<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/api/quantization/keras/__init__.py) |

Module containing quantization code built on Keras abstractions.

## Modules

[`collab_opts`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/collab_opts) module: Module containing collaborative optimization code.

[`default_8bit`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/default_8bit) module: Module containing 8bit default quantization scheme.

[`experimental`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/experimental) module: Module containing experimental quantization features.

[`graph_transformations`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/graph_transformations) module: Module containing code for graph transformation.

[`quantizers`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/quantizers) module: Module containing Quantization abstraction and quantizers.

## Classes

[`class QuantizeConfig`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/QuantizeConfig): ABC interface for Keras layers to express how they should be quantized.

[`class QuantizeLayoutTransform`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/QuantizeLayoutTransform): Apply transformations to the model.

[`class QuantizeRegistry`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/QuantizeRegistry): ABC interface which specifies how layers should be quantized.

[`class QuantizeScheme`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/QuantizeScheme): ABC interface which specifies transformer and quantization registry.

[`class QuantizeWrapper`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/QuantizeWrapper): Quantizes the weights and activations of the keras layer it wraps.

[`class QuantizeWrapperV2`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/QuantizeWrapperV2): Quantizes the weights and activations of the keras layer it wraps.

## Functions

[`fix_input_output_range(...)`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/fix_input_output_range): Fix the input and output ranges.

[`quantize_annotate_layer(...)`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/quantize_annotate_layer): Annotate a `keras` layer to be quantized.

[`quantize_annotate_model(...)`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/quantize_annotate_model): Annotate a `keras` model to be quantized.

[`quantize_apply(...)`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/quantize_apply): Quantize a `keras` model that has been annotated for quantization.

[`quantize_model(...)`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/quantize_model): Quantize a `keras` model with the default quantization implementation.

[`quantize_scope(...)`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/quantize_scope): Scope which can be used to deserialize quantized Keras models and layers.

[`remove_input_range(...)`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/remove_input_range): Remove the input range.