wehub-resource-sync
32 lines
707 B
ReStructuredText
32 lines
707 B
ReStructuredText
.. role:: hidden
|
|
:class: hidden-section
|
|
|
|
pytorch_quantization.tensor_quant
|
|
===================================
|
|
|
|
.. automodule:: pytorch_quantization.tensor_quant
|
|
.. currentmodule:: pytorch_quantization.tensor_quant
|
|
|
|
|
|
:hidden:`QuantDescriptor`
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
.. autoclass:: QuantDescriptor
|
|
:members:
|
|
|
|
:hidden:`ScaledQuantDescriptor`
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
.. autoclass:: ScaledQuantDescriptor
|
|
:members:
|
|
|
|
:hidden:`TensorQuantFunction`
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
.. autoclass:: TensorQuantFunction
|
|
:members:
|
|
|
|
``tensor_quant`` is alias of ``TensorQuantFunction.apply``
|
|
|
|
``fake_tensor_quant`` is alias of ``FakeTensorQuantFunction.apply``
|