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)NTinplacer F kernel_sizestridebiasr$r%paddingr&)super__init__nn BatchNorm2dnorm1ReLUrelu1Conv2dconv1norm2relu2conv2floatrr)selfrrrrr __class__V/var/www/html/scripts/venv/lib/python3.10/site-packages/torchvision/models/densenet.pyr+ s    z_DenseLayer.__init__inputscCs&t|d}||||}|SNr )torchcatr2r0r.)r7r<concated_featuresbottleneck_outputr:r:r; bn_function/s z_DenseLayer.bn_functioninputcCs|D]}|jr dSqdS)NTF) requires_grad)r7rCtensorr:r:r;any_requires_grad5s z_DenseLayer.any_requires_gradcs$fdd}tj|g|RddiS)Ncs |SN)rB)r<r7r:r;closure=s z7_DenseLayer.call_checkpoint_bottleneck..closure use_reentrantF)cp checkpoint)r7rCrIr:rHr;call_checkpoint_bottleneck;s z&_DenseLayer.call_checkpoint_bottleneckcCdSrGr:r7rCr:r:r;forwardBz_DenseLayer.forwardcCrNrGr:rOr:r:r;rPFrQcCst|tr |g}n|}|jr"||r"tjrtd||}n| |}| | | |}|j dkrAtj||j |jd}|S)Nz%Memory Efficient not supported in JITr)ptraining) isinstancerrrFr>jit is_scripting ExceptionrMrBr5r4r3rFdropoutrS)r7rC prev_featuresrA new_featuresr:r:r;rPLs     F)__name__ __module__ __qualname__intr6boolr+listrrBrFr>rUunusedrM_overload_methodrP __classcell__r:r:r8r;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) r7rgrrrrrilayerr8r:r;r+cs  z_DenseBlock.__init__ init_featurescCs6|g}|D] \}}||}||qt|dSr=)itemsappendr>r?)r7rlfeaturesnamerkr[r:r:r;rPws   z_DenseBlock.forwardr\) r]r^r__versionr`r6rar+rrPrer:r:r8r;rf`s& rfcs*eZdZdededdffdd ZZS) _Transitionrnum_output_featuresr NcsNtt||_tjdd|_tj||dddd|_tj ddd|_ dS)NTr!r Fr#r)r$r%) r*r+r,r-normr/relur1conv AvgPool2dpool)r7rrsr8r:r;r+s  z_Transition.__init__)r]r^r_r`r+rer:r:r8r;rrs"rrcspeZdZdZ       dd ed eeeeefd ed ed edededdffdd Zde de fddZ Z S)raKDensenet-BC model class, based on `"Densely Connected Convolutional Networks" `_. Args: growth_rate (int) - how many filters to add each layer (`k` in paper) block_config (list of 4 ints) - how many layers in each pooling block num_init_features (int) - the number of filters to learn in the first convolution layer bn_size (int) - multiplicative factor for number of bottle neck layers (i.e. bn_size * k features in the bottleneck layer) drop_rate (float) - dropout rate after each dense layer num_classes (int) - number of classification classes memory_efficient (bool) - If True, uses checkpointing. Much more memory efficient, but slower. Default: *False*. See `"paper" `_.  @rFr block_confignum_init_featuresrr num_classesrr Nc stt|ttdtjd|dddddfdt|fdtjd d fd tj ddd d fg|_ |}t |D]>\} } t | |||||d} |j d| d | || |}| t|d krwt||dd} |j d| d | |d}q9|j dt|t|||_|D]5} t| tjrtj| jqt| tjrtj| jd tj| jdqt| tjrtj| jdqdS)Nconv0r'rFr(norm0relu0Tr!pool0r )r$r%r))rgrrrrrz denseblock%d)rrsz transition%dnorm5r)r*r+r r, Sequentialrr1r-r/ MaxPool2dro enumeraterfrilenrrLinear classifiermodulesrTinitkaiming_normal_weight constant_r&)r7rrrrrrr num_featuresrjrgblocktransmr8r:r;r+sP        zDenseNet.__init__xcCs>||}tj|dd}t|d}t|d}||}|S)NTr!)r r r )rorXruadaptive_avg_pool2dr>flattenr)r7rrooutr:r:r;rPs    zDenseNet.forward)ryrzrrrrF) r]r^r___doc__r`tupler6rar+rrPrer:r:r8r;rs6 @ num_params_metrics_ops _file_sizeurl transformsrN r]r^r_r rr _COMMON_META IMAGENET1K_V1DEFAULTr:r:r:r;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: ryrzr)rverifyrrrrr:r:r;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)r{r|$r}`)rrrrr:r:r;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: ry)r{r|ryryr)rrrrr:r:r;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: ry)r{r|rryr)rrrrr:r:r;rrr)6r collectionsr functoolsrtypingrrr>torch.nnr,torch.nn.functional functionalrXtorch.utils.checkpointutilsrLrKrtransforms._presetsrr _apir r r _metar_utilsrr__all__Moduler ModuleDictrfrrrrrarr`rrrrrrrrrrrrr:r:r:r;sp        A U ***.