ڧgR@ UddlZddlZddlmZddlmZddlmZmZm Z m Z m Z m Z m Z mZddlZddlmZmZddlmZddlmZmZdd lmZmZdd lmZd d lmZmZmZd d l m!Z!d dl"m#Z#m$Z$m%Z%gdZ&eGddZ'Gdde'Z(Gdde'Z)Gddej*Z+Gddej*Z,Gddej*Z-de ee(e)fde.de e/de ed e0d!ed"e-fd#Z1d$e2d!ed"e e ee(e)fe e/ffd%Z3d&e!iZ4e e2efe5d'<ie4d(d)d*Z6ie4d+d,d*Z7Gd-d.eZ8Gd/d0eZ9Gd1d2eZ:Gd3d4eZ;Gd5d6eZ<Gd7d8eZ=Gd9d:eZ>Gd;deZ@Gd?d@eZAGdAdBeZBee%dCe8jCfDddEdFde e8d e0d!ed"e-fdGZDee%dCe9jCfDddEdFde e9d e0d!ed"e-fdHZEee%dCe:jCfDddEdFde e:d e0d!ed"e-fdIZFee%dCe;jCfDddEdFde e;d e0d!ed"e-fdJZGee%dCejCfDddEdFde e>d e0d!ed"e-fdMZJee%dCe?jCfDddEdFde e?d e0d!ed"e-fdNZKee%dCe@jCfDddEdFde e@d e0d!ed"e-fdOZLee%dCeAjCfDddEdFde eAd e0d!ed"e-fdPZMee%dCeBjCfDddEdFde eBd e0d!ed"e-fdQZNdS)RN) dataclass)partial)AnyCallableDictListOptionalSequenceTupleUnion)nnTensor)StochasticDepth)Conv2dNormActivationSqueezeExcitation)ImageClassificationInterpolationMode)_log_api_usage_once)register_modelWeights WeightsEnum)_IMAGENET_CATEGORIES)_make_divisible_ovewrite_named_paramhandle_legacy_interface) EfficientNetEfficientNet_B0_WeightsEfficientNet_B1_WeightsEfficientNet_B2_WeightsEfficientNet_B3_WeightsEfficientNet_B4_WeightsEfficientNet_B5_WeightsEfficientNet_B6_WeightsEfficientNet_B7_WeightsEfficientNet_V2_S_WeightsEfficientNet_V2_M_WeightsEfficientNet_V2_L_Weightsefficientnet_b0efficientnet_b1efficientnet_b2efficientnet_b3efficientnet_b4efficientnet_b5efficientnet_b6efficientnet_b7efficientnet_v2_sefficientnet_v2_mefficientnet_v2_lc eZdZUeed<eed<eed<eed<eed<eed<edejfed<e dd ed ed e ed efdZ d S) _MBConvConfig expand_ratiokernelstrideinput_channels out_channels num_layers.blockNchannels width_mult min_valuereturnc*t||zd|S)N)r)r>r?r@s [/var/www/html/ai-engine/env/lib/python3.11/site-packages/torchvision/models/efficientnet.pyadjust_channelsz_MBConvConfig.adjust_channels8sx*4aCCCN) __name__ __module__ __qualname__float__annotations__intrr Module staticmethodr rErFrDr6r6.s KKK KKKOOO CN ####DD#D5DXc]D^aDDD\DDDrFr6ceZdZ ddedededededed ed ed eed ejfd dffd Z e ded efdZ xZ S) MBConvConfig?Nr7r8r9r:r;r<r? depth_multr=.rAc |||}|||}|||}| t} t||||||| dSrG)rE adjust_depthMBConvsuper__init__) selfr7r8r9r:r;r<r?rTr= __class__s rDrYzMBConvConfig.__init__?sz--njII++L*EE &&z:>> =E vv~|U_afgggggrFcJttj||zSrG)rMmathceil)r<rTs rDrVzMBConvConfig.adjust_depthRs49Z*455666rF)rSrSN) rHrIrJrKrMr rr rNrYrOrV __classcell__r[s@rDrRrR=s 48hhhh h  h  hhhhbi01h hhhhhh&77%777\77777rFrRcjeZdZ d dededededededeed ejfd dffd Z xZ S) FusedMBConvConfigNr7r8r9r:r;r<r=.rAc h|t}t|||||||dSrG) FusedMBConvrXrY) rZr7r8r9r:r;r<r=r[s rDrYzFusedMBConvConfig.__init__Ys; =E vv~|U_afgggggrFrG) rHrIrJrKrMr rr rNrYr_r`s@rDrbrbWs59 h h h h h  h  h hbi01 h  h h h h h h h h h hrFrbc |eZdZefdedededejfdedejfddf fd Z d e de fd Z xZ S) rWcnfstochastic_depth_prob norm_layer.se_layerrANc btd|jcxkrdksntd|jdko|j|jk|_g}tj}| |j|j }||jkr,| t|j|d||| t|||j |j|||td|jdz}| |||ttjd | t||jd|dtj||_t%|d |_|j|_dS) Nrrillegal stride value kernel_sizerhactivation_layer)rmr9groupsrhrnT)inplace) activationrow)rXrYr9 ValueErrorr:r;use_res_connectr SiLUrEr7appendrr8maxr Sequentialr=rstochastic_depth) rZrfrgrhrilayersrnexpanded_channelssqueeze_channelsr[s rDrYzMBConv.__init__is SZ$$$$1$$$$344 4"zQY33EIY3Y"$7 //0BCDTUU  2 2 2 MM$&% !)%5      !!Jz(%!1    q#"4"9:: hh02BwWYW^hlOmOmOmnnnooo  !3#3zlp      ]F+ /0Eu M M,rFinputcr||}|jr||}||z }|SrGr=rurzrZr~results rDforwardzMBConv.forward?E""   **622F eOF rF) rHrIrJrrRrKrr rNrYrrr_r`s@rDrWrWhs .? 8-8- 8- %8-S")^, 8- 3 >* 8-  8-8-8-8-8-8-tVrFrWcZeZdZdedededejfddffd Zde de fd Z xZ S) rdrfrgrh.rANc td|jcxkrdksntd|jdko|j|jk|_g}tj}| |j|j }||jkrd| t|j||j |j||| t||jd|dn<| t|j|j|j |j||tj||_t!|d|_|j|_dS)Nrrrkrmr9rhrnrlrs)rXrYr9rtr:r;rur rvrEr7rwrr8ryr=rrz)rZrfrgrhr{rnr|r[s rDrYzFusedMBConv.__init__s SZ$$$$1$$$$344 4"zQY33EIY3Y"$7//0BCDTUU  2 2 2 MM$&% # :)%5     MM$%s'7QS]pt     MM$&$ # :)%5    ]F+ /0Eu M M,rFr~cr||}|jr||}||z }|SrGrrs rDrzFusedMBConv.forwardrrF) rHrIrJrbrKrr rNrYrrr_r`s@rDrdrds2- 2- %2-S")^, 2-  2-2-2-2-2-2-hVrFrdceZdZ ddeeeefdededede e d e j fd e ed dffd Z d ed efdZd ed efdZxZS)r皙?Ninverted_residual_settingdropoutrg num_classesrh. last_channelrAc tt||stdt |t rt d|Dstd| tj }g}|dj }| td|dd|tj td |D} d} |D]} g} t| jD]o} t#j| }| r|j|_ d |_|t)| z| z }| ||||| d z } p| tj| |d j}||nd |z}| t||d |tj tj||_tjd |_tjtj|dtj|||_|D]_}t |tjrRtj |j!d|j"$tj#|j"ot |tj tj$frItj%|j!tj#|j"t |tjrgdtMj'|j(z }tj)|j!| |tj#|j"adS)a EfficientNet V1 and V2 main class Args: inverted_residual_setting (Sequence[Union[MBConvConfig, FusedMBConvConfig]]): Network structure dropout (float): The droupout probability stochastic_depth_prob (float): The stochastic depth probability num_classes (int): Number of classes norm_layer (Optional[Callable[..., nn.Module]]): Module specifying the normalization layer to use last_channel (int): The number of channels on the penultimate layer z1The inverted_residual_setting should not be emptyc8g|]}t|tSrP) isinstancer6).0ss rD z)EfficientNet.__init__..s"UUUaZ=11UUUrFz:The inverted_residual_setting should be List[MBConvConfig]Nrrrc3$K|] }|jV dSrG)r<)rrfs rD z(EfficientNet.__init__..s$ U UC U U U U U UrFrrprlT)prqfan_out)moderS)*rXrYrrtrr all TypeErrorr BatchNorm2dr:rwrrvsumranger<copyr;r9rKr=ryfeaturesAdaptiveAvgPool2davgpoolDropoutLinear classifiermodulesConv2dinitkaiming_normal_weightbiaszeros_ GroupNormones_r]sqrt out_featuresuniform_)rZrrrgrrhrr{firstconv_output_channelstotal_stage_blocksstage_block_idrfstage_ block_cnfsd_problastconv_input_channelslastconv_output_channelsm init_ranger[s rDrYzEfficientNet.__init__s( D!!!( ZPQQ Q 0( ; ; ZUU;TUUUVV ZXYY Y  J"$%>a$@$O! ,!AR\oqov      ! U U;T U U UUU, 1 1C%'E3>** $ $ IcNN )/8/EI,'(I$0%2G2GGJ\\ Y__YLLMMM!# MM"-/ 0 0 0 0#> ' ah'''qv&&&&Ary)) ' 49Q^#<#<<   J; CCCqv&&& ' 'rFxc||}||}tj|d}||}|S)Nr)rrtorchflattenrrZrs rD _forward_implzEfficientNet._forward_implLsI MM!   LLOO M!Q   OOA  rFc,||SrG)rrs rDrzEfficientNet.forwardVs!!!$$$rF)rrNN)rHrIrJr r rRrbrKrMr rr rNrYrrrr_r`s@rDrrs  (+9=&*a'a'#+E,@Q2Q,R#Sa'a' % a'  a' Xc29n56 a'sma' a'a'a'a'a'a'Fv&%%F%%%%%%%%rFrrrrweightsprogresskwargsrAc |)t|dt|jdt||fd|i|}|*|||d|S)Nr categoriesrT)r check_hash)rlenmetarload_state_dictget_state_dict)rrrrrrmodels rD _efficientnetrZs|fmSl9S5T5TUUU 2G a a, aZ` a aE g44hSW4XXYYY LrFarchc F|drtt|d|d}|dddddd|d dd dd d |d d d d d d |d dd d dd|d d dddd|d d d ddd|d dddddg}d}n|drxt dddd d d t ddd d ddt ddd dddtddd ddd td dddddtd dd dddg}d}nP|drt dddd d dt ddd d dd t ddd ddd tddd dddtd dddddtd dd dd d!td ddd d"d g}d}n|d#rt ddddddt ddd dddt ddd dd$dtddd d$dd%td dddd&d'td dd d&d(d)td ddd(d*dg}d}nt d+|||fS),Nefficientnet_br?rTr?rTrr r(Pprp@r20@ ir3i0ir4` izUnsupported model type ) startswithrrRpoprbrt)rr bneck_confrrs rD_efficientnet_confrms3  '((-;\fjj6N6N[a[e[efr[s[sttt Jq!QB * * Jq!QB * * Jq!QB * * Jq!QB * * Jq!QC + + Jq!QS! , , Jq!QS! , ,% ! , - -!; aAr2q 1 1 aAr2q 1 1 aAr2q 1 1 Aq"c1 - - Aq#sA . . Aq#sB / / % ! , - -; aAr2q 1 1 aAr2q 1 1 aAr2q 1 1 Aq"c1 - - Aq#sB / / Aq#sB / / Aq#sA . .% ! , - - ; aAr2q 1 1 aAr2q 1 1 aAr2q 1 1 Aq"c2 . . Aq#sB / / Aq#sB / / Aq#sA . .% ! 9499::: $l 22rFr _COMMON_META)rrzUhttps://github.com/pytorch/vision/tree/main/references/classification#efficientnet-v1)min_sizerecipe)!rzUhttps://github.com/pytorch/vision/tree/main/references/classification#efficientnet-v2c peZdZedeeddejieddddd id d d d Z e Z dS)rzJhttps://download.pytorch.org/models/efficientnet_b0_rwightman-7f5810bc.pthrr crop_size resize_size interpolationidP ImageNet-1Kg?5^IlS@g5^I bW@zacc@1zacc@5gNbX9?g~jts4@1These weights are ported from the original paper. num_params_metrics_ops _file_size_docsurl transformsrN rHrIrJrrrrBICUBIC_COMMON_META_V1 IMAGENET1K_V1DEFAULTrPrFrDrrG X7 3CO`Oh       !##    L    M(GGGrFrc eZdZedeeddejieddddd id d d d Z edeeddej iedddddd id dddZ e Z dS)r zJhttps://download.pytorch.org/models/efficientnet_b1_rwightman-bac287d4.pthrrivrg +S@gClW@rgCl?gM">@rrrz@https://download.pytorch.org/models/efficientnet_b1-c27df63c.pthzOhttps://github.com/pytorch/vision/issues/3995#new-recipe-with-lr-wd-crop-tuninggʡS@gƻW@gA`">@$ These weights improve upon the results of the original paper by using a modified version of TorchVision's `new training recipe `_. )rrrrrrN) rHrIrJrrrrr r rBILINEAR IMAGENET1K_V2rrPrFrDr r sG X7 3CO`Oh       !##    L    M(G N7 3CO`Oi     !g##       M0GGGrFr c peZdZedeeddejiedddddid d d d  Z e Z dS)r!zJhttps://download.pytorch.org/models/efficientnet_b2_rwightman-c35c1473.pthi rirgx&T@gp= W@rg rh?gʡEA@rrrNr rPrFrDr!r!rrFr!c peZdZedeeddejieddddd id d d d Z e Z dS)r"zJhttps://download.pytorch.org/models/efficientnet_b3_rwightman-b3899882.pthi,rrirgnT@g~jtX@rgZd;?gd;OG@rrrNr rPrFrDr"r"G X7 3CO`Oh       "##    L    M(GGGrFr"c peZdZedeeddejieddddd id d d d Z e Z dS)r#zJhttps://download.pytorch.org/models/efficientnet_b4_rwightman-23ab8bcd.pthi|rri0!'rgjtT@gt&X@rg~jt@gKR@rrrNr rPrFrDr#r#/rrFr#c peZdZedeeddejiedddddid d d d  Z e Z dS)r$zJhttps://download.pytorch.org/models/efficientnet_b5_lukemelas-1a07897c.pthirirg#~jT@gx&1(X@rgx&1$@gK7]@rrrNr rPrFrDr$r$GG X7 3CO`Oh       "##   !L    M(GGGrFr$c peZdZedeeddejiedddddid d d d  Z e Z dS)r%zJhttps://download.pytorch.org/models/efficientnet_b6_lukemelas-24a108a5.pthirirgnU@gv:X@rg rh3@g$d@rrrNr rPrFrDr%r%_rrFr%c peZdZedeeddejiedddddid d d d  Z e Z dS)r&zJhttps://download.pytorch.org/models/efficientnet_b7_lukemelas-c5b4e57e.pthiXricrg+U@g'1:X@rgsh|B@go@rrrNr rPrFrDr&r&wrrFr&c peZdZedeeddejiedddddid d d d  Z e Z dS)r'zBhttps://download.pytorch.org/models/efficientnet_v2_s-dd5fe13b.pthrri8nGrg;OU@gx&18X@rgZd @gVT@rrrN rHrIrJrrrrr_COMMON_META_V2rrrPrFrDr'r'sG P7 +4      "##       M4GGGrFr'c peZdZedeeddejiedddddid d d d  Z e Z dS)r(zBhttps://download.pytorch.org/models/efficientnet_v2_m-dc08266a.pthri:rgI +GU@gDlIX@rgE8@gQj@rrrNr rPrFrDr(r(sG P7 +4      "##       M4GGGrFr(c teZdZedeeddejddieddddd id d d d Z e Z dS)r)zBhttps://download.pytorch.org/models/efficientnet_v2_l-59c71312.pthr#)?r%r%)rrrmeanstdiHfrgʡEsU@gOnrX@rg ףp= L@gI +i|@rrrN) rHrIrJrrrrr r!rrrPrFrDr)r)sG P7 +3         ###   !L    M0GGGrFr) pretrained)rT)rrc t|}tddd\}}t||dd|||fi|S)aEfficientNet B0 model architecture from the `EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks `_ paper. Args: weights (:class:`~torchvision.models.EfficientNet_B0_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.EfficientNet_B0_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.efficientnet.EfficientNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.EfficientNet_B0_Weights :members: r*rSrrr)rverifyrrrrrrrrs rDr*r*m.&,,W55G.@AR_bor.s.s.s+| !6::i#=#=|WV^  bh  rFc t|}tddd\}}t||dd|||fi|S)aEfficientNet B1 model architecture from the `EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks `_ paper. Args: weights (:class:`~torchvision.models.EfficientNet_B1_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.EfficientNet_B1_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.efficientnet.EfficientNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.EfficientNet_B1_Weights :members: r+rS皙?rrr)r r*rrrr+s rDr+r+r,rFc t|}tddd\}}t||dd|||fi|S)aEfficientNet B2 model architecture from the `EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks `_ paper. Args: weights (:class:`~torchvision.models.EfficientNet_B2_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.EfficientNet_B2_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.efficientnet.EfficientNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.EfficientNet_B2_Weights :members: r,r.333333?rr333333?)r!r*rrrr+s rDr,r,&r,rFc t|}tddd\}}t||dd|||fi|S)aEfficientNet B3 model architecture from the `EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks `_ paper. Args: weights (:class:`~torchvision.models.EfficientNet_B3_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.EfficientNet_B3_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.efficientnet.EfficientNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.EfficientNet_B3_Weights :members: r-r0ffffff?rrr1)r"r*rrrr+s rDr-r-Er.&,,W55G.@AR_bor.s.s.s+| ! 9c""       rFc t|}tddd\}}t||dd|||fi|S)aEfficientNet B4 model architecture from the `EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks `_ paper. Args: weights (:class:`~torchvision.models.EfficientNet_B4_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.EfficientNet_B4_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.efficientnet.EfficientNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.EfficientNet_B4_Weights :members: r.r3?rr皙?)r#r*rrrr+s rDr.r.ir4rFc t|}tddd\}}t||dd|||fdt t jdd i|S) aEfficientNet B5 model architecture from the `EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks `_ paper. Args: weights (:class:`~torchvision.models.EfficientNet_B5_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.EfficientNet_B5_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.efficientnet.EfficientNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.EfficientNet_B5_Weights :members: r/g?g@rrr7rhMbP?{Gz?epsmomentum)r$r*rrrrr rr+s rDr/r/.&,,W55G.@AR_bor.s.s.s+| ! 9c""    2>utDDD     rFc t|}tddd\}}t||dd|||fdt t jdd i|S) aEfficientNet B6 model architecture from the `EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks `_ paper. Args: weights (:class:`~torchvision.models.EfficientNet_B6_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.EfficientNet_B6_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.efficientnet.EfficientNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.EfficientNet_B6_Weights :members: r0r6g@rrr%rhr9r:r;)r%r*rrrrr rr+s rDr0r0r>rFc t|}tddd\}}t||dd|||fdt t jdd i|S) aEfficientNet B7 model architecture from the `EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks `_ paper. Args: weights (:class:`~torchvision.models.EfficientNet_B7_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.EfficientNet_B7_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.efficientnet.EfficientNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.EfficientNet_B7_Weights :members: r1g@g@rrr%rhr9r:r;)r&r*rrrrr rr+s rDr1r1r>rFc t|}td\}}t||dd|||fdt t jdi|S)a Constructs an EfficientNetV2-S architecture from `EfficientNetV2: Smaller Models and Faster Training `_. Args: weights (:class:`~torchvision.models.EfficientNet_V2_S_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.EfficientNet_V2_S_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.efficientnet.EfficientNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.EfficientNet_V2_S_Weights :members: r2rrrhr9r<)r'r*rrrrr rr+s rDr2r20(..w77G.@AT.U.U+| ! 9c""    2>u555     rFc t|}td\}}t||dd|||fdt t jdi|S)a Constructs an EfficientNetV2-M architecture from `EfficientNetV2: Smaller Models and Faster Training `_. Args: weights (:class:`~torchvision.models.EfficientNet_V2_M_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.EfficientNet_V2_M_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.efficientnet.EfficientNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.EfficientNet_V2_M_Weights :members: r3rr1rhr9rB)r(r*rrrrr rr+s rDr3r3"rCrFc t|}td\}}t||dd|||fdt t jdi|S)a Constructs an EfficientNetV2-L architecture from `EfficientNetV2: Smaller Models and Faster Training `_. Args: weights (:class:`~torchvision.models.EfficientNet_V2_L_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.EfficientNet_V2_L_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.efficientnet.EfficientNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.EfficientNet_V2_L_Weights :members: r4rr7rhr9rB)r)r*rrrrr rr+s rDr4r4HrCrF)Orr] dataclassesr functoolsrtypingrrrrr r r r rr rtorchvision.opsrops.miscrrtransforms._presetsrrutilsr_apirrr_metar_utilsrrr__all__r6rRrbrNrWrdrrKrMboolrstrrrrLr r!rr r!r"r#r$r%r&r'r(r)rr*r+r,r-r.r/r0r1r2r3r4rPrFrDrSs  !!!!!!NNNNNNNNNNNNNNNNNNNN ++++++>>>>>>>>HHHHHHHH''''''6666666666''''''SSSSSSSSSS   6  D D D D D D D  D77777=7774hhhhh hhh"@@@@@RY@@@F:::::"):::zo%o%o%o%o%29o%o%o%d'l