tfmot.quantization.keras.quantizers.Quantizer  |  TensorFlow Model Optimization (original) (raw)

tfmot.quantization.keras.quantizers.Quantizer

Stay organized with collections Save and categorize content based on your preferences.

ABC interface which encapsulates the logic of how to quantize tensors.

Used in the notebooks

This is an experimental API not subject to backward compatibility.

A Quantizer is used by the library code to apply the mathematical transformations which actually quantize a tensor, hence allowing the user precise control over the algorithm with which tensors are quantized. When used in conjunction with QuantizeConfig it controls how a layer is quantized.

Create a custom quantizer:

class FixedRangeQuantizer(Quantizer):
  # Example quantizer which clips tensors in a fixed range.

  def build(self, tensor_shape, name, layer):
    range_var = layer.add_weight(
      name + '_range',
      initializer=keras.initializers.Constant(6.0),
      trainable=False)

    return {
      'range_var': range_var,
    }

  def __call__(self, inputs, training, weights, **kwargs):
    return tf.keras.backend.clip(
        inputs, 0.0, weights['range_var'])

  def get_config(self):
    # Not needed. No __init__ parameters to serialize.
    return {}

For a full example, seehttps://www.tensorflow.org/model_optimization/guide/quantization/training_comprehensive_guide.md

Methods

build

View source

@abc.abstractmethod build( tensor_shape, name, layer )

Construct the weights required by the quantizer.

A quantizer may need to construct variables to hold the state for its algorithm. This function is invoked during the build stage of the layer that the quantizer is used for. Any variables constructed are under the scope of the layer and serialized as part of the layer.

Returns: Dictionary of constructed weights. This dictionary will be passed to the quantizer's call function as a weights dictionary.

from_config

View source

@classmethod from_config( config )

Instantiates a Quantizer from its config.

get_config

View source

@abc.abstractmethod get_config()

Returns the config used to serialize the Quantizer.

__call__

View source

@abc.abstractmethod __call__( inputs, training, weights, **kwargs )

Apply quantization to the input tensor.

This is the main function of the Quantizer which implements the core logic to quantize the tensor. It is invoked during the call stage of the layer, and allows modifying the tensors used in graph construction.

Returns: quantized tensor.