<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/utils/image_utils.py#L35-L107) |

Converts a 3D NumPy array to a PIL Image instance.

#### View aliases


**Main aliases**

[`tf.keras.preprocessing.image.array_to_img`](https://www.tensorflow.org/api_docs/python/tf/keras/utils/array_to_img)

<br />

    tf.keras.utils.array_to_img(
        x, data_format=None, scale=True, dtype=None
    )

### Used in the notebooks

| Used in the tutorials |
|---|
| - [Image segmentation](https://www.tensorflow.org/tutorials/images/segmentation) - [Semantic Segmentation with Model Garden](https://www.tensorflow.org/tfmodels/vision/semantic_segmentation) - [Adversarial regularization for image classification](https://www.tensorflow.org/neural_structured_learning/tutorials/adversarial_keras_cnn_mnist) |

#### Example:

    from PIL import Image
    img = np.random.random(size=(100, 100, 3))
    pil_img = keras.utils.array_to_img(img)

<br />

<br />

<br />

| ## Args ||
|---|---|
| `x` | Input data, in any form that can be converted to a NumPy array. |
| `data_format` | Image data format, can be either `"channels_first"` or `"channels_last"`. Defaults to `None`, in which case the global setting [`keras.backend.image_data_format()`](https://www.tensorflow.org/api_docs/python/tf/keras/backend/image_data_format) is used (unless you changed it, it defaults to `"channels_last"`). |
| `scale` | Whether to rescale the image such that minimum and maximum values are 0 and 255 respectively. Defaults to `True`. |
| `dtype` | Dtype to use. `None` means the global setting [`keras.backend.floatx()`](https://www.tensorflow.org/api_docs/python/tf/keras/backend/floatx) is used (unless you changed it, it defaults to `"float32"`). Defaults to `None`. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| A PIL Image instance. ||

<br />