[ThSSKrSSKJr SSKJr SSKJrJrJr SSK J r /SQr Sr Sr SSjr\S4S jrS \S4S jrS \S4S jrS \S4S jrg)N)Optional) fuse_conv_bnfuse_conv_bn_reluget_fuser_methodtype_before_parametrizations)fuse_known_modules fuse_modulesfuse_modules_qatcTURS5nUnUHn[X45nM U$)N.)splitgetattr)model submodule_keytokenscur_modss Z/var/www/auris/envauris/lib/python3.13/site-packages/torch/ao/quantization/fuse_modules.py _get_modulers0   %FG '% NczURS5nUSSnUnUHn[XV5nM [XSSU5 g)Nr )rrsetattr)rrmoduler sub_tokensrrs r _set_moduler!sF   %FJG '% GBZ(rct[SU55n[X25nUc[SU35eS/[U5-nU"U/UQ76nUSRR 5HnUR U5 M USRR5 USRR 5HnURU5 M USRR5 XeS'[S[U55H0n [R"5n USRU l XU 'M2 U$)azReturn a list of known fuse modules. Returns a list of modules that fuses the operations specified in the input module list. Fuses only the following sequence of modules: conv, bn conv, bn, relu conv, relu linear, bn linear, relu For these sequences, the first element in the output module list performs the fused operation. The rest of the elements are set to nn.Identity() c38# UHn[U5v M g7fNr).0ms r %fuse_known_modules..:sD8a.q118sNzCannot fuse modules: rr)tuplerNotImplementedErrorlen_forward_pre_hooksvaluesregister_forward_pre_hookclear_forward_hooksregister_forward_hookrangennIdentitytraining) mod_listis_qatadditional_fuser_method_mappingtypes fuser_methodnew_modfused pre_hook_fnhook_fniidentitys rr r +s! D8D DE#EKL!$9%"ABB*.#h-)?G  +( +E {55<<>  '' 4? QK""((*B<..557 ##G,8 RL%%'AJ 1c(m $;;=$QK00 % NrcUc0nURS05nUVs/sHn[X5PM nnU"XrU5n[U5Hup[XX5 M gs snf)Nr5)getr enumerater) rmodules_to_fuser4 fuser_funcfuse_custom_config_dictr5itemr3 new_mod_listr<s r_fuse_modules_helperrFSsv&"$&=&A&A)2'#6EE_T E(_HEh0OPL_-E1. FsAFcU(d[R"U5n[SU55(a[XX$U5 U$UHn[XX$U5 M U$)Nc3B# UHn[U[5v M g7fr ) isinstancestr)r!module_elements rr# _fuse_modules..ts Q~:nc * *s)copydeepcopyallrF)rrAr4inplacerBrC module_lists r _fuse_modulesrRis`  e$ Q QQQ F8O  L +K F8O + Lrc [UUSUUUS9$)aFuse a list of modules into a single module. Fuses only the following sequence of modules: conv, bn conv, bn, relu conv, relu linear, relu bn, relu All other sequences are left unchanged. For these sequences, replaces the first item in the list with the fused module, replacing the rest of the modules with identity. Args: model: Model containing the modules to be fused modules_to_fuse: list of list of module names to fuse. Can also be a list of strings if there is only a single list of modules to fuse. inplace: bool specifying if fusion happens in place on the model, by default a new model is returned fuser_func: Function that takes in a list of modules and outputs a list of fused modules of the same length. For example, fuser_func([convModule, BNModule]) returns the list [ConvBNModule, nn.Identity()] Defaults to torch.ao.quantization.fuse_known_modules `fuse_custom_config_dict`: custom configuration for fusion .. code-block:: python # Example of fuse_custom_config_dict fuse_custom_config_dict = { # Additional fuser_method mapping "additional_fuser_method_mapping": { (torch.nn.Conv2d, torch.nn.BatchNorm2d): fuse_conv_bn }, } Returns: model with fused modules. A new copy is created if inplace=True. Examples:: >>> # xdoctest: +SKIP >>> m = M().eval() >>> # m is a module containing the sub-modules below >>> modules_to_fuse = [ ['conv1', 'bn1', 'relu1'], ['submodule.conv', 'submodule.relu']] >>> fused_m = torch.ao.quantization.fuse_modules(m, modules_to_fuse) >>> output = fused_m(input) >>> m = M().eval() >>> # Alternately provide a single list of modules to fuse >>> modules_to_fuse = ['conv1', 'bn1', 'relu1'] >>> fused_m = torch.ao.quantization.fuse_modules(m, modules_to_fuse) >>> output = fused_m(input) Fr4rPrBrCrRrrArPrBrCs rr r s$z   7  rc [UUSUUUS9$)zQAT version for `fuse_modules`.TrTrUrVs rr r s#   7  rr )rMtypingrtorch.nnr0+torch.ao.quantization.fuser_method_mappingsrrrtorch.nn.utils.parametrizer__all__rrr rFrRr r rrr^st  D )%X" 24 ! 8 ! DT ! r