Ei #SSKJr SSKJrJr SSKJr SSKJr SSK J r J r J r SSK Jr SS KJrJrJr SS KJrJrJrJrJr S S KJr /S Qr"SS\5r"SS\R85r\SSS.r"SS\ 5r"SS\ 5r S\S\!S\\"S\4Sjr#\ "5\"S\RH4S\RJ4S 9S!S"S!S!\RJS#.S$\\S%\"S\\!S&\\"S'\\S(\S\4S)jj55r&\ "5\"S\ RH4S\RJ4S 9S!S"S!S!\RJS#.S$\\ S%\"S\\!S&\\"S'\\S(\S\4S*jj55r'g!)+)partial)AnyOptional)nn)SemanticSegmentation)register_modelWeights WeightsEnum)_VOC_CATEGORIES)_ovewrite_value_paramhandle_legacy_interfaceIntermediateLayerGetter)ResNet resnet101ResNet101_Weightsresnet50ResNet50_Weights)_SimpleSegmentationModel)FCNFCN_ResNet50_WeightsFCN_ResNet101_Weights fcn_resnet50 fcn_resnet101c\rSrSrSrSrg)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__r`/home/mande/repo/quber/.venv/lib/python3.13/site-packages/torchvision/models/segmentation/fcn.pyrrs   r&rc8^\rSrSrS\S\SS4U4SjjrSrU=r$)FCNHead$ in_channelschannelsreturnNc >US-n[R"XSSSS9[R"U5[R"5[R"S5[R"X2S5/n[ TU]"U6 g)NrrF)paddingbiasg?)rConv2d BatchNorm2dReLUDropoutsuper__init__)selfr+r,inter_channelslayers __class__s r'r7FCNHead.__init__%sc$) IIk1ae L NN> * GGI JJsO IIn 2   &!r&r)r r!r"r#intr7r% __classcell__)r;s@r'r)r)$s" "C "3 "4 " "r&r))rrz These weights were trained on a subset of COCO, using only the 20 categories that are present in the Pascal VOC dataset. ) categoriesmin_size_docsc P\rSrSr\"S\"\SS90\ESSSSS S .0S S S .ES9r\r Sr g)r<zBhttps://download.pytorch.org/models/fcn_resnet50_coco-1167a1af.pth resize_sizeijzPhttps://github.com/pytorch/vision/tree/main/references/segmentation#fcn_resnet50COCO-val2017-VOC-labelsg@N@gV@miou pixel_accgmc@g?5^I`@ num_paramsrecipe_metrics_ops _file_sizeurl transformsmetarN r r!r"r#r rr _COMMON_METACOCO_WITH_VOC_LABELS_V1DEFAULTr%rr&r'rr<sU% P/SA    "h) !%, !  "&Gr&rc P\rSrSr\"S\"\SS90\ESSSSS S .0S S S .ES9r\r Sr g)rQzChttps://download.pytorch.org/models/fcn_resnet101_coco-7ecb50ca.pthrDrEij<zWhttps://github.com/pytorch/vision/tree/main/references/segmentation#deeplabv3_resnet101rGgO@gV@rHgV-m@gni@rKrQrNrUrr&r'rrQsU% Q/SA    "o) !%, !  "&Gr&rbackbone num_classesauxr-cSS0nU(aSUS'[XS9nU(a [SU5OSn[SU5n[XU5$)Nlayer4outr]layer3) return_layersii)rr)r)r[r\r]rbaux_classifier classifiers r' _fcn_resnetrefsN u%M "' h&xMH36WT;/DN{+J x^ 44r& pretrainedpretrained_backbone)weightsweights_backboneNT)rhprogressr\aux_lossrirhrjrkrikwargsc F[RU5n[R"U5nUb3Sn[SU[ UR S55n[SUS5nOUcSn[ U/SQS9n[XbU5nUbURURUSS 95 U$) aFully-Convolutional Network model with a ResNet-50 backbone from the `Fully Convolutional Networks for Semantic Segmentation `_ 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: Nr\r?rkTFTTrhreplace_stride_with_dilationrj check_hash) rverifyrrlenrTrreload_state_dictget_state_dictrhrjr\rkrirlr[models r'rrusP#))'2G'../?@+M;GLLYeLfHgh (XtD    0ObcH x 8E g44hSW4XY Lr&c F[RU5n[R"U5nUb3Sn[SU[ UR S55n[SUS5nOUcSn[ U/SQS9n[XbU5nUbURURUSS 95 U$) a Fully-Convolutional Network model with a ResNet-101 backbone from the `Fully Convolutional Networks for Semantic Segmentation `_ paper. .. betastatus:: segmentation module Args: weights (:class:`~torchvision.models.segmentation.FCN_ResNet101_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.segmentation.FCN_ResNet101_Weights` below for more details, and possible values. By default, no pre-trained weights are used. progress (bool, optional): If True, displays a progress bar of the download to stderr. Default is True. num_classes (int, optional): number of output classes of the model (including the background). aux_loss (bool, optional): If True, it uses an auxiliary loss. weights_backbone (:class:`~torchvision.models.ResNet101_Weights`, optional): The pretrained weights for the backbone. **kwargs: parameters passed to the ``torchvision.models.segmentation.fcn.FCN`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.segmentation.FCN_ResNet101_Weights :members: Nr\r?rkTrnrorprr) rrtrrrurTrrervrwrxs r'rrsP$**73G(//0@A+M;GLLYeLfHgh (XtD   !1PcdH x 8E g44hSW4XY Lr&)( functoolsrtypingrrtorchrtransforms._presetsr_apir r r _metar _utilsrrrresnetrrrrrr__all__r Sequentialr)rVrrr=boolrerW IMAGENET1K_V1rrrr&r'rs  777#\\UU, d " & "bmm "" &;&*&K&* 5 5 5 $ 5 5 /GG H+-=-K-KL /3!%#3C3Q3Q 3 * +33# 3 tn 3 /0 33 3  3l 0HH I+->-L-LM 04!%#4E4S4S 3 + ,33# 3 tn 3 01 33 3  3r&