TensorFlow functions for setting up an input-prefetching pipeline. Please see the reading data how-to for context.

### Beginning of an input pipeline

The "producer" functions add a queue to the graph and a corresponding
`QueueRunner`

for running the subgraph that fills that queue.

`tf.train.match_filenames_once(pattern, name=None)`

Save the list of files matching pattern, so it is only computed once.

##### Args:

: A file pattern (glob).`pattern`

: A name for the operations (optional).`name`

##### Returns:

A variable that is initialized to the list of files matching pattern.

`tf.train.limit_epochs(tensor, num_epochs=None, name=None)`

Returns tensor `num_epochs`

times and then raises an `OutOfRange`

error.

##### Args:

: Any`tensor`

`Tensor`

.: A positive integer (optional). If specified, limits the number of steps the output tensor may be evaluated.`num_epochs`

: A name for the operations (optional).`name`

##### Returns:

tensor or `OutOfRange`

.

##### Raises:

: if`ValueError`

`num_epochs`

is invalid.

`tf.train.input_producer(input_tensor, element_shape=None, num_epochs=None, shuffle=True, seed=None, capacity=32, shared_name=None, summary_name=None, name=None)`

Output the rows of `input_tensor`

to a queue for an input pipeline.

##### Args:

: A tensor with the rows to produce. Must be at least one-dimensional. Must either have a fully-defined shape, or`input_tensor`

`element_shape`

must be defined.: (Optional.) A`element_shape`

`TensorShape`

representing the shape of a row of`input_tensor`

, if it cannot be inferred.: (Optional.) An integer. If specified`num_epochs`

`input_producer`

produces each row of`input_tensor`

`num_epochs`

times before generating an`OutOfRange`

error. If not specified,`input_producer`

can cycle through the rows of`input_tensor`

an unlimited number of times.: (Optional.) A boolean. If true, the rows are randomly shuffled within each epoch.`shuffle`

: (Optional.) An integer. The seed to use if`seed`

`shuffle`

is true.: (Optional.) The capacity of the queue to be used for buffering the input.`capacity`

: (Optional.) If set, this queue will be shared under the given name across multiple sessions.`shared_name`

: (Optional.) If set, a scalar summary for the current queue size will be generated, using this name as part of the tag.`summary_name`

: (Optional.) A name for queue.`name`

##### Returns:

A queue with the output rows. A `QueueRunner`

for the queue is
added to the current `QUEUE_RUNNER`

collection of the current
graph.

##### Raises:

: If the shape of the input cannot be inferred from the arguments.`ValueError`

`tf.train.range_input_producer(limit, num_epochs=None, shuffle=True, seed=None, capacity=32, shared_name=None, name=None)`

Produces the integers from 0 to limit-1 in a queue.

##### Args:

: An int32 scalar tensor.`limit`

: An integer (optional). If specified,`num_epochs`

`range_input_producer`

produces each integer`num_epochs`

times before generating an OutOfRange error. If not specified,`range_input_producer`

can cycle through the integers an unlimited number of times.: Boolean. If true, the integers are randomly shuffled within each epoch.`shuffle`

: An integer (optional). Seed used if shuffle == True.`seed`

: An integer. Sets the queue capacity.`capacity`

: (optional). If set, this queue will be shared under the given name across multiple sessions.`shared_name`

: A name for the operations (optional).`name`

##### Returns:

A Queue with the output integers. A `QueueRunner`

for the Queue
is added to the current `Graph`

's `QUEUE_RUNNER`

collection.

`tf.train.slice_input_producer(tensor_list, num_epochs=None, shuffle=True, seed=None, capacity=32, shared_name=None, name=None)`

Produces a slice of each `Tensor`

in `tensor_list`

.

Implemented using a Queue -- a `QueueRunner`

for the Queue
is added to the current `Graph`

's `QUEUE_RUNNER`

collection.

##### Args:

: A list of`tensor_list`

`Tensor`

objects. Every`Tensor`

in`tensor_list`

must have the same size in the first dimension.: An integer (optional). If specified,`num_epochs`

`slice_input_producer`

produces each slice`num_epochs`

times before generating an`OutOfRange`

error. If not specified,`slice_input_producer`

can cycle through the slices an unlimited number of times.: Boolean. If true, the integers are randomly shuffled within each epoch.`shuffle`

: An integer (optional). Seed used if shuffle == True.`seed`

: An integer. Sets the queue capacity.`capacity`

: (optional). If set, this queue will be shared under the given name across multiple sessions.`shared_name`

: A name for the operations (optional).`name`

##### Returns:

A list of tensors, one for each element of `tensor_list`

. If the tensor
in `tensor_list`

has shape `[N, a, b, .., z]`

, then the corresponding output
tensor will have shape `[a, b, ..., z]`

.

##### Raises:

: if`ValueError`

`slice_input_producer`

produces nothing from`tensor_list`

.

`tf.train.string_input_producer(string_tensor, num_epochs=None, shuffle=True, seed=None, capacity=32, shared_name=None, name=None)`

Output strings (e.g. filenames) to a queue for an input pipeline.

##### Args:

: A 1-D string tensor with the strings to produce.`string_tensor`

: An integer (optional). If specified,`num_epochs`

`string_input_producer`

produces each string from`string_tensor`

`num_epochs`

times before generating an`OutOfRange`

error. If not specified,`string_input_producer`

can cycle through the strings in`string_tensor`

an unlimited number of times.: Boolean. If true, the strings are randomly shuffled within each epoch.`shuffle`

: An integer (optional). Seed used if shuffle == True.`seed`

: An integer. Sets the queue capacity.`capacity`

: (optional). If set, this queue will be shared under the given name across multiple sessions.`shared_name`

: A name for the operations (optional).`name`

##### Returns:

A queue with the output strings. A `QueueRunner`

for the Queue
is added to the current `Graph`

's `QUEUE_RUNNER`

collection.

##### Raises:

: If the string_tensor is a null Python list. At runtime, will fail with an assertion if string_tensor becomes a null tensor.`ValueError`

### Batching at the end of an input pipeline

These functions add a queue to the graph to assemble a batch of
examples, with possible shuffling. They also add a `QueueRunner`

for
running the subgraph that fills that queue.

Use `batch`

or `batch_join`

for batching
examples that have already been well shuffled. Use
`shuffle_batch`

or
`shuffle_batch_join`

for examples that would
benefit from additional shuffling.

Use `batch`

or `shuffle_batch`

if you want a
single thread producing examples to batch, or if you have a
single subgraph producing examples but you want to run it in *N* threads
(where you increase *N* until it can keep the queue full). Use
`batch_join`

or `shuffle_batch_join`

if you have *N* different subgraphs producing examples to batch and you
want them run by *N* threads.

`tf.train.batch(tensors, batch_size, num_threads=1, capacity=32, enqueue_many=False, shapes=None, dynamic_pad=False, allow_smaller_final_batch=False, shared_name=None, name=None)`

Creates batches of tensors in `tensors`

.

The argument `tensors`

can be a list or a dictionary of tensors.
The value returned by the function will be of the same type
as `tensors`

.

This function is implemented using a queue. A `QueueRunner`

for the
queue is added to the current `Graph`

's `QUEUE_RUNNER`

collection.

If `enqueue_many`

is `False`

, `tensors`

is assumed to represent a single
example. An input tensor with shape `[x, y, z]`

will be output as a tensor
with shape `[batch_size, x, y, z]`

.

If `enqueue_many`

is `True`

, `tensors`

is assumed to represent a batch of
examples, where the first dimension is indexed by example, and all members of
`tensors`

should have the same size in the first dimension. If an input
tensor has shape `[*, x, y, z]`

, the output will have shape ```
[batch_size, x,
y, z]
```

. The `capacity`

argument controls the how long the prefetching is
allowed to grow the queues.

The returned operation is a dequeue operation and will throw
`tf.errors.OutOfRangeError`

if the input queue is exhausted. If this
operation is feeding another input queue, its queue runner will catch
this exception, however, if this operation is used in your main thread
you are responsible for catching this yourself.

*N.B.:* If `dynamic_pad`

is `False`

, you must ensure that either
(i) the `shapes`

argument is passed, or (ii) all of the tensors in
`tensors`

must have fully-defined shapes. `ValueError`

will be
raised if neither of these conditions holds.

If `dynamic_pad`

is `True`

, it is sufficient that the *rank* of the
tensors is known, but individual dimensions may have shape `None`

.
In this case, for each enqueue the dimensions with value `None`

may have a variable length; upon dequeue, the output tensors will be padded
on the right to the maximum shape of the tensors in the current minibatch.
For numbers, this padding takes value 0. For strings, this padding is
the empty string. See `PaddingFIFOQueue`

for more info.

If `allow_smaller_final_batch`

is `True`

, a smaller batch value than
`batch_size`

is returned when the queue is closed and there are not enough
elements to fill the batch, otherwise the pending elements are discarded.
In addition, all output tensors' static shapes, as accessed via the
`get_shape`

method will have a first `Dimension`

value of `None`

, and
operations that depend on fixed batch_size would fail.

##### Args:

: The list or dictionary of tensors to enqueue.`tensors`

: The new batch size pulled from the queue.`batch_size`

: The number of threads enqueuing`num_threads`

`tensors`

.: An integer. The maximum number of elements in the queue.`capacity`

: Whether each tensor in`enqueue_many`

`tensors`

is a single example.: (Optional) The shapes for each example. Defaults to the inferred shapes for`shapes`

`tensors`

.: Boolean. Allow variable dimensions in input shapes. The given dimensions are padded upon dequeue so that tensors within a batch have the same shapes.`dynamic_pad`

: (Optional) Boolean. If`allow_smaller_final_batch`

`True`

, allow the final batch to be smaller if there are insufficient items left in the queue.: (Optional). If set, this queue will be shared under the given name across multiple sessions.`shared_name`

: (Optional) A name for the operations.`name`

##### Returns:

A list or dictionary of tensors with the same types as `tensors`

.

##### Raises:

: If the`ValueError`

`shapes`

are not specified, and cannot be inferred from the elements of`tensors`

.

`tf.train.batch_join(tensors_list, batch_size, capacity=32, enqueue_many=False, shapes=None, dynamic_pad=False, allow_smaller_final_batch=False, shared_name=None, name=None)`

Runs a list of tensors to fill a queue to create batches of examples.

The `tensors_list`

argument is a list of tuples of tensors, or a list of
dictionaries of tensors. Each element in the list is treated similarly
to the `tensors`

argument of `tf.train.batch()`

.

Enqueues a different list of tensors in different threads.
Implemented using a queue -- a `QueueRunner`

for the queue
is added to the current `Graph`

's `QUEUE_RUNNER`

collection.

`len(tensors_list)`

threads will be started,
with thread `i`

enqueuing the tensors from
`tensors_list[i]`

. `tensors_list[i1][j]`

must match
`tensors_list[i2][j]`

in type and shape, except in the first
dimension if `enqueue_many`

is true.

If `enqueue_many`

is `False`

, each `tensors_list[i]`

is assumed
to represent a single example. An input tensor `x`

will be output as a
tensor with shape `[batch_size] + x.shape`

.

If `enqueue_many`

is `True`

, `tensors_list[i]`

is assumed to
represent a batch of examples, where the first dimension is indexed
by example, and all members of `tensors_list[i]`

should have the
same size in the first dimension. The slices of any input tensor
`x`

are treated as examples, and the output tensors will have shape
`[batch_size] + x.shape[1:]`

.

The `capacity`

argument controls the how long the prefetching is allowed to
grow the queues.

The returned operation is a dequeue operation and will throw
`tf.errors.OutOfRangeError`

if the input queue is exhausted. If this
operation is feeding another input queue, its queue runner will catch
this exception, however, if this operation is used in your main thread
you are responsible for catching this yourself.

*N.B.:* If `dynamic_pad`

is `False`

, you must ensure that either
(i) the `shapes`

argument is passed, or (ii) all of the tensors in
`tensors_list`

must have fully-defined shapes. `ValueError`

will be
raised if neither of these conditions holds.

If `dynamic_pad`

is `True`

, it is sufficient that the *rank* of the
tensors is known, but individual dimensions may have value `None`

.
In this case, for each enqueue the dimensions with value `None`

may have a variable length; upon dequeue, the output tensors will be padded
on the right to the maximum shape of the tensors in the current minibatch.
For numbers, this padding takes value 0. For strings, this padding is
the empty string. See `PaddingFIFOQueue`

for more info.

If `allow_smaller_final_batch`

is `True`

, a smaller batch value than
`batch_size`

is returned when the queue is closed and there are not enough
elements to fill the batch, otherwise the pending elements are discarded.
In addition, all output tensors' static shapes, as accessed via the
`get_shape`

method will have a first `Dimension`

value of `None`

, and
operations that depend on fixed batch_size would fail.

##### Args:

: A list of tuples or dictionaries of tensors to enqueue.`tensors_list`

: An integer. The new batch size pulled from the queue.`batch_size`

: An integer. The maximum number of elements in the queue.`capacity`

: Whether each tensor in`enqueue_many`

`tensor_list_list`

is a single example.: (Optional) The shapes for each example. Defaults to the inferred shapes for`shapes`

`tensor_list_list[i]`

.: Boolean. Allow variable dimensions in input shapes. The given dimensions are padded upon dequeue so that tensors within a batch have the same shapes.`dynamic_pad`

: (Optional) Boolean. If`allow_smaller_final_batch`

`True`

, allow the final batch to be smaller if there are insufficient items left in the queue.: (Optional) If set, this queue will be shared under the given name across multiple sessions.`shared_name`

: (Optional) A name for the operations.`name`

##### Returns:

A list or dictionary of tensors with the same number and types as
`tensors_list[i]`

.

##### Raises:

: If the`ValueError`

`shapes`

are not specified, and cannot be inferred from the elements of`tensor_list_list`

.

`tf.train.shuffle_batch(tensors, batch_size, capacity, min_after_dequeue, num_threads=1, seed=None, enqueue_many=False, shapes=None, allow_smaller_final_batch=False, shared_name=None, name=None)`

Creates batches by randomly shuffling tensors.

This function adds the following to the current `Graph`

:

- A shuffling queue into which tensors from
`tensors`

are enqueued. - A
`dequeue_many`

operation to create batches from the queue. - A
`QueueRunner`

to`QUEUE_RUNNER`

collection, to enqueue the tensors from`tensors`

.

If `enqueue_many`

is `False`

, `tensors`

is assumed to represent a
single example. An input tensor with shape `[x, y, z]`

will be output
as a tensor with shape `[batch_size, x, y, z]`

.

If `enqueue_many`

is `True`

, `tensors`

is assumed to represent a
batch of examples, where the first dimension is indexed by example,
and all members of `tensors`

should have the same size in the
first dimension. If an input tensor has shape `[*, x, y, z]`

, the
output will have shape `[batch_size, x, y, z]`

.

The `capacity`

argument controls the how long the prefetching is allowed to
grow the queues.

The returned operation is a dequeue operation and will throw
`tf.errors.OutOfRangeError`

if the input queue is exhausted. If this
operation is feeding another input queue, its queue runner will catch
this exception, however, if this operation is used in your main thread
you are responsible for catching this yourself.

For example:

```
# Creates batches of 32 images and 32 labels.
image_batch, label_batch = tf.train.shuffle_batch(
[single_image, single_label],
batch_size=32,
num_threads=4,
capacity=50000,
min_after_dequeue=10000)
```

*N.B.:* You must ensure that either (i) the `shapes`

argument is
passed, or (ii) all of the tensors in `tensors`

must have
fully-defined shapes. `ValueError`

will be raised if neither of
these conditions holds.

If `allow_smaller_final_batch`

is `True`

, a smaller batch value than
`batch_size`

is returned when the queue is closed and there are not enough
elements to fill the batch, otherwise the pending elements are discarded.
In addition, all output tensors' static shapes, as accessed via the
`get_shape`

method will have a first `Dimension`

value of `None`

, and
operations that depend on fixed batch_size would fail.

##### Args:

: The list or dictionary of tensors to enqueue.`tensors`

: The new batch size pulled from the queue.`batch_size`

: An integer. The maximum number of elements in the queue.`capacity`

: Minimum number elements in the queue after a dequeue, used to ensure a level of mixing of elements.`min_after_dequeue`

: The number of threads enqueuing`num_threads`

`tensor_list`

.: Seed for the random shuffling within the queue.`seed`

: Whether each tensor in`enqueue_many`

`tensor_list`

is a single example.: (Optional) The shapes for each example. Defaults to the inferred shapes for`shapes`

`tensor_list`

.: (Optional) Boolean. If`allow_smaller_final_batch`

`True`

, allow the final batch to be smaller if there are insufficient items left in the queue.: (Optional) If set, this queue will be shared under the given name across multiple sessions.`shared_name`

: (Optional) A name for the operations.`name`

##### Returns:

A list or dictionary of tensors with the types as `tensors`

.

##### Raises:

: If the`ValueError`

`shapes`

are not specified, and cannot be inferred from the elements of`tensors`

.

`tf.train.shuffle_batch_join(tensors_list, batch_size, capacity, min_after_dequeue, seed=None, enqueue_many=False, shapes=None, allow_smaller_final_batch=False, shared_name=None, name=None)`

Create batches by randomly shuffling tensors.

The `tensors_list`

argument is a list of tuples of tensors, or a list of
dictionaries of tensors. Each element in the list is treated similarly
to the `tensors`

argument of `tf.train.shuffle_batch()`

.

This version enqueues a different list of tensors in different threads.
It adds the following to the current `Graph`

:

- A shuffling queue into which tensors from
`tensors_list`

are enqueued. - A
`dequeue_many`

operation to create batches from the queue. - A
`QueueRunner`

to`QUEUE_RUNNER`

collection, to enqueue the tensors from`tensors_list`

.

`len(tensors_list)`

threads will be started, with thread `i`

enqueuing
the tensors from `tensors_list[i]`

. `tensors_list[i1][j]`

must match
`tensors_list[i2][j]`

in type and shape, except in the first dimension if
`enqueue_many`

is true.

If `enqueue_many`

is `False`

, each `tensors_list[i]`

is assumed
to represent a single example. An input tensor with shape `[x, y, z]`

will be output as a tensor with shape `[batch_size, x, y, z]`

.

If `enqueue_many`

is `True`

, `tensors_list[i]`

is assumed to
represent a batch of examples, where the first dimension is indexed
by example, and all members of `tensors_list[i]`

should have the
same size in the first dimension. If an input tensor has shape ```
[*, x,
y, z]
```

, the output will have shape `[batch_size, x, y, z]`

.

The `capacity`

argument controls the how long the prefetching is allowed to
grow the queues.

`tf.errors.OutOfRangeError`

if the input queue is exhausted. If this
operation is feeding another input queue, its queue runner will catch
this exception, however, if this operation is used in your main thread
you are responsible for catching this yourself.

`allow_smaller_final_batch`

is `True`

, a smaller batch value than
`batch_size`

is returned when the queue is closed and there are not enough
elements to fill the batch, otherwise the pending elements are discarded.
In addition, all output tensors' static shapes, as accessed via the
`get_shape`

method will have a first `Dimension`

value of `None`

, and
operations that depend on fixed batch_size would fail.

##### Args:

: A list of tuples or dictionaries of tensors to enqueue.`tensors_list`

: An integer. The new batch size pulled from the queue.`batch_size`

: An integer. The maximum number of elements in the queue.`capacity`

: Minimum number elements in the queue after a dequeue, used to ensure a level of mixing of elements.`min_after_dequeue`

: Seed for the random shuffling within the queue.`seed`

: Whether each tensor in`enqueue_many`

`tensor_list_list`

is a single example.: (Optional) The shapes for each example. Defaults to the inferred shapes for`shapes`

`tensors_list[i]`

.: (Optional) Boolean. If`allow_smaller_final_batch`

`True`

, allow the final batch to be smaller if there are insufficient items left in the queue.: (optional). If set, this queue will be shared under the given name across multiple sessions.`shared_name`

: (Optional) A name for the operations.`name`

##### Returns:

A list or dictionary of tensors with the same number and types as
`tensors_list[i]`

.

##### Raises:

: If the`ValueError`

`shapes`

are not specified, and cannot be inferred from the elements of`tensors_list`

.