<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/quantize.py#L288-L501) |

Quantize a `keras` model that has been annotated for quantization.

    tfmot.quantization.keras.quantize_apply(
        model,
        scheme=https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/default_8bit/Default8BitQuantizeScheme,
        quantized_layer_name_prefix='quant_'
    )

### Used in the notebooks

| Used in the guide |
|---|
| - [Quantization aware training comprehensive guide](https://www.tensorflow.org/model_optimization/guide/quantization/training_comprehensive_guide) - [Cluster preserving quantization aware training (CQAT) Keras example](https://www.tensorflow.org/model_optimization/guide/combine/cqat_example) - [Sparsity and cluster preserving quantization aware training (PCQAT) Keras example](https://www.tensorflow.org/model_optimization/guide/combine/pcqat_example) - [Pruning preserving quantization aware training (PQAT) Keras example](https://www.tensorflow.org/model_optimization/guide/combine/pqat_example) |

Quantization constructs a model which emulates quantization during training.
This allows the model to learn parameters robust to quantization loss, and
also model the accuracy of a quantized model.

For more information, see
<https://www.tensorflow.org/model_optimization/guide/quantization/training>

This function takes a `keras` model in which the desired layers for
quantization have already been annotated. See `quantize_annotate_model`
and `quantize_annotate_layer`.

#### Example:

    model = keras.Sequential([
        layers.Dense(10, activation='relu', input_shape=(100,)),
        quantize_annotate_layer(layers.Dense(2, activation='sigmoid'))
    ])

    # Only the second Dense layer is quantized.
    quantized_model = quantize_apply(model)

Note that this function removes the optimizer from the original model.

The returned model copies over weights from the original model. So while
it preserves the original weights, training it will not modify the weights
of the original model.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `model` | A `keras` Sequential or Functional model which has been annotated with `quantize_annotate`. It can have pre-trained weights. |
| `scheme` | A `QuantizeScheme` which specifies transformer and quantization registry. The default is `Default8BitQuantizeScheme()`. |
| `quantized_layer_name_prefix` | A name prefix for quantized layers. The default is `quant_`. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| Returns a new `keras` model in which the annotated layers have been prepared for quantization. ||

<br />