QЦiAHSSKJr SSKJrJrJrJr SSKrSSKJ r SSKJ r SSK J r SSK Jr SS KJrJrJr SS KJr SS KJrJr SS K JrJrJrJr S SKJrJrJr /SQr "SS\ RB5r""SS\ RF5r$S\\%S\\%S\\S\&S\&S\S\$4Sjr'S\SSSS .r("S!S"\5r)"S#S$\5r*"S%S&\5r+"S'S(\5r,\"S)S*9\"S+S,4S-9SS.S/S0.S\\\)\4S\&S\&S\S\$4 S1jj55r-\"S2S*9\"S+S34S-9SS.S/S0.S\\\*\4S\&S\&S\S\$4 S4jj55r.\"S5S*9\"S+S64S-9SS.S/S0.S\\\+\4S\&S\&S\S\$4 S7jj55r/\"S8S*9\"S+S94S-9SS.S/S0.S\\\,\4S\&S\&S\S\$4 S:jj55r0g);)partial)AnyListOptionalUnionN)Tensor) shufflenetv2)ImageClassification)register_modelWeights WeightsEnum)_IMAGENET_CATEGORIES)_ovewrite_named_paramhandle_legacy_interface)ShuffleNet_V2_X0_5_WeightsShuffleNet_V2_X1_0_WeightsShuffleNet_V2_X1_5_WeightsShuffleNet_V2_X2_0_Weights) _fuse_modules _replace_reluquantize_model) QuantizableShuffleNetV2#ShuffleNet_V2_X0_5_QuantizedWeights#ShuffleNet_V2_X1_0_QuantizedWeights#ShuffleNet_V2_X1_5_QuantizedWeights#ShuffleNet_V2_X2_0_QuantizedWeightsshufflenet_v2_x0_5shufflenet_v2_x1_0shufflenet_v2_x1_5shufflenet_v2_x2_0cJ^\rSrSrS\S\SS4U4SjjrS\S\4SjrS rU=r $) QuantizableInvertedResidual#argskwargsreturnNcl>[TU]"U0UD6 [RR 5UlgN)super__init__nn quantizedFloatFunctionalcatselfr'r( __class__s k/var/www/html/ai-image-ml/venv/lib/python3.13/site-packages/torchvision/models/quantization/shufflenetv2.pyr-$QuantizableInvertedResidual.__init__$s) $)&)<<//1xcBURS:Xa=URSSS9up#URRX RU5/SS9nO:URRUR U5URU5/SS9n[ R "US5nU$)Nrr )dim)stridechunkr1branch2branch1r channel_shuffle)r3r8x1x2outs r5forward#QuantizableInvertedResidual.forward(s ;;! WWQAW&FB((,,LL$451,=C((,, QaAq,IC**32 r7)r1) __name__ __module__ __qualname____firstlineno__rr-rrC__static_attributes__ __classcell__r4s@r5r%r%#s52c2S2T2  F  r7r%cf^\rSrSrS\S\SS4U4SjjrS\S\4SjrS S \\ SS4S jjr S r U=r $) r4r'r(r)Nc>[TU]"US[0UD6 [RR R 5Ul[RR R5Ul g)Ninverted_residual) r,r-r%torchao quantization QuantStubquant DeQuantStubdequantr2s r5r- QuantizableShuffleNetV2.__init__6sP $X2MXQWXXX**446 xx,,88: r7r8clURU5nURU5nURU5nU$r+)rT _forward_implrV)r3r8s r5rCQuantizableShuffleNetV2.forward;s1 JJqM   q ! LLOr7is_qatcURR5H!up#US;dM UcM[U/SQ/USS9 M# UR5Hn[ U5[ LdM[ URRR55S:a[URSS//S Q/USS9 [UR/SQS S //S Q/USS9 M g) aFuse conv/bn/relu modules in shufflenetv2 model Fuse conv+bn+relu/ conv+relu/conv+bn modules to prepare for quantization. Model is modified in place. .. note:: Note that this operation does not change numerics and the model after modification is in floating point )conv1conv5N)012T)inplacerr_r`)ra34rcrd)567) _modulesitemsrmodulestyper%lenr>r=)r3r[namems r5 fuse_model"QuantizableShuffleNetV2.fuse_modelAs}}**,GD))ama/!2FDI-AAw55qyy))//12Q6!!))sCj/-JF\`aII$sCj/B   r7)rVrTr+) rErFrGrHrr-rrCrboolrorIrJrKs@r5rr4sL;c;S;T; F $4r7rstages_repeatsstages_out_channelsweightsprogressquantizer(r)c `UbM[US[URS55 SUR;a[USURS5 URSS5n[ X40UD6n[ U5 U(a [ Xv5 UbURURUSS95 U$)N num_classes categoriesbackendfbgemmT)ru check_hash) rrlmetapoprrrload_state_dictget_state_dict)rrrsrtrurvr(rzmodels r5 _shufflenetv2rZsfmSl9S5TU  $ !&)W\\)5L MjjH-G #N R6 RE%u& g44hSW4XY Lr7)rrr{zdhttps://github.com/pytorch/vision/tree/main/references/classification#post-training-quantized-modelsz These weights were produced by doing Post Training Quantization (eager mode) on top of the unquantized weights listed below. )min_sizeryrzrecipe_docsc d\rSrSr\"S\"\SS90\ES\RSSSS .0S S S .ES 9r \ r Sr g)rzShttps://download.pytorch.org/models/quantized/shufflenetv2_x0.5_fbgemm-00845098.pth crop_sizei ImageNet-1Kg#~jL@gRS@zacc@1zacc@5g{Gz?gjt? num_params unquantized_metrics_ops _file_sizeurl transformsr}N) rErFrGrHrrr _COMMON_METAr IMAGENET1K_V1IMAGENET1K_FBGEMM_V1DEFAULTrIrr7r5rrs[" a.#>    !5CC##    "#Gr7rc d\rSrSr\"S\"\SS90\ES\RSSSS .0S S S .ES 9r \ r Sr g)rzQhttps://download.pytorch.org/models/quantized/shufflenetv2_x1_fbgemm-1e62bb32.pthrri"rgףp= Q@gh|?U@rg(\?gy&1@rrrN) rErFrGrHrrr rrrrrrIrr7r5rrs[" _.#>    !5CC##    "#Gr7rc h\rSrSr\"S\"\SSS90\ESS\RSS S S .0S S S.ES9r \ r Sr g)rzShttps://download.pytorch.org/models/quantized/shufflenetv2_x1_5_fbgemm-d7401f05.pthrr resize_size+https://github.com/pytorch/vision/pull/5906iv5rgSR@g̬V@rgl?gK7A` @rrrrrrrrN) rErFrGrHrrr rrrrrrIrr7r5rr`" a.#3O    C!5CC##    $#Gr7rc h\rSrSr\"S\"\SSS90\ESS\RSS S S .0S S S.ES9r \ r Sr g)rzShttps://download.pytorch.org/models/quantized/shufflenetv2_x2_0_fbgemm-5cac526c.pthrrrriprg-R@gZd;W@rg-?g|?5@rrrN) rErFrGrHrrr rrrrrrIrr7r5rrrr7rquantized_shufflenet_v2_x0_5)rm pretrainedcpURSS5(a[R$[R$NrvF)getrrrrr(s r5r1 ::j% ( (;OO6 ' 5 56r7)rtTFrtrurvc nU(a[O[RU5n[/SQ/SQ4XUS.UD6$)a Constructs a ShuffleNetV2 with 0.5x output channels, as described in `ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design `__. .. note:: Note that ``quantize = True`` returns a quantized model with 8 bit weights. Quantized models only support inference and run on CPUs. GPU inference is not yet supported. Args: weights (:class:`~torchvision.models.quantization.ShuffleNet_V2_X0_5_QuantizedWeights` or :class:`~torchvision.models.ShuffleNet_V2_X0_5_Weights`, optional): The pretrained weights for the model. See :class:`~torchvision.models.quantization.ShuffleNet_V2_X0_5_QuantizedWeights` below for more details, and possible values. By default, no pre-trained weights are used. progress (bool, optional): If True, displays a progress bar of the download to stderr. Default is True. quantize (bool, optional): If True, return a quantized version of the model. Default is False. **kwargs: parameters passed to the ``torchvision.models.quantization.ShuffleNet_V2_X0_5_QuantizedWeights`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.quantization.ShuffleNet_V2_X0_5_QuantizedWeights :members: .. autoclass:: torchvision.models.ShuffleNet_V2_X0_5_Weights :members: :noindex: r)0`rr)rrverifyrrtrurvr(s r5r r sB`7?2D^ffgnoG * 4;Ya ek r7quantized_shufflenet_v2_x1_0cpURSS5(a[R$[R$r)rrrrrrs r5rrrr7c nU(a[O[RU5n[/SQ/SQ4XUS.UD6$)a Constructs a ShuffleNetV2 with 1.0x output channels, as described in `ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design `__. .. note:: Note that ``quantize = True`` returns a quantized model with 8 bit weights. Quantized models only support inference and run on CPUs. GPU inference is not yet supported. Args: weights (:class:`~torchvision.models.quantization.ShuffleNet_V2_X1_0_QuantizedWeights` or :class:`~torchvision.models.ShuffleNet_V2_X1_0_Weights`, optional): The pretrained weights for the model. See :class:`~torchvision.models.quantization.ShuffleNet_V2_X1_0_QuantizedWeights` below for more details, and possible values. By default, no pre-trained weights are used. progress (bool, optional): If True, displays a progress bar of the download to stderr. Default is True. quantize (bool, optional): If True, return a quantized version of the model. Default is False. **kwargs: parameters passed to the ``torchvision.models.quantization.ShuffleNet_V2_X1_0_QuantizedWeights`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.quantization.ShuffleNet_V2_X1_0_QuantizedWeights :members: .. autoclass:: torchvision.models.ShuffleNet_V2_X1_0_Weights :members: :noindex: r)rtrirr)rrrrrs r5r!r! B`7?2D^ffgnoG , 6=[c gm r7quantized_shufflenet_v2_x1_5cpURSS5(a[R$[R$r)rrrrrrs r5rrFrr7c nU(a[O[RU5n[/SQ/SQ4XUS.UD6$)a Constructs a ShuffleNetV2 with 1.5x output channels, as described in `ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design `__. .. note:: Note that ``quantize = True`` returns a quantized model with 8 bit weights. Quantized models only support inference and run on CPUs. GPU inference is not yet supported. Args: weights (:class:`~torchvision.models.quantization.ShuffleNet_V2_X1_5_QuantizedWeights` or :class:`~torchvision.models.ShuffleNet_V2_X1_5_Weights`, optional): The pretrained weights for the model. See :class:`~torchvision.models.quantization.ShuffleNet_V2_X1_5_QuantizedWeights` below for more details, and possible values. By default, no pre-trained weights are used. progress (bool, optional): If True, displays a progress bar of the download to stderr. Default is True. quantize (bool, optional): If True, return a quantized version of the model. Default is False. **kwargs: parameters passed to the ``torchvision.models.quantization.ShuffleNet_V2_X1_5_QuantizedWeights`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.quantization.ShuffleNet_V2_X1_5_QuantizedWeights :members: .. autoclass:: torchvision.models.ShuffleNet_V2_X1_5_Weights :members: :noindex: r)ri`irr)rrrrrs r5r"r"Brr7quantized_shufflenet_v2_x2_0cpURSS5(a[R$[R$r)rrrrrrs r5rr|rr7c nU(a[O[RU5n[/SQ/SQ4XUS.UD6$)a Constructs a ShuffleNetV2 with 2.0x output channels, as described in `ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design `__. .. note:: Note that ``quantize = True`` returns a quantized model with 8 bit weights. Quantized models only support inference and run on CPUs. GPU inference is not yet supported. Args: weights (:class:`~torchvision.models.quantization.ShuffleNet_V2_X2_0_QuantizedWeights` or :class:`~torchvision.models.ShuffleNet_V2_X2_0_Weights`, optional): The pretrained weights for the model. See :class:`~torchvision.models.quantization.ShuffleNet_V2_X2_0_QuantizedWeights` below for more details, and possible values. By default, no pre-trained weights are used. progress (bool, optional): If True, displays a progress bar of the download to stderr. Default is True. quantize (bool, optional): If True, return a quantized version of the model. Default is False. **kwargs: parameters passed to the ``torchvision.models.quantization.ShuffleNet_V2_X2_0_QuantizedWeights`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.quantization.ShuffleNet_V2_X2_0_QuantizedWeights :members: .. autoclass:: torchvision.models.ShuffleNet_V2_X2_0_Weights :members: :noindex: r)riiir)rrrrrs r5r#r#xrr7)1 functoolsrtypingrrrrrPtorch.nnr.rtorchvision.modelsr transforms._presetsr _apir rr_metar_utilsrrrrrrutilsrrr__all__InvertedResidualr% ShuffleNetV2rintrqrrrrrrr r!r"r#rr7r5rs-- +677(C @? ,"?"?"#l77#LIck "     6&t  #+#*#+#*#+#,#+#,34 6 ae * e?A[[\ ]** *  *  *5*Z34 6 ae * e?A[[\ ]** *  *  *5*Z34 6 ae * e?A[[\ ]** *  *  *5*Z34 6 ae * e?A[[\ ]** *  *  *5*r7