AffineQuantizedObserverBase

class torch.ao.quantization.observer.AffineQuantizedObserverBase(mapping_type, target_dtype, granularity, quant_min=None, quant_max=None, eps=None, scale_dtype=None, zero_point_dtype=None, preserve_zero=True, zero_point_domain=ZeroPointDomain.INT, **kwargs)

Observer module for affine quantization (https://github.com/pytorch/ao/tree/main/torchao/quantization#affine-quantization)

Parameters

• block_size (granularity and) – The granularity of the quantization, must specify at least one, if both are specified block_size takes precedence Current supported granularity type are PerTensor and PerAxis

• args (other) – please see :class:torchao.dtypes.AffineQuantizedTensor

abstract calculate_qparams()

Calculate quantization parameter based on the stats attached to the observer module and returns a tuple of scale and zero_point Tensor

Return type

Tuple[Tensor, Tensor]

abstract forward(input)

forward function should take the input tensor and updates internal stats and return the original input Tensor

Return type

Tensor

classmethod with_args(**kwargs)

Wrapper that allows creation of class factories.

This can be useful when there is a need to create classes with the same constructor arguments, but different instances. Can be used in conjunction with _callable_args

Example:

>>> Foo.with_args = classmethod(_with_args)
>>> foo_builder = Foo.with_args(a=3, b=4).with_args(answer=42)
>>> foo_instance1 = foo_builder()
>>> foo_instance2 = foo_builder()
>>> id(foo_instance1) == id(foo_instance2)
False