<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/models/blob/v2.20.0/official/vision/ops/preprocess_ops.py#L118-L145) |

Normalizes a scaled float image to zero mean and unit variance.

    tfm.vision.preprocess_ops.normalize_scaled_float_image(
        image: tf.Tensor,
        offset: Sequence[float] = https://www.tensorflow.org/api_docs/python/tfm/vision/preprocess_ops#MEAN_NORM,
        scale: Sequence[float] = https://www.tensorflow.org/api_docs/python/tfm/vision/preprocess_ops#STDDEV_NORM
    )

It assumes the input image is float dtype with values in \[0, 1) if offset is
MEAN_NORM, values in \[0, 255\] if offset is MEAN_RGB.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `image` | A tf.Tensor in float32 dtype with values in range \[0, 1) or \[0, 255\]. |
| `offset` | A tuple of mean values to be subtracted from the image. |
| `scale` | A tuple of normalization factors. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| A normalized image tensor. ||

<br />