# tf.raw_ops.MultiDeviceIterator

<br />

Creates a MultiDeviceIterator resource.

#### View aliases


**Compat aliases for migration**

See
[Migration guide](https://www.tensorflow.org/guide/migrate) for
more details.

[`tf.compat.v1.raw_ops.MultiDeviceIterator`](https://www.tensorflow.org/api_docs/python/tf/raw_ops/MultiDeviceIterator)

<br />

    tf.raw_ops.MultiDeviceIterator(
        devices, shared_name, container, output_types, output_shapes, name=None
    )

<br />

<br />

<br />

| ## Args ||
|---|---|
| `devices` | A list of `strings` that has length `>= 1`. A list of devices the iterator works across. |
| `shared_name` | A `string`. If non-empty, this resource will be shared under the given name across multiple sessions. |
| `container` | A `string`. If non-empty, this resource is placed in the given container. Otherwise, a default container is used. |
| `output_types` | A list of `tf.DTypes` that has length `>= 1`. The type list for the return values. |
| `output_shapes` | A list of shapes (each a [`tf.TensorShape`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/TensorShape) or list of `ints`) that has length `>= 1`. The list of shapes being produced. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| A `Tensor` of type `resource`. ||

<br />