+ &ja^RIHt^RIt^RIHt^RIt.ROt]!RRR7t]!RRR7tRR R llt RR R llt R Rlt RRlt R#)) annotationsN)TypeVarConvTztorch.nn.modules.conv._ConvNd)boundLinearTztorch.nn.Linearc(V^8dQhRRRRRRRR/#)convrbn%torch.nn.modules.batchnorm._BatchNorm transposeboolreturn)formats"m/Users/jameslopez/projects/CWCArchive/cwc-podcast/.venv/lib/python3.14/site-packages/torch/nn/utils/fusion.py __annotate__rs0## #-## #c VP'gVP'd \R4h\P!V4pVPeVP f \R4h\ VPVPVPVP VPVPVPV4wVnVnV#)aFuse a convolutional module and a BatchNorm module into a single, new convolutional module. Args: conv (torch.nn.modules.conv._ConvNd): A convolutional module. bn (torch.nn.modules.batchnorm._BatchNorm): A BatchNorm module. transpose (bool, optional): If True, transpose the convolutional weight. Defaults to False. Returns: torch.nn.modules.conv._ConvNd: The fused convolutional module. .. note:: Both ``conv`` and ``bn`` must be in eval mode, and ``bn`` must have its running buffers computed. Fusion only for eval!3bn.running_mean and bn.running_var must not be None) trainingAssertionErrorcopydeepcopy running_mean running_varfuse_conv_bn_weightsweightbiaseps)r r r fused_convs&&& rfuse_conv_bn_evalr#s$ }}} 455t$J ".."8RSS)=      *&Jz rc<V^8dQhRRRRRRRRRRR RR RR R R R/ #)r conv_w torch.Tensorconv_btorch.Tensor | Nonebn_rmbn_rvbn_epsfloatbn_wbn_br rr-tuple[torch.nn.Parameter, torch.nn.Parameter]r)rs"rrr:sb22 2 2 2  2  2  2 2232rc2VPpVe VPMTp Vf\P!V4pVf\P!V4pVf\P!V4p\P!W4,4p V'd/^R.^.\ VP 4^, ,,p M-R^.^.\ VP 4^, ,,p WV ,PV 4,PVR7p W, V ,V,V,PV R7p \PPWP4\PPWP43#)aFuse convolutional module parameters and BatchNorm module parameters into new convolutional module parameters. Args: conv_w (torch.Tensor): Convolutional weight. conv_b (Optional[torch.Tensor]): Convolutional bias. bn_rm (torch.Tensor): BatchNorm running mean. bn_rv (torch.Tensor): BatchNorm running variance. bn_eps (float): BatchNorm epsilon. bn_w (Optional[torch.Tensor]): BatchNorm weight. bn_b (Optional[torch.Tensor]): BatchNorm bias. transpose (bool, optional): If True, transpose the conv weight. Defaults to False. Returns: Tuple[torch.nn.Parameter, torch.nn.Parameter]: Fused convolutional weight and bias. dtype) r2torch zeros_like ones_likersqrtlenshapereshapetonn Parameter requires_grad)r%r'r)r*r+r-r.r conv_weight_dtypeconv_bias_dtype bn_var_rsqrtr9 fused_conv_w fused_conv_bs&&&&&&&& rrr:sI2 &,&8fll>OO ~!!%( |u% |&;;u~.LB1#V\\!2Q!677Q1#V\\!2Q!677\1::5AAEEFL^|3d:TAEEFL <)=)=> <)=)=> rc$V^8dQhRRRRRR/#)r linearrr r rr)rs"rrros&00 0-0 0rc JVP'gVP'd \R4h\P!V4pVPVP 8wd7VP ^8wd&\RVP RVP 24hVP eVPf \R4h\VPVPVP VPVPVPVP4wVn Vn V#)asFuse a linear module and a BatchNorm module into a single, new linear module. Args: linear (torch.nn.Linear): A Linear module. bn (torch.nn.modules.batchnorm._BatchNorm): A BatchNorm module. Returns: torch.nn.Linear: The fused linear module. .. note:: Both ``linear`` and ``bn`` must be in eval mode, and ``bn`` must have its running buffers computed. rzaTo fuse, linear.out_features == bn.num_features or bn.num_features == 1, got linear.out_features=z and bn.num_features=r) rrrr out_features num_featuresrrfuse_linear_bn_weightsrr r!)rEr fused_linears&& rfuse_linear_bn_evalrKos "+++455==(L boo-"//Q2F''-':':&;;PQSQ`Q`Pa c   ".."8RSS-C     .*L* rc8V^8dQhRRRRRRRRRRR RR RR R /#) r linear_wr&linear_br(r)r*r+r,r-r.rr/r)rs"rrrsX"""!" "  "  "  " "3"rcVPpVe VPMTpVf\P!V4pV\P!W4,4,p W P R4P VR7,p W, V ,V,P VR7p \P PWP4\P PWP43#)aFuse linear module parameters and BatchNorm module parameters into new linear module parameters. Args: linear_w (torch.Tensor): Linear weight. linear_b (Optional[torch.Tensor]): Linear bias. bn_rm (torch.Tensor): BatchNorm running mean. bn_rv (torch.Tensor): BatchNorm running variance. bn_eps (float): BatchNorm epsilon. bn_w (torch.Tensor): BatchNorm weight. bn_b (torch.Tensor): BatchNorm bias. Returns: Tuple[torch.nn.Parameter, torch.nn.Parameter]: Fused linear weight and bias. r1r3) r2r4r5r7 unsqueezer;r<r=r>) rMrNr)r*r+r-r.linear_weight_dtypelinear_bias_dtypebn_scalefused_wfused_bs &&&&&&& rrIrIs.#..*2*>DW##E*ekk%.11H++B/229L2MMG H,t377>O7PG 88  g'='= >@R@R''A r)r#rrKrI)F) __future__rrtypingrr4__all__rrr#rrKrIrrrrYsK"    >? )#4 5#L2j0f"r