a PSicA@sddlZddlmZddlmZddlmZmZmZm Z ddl Z ddl m Z ddl m mZddlmmZddl mZddlmZddlmZd d lmZmZd d lmZd d lmZmZgd Z Gddde j!Z"Gddde j#Z$Gddde j%Z&Gddde j!Z'e j!ee(ddddZ)e*e e*e*e*e*fe*eee(ee'dddZ+dedddZ,Gd d!d!eZ-Gd"d#d#eZ.Gd$d%d%eZ/Gd&d'd'eZ0ed(e-j1fd)dd*d+ee-e(ee'd,d-d.Z2ed(e.j1fd)dd*d+ee.e(ee'd,d/d0Z3ed(e/j1fd)dd*d+ee/e(ee'd,d1d2Z4ed(e0j1fd)dd*d+ee0e(ee'd,d3d4Z5d d5lm6Z6e6e-j1j7e/j1j7e0j1j7e.j1j7d6Z8dS)7N) OrderedDict)partial)AnyListOptionalTuple)Tensor)ImageClassification)_log_api_usage_once) WeightsEnumWeights)_IMAGENET_CATEGORIES)handle_legacy_interface_ovewrite_named_param) DenseNetDenseNet121_WeightsDenseNet161_WeightsDenseNet169_WeightsDenseNet201_Weights densenet121 densenet161 densenet169 densenet201cseZdZdeeeeeddfdd ZeeedddZ eeed d d Z e j j eeed d d Ze j jeeed ddZe j jeed ddZeed ddZZS) _DenseLayerFN)num_input_features growth_ratebn_size drop_ratememory_efficientreturncstt||_tjdd|_tj|||dddd|_t|||_ tjdd|_ tj|||ddddd|_ t ||_ ||_dS)NTinplacer F kernel_sizestridebiasr%r&paddingr')super__init__nn BatchNorm2dnorm1ReLUrelu1Conv2dconv1norm2relu2conv2floatrr )selfrrrrr  __class__W/var/www/html/django/DPS/env/lib/python3.9/site-packages/torchvision/models/densenet.pyr,!s   z_DenseLayer.__init__)inputsr!cCs&t|d}||||}|SNr )torchcatr3r1r/)r8r=Zconcated_featuresbottleneck_outputr;r;r< bn_function0s z_DenseLayer.bn_function)inputr!cCs|D]}|jrdSqdS)NTF) requires_grad)r8rCtensorr;r;r<any_requires_grad6sz_DenseLayer.any_requires_gradcsfdd}tj|g|RS)Ncs |SN)rB)r=r8r;r<closure>sz7_DenseLayer.call_checkpoint_bottleneck..closure)cp checkpoint)r8rCrIr;rHr<call_checkpoint_bottleneck<s z&_DenseLayer.call_checkpoint_bottleneckcCsdSrGr;r8rCr;r;r<forwardCsz_DenseLayer.forwardcCsdSrGr;rMr;r;r<rNGscCst|tr|g}n|}|jrD||rDtjr8td||}n | |}| | | |}|j dkrtj||j |jd}|S)Nz%Memory Efficient not supported in JITr)ptraining) isinstancerr rFr?jit is_scripting ExceptionrLrBr6r5r4rFdropoutrP)r8rCZ prev_featuresrA new_featuresr;r;r<rNMs     )F)__name__ __module__ __qualname__intr7boolr,rrrBrFr?rRunusedrL_overload_methodrN __classcell__r;r;r9r<r s rc sDeZdZdZd eeeeeeddfdd Zeeddd Z Z S) _DenseBlockr FN) num_layersrrrrr r!c sJtt|D]2}t|||||||d}|d|d|qdS)N)rrrr z denselayer%dr )r+r,ranger add_module) r8rarrrrr ilayerr9r;r<r,ds   z_DenseBlock.__init__) init_featuresr!cCs6|g}|D]\}}||}||qt|dSr>)itemsappendr?r@)r8rffeaturesnamererWr;r;r<rNxs  z_DenseBlock.forward)F) rXrYrZ_versionr[r7r\r,rrNr_r;r;r9r<r`as r`cs&eZdZeeddfdd ZZS) _TransitionN)rnum_output_featuresr!csNtt||_tjdd|_tj||dddd|_tj ddd|_ dS)NTr"r Fr$r )r%r&) r+r,r-r.normr0relur2conv AvgPool2dpool)r8rrmr9r;r<r,s   z_Transition.__init__)rXrYrZr[r,r_r;r;r9r<rlsrlc sReZdZdZdeeeeeefeeeeed d fd d Ze e d ddZ 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" `_.  @rFN)r block_confignum_init_featuresrr num_classesr r!c stt|ttdtjd|dddddfdt|fdtjd d fd tj ddd d fg|_ |}t |D]|\} } t | |||||d} |j d| d | || |}| t|d krrt||dd} |j d| d | |d}qr|j dt|t|||_|D]r} t| tjr||}tj|dd}t|d}t|d}||}|S)NTr")r r r )rirUroadaptive_avg_pool2dr?flattenr)r8rrioutr;r;r<rNs     zDenseNet.forward)rsrtryrzrr{F) rXrYrZ__doc__r[rr7r\r,rrNr_r;r;r9r<rs&eZdZedeeddiedddddid d ZeZd S) rzeZdZedeeddiedddddid d ZeZd S) rzeZdZedeeddiedddddid d ZeZd S) rzeZdZedeeddiedddddid d ZeZd S) 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: rsrtry)rverifyrrrrr;r;r<rTs rcKs"t|}tddd||fi|S)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)rurv$rw`)rrrrr;r;r<rms rcKs"t|}tddd||fi|S)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: rs)rurvrsrsry)rrrrr;r;r<rs rcKs"t|}tddd||fi|S)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: rs)rurvrrsry)rrrrr;r;r<rs r) _ModelURLs)rrrr)9r collectionsr functoolsrtypingrrrrr?torch.nnr-torch.nn.functional functionalrUZtorch.utils.checkpointutilsrKrJrZtransforms._presetsr r _apir r_metar_utilsrr__all__Moduler ModuleDictr`rrlrr\rr[rrrrrrrrrrrrr model_urlsr;r;r;r<sh        A U """"