+
     °³j¬A  ã                   óf  € ^ RI t ^ RIHt ^ RIHt ^ RIHtHt ^ RIt^ RI	H
t
 ^ RIH
u Ht ^ RIHu Ht ^ RIHt ^RIHt ^RIHt ^RIHtHtHt ^R	IHt ^R
IHtHt . R2Ot ! R R]
P@                  4      t! ! R R]
PD                  4      t# ! R R]
PH                  4      t% ! R R]
P@                  4      t&R R lt'R R lt(RR3R]RRRR /t) ! R! R]4      t* ! R" R]4      t+ ! R# R]4      t, ! R$ R]4      t-]! 4       ]! R%]*P\                  3R&7      R'RR(R)/R* R+ ll4       4       t/]! 4       ]! R%]+P\                  3R&7      R'RR(R)/R, R- ll4       4       t0]! 4       ]! R%],P\                  3R&7      R'RR(R)/R. R/ ll4       4       t1]! 4       ]! R%]-P\                  3R&7      R'RR(R)/R0 R1 ll4       4       t2R# )4é    N)ÚOrderedDict)Úpartial)ÚAnyÚOptional©ÚTensor)ÚImageClassification)Ú_log_api_usage_once)Úregister_modelÚWeightsÚWeightsEnum)Ú_IMAGENET_CATEGORIES)Ú_ovewrite_named_paramÚhandle_legacy_interfaceÚDenseNetÚDenseNet121_WeightsÚDenseNet161_WeightsÚDenseNet169_WeightsÚDenseNet201_Weightsc                   óD  a a€ ] tR t^t oRV3R lV 3R llltV3R lR ltV3R lR lt]P                  P                  V3R lR l4       t
]P                  P                  V3R	 lR
 l4       t]P                  P                  V3R lR l4       tV3R lR ltRtVtV ;t# )Ú_DenseLayerc                ó<   <€ V ^8„  d   QhRS[ RS[ RS[ RS[RS[RR/# )é   Únum_input_featuresÚgrowth_rateÚbn_sizeÚ	drop_rateÚmemory_efficientÚreturnN©ÚintÚfloatÚbool)ÚformatÚ__classdict__s   "€Ú\/home/luca/screen-checking/.venv/lib/python3.14/site-packages/torchvision/models/densenet.pyÚ__annotate__Ú_DenseLayer.__annotate__    s=   ø€ ÷ 1ñ 1Ù"%ð1Ù47ð1ÙBEð1ÙRWð1Ùkoð1à	ñ1ó    c           	     óÒ  <€ \         SV `  4        \        P                  ! V4      V n        \        P
                  ! R R7      V n        \        P                  ! WV,          ^^RR7      V n        \        P                  ! W2,          4      V n	        \        P
                  ! R R7      V n
        \        P                  ! W2,          V^^^RR7      V n        \        V4      V n        WPn        R# )T©ÚinplaceF©Úkernel_sizeÚstrideÚbias©r.   r/   Úpaddingr0   N)ÚsuperÚ__init__ÚnnÚBatchNorm2dÚnorm1ÚReLUÚrelu1ÚConv2dÚconv1Únorm2Úrelu2Úconv2r"   r   r   )Úselfr   r   r   r   r   Ú	__class__s   &&&&&&€r&   r4   Ú_DenseLayer.__init__    s¥   ø€ ô 	‰ÑÔÜ—^’^Ð$6Ó7ˆŒ
Ü—W’W TÔ*ˆŒ
Ü—Y’YÐ1¸[Õ3HÐVWÐ`aÐhmÔnˆŒ
ä—^’^ GÕ$9Ó:ˆŒ
Ü—W’W TÔ*ˆŒ
Ü—Y’Y˜wÕ4°kÈqÐYZÐdeÐlqÔrˆŒ
ä˜yÓ)ˆŒØ 0Ör)   c                ó6   <€ V ^8„  d   QhRS[ S[,          RS[/# )r   Úinputsr   ©Úlistr   )r$   r%   s   "€r&   r'   r(   /   s   ø€ ÷ !ñ !¡$¡v¥,ð !±6ñ !r)   c                ó’   € \         P                  ! V^4      pV P                  V P                  V P	                  V4      4      4      pV# ©é   )ÚtorchÚcatr;   r9   r7   )r?   rC   Úconcated_featuresÚbottleneck_outputs   &&  r&   Úbn_functionÚ_DenseLayer.bn_function/   s;   € Ü!ŸIšI f¨aÓ0ÐØ ŸJ™J t§z¡z°$·*±*Ð=NÓ2OÓ'PÓQÐØ Ð r)   c                ó6   <€ V ^8„  d   QhRS[ S[,          RS[/# ©r   Úinputr   )rE   r   r#   )r$   r%   s   "€r&   r'   r(   5   s   ø€ ÷ ñ ¡t©F¥|ð ¹ñ r)   c                óB   € V F  pVP                   '       g   K   R # 	  R# )TF)Úrequires_grad)r?   rQ   Útensors   && r&   Úany_requires_gradÚ_DenseLayer.any_requires_grad5   s    € ÛˆFØ×#×#Ò#Úñ ñ r)   c                ó6   <€ V ^8„  d   QhRS[ S[,          RS[/# rP   rD   )r$   r%   s   "€r&   r'   r(   <   s#   ø€ ÷ Cñ C±±Vµð CÁñ Cr)   c                óD   a € V 3R  lp\         P                  ! V.VO5RR/ # )c                  ó&   <€ SP                  V 4      # ©N)rM   )rC   r?   s   *€r&   ÚclosureÚ7_DenseLayer.call_checkpoint_bottleneck.<locals>.closure=   s   ø€ Ø×#Ñ# FÓ+Ð+r)   Úuse_reentrantF)ÚcpÚ
checkpoint)r?   rQ   r[   s   f& r&   Úcall_checkpoint_bottleneckÚ&_DenseLayer.call_checkpoint_bottleneck;   s#   ø€ õ	,ô �}Š}˜WÐB uÒB¸EÑBÐBr)   c                ó6   <€ V ^8„  d   QhRS[ S[,          RS[/# rP   rD   )r$   r%   s   "€r&   r'   r(   C   s   ø€ ÷ ñ ™T¡&�\ð ©fñ r)   c                ó   € R # rZ   © ©r?   rQ   s   &&r&   ÚforwardÚ_DenseLayer.forwardB   ó   € ár)   c                ó&   <€ V ^8„  d   QhRS[ RS[ /# rP   r   )r$   r%   s   "€r&   r'   r(   G   s   ø€ ÷ ñ ™Vð ©ñ r)   c                ó   € R # rZ   rd   re   s   &&r&   rf   rg   F   rh   r)   c                ó&   <€ V ^8„  d   QhRS[ RS[ /# rP   r   )r$   r%   s   "€r&   r'   r(   L   s   ø€ ÷ ñ ™Vð ©ñ r)   c                ó  € \        V\        4      '       d   V.pMTpV P                  '       dY   V P                  V4      '       dB   \        P
                  P                  4       '       d   \        R 4      hV P                  V4      pMV P                  V4      pV P                  V P                  V P                  V4      4      4      pV P                  ^ 8”  d-   \        P                  ! W@P                  V P                   R7      pV# )z%Memory Efficient not supported in JIT)ÚpÚtraining)Ú
isinstancer   r   rU   rI   ÚjitÚis_scriptingÚ	Exceptionr`   rM   r>   r=   r<   r   ÚFÚdropoutrn   )r?   rQ   Úprev_featuresrL   Únew_featuress   &&   r&   rf   rg   L   sÃ   € Ü�eœV×$Ò$Ø"˜G‰Mà!ˆMà× × Ð  T×%;Ñ%;¸M×%JÒ%JÜ�y‰y×%Ñ%×'Ò'ÜÐ GÓHÐHà $× ?Ñ ?ÀÓ NÑà $× 0Ñ 0°Ó ?Ðà—z‘z $§*¡*¨T¯Z©ZÐ8IÓ-JÓ"KÓLˆØ�>‰>˜AÔÜŸ9š9 \·^±^ÈdÏmÉmÔ\ˆLØÐr)   )r;   r>   r   r   r7   r<   r9   r=   ©F)Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__r4   rM   rU   rI   rp   Úunusedr`   Ú_overload_methodrf   Ú__static_attributes__Ú__classdictcell__Ú__classcell__©r@   r%   s   @@r&   r   r      sŽ   ù‡ € ÷1õ 1÷!ð !÷ð ð ‡Y�Y×Ñ÷Có ðCð ‡Y�Y×Ñ÷ó  ðð ‡Y�Y×Ñ÷ó  ð÷
÷ ð r)   r   c                   óX   a a€ ] tR t^`t o^tRV3R lV 3R llltV3R lR ltRtVtV ;t	# )Ú_DenseBlockc                óB   <€ V ^8„  d   QhRS[ RS[ RS[ RS[ RS[RS[RR/# )	r   Ú
num_layersr   r   r   r   r   r   Nr    )r$   r%   s   "€r&   r'   Ú_DenseBlock.__annotate__c   sQ   ø€ ÷ =ñ =áð=ñ  ð=ñ ð	=ñ
 ð=ñ ð=ñ ð=ð 
ñ=r)   c           	     óÂ   <€ \         S	V `  4        \        V4       F@  p\        W'V,          ,           VVVVR 7      pV P	                  RV^,           ,          V4       KB  	  R# ))r   r   r   r   zdenselayer%dN)r3   r4   Úranger   Ú
add_module)
r?   r…   r   r   r   r   r   ÚiÚlayerr@   s
   &&&&&&&  €r&   r4   Ú_DenseBlock.__init__c   sX   ø€ ô 	‰ÑÔÜ�zÖ"ˆAÜØ"¨¥_Õ4Ø'ØØ#Ø!1ôˆEð �O‰O˜N¨a°!­eÕ4°eÖ<ó #r)   c                ó&   <€ V ^8„  d   QhRS[ RS[ /# )r   Úinit_featuresr   r   )r$   r%   s   "€r&   r'   r†   w   s   ø€ ÷ &ñ &¡Vð &±ñ &r)   c                óš   € V.pV P                  4        F  w  r4V! V4      pVP                  V4       K   	  \        P                  ! V^4      # rG   )ÚitemsÚappendrI   rJ   )r?   rŽ   ÚfeaturesÚnamer‹   rv   s   &&    r&   rf   Ú_DenseBlock.forwardw   sC   € Ø!�?ˆØŸ:™:ž<‰KˆDÙ  ›?ˆLØ�O‰O˜LÖ)ñ (ô �yŠy˜ 1Ó%Ð%r)   rd   rw   )
rx   ry   rz   r{   Ú_versionr4   rf   r~   r   r€   r�   s   @@r&   rƒ   rƒ   `   s#   ù‡ € Ø€H÷=õ =÷(&÷ &ð &r)   rƒ   c                   ó>   a a€ ] tR t^t oV3R lV 3R lltRtVtV ;t# )Ú_Transitionc                ó*   <€ V ^8„  d   QhRS[ RS[ RR/# )r   r   Únum_output_featuresr   N)r!   )r$   r%   s   "€r&   r'   Ú_Transition.__annotate__€   s"   ø€ ÷ :ñ :©3ð :ÁSð :ÈTñ :r)   c                ó
  <€ \         SV `  4        \        P                  ! V4      V n        \        P
                  ! R R7      V n        \        P                  ! W^^RR7      V n        \        P                  ! ^^R7      V n
        R# )Tr+   Fr-   )r.   r/   N)r3   r4   r5   r6   Únormr8   Úrelur:   ÚconvÚ	AvgPool2dÚpool)r?   r   r™   r@   s   &&&€r&   r4   Ú_Transition.__init__€   s[   ø€ Ü‰ÑÔÜ—N’NÐ#5Ó6ˆŒ	Ü—G’G DÔ)ˆŒ	Ü—I’IÐ0ÐSTÐ]^ÐejÔkˆŒ	Ü—L’L¨Q°qÔ9ˆŽ	r)   )rž   rœ   r    r�   )rx   ry   rz   r{   r4   r~   r   r€   r�   s   @@r&   r—   r—      s   ù‡ € ÷:÷ :ó :r)   r—   c                   óX   a a€ ] tR t^ˆt oRtRV3R lV 3R llltV3R lR ltRtVtV ;t	# )r   a  Densenet-BC model class, based on
`"Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf>`_.

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" <https://arxiv.org/pdf/1707.06990.pdf>`_.
c                óf   <€ V ^8„  d   QhRS[ RS[S[ S[ S[ S[ 3,          RS[ RS[ RS[RS[ RS[RR	/# )
r   r   Úblock_configÚnum_init_featuresr   r   Únum_classesr   r   N)r!   Útupler"   r#   )r$   r%   s   "€r&   r'   ÚDenseNet.__annotate__˜   si   ø€ ÷ :-ñ :-áð:-ñ ™C¡¡c©3Ð.Õ/ð:-ñ ð	:-ñ
 ð:-ñ ð:-ñ ð:-ñ ð:-ð 
ñ:-r)   c                ó®  <€ \         SV `  4        \        V 4       \        P                  ! \        R \        P                  ! ^V^^^RR7      3R\        P                  ! V4      3R\        P                  ! RR7      3R\        P                  ! ^^^R7      3.4      4      V n
        Tp\        V4       F®  w  rš\        V
VVVVVR	7      pV P                  P                  R
V	^,           ,          V4       WŠV,          ,           pV	\        V4      ^,
          8w  g   Kh  \        Wˆ^,          R7      pV P                  P                  RV	^,           ,          V4       V^,          pK°  	  V P                  P                  R\        P                  ! V4      4       \        P                   ! W†4      V n        V P%                  4        EF  p\'        V\        P                  4      '       d,   \        P(                  P+                  VP,                  4       KO  \'        V\        P                  4      '       dW   \        P(                  P/                  VP,                  ^4       \        P(                  P/                  VP0                  ^ 4       KÅ  \'        V\        P                   4      '       g   Kç  \        P(                  P/                  VP0                  ^ 4       EK  	  R# )Úconv0Fr1   Únorm0Úrelu0Tr+   Úpool0)r.   r/   r2   )r…   r   r   r   r   r   zdenseblock%d)r   r™   ztransition%dÚnorm5N)r3   r4   r
   r5   Ú
Sequentialr   r:   r6   r8   Ú	MaxPool2dr’   Ú	enumeraterƒ   r‰   Úlenr—   ÚLinearÚ
classifierÚmodulesro   ÚinitÚkaiming_normal_ÚweightÚ	constant_r0   )r?   r   r¤   r¥   r   r   r¦   r   Únum_featuresrŠ   r…   ÚblockÚtransÚmr@   s   &&&&&&&&      €r&   r4   ÚDenseNet.__init__˜   s  ø€ ô 	‰ÑÔÜ˜DÔ!ô ŸšÜàœbŸiši¨Ð+<È!ÐTUÐ_`ÐglÔmÐnØœbŸnšnÐ->Ó?Ð@ØœbŸgšg¨dÔ3Ð4ØœbŸlšl°qÀÈAÔNÐOð	óó	
ˆŒð )ˆÜ& |Ö4‰MˆAÜØ%Ø#/ØØ'Ø#Ø!1ôˆEð �M‰M×$Ñ$ ^°q¸1µuÕ%=¸uÔEØ'°{Õ*BÕBˆLØ”C˜Ó%¨Õ)Ö)Ü#°|ÐijÕYjÔk�Ø—‘×(Ñ(¨¸1¸q½5Õ)AÀ5ÔIØ+¨qÕ0’ñ 5ð" 	�‰× Ñ  ¬"¯.ª.¸Ó*FÔGô Ÿ)š) LÓ>ˆŒð —‘—ˆAÜ˜!œRŸY™Y×'Ò'Ü—‘×'Ñ'¨¯©Ö1Ü˜AœrŸ~™~×.Ò.Ü—‘×!Ñ! !§(¡(¨AÔ.Ü—‘×!Ñ! !§&¡&¨!Ö,Ü˜AœrŸy™y×)Ô)Ü—‘×!Ñ! !§&¡&¨!×,ó  r)   c                ó&   <€ V ^8„  d   QhRS[ RS[ /# )r   Úxr   r   )r$   r%   s   "€r&   r'   r¨   Ô   s   ø€ ÷ ñ ™ð ¡Fñ r)   c                óÖ   € V P                  V4      p\        P                  ! VR R7      p\        P                  ! VR4      p\        P
                  ! V^4      pV P                  V4      pV# )Tr+   )rH   rH   )r’   rs   r�   Úadaptive_avg_pool2drI   Úflattenr´   )r?   rÀ   r’   Úouts   &&  r&   rf   ÚDenseNet.forwardÔ   sU   € Ø—=‘= Ó#ˆÜ�fŠf�X tÔ,ˆÜ×#Ò# C¨Ó0ˆÜ�mŠm˜C Ó#ˆØ�o‰o˜cÓ"ˆØˆ
r)   )r´   r’   )é    ©é   é   é   é   é@   é   r   iè  F)
rx   ry   rz   r{   Ú__doc__r4   rf   r~   r   r€   r�   s   @@r&   r   r   ˆ   s$   ù‡ € ñ÷:-õ :-÷x÷ ð r)   c                óT   € V ^8„  d   QhR\         P                  R\        R\        RR/# )r   ÚmodelÚweightsÚprogressr   N)r5   ÚModuler   r#   )r$   s   "r&   r'   r'   Ý   s-   € ÷ &ñ &œBŸI™Ið &´ð &Ätð &ÐPTñ &r)   c                 óV  € \         P                  ! R 4      pVP                  VRR7      p\        VP	                  4       4       FQ  pVP                  V4      pV'       g   K  VP                  ^4      VP                  ^4      ,           pWE,          WG&   WE KS  	  V P                  V4       R# )z]^(.*denselayer\d+\.(?:norm|relu|conv))\.((?:[12])\.(?:weight|bias|running_mean|running_var))$T)rÒ   Ú
check_hashN)ÚreÚcompileÚget_state_dictrE   ÚkeysÚmatchÚgroupÚload_state_dict)rÐ   rÑ   rÒ   ÚpatternÚ
state_dictÚkeyÚresÚnew_keys   &&&     r&   Ú_load_state_dictrâ   Ý   sŽ   € ô
 �jŠjØhó€Gð ×'Ñ'°ÀdÐ'ÓK€JÜ�J—O‘OÓ%Ö&ˆØ�m‰m˜CÓ ˆß‰3Ø—i‘i “l S§Y¡Y¨q£\Õ1ˆGØ",¥/ˆJÑØ’ñ 'ð 
×Ñ˜*Ö%r)   c                ó¸   € V ^8„  d   QhR\         R\        \         \         \         \         3,          R\         R\        \        ,          R\        R\
        R\        /# )r   r   r¤   r¥   rÑ   rÒ   Úkwargsr   )r!   r§   r   r   r#   r   r   )r$   s   "r&   r'   r'   ð   sa   € ÷ ñ ÜðäœœS¤#¤sÐ*Õ+ðô ðô ”kÕ"ð	ô
 ðô ðô ñr)   c                 ó˜   € Ve(   \        VR\        VP                  R,          4      4       \        WV3/ VB pVe   \	        WcVR7       V# )Nr¦   Ú
categories)rÐ   rÑ   rÒ   )r   r²   Úmetar   râ   )r   r¤   r¥   rÑ   rÒ   rä   rÐ   s   &&&&&, r&   Ú	_densenetrè   ð   sK   € ð ÒÜ˜f m´S¸¿¹ÀlÕ9SÓ5TÔUä�[Ð0AÑLÀVÑL€EàÒÜ˜uÀÕIà€Lr)   Úmin_sizeræ   Úrecipez*https://github.com/pytorch/vision/pull/116Ú_docsz'These weights are ported from LuaTorch.c                   ód   € ] tR tRt]! R]! ]^àR7      / ]CRRRRRR	R
R//RRRR/CR7      t]t	Rt
R# )r   i  z<https://download.pytorch.org/models/densenet121-a639ec97.pth©Ú	crop_sizeÚ
num_paramsih¿y Ú_metricsúImageNet-1Kúacc@1g²�ï§Æ›R@úacc@5g‘í|?5þV@Ú_opsgyé&1¬@Ú
_file_sizeg¸…ëQØ>@©ÚurlÚ
transformsrç   rd   N©rx   ry   rz   r{   r   r   r	   Ú_COMMON_METAÚIMAGENET1K_V1ÚDEFAULTr~   rd   r)   r&   r   r     s^   † ÙØJÙÐ.¸#Ô>ð
Øð
à˜'ØØØ˜VØ˜Vð ðð �EØ˜&ñ
ô€Mð  „Gr)   c                   ód   € ] tR tRt]! R]! ]^àR7      / ]CRRRRRR	R
R//RRRR/CR7      t]t	Rt
R# )r   i  z<https://download.pytorch.org/models/densenet161-8d451a50.pthrí   rï   i(£µrð   rñ   rò   gF¶óýÔHS@ró   g¤p=
×cW@rô   g¶óýÔxé@rõ   gV-²�—[@rö   rd   Nrù   rd   r)   r&   r   r     s^   † ÙØJÙÐ.¸#Ô>ð
Øð
à˜(ØØØ˜VØ˜Vð ðð �EØ˜'ñ
ô€Mð  „Gr)   c                   ód   € ] tR tRt]! R]! ]^àR7      / ]CRRRRRR	R
R//RRRR/CR7      t]t	Rt
R# )r   i3  z<https://download.pytorch.org/models/densenet169-b2777c0a.pthrí   rï   ihç× rð   rñ   rò   gfffffæR@ró   gÝ$�•3W@rô   gáz®Gá
@rõ   g´Èv¾ŸZK@rö   rd   Nrù   rd   r)   r&   r   r   3  s^   † ÙØJÙÐ.¸#Ô>ð
Øð
à˜(ØØØ˜VØ˜Vð ðð �DØ˜&ñ
ô€Mð  „Gr)   c                   ód   € ] tR tRt]! R]! ]^àR7      / ]CRRRRRR	R
R//RRRR/CR7      t]t	Rt
R# )r   iG  z<https://download.pytorch.org/models/densenet201-c1103571.pthrí   rï   ihc1rð   rñ   rò   gÓMbX9S@ró   gHáz®WW@rô   gD‹lçû)@rõ   gZd;ßWS@rö   rd   Nrù   rd   r)   r&   r   r   G  s^   † ÙØJÙÐ.¸#Ô>ð
Øð
à˜(ØØØ˜VØ˜Vð ðð �EØ˜&ñ
ô€Mð  „Gr)   Ú
pretrained)rÑ   rÑ   rÒ   Tc                ó^   € V ^8„  d   QhR\         \        ,          R\        R\        R\        /# ©r   rÑ   rÒ   rä   r   )r   r   r#   r   r   )r$   s   "r&   r'   r'   ]  ó6   € ÷ Kñ KœHÔ%8Õ9ð KÌDð KÔcfð KÔksñ Kr)   c                óJ   € \         P                  V 4      p \        ^ R^@W3/ VB # )a?  Densenet-121 model from
`Densely Connected Convolutional Networks <https://arxiv.org/abs/1608.06993>`_.

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
        <https://github.com/pytorch/vision/blob/main/torchvision/models/densenet.py>`_
        for more details about this class.

.. autoclass:: torchvision.models.DenseNet121_Weights
    :members:
rÇ   )r   Úverifyrè   ©rÑ   rÒ   rä   s   $$,r&   Údensenet121r  [  ó*   € ô* "×(Ñ(¨Ó1€Gä�R˜¨"¨gÑJÀ6ÑJÐJr)   c                ó^   € V ^8„  d   QhR\         \        ,          R\        R\        R\        /# r  )r   r   r#   r   r   )r$   s   "r&   r'   r'   w  r  r)   c                óJ   € \         P                  V 4      p \        ^0R^`W3/ VB # )a?  Densenet-161 model from
`Densely Connected Convolutional Networks <https://arxiv.org/abs/1608.06993>`_.

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
        <https://github.com/pytorch/vision/blob/main/torchvision/models/densenet.py>`_
        for more details about this class.

.. autoclass:: torchvision.models.DenseNet161_Weights
    :members:
)rÈ   rÉ   é$   rÊ   )r   r  rè   r  s   $$,r&   Údensenet161r  u  r  r)   c                ó^   € V ^8„  d   QhR\         \        ,          R\        R\        R\        /# r  )r   r   r#   r   r   )r$   s   "r&   r'   r'   ‘  r  r)   c                óJ   € \         P                  V 4      p \        ^ R^@W3/ VB # )a?  Densenet-169 model from
`Densely Connected Convolutional Networks <https://arxiv.org/abs/1608.06993>`_.

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
        <https://github.com/pytorch/vision/blob/main/torchvision/models/densenet.py>`_
        for more details about this class.

.. autoclass:: torchvision.models.DenseNet169_Weights
    :members:
)rÈ   rÉ   rÆ   rÆ   )r   r  rè   r  s   $$,r&   Údensenet169r  �  r  r)   c                ó^   € V ^8„  d   QhR\         \        ,          R\        R\        R\        /# r  )r   r   r#   r   r   )r$   s   "r&   r'   r'   «  r  r)   c                óJ   € \         P                  V 4      p \        ^ R^@W3/ VB # )a?  Densenet-201 model from
`Densely Connected Convolutional Networks <https://arxiv.org/abs/1608.06993>`_.

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
        <https://github.com/pytorch/vision/blob/main/torchvision/models/densenet.py>`_
        for more details about this class.

.. autoclass:: torchvision.models.DenseNet201_Weights
    :members:
)rÈ   rÉ   é0   rÆ   )r   r  rè   r  s   $$,r&   Údensenet201r  ©  r  r)   )	r   r   r   r   r   r  r  r  r  )é   r  )3rÖ   Úcollectionsr   Ú	functoolsr   Útypingr   r   rI   Útorch.nnr5   Útorch.nn.functionalÚ
functionalrs   Útorch.utils.checkpointÚutilsr_   r^   r   Útransforms._presetsr	   r
   Ú_apir   r   r   Ú_metar   Ú_utilsr   r   Ú__all__rÓ   r   Ú
ModuleDictrƒ   r¯   r—   r   râ   rè   rú   r   r   r   r   rû   r  r  r  r  rd   r)   r&   Ú<module>r#     sí  ðÛ 	Ý #Ý ß  ã Ý ß Ð ß #Ð #Ý å 5Ý 'ß 6Ñ 6Ý 'ß Bò
€ô>�"—)‘)ô >ôB&�"—-‘-ô &ô>:�"—-‘-ô :ôRˆr�y‰yô Rõj&õ&ð( �ØÐ&ØÐ:ØÐ:ð	€ô˜+ô ô(˜+ô ô(˜+ô ô(˜+ô ñ( ÓÙ ,Ð0C×0QÑ0QÐ!RÔSðK¸Dð KÐSWö Kó Tó ðKñ0 ÓÙ ,Ð0C×0QÑ0QÐ!RÔSðK¸Dð KÐSWö Kó Tó ðKñ0 ÓÙ ,Ð0C×0QÑ0QÐ!RÔSðK¸Dð KÐSWö Kó Tó ðKñ0 ÓÙ ,Ð0C×0QÑ0QÐ!RÔSðK¸Dð KÐSWö Kó Tó òKr)   