+ j($^RIHt^RIHtHtHt^RIt^RIHtHt^RI H t H t ^RI H t Ht^RIHt^RIHtHtHt^R IHt^R IHtHt^R IHtHtHtHtHt^R I H!t!H"t".R#Ot#!RR]4t$!RR]4t%!RR ]4t&RRlt'!RR]4t(]!RR7]!RR3R7RRRRRR /R!R"ll44t)R#)$)partial)AnyOptionalUnionN)nnTensor) DeQuantStub QuantStub)Conv2dNormActivationSqueezeExcitation)ImageClassification)register_modelWeights WeightsEnum)_IMAGENET_CATEGORIES)_ovewrite_named_paramhandle_legacy_interface)_mobilenet_v3_confInvertedResidualInvertedResidualConfigMobileNet_V3_Large_Weights MobileNetV3) _fuse_modules _replace_reluQuantizableMobileNetV3#MobileNet_V3_Large_QuantizedWeightscvaa]tRt^to^tV3RlV3RlltV3RlRltR V3RlRlltV3RltRt Vt V;t #) QuantizableSqueezeExcitationc*<V^8dQhRS[RS[RR/#argskwargsreturnNr)format __classdict__s"l/home/luca/screen-checking/.venv/lib/python3.14/site-packages/torchvision/models/quantization/mobilenetv3.py __annotate__)QuantizableSqueezeExcitation.__annotate__!s"77c7S7T7c<\PVR&\SV` !V/VB\PP 4VnR#)scale_activationN)r Hardsigmoidsuper__init__ quantizedFloatFunctionalskip_mulselfr"r# __class__s&*,r(r0%QuantizableSqueezeExcitation.__init__!s8%'^^!" $)&) 446 r+c&<V^8dQhRS[RS[/#)r!inputr$r)r&r's"r(r)r*&s< g44hSW4XY %%eT%: Lr+c]tRt^t]!R]!]^R7RRRRR]RRR R R ]PR R RRRR//RRRRRR/ R7t ] t Rt R#)rzUhttps://download.pytorch.org/models/quantized/mobilenet_v3_large_qnnpack-5bcacf28.pth) crop_size num_paramsiSmin_sizerrrrecipezUhttps://github.com/pytorch/vision/tree/main/references/classification#qat-mobilenetv3 unquantized_metricsz ImageNet-1Kzacc@1gK7A@R@zacc@5gxV@_opsg-? _file_sizegҍ5@_docsz These weights were produced by doing Quantization Aware Training (eager mode) on top of the unquantized weights listed below. )url transformsrN)r) rdrerfrgrrr rr IMAGENET1K_V1IMAGENET1K_QNNPACK_V1DEFAULTrirr+r(rrs|# c.#> '  . y m 5CC VV  E &  0$Gr+quantized_mobilenet_v3_large)name pretrainedcrVPRR4'd\P#\P#)rF)rQrrrr)r#s&r(rs1zz*e,, 0 E E :+99 :r+)rrrTrFc V^8dQhR\\\\3,,R\R\R\ R\ /#)r!rrrr#r$)rrrrrErr)r&s"r(r)r)sT'o'o e?A[[\ ]'o'o 'o  'o  'or+c ~V'd\M\PV4p\R/VBwrE\ WEWV3/VB#)ap MobileNetV3 (Large) model from `Searching for MobileNetV3 `_. .. 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.MobileNet_V3_Large_QuantizedWeights` or :class:`~torchvision.models.MobileNet_V3_Large_Weights`, optional): The pretrained weights for the model. See :class:`~torchvision.models.quantization.MobileNet_V3_Large_QuantizedWeights` below for more details, and possible values. By default, no pre-trained weights are used. progress (bool): If True, displays a progress bar of the download to stderr. Default is True. quantize (bool): If True, return a quantized version of the model. Default is False. **kwargs: parameters passed to the ``torchvision.models.quantization.MobileNet_V3_Large_QuantizedWeights`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.quantization.MobileNet_V3_Large_QuantizedWeights :members: .. autoclass:: torchvision.models.MobileNet_V3_Large_Weights :members: :noindex: )mobilenet_v3_large)rrverifyrr)rrrr#rrs$$$, r(rrsE^7?2D^ffgnoG.@.`Y_.`+ 8[c ngm nnr+)rrr)* functoolsrtypingrrrrSrrtorch.ao.quantizationr r ops.miscr r transforms._presetsr _apirrr_metar_utilsrr mobilenetv3rrrrrutilsrr__all__rrnrrrrrr+r(rs'' 8?677(C0 2 #42 j !"2 !%[%:!H$+$834   'o`d'o'o 'o 5'or+