<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/applications/densenet.py#L415-L419) |

Preprocesses a tensor or Numpy array encoding a batch of images.

    tf.keras.applications.densenet.preprocess_input(
        x, data_format=None
    )

Usage example with [`applications.MobileNet`](https://www.tensorflow.org/api_docs/python/tf/keras/applications/MobileNet):

    i = keras.layers.Input([None, None, 3], dtype="uint8")
    x = ops.cast(i, "float32")
    x = keras.applications.mobilenet.preprocess_input(x)
    core = keras.applications.MobileNet()
    x = core(x)
    model = keras.Model(inputs=[i], outputs=[x])
    result = model(image)

<br />

<br />

<br />

| ## Args ||
|---|---|
| `x` | A floating point [`numpy.array`](https://www.tensorflow.org/api_docs/python/tf/keras/ops/array) or a backend-native tensor, 3D or 4D with 3 color channels, with values in the range \[0, 255\]. The preprocessed data are written over the input data if the data types are compatible. To avoid this behaviour, [`numpy.copy(x)`](https://www.tensorflow.org/api_docs/python/tf/keras/ops/copy) can be used. |
| `data_format` | Optional data format of the image tensor/array. None, means 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 uses "channels_last"). Defaults to `None`. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| Preprocessed array with type `float32`. <br /> The input pixels values are scaled between 0 and 1 and each channel is normalized with respect to the ImageNet dataset. ||

<br />

<br />

<br />

<br />

| ## Raises ||
|---|---|
| `ValueError` | In case of unknown `data_format` argument. |

<br />