.random(
    seed=4, rerandomize_each_iteration=True).take(10)
ds4_first_epoch = list(ds4.as_numpy_iterator())
ds4_second_epoch = list(ds4.as_numpy_iterator())
print(ds4_first_epoch == ds4_second_epoch)
False

@staticmethod
range(
    *args, **kwargs
) -> 'DatasetV2'

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]
list(Dataset.range(2, 5, output_type=tf.int32).as_numpy_iterator())
[2, 3, 4]
list(Dataset.range(1, 5, 2, output_type=tf.float32).as_numpy_iterator())
[1.0, 3.0]

rebatch(
    batch_size, drop_remainder=False, name=None
) -> 'DatasetV2'

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

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

ds = tf.data.Dataset.range(7)
ds = ds.batch(2)
ds = ds.rebatch(3, drop_remainder=True)
list(ds.as_numpy_iterator())
[array([0, 1, 2]), array([3, 4, 5])]

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

reduce(
    initial_state, reduce_func, name=None
)

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

rejection_resample(
    class_func, target_dist, initial_dist=None, seed=None, name=None
) -> 'DatasetV2'

initial_dist = [0.6, 0.4]
n = 1000
elems = np.random.choice(len(initial_dist), size=n, p=initial_dist)
dataset = tf.data.Dataset.from_tensor_slices(elems)
zero, one = np.bincount(list(dataset.as_numpy_iterator())) / n

target_dist = [0.5, 0.5]
dataset = dataset.rejection_resample(
   class_func=lambda x: x,
   target_dist=target_dist,
   initial_dist=initial_dist)
dataset = dataset.map(lambda class_func_result, data: data)
zero, one = np.bincount(list(dataset.as_numpy_iterator())) / n

repeat(
    count=None, name=None
) -> 'DatasetV2'

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]

@staticmethod
sample_from_datasets(
    datasets,
    weights=None,
    seed=None,
    stop_on_empty_dataset=False,
    rerandomize_each_iteration=None
) -> 'DatasetV2'

dataset1 = tf.data.Dataset.range(0, 3)
dataset2 = tf.data.Dataset.range(100, 103)

sample_dataset = tf.data.Dataset.sample_from_datasets(
    [dataset1, dataset2], weights=[0.5, 0.5])

print(list(sample_dataset.as_numpy_iterator()))
# [100, 0, 1, 101, 2, 102]

save(
    path, compression=None, shard_func=None, checkpoint_args=None
)

import tempfile
path = os.path.join(tempfile.gettempdir(), "saved_data")
# Save a dataset
dataset = tf.data.Dataset.range(2)
dataset.save(path)
new_dataset = tf.data.Dataset.load(path)
for elem in new_dataset:
  print(elem)
  tf.Tensor(0, shape=(), dtype=int64)
  tf.Tensor(1, shape=(), dtype=int64)
  

dataset = make_dataset()
def custom_shard_func(element):
  return np.int64(0)
dataset.save(
    path="/path/to/data", ..., shard_func=custom_shard_func)

dataset = tf.data.Dataset.range(100)
save_dir = "..."
checkpoint_prefix = "..."
step_counter = tf.Variable(0, trainable=False)
checkpoint_args = {
  "checkpoint_interval": 50,
  "step_counter": step_counter,
  "directory": checkpoint_prefix,
  "max_to_keep": 20,
}
dataset.save(dataset, save_dir, checkpoint_args=checkpoint_args)

scan(
    initial_state, scan_func, name=None
) -> 'DatasetV2'

dataset = tf.data.Dataset.range(10)
initial_state = tf.constant(0, dtype=tf.int64)
scan_func = lambda state, i: (state + i, state + i)
dataset = dataset.scan(initial_state=initial_state, scan_func=scan_func)
list(dataset.as_numpy_iterator())
[0, 1, 3, 6, 10, 15, 21, 28, 36, 45]

shard(
    num_shards, index, name=None
) -> 'DatasetV2'

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, shuffle=False)
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, name=None
) -> 'DatasetV2'

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

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

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

dataset = tf.data.Dataset.range(20)
dataset = dataset.shuffle(dataset.cardinality())
# [18, 4, 9, 2, 17, 8, 5, 10, 0, 6, 16, 3, 19, 7, 14, 11, 15, 13, 12, 1]

skip(
    count, name=None
) -> 'DatasetV2'

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

snapshot(
    path,
    compression='AUTO',
    reader_func=None,
    shard_func=None,
    name=None
) -> 'DatasetV2'

dataset = ...
dataset = dataset.enumerate()
dataset = dataset.snapshot("/path/to/snapshot/dir",
    shard_func=lambda x, y: x % NUM_SHARDS, ...)
dataset = dataset.map(lambda x, y: y)

def user_reader_func(datasets):
  # shuffle the datasets splits
  datasets = datasets.shuffle(NUM_CORES)
  # read datasets in parallel and interleave their elements
  return datasets.interleave(lambda x: x, num_parallel_calls=AUTOTUNE)

dataset = dataset.snapshot("/path/to/snapshot/dir",
    reader_func=user_reader_func)

sparse_batch(
    batch_size, row_shape, name=None
) -> 'DatasetV2'

# NOTE: The following examples use `{ ... }` to represent the
# contents of a dataset.
a = { ['a', 'b', 'c'], ['a', 'b'], ['a', 'b', 'c', 'd'] }

a.apply(tf.data.experimental.dense_to_sparse_batch(
    batch_size=2, row_shape=[6])) ==
{
    ([[0, 0], [0, 1], [0, 2], [1, 0], [1, 1]],  # indices
     ['a', 'b', 'c', 'a', 'b'],                 # values
     [2, 6]),                                   # dense_shape
    ([[0, 0], [0, 1], [0, 2], [0, 3]],
     ['a', 'b', 'c', 'd'],
     [1, 6])
}

take(
    count, name=None
) -> 'DatasetV2'

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

take_while(
    predicate, name=None
) -> 'DatasetV2'

dataset = tf.data.Dataset.range(10)
dataset = dataset.take_while(lambda x: x < 5)
list(dataset.as_numpy_iterator())
[0, 1, 2, 3, 4]

unbatch(
    name=None
) -> 'DatasetV2'

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]

unique(
    name=None
) -> 'DatasetV2'

dataset = tf.data.Dataset.from_tensor_slices([1, 37, 2, 37, 2, 1])
dataset = dataset.unique()
sorted(list(dataset.as_numpy_iterator()))
[1, 2, 37]

window(
    size, shift=None, stride=1, drop_remainder=False, name=None
) -> 'DatasetV2'

dataset = tf.data.Dataset.range(7).window(3)
for window in dataset:
  print(window)
<...Dataset element_spec=TensorSpec(shape=(), dtype=tf.int64, name=None)>
<...Dataset element_spec=TensorSpec(shape=(), dtype=tf.int64, name=None)>
<...Dataset element_spec=TensorSpec(shape=(), dtype=tf.int64, name=None)>

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, shift=1,
                                          drop_remainder=True)
for window in dataset:
  print(list(window.as_numpy_iterator()))
[0, 1, 2]
[1, 2, 3]
[2, 3, 4]
[3, 4, 5]
[4, 5, 6]

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

def window(
    self: Dataset[Nest[T]], ...
) -> Dataset[Nest[Dataset[T]]]

dataset = tf.data.Dataset.from_tensor_slices(([1, 2, 3, 4, 5],
                                              [6, 7, 8, 9, 10]))
dataset = dataset.window(2)
windows = next(iter(dataset))
windows
(<...Dataset element_spec=TensorSpec(shape=(), dtype=tf.int32, name=None)>,
 <...Dataset element_spec=TensorSpec(shape=(), dtype=tf.int32, name=None)>)

def to_numpy(ds):
  return list(ds.as_numpy_iterator())

for windows in dataset:
  print(to_numpy(windows[0]), to_numpy(windows[1]))
[1, 2] [6, 7]
[3, 4] [8, 9]
[5] [10]

dataset = tf.data.Dataset.from_tensor_slices({'a': [1, 2, 3],
                                              'b': [4, 5, 6],
                                              'c': [7, 8, 9]})
dataset = dataset.window(2)
def to_numpy(ds):
  return list(ds.as_numpy_iterator())

for windows in dataset:
  print(tf.nest.map_structure(to_numpy, windows))
{'a': [1, 2], 'b': [4, 5], 'c': [7, 8]}
{'a': [3], 'b': [6], 'c': [9]}

dataset = tf.data.Dataset.range(7).window(3, shift=1,
                                          drop_remainder=True)
batched = dataset.flat_map(lambda x:x.batch(3))
for batch in batched:
  print(batch.numpy())
[0 1 2]
[1 2 3]
[2 3 4]
[3 4 5]
[4 5 6]

with_options(
    options, name=None
) -> 'DatasetV2'

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.deterministic = False
ds = ds.with_options(options)

@staticmethod
zip(
    *args, datasets=None, name=None
) -> 'DatasetV2'

# The datasets or nested structure of datasets `*args` 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)]

__bool__()

__iter__() -> iterator_ops.OwnedIterator

__len__()

__nonzero__()