jddlZddlZddlmZmZmZmZmZddlZddl m Z ddl m Z ddl mZmZddlmZddlmZmZmZdd lmZdd lmZdd lmZdd lmZmZmZdd l m!Z!m"Z"ddl#m$Z$dee ej%j&fdee'efddfdZ(dej%j&ddfdZ)de ddfdZ*dej%j&ddfdZ+ d1de de,deeee'efdfdeeee'efdfde f dZ- d2dej%j&dee$ee'effde,deedfdeeee'efdfdeee$ee'effdeeee'efdfd e,de fd!Z. d1dej%j&dee$ee'effde,deedfdeeee'efdfdeeee'efdfde fd"Z/ d1dej%j&deeee'efdfdeeee'efdfde fd#Z0 d3dej%j&dee$ee'effdeedfdeeee'efdfdeee$ee'effdeeee'efdfde fd$Z1 d1dej%j&dee$ee'effdeedfdeeee'efdfdeeee'efdfde f d%Z2 d4d'e d(e,d)eeee'efdfd e,d*e,dee$ee'efdfdeeee'efdfd+e,de fd,Z3 d5d'e d)eeee'efdfd*e,dee$ee'efdfdeeee'efdfde f d-Z4 d5d'e d)eeee'efdfd*e,dee$ee'efdfdeeee'efdfde f d.Z5 d3d'e d)eeee'efdfdee$ee'efdfdeeee'efdfde f d/Z6 d6d'e d(e,d)eeee'efdfde fd0Z7dS)7N)AnyDictOptionalTupleUnion) GraphModule)_USER_PRESERVED_ATTRIBUTES_KEY) BackendConfigget_tensorrt_backend_config)convert)ConvertCustomConfigFuseCustomConfigPrepareCustomConfig)fuse)ObservedGraphModule)prepare)QuantizationTracerScopeScopeContextManager)get_custom_module_class_keys#get_skipped_module_name_and_classes)QConfigMappingmodelpreserved_attrsreturnctj||jt<|jtD]\}}t |||dS)zXStore preserved attributes to the model.meta so that it can be preserved during deepcopyN)copymetar itemssetattr)rr attr_nameattrs RC:\Projects\Historical\venv\Lib\site-packages\torch/ao/quantization/quantize_fx.pyattach_preserved_attrs_to_modelr%sc 26?1K1KEJ-.!:&DEKKMM(( 4y$''''((ct|ts2tdtt |zdzdzdS)Nz,input model must be a GraphModule, Got type:z Please make zsure to follow the tutorials.) isinstancer ValueErrorstrtype)rs r$_check_is_graph_moduler,#s_ e[ ) )  $u++  .  .     r&cR|jjD]}t|dsi|_dS)aAttach meta field to all nodes of the graph if it does not exist, meta field is a field stores some meta information about the node, such as dtype and shape information for output of the node, this only exists if the program is captured by make_fx (used in quantize_pt2e flow), if the program is captured by torch.fx symbolic tracing, this field may not exist, so we add it here to avoid checking this all over the places rN)graphnodeshasattrr)rnodes r$!_attach_meta_to_node_if_not_existr2.s< !tV$$ DIr&cTg}|D]S\}}t|tjjjjr||Dt|T|D]:}|j |=tjjj |j |<;dS)z+Swap FloatFunctional with FXFloatFunctionalN) named_childrenr(torchaonn quantizedFloatFunctionalappend_swap_ff_with_fxff_modulesFXFloatFunctional)rmodules_to_swapnamemodules r$r;r;;sO,,..'' f fehk3C D D '  " "4 ( ( ( ( v & & & &II N4 $x{4FFHHtIIr&is_qatfuse_custom_configbackend_configcDt|t||||S)zInternal helper function to fuse modules in preparation for quantization Args: model: GraphModule object from symbolic tracing (torch.fx.symbolic_trace) )r,r)rrArBrCs r$_fuse_fxrEIs.5!!!  v)>  r&Fqconfig_mappingexample_inputs.prepare_custom_config_equalization_configis_standalone_modulec |t}|t}t|tr0t jdt dtj|}tt||\}} |j } fd| D} t|| } t| } t| t|j }t#| |||} t%| ||| j||||| }t)|| |S)aZInternal helper function for prepare_fx Args: `model`, `qconfig_mapping`, `prepare_custom_config`, `_equalization_config`: see docs for :func:`~torch.ao.quantization.prepare_fx` `is_standalone_module`: a boolean flag indicates whether we are quantizing a standalone module or not, a standalone module is a submodule of the parent module that is not inlined in the forward graph of the parent module, the way we quantize standalone module is described in: :func:`~torch.ao.quantization._prepare_standalone_module_fx` NzPassing a prepare_custom_config_dict to prepare is deprecated and will not be supported in a future version. Please pass in a PrepareCustomConfig instead. stacklevelcRi|]#}t||t|$Sr0getattr.0r#rs r$ z_prepare_fx..E  5$   geT""r&)rGrHrIrCrJ)rrr(dictwarningswarn FutureWarning from_dictr;rpreserved_attributesrrtracer2rset_preserved_attributesrErnode_name_to_scoper%)rrFrArGrHrIrCrJskipped_module_namesskipped_module_classespreserved_attr_namesrtracer graph_modulerBprepareds` r$ _prepare_fxrfZs*$ 3 5 5#-//'..U  Q      !4 =>S T Tu3V344001E(O  46L M MFufll5&9&9::L%l333)++DD2L&2DnUUL!%31%1   H$Ho>>> Or&c .t||||||dS)a[Internal use only] Prepare a standalone module, so that it can be used when quantizing the parent module. standalone_module means it a submodule that is not inlined in parent module, and will be quantized separately as one unit. How the standalone module is observed is specified by `input_quantized_idxs` and `output_quantized_idxs` in the prepare_custom_config for the standalone module Returns: * model(GraphModule): prepared standalone module. It has these attributes in model.meta: * `standalone_module_input_quantized_idxs(List[Int])`: a list of indexes for the graph input that is expected to be quantized, same as input_quantized_idxs configuration provided for the standalone module * `standalone_module_output_quantized_idxs(List[Int])`: a list of indexs for the graph output that is quantized same as input_quantized_idxs configuration provided for the standalone module T)rCrJ)rf)rrFrArGrHrCs r$_prepare_standalone_module_fxrhs0>  %!   r&c|t}t|tr0tjdt dtj|}tj d|j }fd|D}tj }t|t|d||}t|||S)aFuse modules like conv+bn, conv+bn+relu etc, model must be in eval mode. Fusion rules are defined in torch.ao.quantization.fx.fusion_pattern.py Args: * `model` (torch.nn.Module): a torch.nn.Module model * `fuse_custom_config` (FuseCustomConfig): custom configurations for fuse_fx. See :class:`~torch.ao.quantization.fx.custom_config.FuseCustomConfig` for more details Example:: from torch.ao.quantization import fuse_fx m = Model().eval() m = fuse_fx(m) NzPassing a fuse_custom_config_dict to fuse is deprecated and will not be supported in a future version. Please pass in a FuseCustomConfig instead.rMz$quantization_api.quantize_fx.fuse_fxcRi|]#}t||t|$SrPrQrSs r$rUzfuse_fx..rVr&F)rr(rWrXrYrZr[r5_C_log_api_usage_oncer\fxsymbolic_tracer2rEr%)rrBrCrbrrds` r$fuse_fxrps(!-//$d++L  N      .78JKK H  !GHHH-B(O 8**511L%l333L%1C^TTL#L/BBB r&c jtjdt||d||||S)a Prepare a model for post training quantization Args: * `model` (torch.nn.Module): torch.nn.Module model * `qconfig_mapping` (QConfigMapping): QConfigMapping object to configure how a model is quantized, see :class:`~torch.ao.quantization.qconfig_mapping.QConfigMapping` for more details * `example_inputs` (Tuple[Any, ...]): Example inputs for forward function of the model, Tuple of positional args (keyword args can be passed as positional args as well) * `prepare_custom_config` (PrepareCustomConfig): customization configuration for quantization tool. See :class:`~torch.ao.quantization.fx.custom_config.PrepareCustomConfig` for more details * `_equalization_config`: config for specifying how to perform equalization on the model * `backend_config` (BackendConfig): config that specifies how operators are quantized in a backend, this includes how the operators are observed, supported fusion patterns, how quantize/dequantize ops are inserted, supported dtypes etc. See :class:`~torch.ao.quantization.backend_config.BackendConfig` for more details Return: A GraphModule with observer (configured by qconfig_mapping), ready for calibration Example:: import torch from torch.ao.quantization import get_default_qconfig_mapping from torch.ao.quantization.quantize_fx import prepare_fx class Submodule(torch.nn.Module): def __init__(self) -> None: super().__init__() self.linear = torch.nn.Linear(5, 5) def forward(self, x): x = self.linear(x) return x class M(torch.nn.Module): def __init__(self) -> None: super().__init__() self.linear = torch.nn.Linear(5, 5) self.sub = Submodule() def forward(self, x): x = self.linear(x) x = self.sub(x) + x return x # initialize a floating point model float_model = M().eval() # define calibration function def calibrate(model, data_loader): model.eval() with torch.no_grad(): for image, target in data_loader: model(image) # qconfig is the configuration for how we insert observers for a particular # operator # qconfig = get_default_qconfig("fbgemm") # Example of customizing qconfig: # qconfig = torch.ao.quantization.QConfig( # activation=MinMaxObserver.with_args(dtype=torch.qint8), # weight=MinMaxObserver.with_args(dtype=torch.qint8)) # `activation` and `weight` are constructors of observer module # qconfig_mapping is a collection of quantization configurations, user can # set the qconfig for each operator (torch op calls, functional calls, module calls) # in the model through qconfig_mapping # the following call will get the qconfig_mapping that works best for models # that target "fbgemm" backend qconfig_mapping = get_default_qconfig_mapping("fbgemm") # We can customize qconfig_mapping in different ways. # e.g. set the global qconfig, which means we will use the same qconfig for # all operators in the model, this can be overwritten by other settings # qconfig_mapping = QConfigMapping().set_global(qconfig) # e.g. quantize the linear submodule with a specific qconfig # qconfig_mapping = QConfigMapping().set_module_name("linear", qconfig) # e.g. quantize all nn.Linear modules with a specific qconfig # qconfig_mapping = QConfigMapping().set_object_type(torch.nn.Linear, qconfig) # for a more complete list, please see the docstring for :class:`torch.ao.quantization.QConfigMapping` # argument # example_inputs is a tuple of inputs, that is used to infer the type of the # outputs in the model # currently it's not used, but please make sure model(*example_inputs) runs example_inputs = (torch.randn(1, 3, 224, 224),) # TODO: add backend_config after we split the backend_config for fbgemm and qnnpack # e.g. backend_config = get_default_backend_config("fbgemm") # `prepare_fx` inserts observers in the model based on qconfig_mapping and # backend_config. If the configuration for an operator in qconfig_mapping # is supported in the backend_config (meaning it's supported by the target # hardware), we'll insert observer modules according to the qconfig_mapping # otherwise the configuration in qconfig_mapping will be ignored # # Example: # in qconfig_mapping, user sets linear module to be quantized with quint8 for # activation and qint8 for weight: # qconfig = torch.ao.quantization.QConfig( # observer=MinMaxObserver.with_args(dtype=torch.quint8), # weight=MinMaxObserver.with-args(dtype=torch.qint8)) # Note: current qconfig api does not support setting output observer, but # we may extend this to support these more fine grained control in the # future # # qconfig_mapping = QConfigMapping().set_object_type(torch.nn.Linear, qconfig) # in backend config, linear module also supports in this configuration: # weighted_int8_dtype_config = DTypeConfig( # input_dtype=torch.quint8, # output_dtype=torch.quint8, # weight_dtype=torch.qint8, # bias_type=torch.float) # linear_pattern_config = BackendPatternConfig(torch.nn.Linear) \ # .set_observation_type(ObservationType.OUTPUT_USE_DIFFERENT_OBSERVER_AS_INPUT) \ # .add_dtype_config(weighted_int8_dtype_config) \ # ... # backend_config = BackendConfig().set_backend_pattern_config(linear_pattern_config) # `prepare_fx` will check that the setting requested by suer in qconfig_mapping # is supported by the backend_config and insert observers and fake quant modules # in the model prepared_model = prepare_fx(float_model, qconfig_mapping, example_inputs) # Run calibration calibrate(prepared_model, sample_inference_data) z'quantization_api.quantize_fx.prepare_fxFr5rlrmrf)rrFrGrHrIrCs r$ prepare_fxrssCV H  !JKKK     r&cjtjdt||d|||S)aPrepare a model for quantization aware training Args: * `model` (torch.nn.Module): torch.nn.Module model * `qconfig_mapping` (QConfigMapping): see :func:`~torch.ao.quantization.prepare_fx` * `example_inputs` (Tuple[Any, ...]): see :func:`~torch.ao.quantization.prepare_fx` * `prepare_custom_config` (PrepareCustomConfig): see :func:`~torch.ao.quantization.prepare_fx` * `backend_config` (BackendConfig): see :func:`~torch.ao.quantization.prepare_fx` Return: A GraphModule with fake quant modules (configured by qconfig_mapping and backend_config), ready for quantization aware training Example:: import torch from torch.ao.quantization import get_default_qat_qconfig_mapping from torch.ao.quantization.quantize_fx import prepare_qat_fx class Submodule(torch.nn.Module): def __init__(self) -> None: super().__init__() self.linear = torch.nn.Linear(5, 5) def forward(self, x): x = self.linear(x) return x class M(torch.nn.Module): def __init__(self) -> None: super().__init__() self.linear = torch.nn.Linear(5, 5) self.sub = Submodule() def forward(self, x): x = self.linear(x) x = self.sub(x) + x return x # initialize a floating point model float_model = M().train() # (optional, but preferred) load the weights from pretrained model # float_model.load_weights(...) # define the training loop for quantization aware training def train_loop(model, train_data): model.train() for image, target in data_loader: ... # qconfig is the configuration for how we insert observers for a particular # operator # qconfig = get_default_qconfig("fbgemm") # Example of customizing qconfig: # qconfig = torch.ao.quantization.QConfig( # activation=FakeQuantize.with_args(observer=MinMaxObserver.with_args(dtype=torch.qint8)), # weight=FakeQuantize.with_args(observer=MinMaxObserver.with_args(dtype=torch.qint8))) # `activation` and `weight` are constructors of observer module # qconfig_mapping is a collection of quantization configurations, user can # set the qconfig for each operator (torch op calls, functional calls, module calls) # in the model through qconfig_mapping # the following call will get the qconfig_mapping that works best for models # that target "fbgemm" backend qconfig_mapping = get_default_qat_qconfig("fbgemm") # We can customize qconfig_mapping in different ways, please take a look at # the docstring for :func:`~torch.ao.quantization.prepare_fx` for different ways # to configure this # example_inputs is a tuple of inputs, that is used to infer the type of the # outputs in the model # currently it's not used, but please make sure model(*example_inputs) runs example_inputs = (torch.randn(1, 3, 224, 224),) # TODO: add backend_config after we split the backend_config for fbgemm and qnnpack # e.g. backend_config = get_default_backend_config("fbgemm") # `prepare_qat_fx` inserts observers in the model based on qconfig_mapping and # backend_config, if the configuration for an operator in qconfig_mapping # is supported in the backend_config (meaning it's supported by the target # hardware), we'll insert fake_quantize modules according to the qconfig_mapping # otherwise the configuration in qconfig_mapping will be ignored # see :func:`~torch.ao.quantization.prepare_fx` for a detailed explanation of # how qconfig_mapping interacts with backend_config prepared_model = prepare_qat_fx(float_model, qconfig_mapping, example_inputs) # Run training train_loop(prepared_model, train_loop) z+quantization_api.quantize_fx.prepare_qat_fxT)rCrr)rrFrGrHrCs r$prepare_qat_fxrusE~ H  !NOOO   %    r&Trd is_referenceconvert_custom_config_remove_qconfig is_decomposedc H|t}t|tr0tjdt dtj|}t|j}fd|D} t|||||||} t| | | S)z_`is_standalone_module`: see docs in :func:`~torch.ao.quantization.prepare_standalone_module_fx`NzPassing a convert_custom_config_dict to convert is deprecated and will not be supported in a future version. Please pass in a ConvertCustomConfig instead.rLrMcRi|]#}t||t|$SrPrQ)rTr#rds r$rUz_convert_fx..sE  < & & glD))r&)_remove_qconfig_flagrFrCry) rr(rWrXrYrZr[r,r\r r%) rdrvrwrJrxrFrCryrbrr8s ` r$ _convert_fxr}s$ 3 5 5'..U  Q      !4 =>S T T<(((0E(O ,'%#   I$I??? r&cjtjdt|d||||S)a Convert a calibrated or trained model to a quantized model Args: * `graph_module` (torch.fx.GraphModule): A prepared and calibrated/trained model (GraphModule) * `convert_custom_config` (ConvertCustomConfig): custom configurations for convert function. See :class:`~torch.ao.quantization.fx.custom_config.ConvertCustomConfig` for more details * `_remove_qconfig` (bool): Option to remove the qconfig attributes in the model after convert. * `qconfig_mapping` (QConfigMapping): config for specifying how to convert a model for quantization. The keys must include the ones in the qconfig_mapping passed to `prepare_fx` or `prepare_qat_fx`, with the same values or `None`. Additional keys can be specified with values set to `None`. For each entry whose value is set to None, we skip quantizing that entry in the model:: qconfig_mapping = QConfigMapping .set_global(qconfig_from_prepare) .set_object_type(torch.nn.functional.add, None) # skip quantizing torch.nn.functional.add .set_object_type(torch.nn.functional.linear, qconfig_from_prepare) .set_module_name("foo.bar", None) # skip quantizing module "foo.bar" * `backend_config` (BackendConfig): A configuration for the backend which describes how operators should be quantized in the backend, this includes quantization mode support (static/dynamic/weight_only), dtype support (quint8/qint8 etc.), observer placement for each operators and fused operators. See :class:`~torch.ao.quantization.backend_config.BackendConfig` for more details Return: A quantized model (torch.nn.Module) Example:: # prepared_model: the model after prepare_fx/prepare_qat_fx and calibration/training # convert_fx converts a calibrated/trained model to a quantized model for the # target hardware, this includes converting the model first to a reference # quantized model, and then lower the reference quantized model to a backend # Currently, the supported backends are fbgemm (onednn), qnnpack (xnnpack) and # they share the same set of quantized operators, so we are using the same # lowering procedure # # backend_config defines the corresponding reference quantized module for # the weighted modules in the model, e.g. nn.Linear # TODO: add backend_config after we split the backend_config for fbgemm and qnnpack # e.g. backend_config = get_default_backend_config("fbgemm") quantized_model = convert_fx(prepared_model) z'quantization_api.quantize_fx.convert_fxFrvrwrxrFrCr5rlrmr}rdrwrxrFrCs r$ convert_fxr+sEp H  !JKKK 3''%    r&cjtjdt|d||||S)a}Convert a calibrated or trained model to a reference quantized model, see https://github.com/pytorch/rfcs/blob/master/RFC-0019-Extending-PyTorch-Quantization-to-Custom-Backends.md for more details, reference quantized model is a standard representation of a quantized model provided by FX Graph Mode Quantization, it can be further lowered to run on the target hardware, like accelerators Args: * `graph_module` (GraphModule): A prepared and calibrated/trained model (GraphModule) * `convert_custom_config` (ConvertCustomConfig): custom configurations for convert function. See :func:`~torch.ao.quantization.quantize_fx.convert_fx` for more details. * `_remove_qconfig` (bool): Option to remove the qconfig attributes in the model after convert. * `qconfig_mapping` (QConfigMapping): config for specifying how to convert a model for quantization. See :func:`~torch.ao.quantization.quantize_fx.convert_fx` for more details. * `backend_config` (BackendConfig): A configuration for the backend which describes how operators should be quantized in the backend. See :func:`~torch.ao.quantization.quantize_fx.convert_fx` for more details. Return: A reference quantized model (GraphModule) Example:: # prepared_model: the model after prepare_fx/prepare_qat_fx and calibration/training # TODO: add backend_config after we split the backend_config for fbgemm and qnnpack # e.g. backend_config = get_default_backend_config("fbgemm") reference_quantized_model = convert_to_reference_fx(prepared_model) z4quantization_api.quantize_fx.convert_to_reference_fxTrrrs r$convert_to_reference_fxrnsEN H  !WXXX 3''%    r&c ltjdt|d|d||dS)aConvert a calibrated or trained model to a reference quantized model, with decomposed representation for quantized Tensor see https://github.com/pytorch/rfcs/blob/master/RFC-0019-Extending-PyTorch-Quantization-to-Custom-Backends.md for more details, reference quantized model is a standard representation of a quantized model provided by FX Graph Mode Quantization, it can be further lowered to run on the target hardware, like accelerators Note: this is not public API Args: * `graph_module` (GraphModule): A prepared and calibrated/trained model (GraphModule) * `convert_custom_config` (ConvertCustomConfig): custom configurations for convert function. See :func:`~torch.ao.quantization.quantize_fx.convert_fx` for more details. * `_remove_qconfig` (bool): Option to remove the qconfig attributes in the model after convert. * `qconfig_mapping` (QConfigMapping): config for specifying how to convert a model for quantization. See :func:`~torch.ao.quantization.quantize_fx.convert_fx` for more details. * `backend_config` (BackendConfig): A configuration for the backend which describes how operators should be quantized in the backend. See :func:`~torch.ao.quantization.quantize_fx.convert_fx` for more details. Return: A reference quantized model (GraphModule) with operators working with decomposed quantized Tensor Example:: # prepared_model: the model after prepare_fx/prepare_qat_fx and calibration/training # TODO: add backend_config after we split the backend_config for fbgemm and qnnpack # e.g. backend_config = get_default_backend_config("fbgemm") reference_quantized_model = _convert_to_reference_decomposed_fx(prepared_model) z@quantization_api.quantize_fx._convert_to_reference_decomposed_fxTF)rvrwrxrFrCryr)rdrwrFrCs r$#_convert_to_reference_decomposed_fxrsPR H  J 3'%   r&c(t|||dS)av[Internal use only] Convert a model produced by :func:`~torch.ao.quantization.prepare_standalone_module_fx` and convert it to a quantized model Returns a quantized standalone module, whether input/output is quantized is specified by prepare_custom_config, with input_quantized_idxs, output_quantized_idxs, please see docs for prepare_fx for details T)rJ)r})rdrvrws r$_convert_standalone_module_fxrs' !    r&)NN)NNNF)NNN)NFTNNF)NTNN)FN)8rrXtypingrrrrrr5torch.fxrtorch.fx.graph_moduler rCr r fx.convertr fx.custom_configrrrfx.fuserfx.graph_moduler fx.preparer fx.tracerrrrfx.utilsrrrFrr7Moduler*r%r,r2r;boolrErfrhrprsrur}rrrrrPr&r$rs  44444444444444 @@@@@@FFFFFFFFXXXXXXXXXX000000EEEEEEEEEE,+++++ ( eho- . (#s(^ (  ( ( ( ( %(/ d     [ T     Ieho I$ I I I I"IMAE   .S#XDE-c3h=>   ,OSLPAE!&EE 8?E>4S>9:E E#s(O E !!4d38nd!JK E #5c3h)G#HI E-c3h=>EEEEEEZOSAE '' 8?'>4S>9:' '#s(O ' !!4d38nd!JK ' -c3h=> '''''XIMAE-- 8?-.S#XDE--c3h=>- ----hOSLPAE TT 8?T>4S>9:T#s(OT!!4d38nd!JK T #5c3h)G#HI T -c3h=> TTTTTvOSAE gg 8?g>4S>9:g#s(Og!!4d38nd!JK g -c3h=> g  ggggZOS!& CGAE++++!!4d38nd!JK+ +  + >4S>4?@ +-c3h=>++++++`OS CGAE @@@ !4d38nd!JK@@>4S>4?@ @ -c3h=> @  @@@@JOS CGAE /// !4d38nd!JK//>4S>4?@ / -c3h=> /  ////hOSCGAE 444 !4d38nd!JK4>4S>4?@4-c3h=> 4  4444rNR!!4d38nd!JK r&