U ʹjs: @sddlmZddlmZmZmZddlZddlmZddlm Z ddl m Z dd l mZmZmZdd lmZdd lmZmZmZdd lmZmZmZdd lmZmZmZmZm Z ddlm!Z!ddl"m#Z#dddddddgZ$Gddde!Z%Gdddej&Z'Gdddej&Z(Gdddej&Z)Gdd d ej*Z+ee,ee-e%d!d"d#Z.ed$d%d&Z/Gd'ddeZ0Gd(ddeZ1Gd)ddeZ2ee,ee-e%d!d*d+Z3eed,e0j4fd-e j5fd.dd/dde j5d0ee0e-ee,ee-ee ee%d1d2dZ6eed,e1j4fd-ej5fd.dd/ddej5d0ee1e-ee,ee-eeee%d1d3dZ7eed,e2j4fd-ej5fd.dd/ddej5d0ee2e-ee,ee-eeee%d1d4dZ8dS)5)partial)AnyListOptionalN)nn) functional)SemanticSegmentation)register_modelWeights WeightsEnum)_VOC_CATEGORIES)_ovewrite_value_paramhandle_legacy_interfaceIntermediateLayerGetter)mobilenet_v3_largeMobileNet_V3_Large_Weights MobileNetV3)ResNet resnet101ResNet101_Weightsresnet50ResNet50_Weights)_SimpleSegmentationModel)FCNHead DeepLabV3DeepLabV3_ResNet50_WeightsDeepLabV3_ResNet101_Weights$DeepLabV3_MobileNet_V3_Large_Weightsdeeplabv3_mobilenet_v3_largedeeplabv3_resnet50deeplabv3_resnet101c@seZdZdZdS)ra Implements DeepLabV3 model from `"Rethinking Atrous Convolution for Semantic Image 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____doc__r(r(h/var/www/html/bwave/python/venv/lib/python3.8/site-packages/torchvision/models/segmentation/deeplabv3.pyrscs&eZdZeeddfdd ZZS) DeepLabHeadN) in_channels num_classesreturnc sHtt|dddgtjddddddtdttd|ddS) N $rrF)paddingbias)super__init__ASPPrConv2d BatchNorm2dReLU)selfr+r, __class__r(r)r51s zDeepLabHead.__init__r$r%r&intr5 __classcell__r(r(r;r)r*0sr*cs(eZdZeeeddfdd ZZS)ASPPConvN)r+ out_channelsdilationr-cs6tj||d||ddt|tg}tj|dS)NrF)r2rBr3)rr7r8r9r4r5)r:r+rArBmodulesr;r(r)r5<s zASPPConv.__init__r=r(r(r;r)r@;sr@cs:eZdZeeddfdd ZejejdddZZS) ASPPPoolingN)r+rAr-c s4ttdtj||dddt|tdS)NrFr3)r4r5rZAdaptiveAvgPool2dr7r8r9)r:r+rAr;r(r)r5Fs zASPPPooling.__init__xr-cCs2|jdd}|D] }||}qtj||dddS)NZbilinearF)sizemodeZ align_corners)shapeFZ interpolate)r:rGrImodr(r(r)forwardNs zASPPPooling.forward) r$r%r&r>r5torchTensorrNr?r(r(r;r)rDEsrDcsBeZdZd eeeeddfdd ZejejdddZZ S) r6r1N)r+ atrous_ratesrAr-c stg}|ttj||dddt|tt|}|D]}|t |||qF|t ||t ||_ ttjt |j ||dddt|ttd|_dS)NrFrEg?)r4r5appendr Sequentialr7r8r9tupler@rDZ ModuleListconvslenZDropoutproject)r:r+rQrArCZratesZrater;r(r)r5Vs  $ z ASPP.__init__rFcCs6g}|jD]}|||q tj|dd}||S)Nr)dim)rUrRrOcatrW)r:rGZ_resconvresr(r(r)rNls  z ASPP.forward)r1) r$r%r&r>rr5rOrPrNr?r(r(r;r)r6Usr6)backboner,auxr-cCsHddi}|rd|d<t||d}|r.td|nd}td|}t|||S)NZlayer4outr]Zlayer3 return_layersii)rrr*r)r\r,r]r`aux_classifier classifierr(r(r)_deeplabv3_resnetts  rc)rrz These weights were trained on a subset of COCO, using only the 20 categories that are present in the Pascal VOC dataset. ) categoriesZmin_sizeZ_docsc @s@eZdZedeeddedddddd id d d d ZeZdS)rzHhttps://download.pytorch.org/models/deeplabv3_resnet50_coco-cd0a2569.pthZ resize_sizeijzVhttps://github.com/pytorch/vision/tree/main/references/segmentation#deeplabv3_resnet50COCO-val2017-VOC-labelsgP@皙W@ZmiouZ pixel_accgvWf@gGzd@Z num_paramsZrecipeZ_metricsZ_ops _file_sizeurlZ transformsmetaN r$r%r&r rr _COMMON_METACOCO_WITH_VOC_LABELS_V1DEFAULTr(r(r(r)rs  c @s@eZdZedeeddedddddd id d d d ZeZdS)rzIhttps://download.pytorch.org/models/deeplabv3_resnet101_coco-586e9e4e.pthrerfijzQhttps://github.com/pytorch/vision/tree/main/references/segmentation#fcn_resnet101rggP@rhrigS+p@gm&m@rjrlNror(r(r(r)rs  c @s@eZdZedeeddedddddd id d d d ZeZdS)r zMhttps://download.pytorch.org/models/deeplabv3_mobilenet_v3_large-fc3c493d.pthrerfiPKz`https://github.com/pytorch/vision/tree/main/references/segmentation#deeplabv3_mobilenet_v3_largerggfffff&N@gV@rigCl$@gJ +&E@rjrlNror(r(r(r)r s  c Cs|j}dgddt|Dt|dg}|d}||j}|d}||j}t|di}|rld|t|<t||d }|rt||nd} t||} t|| | S) NrcSs g|]\}}t|ddr|qS)Z_is_cnF)getattr).0ibr(r(r) s z*_deeplabv3_mobilenetv3..rr^r]r_) features enumeraterVrAstrrrr*r) r\r,r]Z stage_indicesZout_posZ out_inplanesZaux_posZ aux_inplanesr`rarbr(r(r)_deeplabv3_mobilenetv3s&      r}Z pretrainedZpretrained_backbone)weightsweights_backboneT)r~progressr,aux_lossr)r~rr,rrkwargsr-cKst|}t|}|dk rDd}td|t|jd}td|d}n |dkrPd}t|dddgd}t|||}|dk r||j |dd |S) adConstructs a DeepLabV3 model with a ResNet-50 backbone. .. betastatus:: segmentation module Reference: `Rethinking Atrous Convolution for Semantic Image Segmentation `__. Args: weights (:class:`~torchvision.models.segmentation.DeepLabV3_ResNet50_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.segmentation.DeepLabV3_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: unused .. autoclass:: torchvision.models.segmentation.DeepLabV3_ResNet50_Weights :members: Nr,rdrTFr~Zreplace_stride_with_dilationrZ check_hash) rverifyrrrVrnrrcload_state_dictget_state_dictr~rr,rrrr\modelr(r(r)r"s%   cKst|}t|}|dk rDd}td|t|jd}td|d}n |dkrPd}t|dddgd}t|||}|dk r||j |dd |S) aiConstructs a DeepLabV3 model with a ResNet-101 backbone. .. betastatus:: segmentation module Reference: `Rethinking Atrous Convolution for Semantic Image Segmentation `__. Args: weights (:class:`~torchvision.models.segmentation.DeepLabV3_ResNet101_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.segmentation.DeepLabV3_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: unused .. autoclass:: torchvision.models.segmentation.DeepLabV3_ResNet101_Weights :members: Nr,rdrTrFrr) rrrrrVrnrrcrrrr(r(r)r#s%   cKst|}t|}|dk rDd}td|t|jd}td|d}n |dkrPd}t|dd}t|||}|dk r||j |dd|S) akConstructs a DeepLabV3 model with a MobileNetV3-Large backbone. Reference: `Rethinking Atrous Convolution for Semantic Image Segmentation `__. Args: weights (:class:`~torchvision.models.segmentation.DeepLabV3_MobileNet_V3_Large_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.segmentation.DeepLabV3_MobileNet_V3_Large_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.MobileNet_V3_Large_Weights`, optional): The pretrained weights for the backbone **kwargs: unused .. autoclass:: torchvision.models.segmentation.DeepLabV3_MobileNet_V3_Large_Weights :members: Nr,rdrTr)r~Zdilatedr) r rrrrVrnrr}rrrr(r(r)r!Ss#    )9 functoolsrtypingrrrrOrZtorch.nnrrLZtransforms._presetsr Z_apir r r _metarZ_utilsrrrZ mobilenetv3rrrZresnetrrrrrrZfcnr__all__rrSr*r@rDModuler6r>boolrcrprrr r}rqZ IMAGENET1K_V1r"r#r!r(r(r(r)s              33