+ j # R^RIHt^RIHtHt^RIHt^RIHt^RI H t H t H t ^RI Ht^RIHtHtHt^RIHtHtHtHtHt^R IHt.R&Ot!R R ]4t!RR]P84tR]RR'RR/t!RR ] 4t!RR ] 4t RRlt!] !4]!R]PD3R]PF3R7RRRRRRR RR!]PF/R"R#ll44t$] !4]!R] PD3R]PF3R7RRRRRRR RR!]PF/R$R%ll44t%R#)()partial)AnyOptional)nn)SemanticSegmentation)register_modelWeights WeightsEnum)_VOC_CATEGORIES)_ovewrite_value_paramhandle_legacy_interfaceIntermediateLayerGetter)ResNet resnet101ResNet101_Weightsresnet50ResNet50_Weights)_SimpleSegmentationModelFCNFCN_ResNet50_WeightsFCN_ResNet101_Weightsc]tRt^tRtRtR#)ra[ Implements FCN model from `"Fully Convolutional Networks for Semantic Segmentation" `_. Args: backbone (nn.Module): the network used to compute the features for the model. The backbone should return an OrderedDict[Tensor], with the key being "out" for the last feature map used, and "aux" if an auxiliary classifier is used. classifier (nn.Module): module that takes the "out" element returned from the backbone and returns a dense prediction. aux_classifier (nn.Module, optional): auxiliary classifier used during training N)__name__ __module__ __qualname____firstlineno____doc____static_attributes__rd/home/luca/screen-checking/.venv/lib/python3.14/site-packages/torchvision/models/segmentation/fcn.pyrrs   r c>aa]tRt^$toV3RlV3RlltRtVtV;t#)FCNHeadc*<V^8dQhRS[RS[RR/#) in_channelschannelsreturnN)int)format __classdict__s"r! __annotate__FCNHead.__annotate__%s" " "C "3 "4 "r c <V^,p\P!W^^RR7\P!V4\P!4\P!R4\P!W2^4.p\ SV`!V!R#)F)paddingbiasg?N)rConv2d BatchNorm2dReLUDropoutsuper__init__)selfr&r'inter_channelslayers __class__s&&& r!r7FCNHead.__init__%sc$) IIk1ae L NN> * GGI JJsO IIn 2   &!r r)rrrrr7r__classdictcell__ __classcell__)r;r+s@@r!r#r#$s " " "r r# categoriesmin_size_docsz These weights were trained on a subset of COCO, using only the 20 categories that are present in the Pascal VOC dataset. ch]tRt^`_ paper. .. betastatus:: segmentation module Args: weights (:class:`~torchvision.models.segmentation.FCN_ResNet50_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.segmentation.FCN_ResNet50_Weights` 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. num_classes (int, optional): number of output classes of the model (including the background). aux_loss (bool, optional): If True, it uses an auxiliary loss. weights_backbone (:class:`~torchvision.models.ResNet50_Weights`, optional): The pretrained weights for the backbone. **kwargs: parameters passed to the ``torchvision.models.segmentation.fcn.FCN`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.segmentation.FCN_ResNet50_Weights :members: NrYr?riTrfreplace_stride_with_dilationrh check_hashFTT) rverifyrr lenrQrrcload_state_dictget_state_dictrfrhrYrirgrlrXmodels$$$$$, r! fcn_resnet50ryusP#))'2G'../?@+M;GLLYeLfHgh (XtD    0ObcH x 8E g44hSW4XY Lr cV^8dQhR\\,R\R\\,R\\,R\\,R\ R\ /#rk)rrr[r)rrr)r*s"r!r,r,sd33 + ,33# 3 tn 3 01 33 3r c `\PV4p\P!V4pVe8Rp\RV\ VP R,44p\RVR4pMVf^p\ V.ROR7p\WbV4pVe#VPVPVRR74V#) a Fully-Convolutional Network model with a ResNet-101 backbone from the `Fully Convolutional Networks for Semantic Segmentation `_ paper. .. betastatus:: segmentation module Args: weights (:class:`~torchvision.models.segmentation.FCN_ResNet101_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.segmentation.FCN_ResNet101_Weights` below for more details, and possible values. By default, no pre-trained weights are used. progress (bool, optional): If True, displays a progress bar of the download to stderr. Default is True. num_classes (int, optional): number of output classes of the model (including the background). aux_loss (bool, optional): If True, it uses an auxiliary loss. weights_backbone (:class:`~torchvision.models.ResNet101_Weights`, optional): The pretrained weights for the backbone. **kwargs: parameters passed to the ``torchvision.models.segmentation.fcn.FCN`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.segmentation.FCN_ResNet101_Weights :members: NrYr?riTrnrprr) rrsrr rtrQrrcrurvrws$$$$$, r! fcn_resnet101r|sP$**73G(//0@A+M;GLLYeLfHgh (XtD   !1PcdH x 8E g44hSW4XY Lr )rrrryr|)r})& functoolsrtypingrrtorchrtransforms._presetsr_apirr r _metar _utilsr r rresnetrrrrrr__all__r Sequentialr#rSrrrcrT IMAGENET1K_V1ryr|rr r!rsy 777#\\UU, d " & "bmm "/  &;&*&K&* 5 /GG H+-=-K-KL3.233"& 3 $ 3 4D3Q3Q 3  3l 0HH I+->-L-LM3/333"& 3 $ 3 5F4S4S 3  3r