o hA@sddlZddlmZddlmZddlmZmZddlZddl m Z ddl m m Z ddlmmZddlmZddlmZddlmZd d lmZmZmZd d lmZd d lmZmZgd ZGddde j Z!Gddde j"Z#Gddde j$Z%Gddde j Z&de j dede'ddfddZ(de)de*e)e)e)e)fde)deede'dede&fd d!Z+d"ed#d$d%Z,Gd&d'd'eZ-Gd(d)d)eZ.Gd*d+d+eZ/Gd,d-d-eZ0eed.e-j1fd/dd0d1dee-de'dede&fd2d3Z2eed.e.j1fd/dd0d1dee.de'dede&fd4d5Z3eed.e/j1fd/dd0d1dee/de'dede&fd6d7Z4eed.e0j1fd/dd0d1dee0de'dede&fd8d9Z5dS):N) OrderedDict)partial)AnyOptional)Tensor)ImageClassification)_log_api_usage_once)register_modelWeights WeightsEnum)_IMAGENET_CATEGORIES)_ovewrite_named_paramhandle_legacy_interface) DenseNetDenseNet121_WeightsDenseNet161_WeightsDenseNet169_WeightsDenseNet201_Weights densenet121 densenet161 densenet169 densenet201c seZdZ ddedededededdf fd d Zd eedefd d Z deedefddZ e j j deedefddZe j jdeedefddZe j jdedefddZdedefddZZS) _DenseLayerFnum_input_features growth_ratebn_size drop_ratememory_efficientreturnNcstt||_tjdd|_tj|||dddd|_t|||_ tjdd|_ tj|||ddddd|_ t ||_ ||_dS)NTZinplacer F kernel_sizestridebiasr#r$paddingr%)super__init__nn BatchNorm2dnorm1ReLUrelu1Conv2dconv1norm2relu2conv2floatrr)selfrrrrr __class__a/home/www/facesmatcher.com/frenv_anti/lib/python3.10/site-packages/torchvision/models/densenet.pyr* s    z_DenseLayer.__init__inputscCs&t|d}||||}|SNr )torchcatr1r/r-)r6r;Zconcated_featuresbottleneck_outputr9r9r: bn_function/s z_DenseLayer.bn_functioninputcCs|D]}|jr dSqdS)NTF)Z requires_grad)r6rAZtensorr9r9r:any_requires_grad5s z_DenseLayer.any_requires_gradcs$fdd}tj|g|RddiS)Ncs |SN)r@)r;r6r9r:closure=s z7_DenseLayer.call_checkpoint_bottleneck..closureZ use_reentrantF)cp checkpoint)r6rArEr9rDr:call_checkpoint_bottleneck;s z&_DenseLayer.call_checkpoint_bottleneckcCdSrCr9r6rAr9r9r:forwardBz_DenseLayer.forwardcCrIrCr9rJr9r9r:rKFrLcCst|tr |g}n|}|jr"||r"tjrtd||}n| |}| | | |}|j dkrAtj||j |jd}|S)Nz%Memory Efficient not supported in JITr)ptraining) isinstancerrrBr=jitZ is_scripting ExceptionrHr@r4r3r2rFZdropoutrN)r6rAZ prev_featuresr? new_featuresr9r9r:rKLs     F)__name__ __module__ __qualname__intr5boolr*listrr@rBr=rPZunusedrHZ_overload_methodrK __classcell__r9r9r7r:rs0rcsTeZdZdZ ddedededededed d ffd d Zd ed efddZ Z S) _DenseBlockrF num_layersrrrrrr Nc sJtt|D]}t|||||||d}|d|d|q dS)N)rrrrz denselayer%dr )r)r*ranger add_module) r6r]rrrrrilayerr7r9r:r*cs  z_DenseBlock.__init__ init_featurescCs6|g}|D] \}}||}||qt|dSr<)itemsappendr=r>)r6rbfeaturesnamerarSr9r9r:rKws   z_DenseBlock.forwardrT) rUrVrW_versionrXr5rYr*rrKr[r9r9r7r:r\`s& r\cs*eZdZdededdffdd ZZS) _Transitionrnum_output_featuresr NcsNtt||_tjdd|_tj||dddd|_tj ddd|_ dS)NTr!r Fr"r)r#r$) r)r*r+r,Znormr.relur0convZ AvgPool2dpool)r6rrir7r9r:r*s  z_Transition.__init__)rUrVrWrXr*r[r9r9r7r:rhs"rhcspeZdZdZ       dd ed eeeeefd ed ed edededdffdd Zde de fddZ Z S)raKDensenet-BC model class, based on `"Densely Connected Convolutional Networks" `_. Args: growth_rate (int) - how many filters to add each layer (`k` in paper) block_config (list of 4 ints) - how many layers in each pooling block num_init_features (int) - the number of filters to learn in the first convolution layer bn_size (int) - multiplicative factor for number of bottle neck layers (i.e. bn_size * k features in the bottleneck layer) drop_rate (float) - dropout rate after each dense layer num_classes (int) - number of classification classes memory_efficient (bool) - If True, uses checkpointing. Much more memory efficient, but slower. Default: *False*. See `"paper" `_.  @rFr block_confignum_init_featuresrr num_classesrr Nc stt|ttdtjd|dddddfdt|fdtjd d fd tj ddd d fg|_ |}t |D]>\} } t | |||||d} |j d| d | || |}| t|d krwt||dd} |j d| d | |d}q9|j dt|t|||_|D]5} t| tjrtj| jqt| tjrtj| jd tj| jdqt| tjrtj| jdqdS)NZconv0r&rFr'Znorm0Zrelu0Tr!Zpool0r )r#r$r()r]rrrrrz denseblock%d)rriz transition%dZnorm5r)r)r*r r+ Sequentialrr0r,r.Z MaxPool2dre enumerater\r_lenrhZLinear classifiermodulesrOinitZkaiming_normal_weightZ constant_r%)r6rrvrwrrrxrZ num_featuresr`r]blockZtransmr7r9r:r*sP        zDenseNet.__init__xcCs>||}tj|dd}t|d}t|d}||}|S)NTr!)r r r )rerRrjZadaptive_avg_pool2dr=flattenr})r6rreoutr9r9r:rKs    zDenseNet.forward)rmrnrsrtrruF) rUrVrW__doc__rXtupler5rYr*rrKr[r9r9r7r:rs6 @Z num_paramsZ_metricsZ_ops _file_sizeurlZ transformsrN rUrVrWr rr _COMMON_META IMAGENET1K_V1DEFAULTr9r9r9r:r $ rc @r)rz`_. Args: weights (:class:`~torchvision.models.DenseNet121_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.DenseNet121_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. **kwargs: parameters passed to the ``torchvision.models.densenet.DenseNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.DenseNet121_Weights :members: rmrnrs)rverifyrrrrr9r9r:r[ rcKr)a{Densenet-161 model from `Densely Connected Convolutional Networks `_. Args: weights (:class:`~torchvision.models.DenseNet161_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.DenseNet161_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. **kwargs: parameters passed to the ``torchvision.models.densenet.DenseNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.DenseNet161_Weights :members: 0)rorp$rq`)rrrrr9r9r:rurrcKr)a{Densenet-169 model from `Densely Connected Convolutional Networks `_. Args: weights (:class:`~torchvision.models.DenseNet169_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.DenseNet169_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. **kwargs: parameters passed to the ``torchvision.models.densenet.DenseNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.DenseNet169_Weights :members: rm)rorprmrmrs)rrrrr9r9r:rrrcKr)a{Densenet-201 model from `Densely Connected Convolutional Networks `_. Args: weights (:class:`~torchvision.models.DenseNet201_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.DenseNet201_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. **kwargs: parameters passed to the ``torchvision.models.densenet.DenseNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.DenseNet201_Weights :members: rm)rorprrmrs)rrrrr9r9r:rrr)6r collectionsr functoolsrtypingrrr=Ztorch.nnr+Ztorch.nn.functionalZ functionalrRZtorch.utils.checkpointutilsrGrFrZtransforms._presetsrr Z_apir r r _metarZ_utilsrr__all__ModulerZ ModuleDictr\rzrhrrYrrXrrrrrrrrrrrrr9r9r9r:sp        A U ***.