U yh4( @sUddlmZddlmmmZddlmZmZm Z m Z m Z m Z m Z mZddlmZmZmZddlZdddddd gZd dZd dZd dZd dZddZejejfeejejejfeejejfeejejejfeejej feejej ejfeejejfeej!ejejfeej"ejejfeej#ej$ejfeej$ejfeej%ejejfeej&ej ejfeej'ej(ejfeej)ejfeej*ej feiZ+e e eej,e ffe-d<dddZ.ddZ/ddZ0ddZ1ee eeej,e ffddd Z2dS)N)AnyUnionCallableListTupleDictOptionalType)Patternget_combined_dict MatchAllNode fuse_conv_bnfuse_conv_bn_relufuse_linear_bnfuse_convtranspose_bnget_fuser_methodget_fuser_method_newcCs|j|jkstdtjtjtjtjtjtj i}|r|j |j ksHtd|j sVtd|j sdtd|t|d}|dk r|||Std||fntj||SdS)aReturn the fused the conv and bn modules. Given the conv and bn modules, fuses them and returns the fused module Args: is_qat: a flag for whether we are using quantization aware training fusion or post training quantization fusion conv: Module instance of type conv2d/conv3d bn: Spatial BN instance that needs to be fused with the conv Examples:: >>> m1 = nn.Conv2d(10, 20, 3) >>> b1 = nn.BatchNorm2d(20) >>> # xdoctest: +SKIP >>> m2 = fuse_conv_bn(m1, b1) :Conv and BN both must be in the same mode (train or eval).z?Output channel of Conv2d must match num_features of BatchNorm2dz7Only support fusing BatchNorm2d with affine set to TruezGOnly support fusing BatchNorm2d with tracking_running_stats set to TrueNCannot fuse train modules: )trainingAssertionErrornnConv1dnniZConvBn1dConv2dZConvBn2dConv3dZConvBn3d num_features out_channelsaffinetrack_running_statsgettypeNotImplementedErrorutilsfuse_conv_bn_eval)is_qatconvbnZfused_module_class_mapZfused_module_classr(]/var/www/html/venv/lib/python3.8/site-packages/torch/ao/quantization/fuser_method_mappings.pyr s& cCs|j|jkr|jks$ntdd}|rtjtjtjtjtjtj i}|j |j ks\td|j sjtd|j sxtd|t|d}|dk r||||Std|||fndtjtjtjtjtjtji}|t|d}|dk rtjj||}|||Std|||fdS)aJReturn the fused conv and bv modules. Given the conv and bn modules, fuses them and returns the fused module Args: is_qat: a flag for whether we are using quantization aware training fusion or post training quantization fusion conv: Module instance of type conv2d/conv3d bn: Spatial BN instance that needs to be fused with the conv Examples:: >>> m1 = nn.Conv2d(10, 20, 3) >>> b1 = nn.BatchNorm2d(20) >>> r1 = nn.ReLU(inplace=False) >>> # xdoctest: +SKIP >>> m2 = fuse_conv_bn_relu(m1, b1, r1) rNz;Output channel of Conv must match num_features of BatchNormz5Only support fusing BatchNorm with affine set to TruezEOnly support fusing BatchNorm with tracking_running_stats set to TruerzCannot fuse eval modules: )rrrrrZ ConvBnReLU1drZ ConvBnReLU2drZ ConvBnReLU3drrrrr r!r" ConvReLU1d ConvReLU2d ConvReLU3dr#fusionr$)r%r&r'ZreluZ fused_moduleZmap_to_fused_module_trainZmap_to_fused_module_evalZ fused_convr(r(r)r8s>   cCsh|j|jkstd|rT|j|jks,td|js:td|jsHtdt||Stj j ||SdS)aReturn the fused linear and bn modules. Given the linear and bn modules, fuses them and returns the fused module Args: is_qat: a flag for whether we are using quantization aware training fusion or post training quantization fusion linear: Module instance of type Linear bn: BatchNorm1d instance that needs to be fused with the linear layer Examples:: >>> m1 = nn.Linear(20, 10) >>> b1 = nn.BatchNorm1d(10) >>> # xdoctest: +SKIP >>> m2 = fuse_linear_bn(m1, b1) z>> m1 = nn.ConvTranspose2d(10, 20, 3) >>> b1 = nn.BatchNorm2d(20) >>> # xdoctest: +SKIP >>> m2 = fuse_convtranspose_bn(m1, b1) zCConvTranspose and BN both must be in the same mode (train or eval).z8Fusing ConvTranspose+BatchNorm not yet supported in QAT.T)Z transposeN)rr Exceptionrr#r-r$)r%Zconvtr'r(r(r)rs  csfdd}|S)a!Return a sequential wrapped that for is_qat and two modules. Given a sequential class for two modules, return a function that takes is_qat, and then two modules as argument, that ignores the is_qat flag and always returns the sequential that combines the two input modules cs ||SNr()r%m1m2 sequentialr(r) fuser_methodsz*_sequential_wrapper2..fuser_methodr()r3r4r(r2r)_sequential_wrapper2s r5 _DEFAULT_OP_LIST_TO_FUSER_METHODcCs>|dkr i}tt|}||d}|dk s:td|d|S)zGet fuser method for the given list of module types. Get fuser method for the given list of module types, return None if fuser method does not exist Ndid not find fuser method for:  )r r6r r)Zop_listZadditional_fuser_method_mappingZ all_mappingsr4r(r(r)rs csfdd}|S)Ncs |||Sr/r()r%xyfr(r)reversedsz_reverse2..reversedr(r<r=r(r;r) _reverse2s r?csfdd}|S)Ncs|\}}||||Sr/r()r%r9wr:zr;r(r)r=sz_reverse3..reversedr(r>r(r;r) _reverse3s rBcCsFt|ttfr:g}|D]}|t|qttj|}n|tg}|S)aQReturn a list of valid patterns generated from the op_pattern. Returns a list of valid patterns generated from the op_pattern, since MatchAllNode can match all types of nodes, e.g. pattern (torch.nn.Conv2d, torch.add) should also be able to match keys like (MatchAllNode, torch.add) and (torch.nn.Conv2d, MatchAllNode) Example Input: (torch.add, (torch.nn.ReLU, torch.nn.Conv2d)) Example Output: [(torch.add, (torch.nn.ReLU, torch.nn.Conv2d)), (torch.add, (torch.nn.ReLU, MatchAllNode)), (torch.add, (MatchAllNode, torch.nn.Conv2d)), (torch.add, (MatchAllNode, MatchAllNode)), (MatchAllNode, (torch.nn.ReLU, torch.nn.Conv2d)), (MatchAllNode, (torch.nn.ReLU, MatchAllNode)), (MatchAllNode, (MatchAllNode, torch.nn.Conv2d)), (MatchAllNode, (MatchAllNode, MatchAllNode)), ] ) isinstancetuplelistappend_get_valid_patterns itertoolsproductr ) op_patternZ sub_combsZ sub_patternresultr(r(r)rGsrG)rJfuser_method_mappingcCsJt|}d}|D]}||d}|dk rq.q|dk sFtd|d|S)zGet fuser method. This will be made default after we deprecate the get_fuser_method Would like to implement this first and have a separate PR for deprecation Nr7r8)rGr r)rJrLZ op_patternsr4r(r(r)rs )N)3Ztorch.nnrZtorch.ao.nn.intrinsicZaoZ intrinsicrtypingrrrrrrrr Ztorch.ao.quantization.utilsr r r rH__all__r rrrr5rZ BatchNorm1dZReLUrZ BatchNorm2drZ BatchNorm3dr*r+r,ZLinearZ LinearReLUZBNReLU2dZBNReLU3dZConvTranspose1dZConvTranspose2dZConvTranspose3dr6Z Sequential__annotations__rr?rBrGrr(r(r(r)sr ( &1              !