neural_compressor.compression.pruner.patterns.base

Pruning patterns.

Module Contents

Classes

BasePattern	Pruning Pattern.
PytorchBasePattern	Pruning Pattern.
KerasBasePattern	Pruning Pattern.

Functions

register_pattern(name)

Class decorator used to register a Pattern subclass to the registry.

neural_compressor.compression.pruner.patterns.base.register_pattern(name)

Class decorator used to register a Pattern subclass to the registry.

Decorator function used before a Pattern subclasses. Make sure that this Pattern class can be registered in PATTERNS.

Parameters:

name – A string defining the pattern type name to be used in a pruning process.

Returns:

The class of register.

Return type:

cls

class neural_compressor.compression.pruner.patterns.base.BasePattern(config, modules)

Pruning Pattern.

It defines the basic pruning unit and how this unit will be pruned during pruning, e.g. 4x1, 2:4.

Parameters:

• config – A config dict object that contains the pattern information.

• modules – neural network modules to be pruned with the pattern.

pattern

A config dict object that includes information of the pattern.

is_global

A bool determining whether the pruning takes global pruning option. Global pruning means that pruning scores by a pruning criterion are evaluated in all layers. Local pruning, by contrast, means that pruning scores by the pruning criterion are evaluated

in every layer individually.

keep_mask_layers

A dict that includes the layers whose mask will not be updated.

invalid_layers

The layers whose shapes don’t fit the pattern.

modules

neural network modules to be pruned with the pattern.

config

A config dict object that contains all the information including the pattern’s.

max_sparsity_ratio_per_op

A float representing the maximum sparsity that one layer could reach.

min_sparsity_ratio_per_op

A float representing the minimum sparsity that one layer could reach.

target_sparsity

A float representing the sparsity ratio of the modules after pruning.

class neural_compressor.compression.pruner.patterns.base.PytorchBasePattern(config, modules)

Pruning Pattern.

It defines the basic pruning unit and how this unit will be pruned during pruning, e.g. 4x1, 2:4.

Parameters:

• config – A config dict object that contains the pattern information.

• modules – neural network modules to be pruned with the pattern.

pattern

A config dict object that includes information of the pattern.

is_global

A bool determining whether the pruning takes global pruning option. Global pruning means that pruning scores by a pruning criterion are evaluated in all layers. Local pruning, by contrast, means that pruning scores by the pruning criterion are evaluated

in every layer individually.

keep_mask_layers

A dict that includes the layers whose mask will not be updated.

invalid_layers

The layers whose shapes don’t fit the pattern.

modules

neural network modules to be pruned with the pattern.

config

A config dict object that contains all the information including the pattern’s.

max_sparsity_ratio_per_op

A float representing the maximum sparsity that one layer could reach.

min_sparsity_ratio_per_op

A float representing the minimum sparsity that one layer could reach.

target_sparsity

A float representing the sparsity ratio of the modules after pruning.

class neural_compressor.compression.pruner.patterns.base.KerasBasePattern(config, modules)

Pruning Pattern.

It defines the basic pruning unit and how this unit will be pruned during pruning, e.g. 4x1, 2:4.

Parameters:

• config – A config dict object that contains the pattern information.

• modules – neural network modules to be pruned with the pattern.

pattern

A config dict object that includes information of the pattern.

is_global

A bool determining whether the pruning takes global pruning option. Global pruning means that pruning scores by a pruning criterion are evaluated in all layers. Local pruning, by contrast, means that pruning scores by the pruning criterion are evaluated

in every layer individually.

keep_mask_layers

A dict that includes the layers whose mask will not be updated.

invalid_layers

The layers whose shapes don’t fit the pattern.

modules

neural network modules to be pruned with the pattern.

config

A config dict object that contains all the information including the pattern’s.

max_sparsity_ratio_per_op

A float representing the maximum sparsity that one layer could reach.

min_sparsity_ratio_per_op

A float representing the minimum sparsity that one layer could reach.

target_sparsity

A float representing the sparsity ratio of the modules after pruning.