oneflow.nn.MinMaxObserver

class oneflow.nn.MinMaxObserver(quantization_formula: str = 'google', quantization_bit: int = 8, quantization_scheme: str = 'symmetric', per_layer_quantization: bool = True)

Compute the quantization parameters of the input tensor.

First compute the max and min values of input tensor:

\[ \begin{align}\begin{aligned}& max\_value = max(input)\\& min\_value = min(input)\end{aligned}\end{align} \]

Then compute the scale and zero_point with the following equations:

if quantization_scheme == “symmetric”:

\[ \begin{align}\begin{aligned}& denom = 2^{quantization\_to\_bit - 1} - 1\\& scale = max(|max\_value|,|min\_value|) / denom\\& zero\_point = 0\end{aligned}\end{align} \]

elif quantization_scheme == “affine”:

\[ \begin{align}\begin{aligned}& denom = 2^{quantization\_to\_bit} - 1\\& scale = (max\_value - min\_value) / denom\\& zero\_point = -min\_value / scale\end{aligned}\end{align} \]

If per_layer_quantization is False, then the shape of scale and zero_point will be (input.shape[0],).

Parameters

• input (oneflow.Tensor) – the input value(s), in oneflow.float32.

• quantization_formula (str) – Support “google” or “cambricon”.

• quantization_bit (int) – Quantize input to uintX / intX, X can be in range [2, 8]. Defaults to 8.

• quantization_scheme (str) – “symmetric” or “affine”, quantize to signed / unsigned integer. Defaults to “symmetric”.

• per_layer_quantization (bool) – True or False, means per-layer / per-channel quantization. Defaults to True.

Returns

The scale and zero_point of input tensor.

Return type

Tuple[oneflow.Tensor, oneflow.Tensor]

For example:

>>> import numpy as np
>>> import oneflow as flow

>>> weight = (np.random.random((2, 3, 4, 5)) - 0.5).astype(np.float32)

>>> input_tensor = flow.tensor(
...    weight, dtype=flow.float32
... )

>>> quantization_bit = 8
>>> quantization_scheme = "symmetric"
>>> quantization_formula = "google"
>>> per_layer_quantization = True

>>> min_max_observer = flow.nn.MinMaxObserver(quantization_formula=quantization_formula, quantization_bit=quantization_bit,
... quantization_scheme=quantization_scheme, per_layer_quantization=per_layer_quantization)

>>> scale, zero_point = min_max_observer(
...    input_tensor, )

__init__(quantization_formula: str = 'google', quantization_bit: int = 8, quantization_scheme: str = 'symmetric', per_layer_quantization: bool = True) → None

Initialize self. See help(type(self)) for accurate signature.

Methods

__call__(*args, **kwargs)	Call self as a function.
__delattr__(name)	Implement delattr(self, name).
__dir__()	Default dir() implementation.
__eq__(value, /)	Return self==value.
__format__(format_spec, /)	Default object formatter.
__ge__(value, /)	Return self>=value.
__getattr__(name)
__getattribute__(name, /)	Return getattr(self, name).
__getstate__()
__gt__(value, /)	Return self>value.
__hash__()	Return hash(self).
__init__([quantization_formula, …])	Initialize self.
__init_subclass__	This method is called when a class is subclassed.
__le__(value, /)	Return self<=value.
__lt__(value, /)	Return self<value.
__ne__(value, /)	Return self!=value.
__new__(**kwargs)	Create and return a new object.
__reduce__()	Helper for pickle.
__reduce_ex__(protocol, /)	Helper for pickle.
__repr__()	Return repr(self).
__setattr__(name, value)	Implement setattr(self, name, value).
__setstate__(state)
__sizeof__()	Size of object in memory, in bytes.
__str__()	Return str(self).
__subclasshook__	Abstract classes can override this to customize issubclass().
_apply(fn)
_get_name()
_load_from_state_dict(state_dict, prefix, …)
_named_members(get_members_fn[, prefix, recurse])
_save_to_state_dict(destination, prefix, …)
_shallow_repr()
add_module(name, module)	Adds a child module to the current module.
apply(fn)	Applies fn recursively to every submodule (as returned by .children()) as well as self.
buffers([recurse])	Returns an iterator over module buffers.
children()	Returns an iterator over immediate children modules.
cpu()	Moves all model parameters and buffers to the CPU.
cuda([device])	Moves all model parameters and buffers to the GPU.
double()	Casts all floating point parameters and buffers to double datatype.
eval()	Sets the module in evaluation mode.
extra_repr()	Set the extra representation of the module
float()	Casts all floating point parameters and buffers to float datatype.
forward(input)
half()	Casts all floating point parameters and buffers to half datatype.
load_state_dict(state_dict[, strict])	Copies parameters and buffers from state_dict into this module and its descendants.
modules()	Returns an iterator over all modules in the network.
named_buffers([prefix, recurse])	Returns an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.
named_children()	Returns an iterator over immediate children modules, yielding both the name of the module as well as the module itself.
named_modules([memo, prefix])	Returns an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
named_parameters([prefix, recurse])	Returns an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
parameters([recurse])	Returns an iterator over module parameters.
register_buffer(name, tensor[, persistent])	Adds a buffer to the module.
register_forward_hook(hook)	Registers a forward hook on the module.
register_forward_pre_hook(hook)	Registers a forward pre-hook on the module.
register_parameter(name, param)	Adds a parameter to the module.
requires_grad_([requires_grad])	Change if autograd should record operations on parameters in this module.
state_dict([destination, prefix, keep_vars])	Returns a dictionary containing a whole state of the module.
to(*args, **kwargs)	Moves and/or casts the parameters and buffers.
to_consistent(*args, **kwargs)	This interface is no longer available, please use oneflow.nn.Module.to_global() instead.
to_global([placement, sbp])	Convert the parameters and buffers to global.
to_local()
train([mode])	Sets the module in training mode.
zero_grad([set_to_none])	Sets gradients of all model parameters to zero.