<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/model-optimization/blob/v0.8.1/tensorflow_model_optimization/python/core/quantization/keras/experimental/default_n_bit/default_n_bit_quantize_layout_transform.py#L29-L137) |

Default model transformations.

Inherits From: [`QuantizeLayoutTransform`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/QuantizeLayoutTransform)

    tfmot.quantization.keras.experimental.default_n_bit.DefaultNBitQuantizeLayoutTransform(
        num_bits_weight: int = 8, num_bits_activation: int = 8
    )

## Methods

### `apply`

[View source](https://github.com/tensorflow/model-optimization/blob/v0.8.1/tensorflow_model_optimization/python/core/quantization/keras/experimental/default_n_bit/default_n_bit_quantize_layout_transform.py#L38-L137)

    apply(
        model, layer_quantize_map
    )

Implement default 8-bit transforms.

Currently this means the following.

1. Pull activations into layers, and apply fuse activations. (
2. Modify range in incoming layers for Concat. (
3. Fuse Conv2D/DepthwiseConv2D + BN into single layer.

<br />

<br />

<br />

| Args ||
|---|---|
| `model` | Keras model to be quantized. |
| `layer_quantize_map` | Map with keys as layer names, and values as dicts containing custom `QuantizeConfig`s which may have been passed with layers. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| (Transformed Keras model to better match TensorFlow Lite backend, updated layer quantize map.) ||

<br />