mqbench.utils package

Submodules

mqbench.utils.logger

mqbench.utils.logger.disable_logging()

mqbench.utils.logger.set_log_level(level)

mqbench.utils.registry

mqbench.utils.registry.register_convert_function(module_type)

mqbench.utils.registry.register_deploy_function(backend_type)

mqbench.utils.registry.register_model_quantizer(backend_type)

mqbench.utils.registry.register_weight_equalization_function(layer1, layer2)

mqbench.utils.state

mqbench.utils.state.disable_all(model)

mqbench.utils.state.enable_calibration(model)

mqbench.utils.state.enable_calibration_quantization(model, quantizer_type='fake_quant')

mqbench.utils.state.enable_calibration_woquantization(model, quantizer_type='fake_quant')

mqbench.utils.state.enable_quantization(model)

mqbench.utils.utils

mqbench.utils.utils.deepcopy_graphmodule(gm: GraphModule)

Rewrite the deepcopy of GraphModule. (Copy its ‘graph’.)

Parameters

gm (GraphModule) –

Returns

A deepcopied gm.

Return type

GraphModule

mqbench.utils.utils.deepcopy_mixedmodule(mm: Module, module_list: list)

Support for module_list which splits modules’ nn part and post precess.

Parameters

• mm (nn.Module) –

• module_list (list) – the children of the mm who are a GraphModule.

Returns

nn.Module

mqbench.utils.utils.getitem2node(model: GraphModule) → dict

mqbench.utils.utils.is_symmetric_quant(qscheme: qscheme) → bool

mqbench.utils.utils.is_tracing_state()

class mqbench.utils.utils.no_jit_trace

Bases: object

mqbench.utils.utils.pot_quantization(tensor: Tensor, mode='round')

mqbench.utils.utils.sync_tensor(tensor)

mqbench.utils.utils.topology_order(model)

Module contents