<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/default_8bit/default_8bit_transforms/__init__.py) |

Module containing 8bit default transforms.

## Classes

[`class ConcatTransform`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/default_8bit/default_8bit_transforms/ConcatTransform): Transform for Concatenate. Quantize only after concatenation.

[`class ConcatTransform3Inputs`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/default_8bit/default_8bit_transforms/ConcatTransform3Inputs): Transform for Concatenate. Quantize only after concatenation.

[`class ConcatTransform4Inputs`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/default_8bit/default_8bit_transforms/ConcatTransform4Inputs): Transform for Concatenate. Quantize only after concatenation.

[`class ConcatTransform5Inputs`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/default_8bit/default_8bit_transforms/ConcatTransform5Inputs): Transform for Concatenate. Quantize only after concatenation.

[`class ConcatTransform6Inputs`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/default_8bit/default_8bit_transforms/ConcatTransform6Inputs): Transform for Concatenate. Quantize only after concatenation.

[`class Conv2DBatchNormActivationQuantize`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/default_8bit/default_8bit_transforms/Conv2DBatchNormActivationQuantize): Transform to be applied to "Conv2D" + "BatchNorm" + "ReLU" Graph.

[`class Conv2DBatchNormQuantize`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/default_8bit/default_8bit_transforms/Conv2DBatchNormQuantize): Transform to be applied to "Conv2D" + "BatchNorm" Graph.

[`class Conv2DBatchNormReLUQuantize`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/default_8bit/default_8bit_transforms/Conv2DBatchNormReLUQuantize): Transform to be applied to "Conv2D" + "BatchNorm" + "ReLU" Graph.

[`class Conv2DReshapeBatchNormActivationQuantize`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/default_8bit/default_8bit_transforms/Conv2DReshapeBatchNormActivationQuantize): Transform to be applied to "Conv2D" + "Reshape" + "BatchNorm" + "ReLU" Graph.

[`class Conv2DReshapeBatchNormQuantize`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/default_8bit/default_8bit_transforms/Conv2DReshapeBatchNormQuantize): Transform to be applied to "Conv2D" + "Reshape" + "BatchNorm" Graph.

[`class Conv2DReshapeBatchNormReLUQuantize`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/default_8bit/default_8bit_transforms/Conv2DReshapeBatchNormReLUQuantize): Transform to be applied to "Conv2D" + "Reshape" + "BatchNorm" + "ReLU" Graph.

[`class InputLayerQuantize`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/default_8bit/default_8bit_transforms/InputLayerQuantize): Quantizes InputLayer, by adding QuantizeLayer after it.

[`class LayerReLUQuantize`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/default_8bit/default_8bit_transforms/LayerReLUQuantize): Transform to be applied to "Add"+ "ReLU" Graph.

[`class LayerReluActivationQuantize`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/default_8bit/default_8bit_transforms/LayerReluActivationQuantize): Transform to be applied to "Add"+ "ReLU" Graph.

[`class SeparableConv1DQuantize`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/default_8bit/default_8bit_transforms/SeparableConv1DQuantize): Add QAT support for Keras SeparableConv1D layer.

[`class SeparableConvQuantize`](https://www.tensorflow.org/model_optimization/api_docs/python/tfmot/quantization/keras/default_8bit/default_8bit_transforms/SeparableConvQuantize): Break SeparableConv into a DepthwiseConv and Conv layer.