def _apply_transform(self, transform_input, **kwargs):
filename_queue = input_ops.string_input_producer(
self.work_units,
num_epochs=kwargs.get("num_epochs"),
shuffle=self.shuffle,
seed=self.seed)
reader_ops = []
for _ in range(self.num_threads):
reader = self._reader_cls(**self._reader_kwargs)
reader_ops.append(
reader.read_up_to(filename_queue, self.enqueue_size))
if self.shuffle:
dequeued = input_ops.shuffle_batch_join(
reader_ops,
self.batch_size,
capacity=self.queue_capacity,
min_after_dequeue=self.min_after_dequeue,
seed=self.seed,
enqueue_many=True,
shared_name=None,
name=None)
else:
dequeued = input_ops.batch_join(reader_ops,
self.batch_size,
capacity=self.queue_capacity,
enqueue_many=True,
dynamic_pad=False,
shared_name=None,
name=None)
# pylint: disable=not-callable
return self.return_type(*dequeued)
def _apply_transform(self, transform_input):
filename_queue = input_ops.string_input_producer(self.work_units,
num_epochs=self.num_epochs,
shuffle=self.shuffle,
seed=self.seed)
reader_ops = []
for _ in range(self.num_threads):
reader = self._reader_cls(**self._reader_kwargs)
reader_ops.append(reader.read_up_to(filename_queue, self.enqueue_size))
if self.shuffle:
dequeued = input_ops.shuffle_batch_join(
reader_ops,
self.batch_size,
capacity=self.queue_capacity,
min_after_dequeue=self.min_after_dequeue,
seed=self.seed,
enqueue_many=True,
shared_name=None,
name=None)
else:
dequeued = input_ops.batch_join(reader_ops,
self.batch_size,
capacity=self.queue_capacity,
enqueue_many=True,
dynamic_pad=False,
shared_name=None,
name=None)
# pylint: disable=not-callable
return self.return_type(*dequeued)
def read_keyed_batch_examples(
file_pattern, batch_size, reader,
randomize_input=True, num_epochs=None,
queue_capacity=10000, num_threads=1,
read_batch_size=1, parse_fn=None,
name=None):
"""Adds operations to read, queue, batch `Example` protos.
Given file pattern (or list of files), will setup a queue for file names,
read `Example` proto using provided `reader`, use batch queue to create
batches of examples of size `batch_size`.
All queue runners are added to the queue runners collection, and may be
started via `start_queue_runners`.
All ops are added to the default graph.
Use `parse_fn` if you need to do parsing / processing on single examples.
Args:
file_pattern: List of files or pattern of file paths containing
`Example` records. See `tf.gfile.Glob` for pattern rules.
batch_size: An int or scalar `Tensor` specifying the batch size to use.
reader: A function or class that returns an object with
`read` method, (filename tensor) -> (example tensor).
randomize_input: Whether the input should be randomized.
num_epochs: Integer specifying the number of times to read through the
dataset. If `None`, cycles through the dataset forever.
NOTE - If specified, creates a variable that must be initialized, so call
`tf.initialize_all_variables()` as shown in the tests.
queue_capacity: Capacity for input queue.
num_threads: The number of threads enqueuing examples.
read_batch_size: An int or scalar `Tensor` specifying the number of
records to read at once
parse_fn: Parsing function, takes `Example` Tensor returns parsed
representation. If `None`, no parsing is done.
name: Name of resulting op.
Returns:
String `Tensor` of batched `Example` proto. If `keep_keys` is True, then
returns tuple of string `Tensor`s, where first value is the key.
Raises:
ValueError: for invalid inputs.
"""
# Retrive files to read.
if isinstance(file_pattern, list):
file_names = file_pattern
if not file_names:
raise ValueError('No files given to dequeue_examples.')
else:
file_names = list(gfile.Glob(file_pattern))
if not file_names:
raise ValueError('No files match %s.' % file_pattern)
# Sort files so it will be deterministic for unit tests. They'll be shuffled
# in `string_input_producer` if `randomize_input` is enabled.
if not randomize_input:
file_names = sorted(file_names)
# Check input parameters are given and reasonable.
if (not queue_capacity) or (queue_capacity <= 0):
raise ValueError('Invalid queue_capacity %s.' % queue_capacity)
if (batch_size is None) or (
(not isinstance(batch_size, ops.Tensor)) and
(batch_size <= 0 or batch_size > queue_capacity)):
raise ValueError(
'Invalid batch_size %s, with queue_capacity %s.' %
(batch_size, queue_capacity))
if (read_batch_size is None) or (
(not isinstance(read_batch_size, ops.Tensor)) and
(read_batch_size <= 0)):
raise ValueError('Invalid read_batch_size %s.' % read_batch_size)
if (not num_threads) or (num_threads <= 0):
raise ValueError('Invalid num_threads %s.' % num_threads)
if (num_epochs is not None) and (num_epochs <= 0):
raise ValueError('Invalid num_epochs %s.' % num_epochs)
with ops.op_scope([file_pattern], name, 'read_batch_examples') as scope:
# Setup filename queue with shuffling.
with ops.name_scope('file_name_queue') as file_name_queue_scope:
file_name_queue = input_ops.string_input_producer(
constant_op.constant(file_names, name='input'),
shuffle=randomize_input, num_epochs=num_epochs,
name=file_name_queue_scope)
# Create readers, one per thread and set them to read from filename queue.
with ops.name_scope('read'):
example_list = []
for _ in range(num_threads):
if read_batch_size > 1:
keys, examples_proto = reader().read_up_to(file_name_queue,
read_batch_size)
else:
keys, examples_proto = reader().read(file_name_queue)
if parse_fn:
parsed_examples = parse_fn(examples_proto)
# Map keys into example map because batch_join doesn't support
# tuple of Tensor + dict.
if isinstance(parsed_examples, dict):
parsed_examples[KEY_FEATURE_NAME] = keys
example_list.append(parsed_examples)
else:
example_list.append((keys, parsed_examples))
else:
example_list.append((keys, examples_proto))
enqueue_many = read_batch_size > 1
# Setup batching queue given list of read example tensors.
if randomize_input:
if isinstance(batch_size, ops.Tensor):
min_after_dequeue = int(queue_capacity * 0.4)
else:
min_after_dequeue = max(queue_capacity - (3 * batch_size), batch_size)
queued_examples_with_keys = input_ops.shuffle_batch_join(
example_list, batch_size, capacity=queue_capacity,
min_after_dequeue=min_after_dequeue,
enqueue_many=enqueue_many, name=scope)
else:
queued_examples_with_keys = input_ops.batch_join(
example_list, batch_size, capacity=queue_capacity,
enqueue_many=enqueue_many, name=scope)
if parse_fn and isinstance(queued_examples_with_keys, dict):
queued_keys = queued_examples_with_keys.pop(KEY_FEATURE_NAME)
return queued_keys, queued_examples_with_keys
return queued_examples_with_keys
def _read_keyed_batch_examples_helper(file_pattern,
batch_size,
reader,
randomize_input=True,
num_epochs=None,
queue_capacity=10000,
num_threads=1,
read_batch_size=1,
parse_fn=None,
setup_shared_queue=False,
name=None):
"""Adds operations to read, queue, batch `Example` protos.
Args:
file_pattern: List of files or pattern of file paths containing
`Example` records. See `tf.gfile.Glob` for pattern rules.
batch_size: An int or scalar `Tensor` specifying the batch size to use.
reader: A function or class that returns an object with
`read` method, (filename tensor) -> (example tensor).
randomize_input: Whether the input should be randomized.
num_epochs: Integer specifying the number of times to read through the
dataset. If `None`, cycles through the dataset forever.
NOTE - If specified, creates a variable that must be initialized, so call
`tf.initialize_all_variables()` as shown in the tests.
queue_capacity: Capacity for input queue.
num_threads: The number of threads enqueuing examples.
read_batch_size: An int or scalar `Tensor` specifying the number of
records to read at once
parse_fn: Parsing function, takes `Example` Tensor returns parsed
representation. If `None`, no parsing is done.
setup_shared_queue: Whether to set up a shared queue for file names.
name: Name of resulting op.
Returns:
Returns tuple of:
- `Tensor` of string keys.
- String `Tensor` of batched `Example` proto.
Raises:
ValueError: for invalid inputs.
"""
# Retrieve files to read.
file_names = _get_file_names(file_pattern, randomize_input)
# Check input parameters are given and reasonable.
if (not queue_capacity) or (queue_capacity <= 0):
raise ValueError('Invalid queue_capacity %s.' % queue_capacity)
if (batch_size is None) or (
(not isinstance(batch_size, ops.Tensor)) and
(batch_size <= 0 or batch_size > queue_capacity)):
raise ValueError(
'Invalid batch_size %s, with queue_capacity %s.' %
(batch_size, queue_capacity))
if (read_batch_size is None) or (
(not isinstance(read_batch_size, ops.Tensor)) and
(read_batch_size <= 0)):
raise ValueError('Invalid read_batch_size %s.' % read_batch_size)
if (not num_threads) or (num_threads <= 0):
raise ValueError('Invalid num_threads %s.' % num_threads)
if (num_epochs is not None) and (num_epochs <= 0):
raise ValueError('Invalid num_epochs %s.' % num_epochs)
with ops.name_scope(name, 'read_batch_examples', [file_pattern]) as scope:
with ops.name_scope('file_name_queue') as file_name_queue_scope:
if setup_shared_queue:
shared_file_name_queue = _get_shared_file_name_queue(
file_names, randomize_input, num_epochs, file_name_queue_scope)
file_name_queue = data_flow_ops.FIFOQueue(
capacity=1, dtypes=[dtypes.string], shapes=[[]])
enqueue_op = file_name_queue.enqueue(shared_file_name_queue.dequeue())
queue_runner.add_queue_runner(
queue_runner.QueueRunner(file_name_queue, [enqueue_op]))
else:
file_name_queue = input_ops.string_input_producer(
constant_op.constant(
file_names, name='input'),
shuffle=randomize_input,
num_epochs=num_epochs,
name=file_name_queue_scope)
example_list = _get_examples(file_name_queue, reader, num_threads,
read_batch_size, parse_fn)
enqueue_many = read_batch_size > 1
if num_epochs is None:
allow_smaller_final_batch = False
else:
allow_smaller_final_batch = True
# Setup batching queue given list of read example tensors.
if randomize_input:
if isinstance(batch_size, ops.Tensor):
min_after_dequeue = int(queue_capacity * 0.4)
else:
min_after_dequeue = max(queue_capacity - (3 * batch_size), batch_size)
queued_examples_with_keys = input_ops.shuffle_batch_join(
example_list, batch_size, capacity=queue_capacity,
min_after_dequeue=min_after_dequeue,
enqueue_many=enqueue_many, name=scope,
allow_smaller_final_batch=allow_smaller_final_batch)
else:
queued_examples_with_keys = input_ops.batch_join(
example_list, batch_size, capacity=queue_capacity,
enqueue_many=enqueue_many, name=scope,
allow_smaller_final_batch=allow_smaller_final_batch)
if parse_fn and isinstance(queued_examples_with_keys, dict):
queued_keys = queued_examples_with_keys.pop(KEY_FEATURE_NAME)
return queued_keys, queued_examples_with_keys
return queued_examples_with_keys
def read_keyed_batch_examples(file_pattern,
batch_size,
reader,
randomize_input=True,
num_epochs=None,
queue_capacity=10000,
num_threads=1,
read_batch_size=1,
parse_fn=None,
name=None):
"""Adds operations to read, queue, batch `Example` protos.
Given file pattern (or list of files), will setup a queue for file names,
read `Example` proto using provided `reader`, use batch queue to create
batches of examples of size `batch_size`.
All queue runners are added to the queue runners collection, and may be
started via `start_queue_runners`.
All ops are added to the default graph.
Use `parse_fn` if you need to do parsing / processing on single examples.
Args:
file_pattern: List of files or pattern of file paths containing
`Example` records. See `tf.gfile.Glob` for pattern rules.
batch_size: An int or scalar `Tensor` specifying the batch size to use.
reader: A function or class that returns an object with
`read` method, (filename tensor) -> (example tensor).
randomize_input: Whether the input should be randomized.
num_epochs: Integer specifying the number of times to read through the
dataset. If `None`, cycles through the dataset forever.
NOTE - If specified, creates a variable that must be initialized, so call
`tf.initialize_all_variables()` as shown in the tests.
queue_capacity: Capacity for input queue.
num_threads: The number of threads enqueuing examples.
read_batch_size: An int or scalar `Tensor` specifying the number of
records to read at once
parse_fn: Parsing function, takes `Example` Tensor returns parsed
representation. If `None`, no parsing is done.
name: Name of resulting op.
Returns:
Returns tuple of:
- `Tensor` of string keys.
- String `Tensor` of batched `Example` proto.
Raises:
ValueError: for invalid inputs.
"""
# Retrieve files to read.
if isinstance(file_pattern, list):
file_names = file_pattern
if not file_names:
raise ValueError('No files given to dequeue_examples.')
else:
file_names = list(gfile.Glob(file_pattern))
if not file_names:
raise ValueError('No files match %s.' % file_pattern)
# Sort files so it will be deterministic for unit tests. They'll be shuffled
# in `string_input_producer` if `randomize_input` is enabled.
if not randomize_input:
file_names = sorted(file_names)
# Check input parameters are given and reasonable.
if (not queue_capacity) or (queue_capacity <= 0):
raise ValueError('Invalid queue_capacity %s.' % queue_capacity)
if (batch_size is None) or (
(not isinstance(batch_size, ops.Tensor)) and
(batch_size <= 0 or batch_size > queue_capacity)):
raise ValueError('Invalid batch_size %s, with queue_capacity %s.' %
(batch_size, queue_capacity))
if (read_batch_size is None) or (
(not isinstance(read_batch_size, ops.Tensor)) and
(read_batch_size <= 0)):
raise ValueError('Invalid read_batch_size %s.' % read_batch_size)
if (not num_threads) or (num_threads <= 0):
raise ValueError('Invalid num_threads %s.' % num_threads)
if (num_epochs is not None) and (num_epochs <= 0):
raise ValueError('Invalid num_epochs %s.' % num_epochs)
with ops.name_scope(name, 'read_batch_examples', [file_pattern]) as scope:
# Setup filename queue with shuffling.
with ops.name_scope('file_name_queue') as file_name_queue_scope:
file_name_queue = input_ops.string_input_producer(
constant_op.constant(file_names, name='input'),
shuffle=randomize_input,
num_epochs=num_epochs,
name=file_name_queue_scope)
# Create readers, one per thread and set them to read from filename queue.
with ops.name_scope('read'):
example_list = []
for _ in range(num_threads):
if read_batch_size > 1:
keys, examples_proto = reader().read_up_to(
file_name_queue, read_batch_size)
else:
keys, examples_proto = reader().read(file_name_queue)
if parse_fn:
parsed_examples = parse_fn(examples_proto)
# Map keys into example map because batch_join doesn't support
# tuple of Tensor + dict.
if isinstance(parsed_examples, dict):
parsed_examples[KEY_FEATURE_NAME] = keys
example_list.append(parsed_examples)
else:
example_list.append((keys, parsed_examples))
else:
example_list.append((keys, examples_proto))
enqueue_many = read_batch_size > 1
if num_epochs is not None:
allow_smaller_final_batch = True
else:
allow_smaller_final_batch = False
# Setup batching queue given list of read example tensors.
if randomize_input:
if isinstance(batch_size, ops.Tensor):
min_after_dequeue = int(queue_capacity * 0.4)
else:
min_after_dequeue = max(queue_capacity - (3 * batch_size),
batch_size)
queued_examples_with_keys = input_ops.shuffle_batch_join(
example_list,
batch_size,
capacity=queue_capacity,
min_after_dequeue=min_after_dequeue,
enqueue_many=enqueue_many,
name=scope,
allow_smaller_final_batch=allow_smaller_final_batch)
else:
queued_examples_with_keys = input_ops.batch_join(
example_list,
batch_size,
capacity=queue_capacity,
enqueue_many=enqueue_many,
name=scope,
allow_smaller_final_batch=allow_smaller_final_batch)
if parse_fn and isinstance(queued_examples_with_keys, dict):
queued_keys = queued_examples_with_keys.pop(KEY_FEATURE_NAME)
return queued_keys, queued_examples_with_keys
return queued_examples_with_keys
def _read_keyed_batch_examples_helper(file_pattern,
batch_size,
reader,
randomize_input=True,
num_epochs=None,
queue_capacity=10000,
num_threads=1,
read_batch_size=1,
parse_fn=None,
setup_shared_queue=False,
name=None):
"""Adds operations to read, queue, batch `Example` protos.
Args:
file_pattern: List of files or pattern of file paths containing
`Example` records. See `tf.gfile.Glob` for pattern rules.
batch_size: An int or scalar `Tensor` specifying the batch size to use.
reader: A function or class that returns an object with
`read` method, (filename tensor) -> (example tensor).
randomize_input: Whether the input should be randomized.
num_epochs: Integer specifying the number of times to read through the
dataset. If `None`, cycles through the dataset forever.
NOTE - If specified, creates a variable that must be initialized, so call
`tf.initialize_all_variables()` as shown in the tests.
queue_capacity: Capacity for input queue.
num_threads: The number of threads enqueuing examples.
read_batch_size: An int or scalar `Tensor` specifying the number of
records to read at once
parse_fn: Parsing function, takes `Example` Tensor returns parsed
representation. If `None`, no parsing is done.
setup_shared_queue: Whether to set up a shared queue for file names.
name: Name of resulting op.
Returns:
Returns tuple of:
- `Tensor` of string keys.
- String `Tensor` of batched `Example` proto.
Raises:
ValueError: for invalid inputs.
"""
# Retrieve files to read.
file_names = _get_file_names(file_pattern, randomize_input)
# Check input parameters are given and reasonable.
if (not queue_capacity) or (queue_capacity <= 0):
raise ValueError('Invalid queue_capacity %s.' % queue_capacity)
if (batch_size is None) or (
(not isinstance(batch_size, ops.Tensor)) and
(batch_size <= 0 or batch_size > queue_capacity)):
raise ValueError('Invalid batch_size %s, with queue_capacity %s.' %
(batch_size, queue_capacity))
if (read_batch_size is None) or (
(not isinstance(read_batch_size, ops.Tensor)) and
(read_batch_size <= 0)):
raise ValueError('Invalid read_batch_size %s.' % read_batch_size)
if (not num_threads) or (num_threads <= 0):
raise ValueError('Invalid num_threads %s.' % num_threads)
if (num_epochs is not None) and (num_epochs <= 0):
raise ValueError('Invalid num_epochs %s.' % num_epochs)
with ops.name_scope(name, 'read_batch_examples', [file_pattern]) as scope:
with ops.name_scope('file_name_queue') as file_name_queue_scope:
if setup_shared_queue:
shared_file_name_queue = _get_shared_file_name_queue(
file_names, randomize_input, num_epochs,
file_name_queue_scope)
file_name_queue = data_flow_ops.FIFOQueue(
capacity=1, dtypes=[dtypes.string], shapes=[[]])
enqueue_op = file_name_queue.enqueue(
shared_file_name_queue.dequeue())
queue_runner.add_queue_runner(
queue_runner.QueueRunner(file_name_queue, [enqueue_op]))
else:
file_name_queue = input_ops.string_input_producer(
constant_op.constant(file_names, name='input'),
shuffle=randomize_input,
num_epochs=num_epochs,
name=file_name_queue_scope)
example_list = _get_examples(file_name_queue, reader, num_threads,
read_batch_size, parse_fn)
enqueue_many = read_batch_size > 1
if num_epochs is None:
allow_smaller_final_batch = False
else:
allow_smaller_final_batch = True
# Setup batching queue given list of read example tensors.
if randomize_input:
if isinstance(batch_size, ops.Tensor):
min_after_dequeue = int(queue_capacity * 0.4)
else:
min_after_dequeue = max(queue_capacity - (3 * batch_size),
batch_size)
queued_examples_with_keys = input_ops.shuffle_batch_join(
example_list,
batch_size,
capacity=queue_capacity,
min_after_dequeue=min_after_dequeue,
enqueue_many=enqueue_many,
name=scope,
allow_smaller_final_batch=allow_smaller_final_batch)
else:
queued_examples_with_keys = input_ops.batch_join(
example_list,
batch_size,
capacity=queue_capacity,
enqueue_many=enqueue_many,
name=scope,
allow_smaller_final_batch=allow_smaller_final_batch)
if parse_fn and isinstance(queued_examples_with_keys, dict):
queued_keys = queued_examples_with_keys.pop(KEY_FEATURE_NAME)
return queued_keys, queued_examples_with_keys
return queued_examples_with_keys
def _read_keyed_batch_examples_helper(file_pattern,
batch_size,
reader,
randomize_input=True,
num_epochs=None,
queue_capacity=10000,
num_threads=1,
read_batch_size=1,
parse_fn=None,
setup_shared_queue=False,
name=None):
# Retrieve files to read.
file_names = _get_file_names(file_pattern, randomize_input)
# Check input parameters are given and reasonable.
if (not queue_capacity) or (queue_capacity <= 0):
raise ValueError('Invalid queue_capacity %s.' % queue_capacity)
if (batch_size is None) or (
(not isinstance(batch_size, ops.Tensor)) and
(batch_size <= 0 or batch_size > queue_capacity)):
raise ValueError(
'Invalid batch_size %s, with queue_capacity %s.' %
(batch_size, queue_capacity))
if (read_batch_size is None) or (
(not isinstance(read_batch_size, ops.Tensor)) and
(read_batch_size <= 0)):
raise ValueError('Invalid read_batch_size %s.' % read_batch_size)
if (not num_threads) or (num_threads <= 0):
raise ValueError('Invalid num_threads %s.' % num_threads)
if (num_epochs is not None) and (num_epochs <= 0):
raise ValueError('Invalid num_epochs %s.' % num_epochs)
with ops.name_scope(name, 'read_batch_examples', [file_pattern]) as scope:
with ops.name_scope('file_name_queue') as file_name_queue_scope:
if setup_shared_queue:
shared_file_name_queue = _get_shared_file_name_queue(
file_names, randomize_input, num_epochs, file_name_queue_scope)
file_name_queue = data_flow_ops.FIFOQueue(
capacity=1, dtypes=[dtypes.string], shapes=[[]])
enqueue_op = file_name_queue.enqueue(shared_file_name_queue.dequeue())
queue_runner.add_queue_runner(
queue_runner.QueueRunner(file_name_queue, [enqueue_op]))
else:
file_name_queue = input_ops.string_input_producer(
constant_op.constant(
file_names, name='input'),
shuffle=randomize_input,
num_epochs=num_epochs,
name=file_name_queue_scope)
example_list = _get_examples(file_name_queue, reader, num_threads,
read_batch_size, parse_fn)
enqueue_many = read_batch_size > 1
if num_epochs is not None:
allow_smaller_final_batch = True
else:
allow_smaller_final_batch = False
# Setup batching queue given list of read example tensors.
if randomize_input:
if isinstance(batch_size, ops.Tensor):
min_after_dequeue = int(queue_capacity * 0.4)
else:
min_after_dequeue = max(queue_capacity - (3 * batch_size), batch_size)
queued_examples_with_keys = input_ops.shuffle_batch_join(
example_list, batch_size, capacity=queue_capacity,
min_after_dequeue=min_after_dequeue,
enqueue_many=enqueue_many, name=scope,
allow_smaller_final_batch=allow_smaller_final_batch)
else:
queued_examples_with_keys = input_ops.batch_join(
example_list, batch_size, capacity=queue_capacity,
enqueue_many=enqueue_many, name=scope,
allow_smaller_final_batch=allow_smaller_final_batch)
if parse_fn and isinstance(queued_examples_with_keys, dict):
queued_keys = queued_examples_with_keys.pop(KEY_FEATURE_NAME)
return queued_keys, queued_examples_with_keys
return queued_examples_with_keys
def read_batch_examples(file_pattern,
batch_size,
reader,
randomize_input=True,
num_epochs=None,
queue_capacity=10000,
num_threads=1,
name=None):
"""Adds operations to read, queue, batch `Example` protos.
Given file pattern (or list of files), will setup a queue for file names,
read `Example` proto using provided `reader`, use batch queue to create
batches of examples of size `batch_size`.
All queue runners are added to the queue runners collection, and may be
started via `start_queue_runners`.
All ops are added to the default graph.
Args:
file_pattern: List of files or pattern of file paths containing
`Example` records. See `tf.gfile.Glob` for pattern rules.
batch_size: An int or scalar `Tensor` specifying the batch size to use.
reader: A function or class that returns an object with
`read` method, (filename tensor) -> (example tensor).
randomize_input: Whether the input should be randomized.
num_epochs: Integer specifying the number of times to read through the
dataset. If `None`, cycles through the dataset forever.
NOTE - If specified, creates a variable that must be initialized, so call
`tf.initialize_all_variables()` as shown in the tests.
queue_capacity: Capacity for input queue.
num_threads: The number of threads enqueuing examples.
name: Name of resulting op.
Returns:
String `Tensor` of batched `Example` proto.
Raises:
ValueError: for invalid inputs.
"""
# Retrive files to read.
if isinstance(file_pattern, list):
file_names = file_pattern
if not file_names:
raise ValueError('No files given to dequeue_examples.')
else:
file_names = list(gfile.Glob(file_pattern))
if not file_names:
raise ValueError('No files match %s.' % file_pattern)
# Sort files so it will be deterministic for unit tests. They'll be shuffled
# in `string_input_producer` if `randomize_input` is enabled.
if not randomize_input:
file_names = sorted(file_names)
# Check input parameters are given and reasonable.
if (not queue_capacity) or (queue_capacity <= 0):
raise ValueError('Invalid queue_capacity %s.' % queue_capacity)
if (batch_size is None) or (
(not isinstance(batch_size, ops.Tensor)) and
(batch_size <= 0 or batch_size > queue_capacity)):
raise ValueError('Invalid batch_size %s, with queue_capacity %s.' %
(batch_size, queue_capacity))
if (not num_threads) or (num_threads <= 0):
raise ValueError('Invalid num_threads %s.' % num_threads)
if (num_epochs is not None) and (num_epochs <= 0):
raise ValueError('Invalid num_epochs %s.' % num_epochs)
with ops.op_scope([file_pattern], name, 'read_batch_examples') as scope:
# Setup filename queue with shuffling.
with ops.name_scope('file_name_queue') as file_name_queue_scope:
file_name_queue = input_ops.string_input_producer(
constant_op.constant(file_names, name='input'),
shuffle=randomize_input,
num_epochs=num_epochs,
name=file_name_queue_scope)
# Create readers, one per thread and set them to read from filename queue.
with ops.name_scope('read'):
example_list = []
for _ in range(num_threads):
_, example_proto = reader().read(file_name_queue)
example_list.append([example_proto])
# Setup batching queue given list of read example tensors.
if randomize_input:
if isinstance(batch_size, ops.Tensor):
min_after_dequeue = int(queue_capacity * 0.4)
else:
min_after_dequeue = max(queue_capacity - (3 * batch_size),
batch_size)
examples = input_ops.shuffle_batch_join(
example_list,
batch_size,
capacity=queue_capacity,
min_after_dequeue=min_after_dequeue,
name=scope)
else:
examples = input_ops.batch_join(example_list,
batch_size,
capacity=queue_capacity,
name=scope)
return examples
def read_batch_examples(file_pattern, batch_size, reader,
randomize_input=True, num_epochs=None,
queue_capacity=10000, num_threads=1,
name=None):
"""Adds operations to read, queue, batch `Example` protos.
Given file pattern (or list of files), will setup a queue for file names,
read `Example` proto using provided `reader`, use batch queue to create
batches of examples of size `batch_size`.
All queue runners are added to the queue runners collection, and may be
started via `start_queue_runners`.
All ops are added to the default graph.
Args:
file_pattern: List of files or pattern of file paths containing
`Example` records. See `tf.gfile.Glob` for pattern rules.
batch_size: An int or scalar `Tensor` specifying the batch size to use.
reader: A function or class that returns an object with
`read` method, (filename tensor) -> (example tensor).
randomize_input: Whether the input should be randomized.
num_epochs: Integer specifying the number of times to read through the
dataset. If `None`, cycles through the dataset forever.
NOTE - If specified, creates a variable that must be initialized, so call
`tf.initialize_all_variables()` as shown in the tests.
queue_capacity: Capacity for input queue.
num_threads: The number of threads enqueuing examples.
name: Name of resulting op.
Returns:
String `Tensor` of batched `Example` proto.
Raises:
ValueError: for invalid inputs.
"""
# Retrive files to read.
if isinstance(file_pattern, list):
file_names = file_pattern
if not file_names:
raise ValueError('No files given to dequeue_examples.')
else:
file_names = list(gfile.Glob(file_pattern))
if not file_names:
raise ValueError('No files match %s.' % file_pattern)
# Sort files so it will be deterministic for unit tests. They'll be shuffled
# in `string_input_producer` if `randomize_input` is enabled.
if not randomize_input:
file_names = sorted(file_names)
# Check input parameters are given and reasonable.
if (not queue_capacity) or (queue_capacity <= 0):
raise ValueError('Invalid queue_capacity %s.' % queue_capacity)
if (batch_size is None) or (
(not isinstance(batch_size, ops.Tensor)) and
(batch_size <= 0 or batch_size > queue_capacity)):
raise ValueError(
'Invalid batch_size %s, with queue_capacity %s.' %
(batch_size, queue_capacity))
if (not num_threads) or (num_threads <= 0):
raise ValueError('Invalid num_threads %s.' % num_threads)
if (num_epochs is not None) and (num_epochs <= 0):
raise ValueError('Invalid num_epochs %s.' % num_epochs)
with ops.op_scope([file_pattern], name, 'read_batch_examples') as scope:
# Setup filename queue with shuffling.
with ops.name_scope('file_name_queue') as file_name_queue_scope:
file_name_queue = input_ops.string_input_producer(
constant_op.constant(file_names, name='input'),
shuffle=randomize_input, num_epochs=num_epochs,
name=file_name_queue_scope)
# Create readers, one per thread and set them to read from filename queue.
with ops.name_scope('read'):
example_list = []
for _ in range(num_threads):
_, example_proto = reader().read(file_name_queue)
example_list.append([example_proto])
# Setup batching queue given list of read example tensors.
if randomize_input:
if isinstance(batch_size, ops.Tensor):
min_after_dequeue = int(queue_capacity * 0.4)
else:
min_after_dequeue = max(queue_capacity - (3 * batch_size), batch_size)
examples = input_ops.shuffle_batch_join(
example_list, batch_size, capacity=queue_capacity,
min_after_dequeue=min_after_dequeue,
name=scope)
else:
examples = input_ops.batch_join(
example_list, batch_size, capacity=queue_capacity,
name=scope)
return examples
