ó
    Eñi¬A  ã                   óÞ  • S SK r S SKJr  S SKJr  S SKJrJr  S SKrS SK	J
r
  S SKJ
s  Jr  S SKJs  Jr  S SKJr  SSKJr  SSKJr  S	S
KJrJrJr  S	SKJr  S	SKJrJr  / SQr " S S\
R@                  5      r! " S S\
RD                  5      r# " S S\
RH                  5      r% " S S\
R@                  5      r&S\
R@                  S\S\'SS4S jr(S\)S\*\)\)\)\)4   S\)S\\   S\'S\S\&4S jr+S \S!S"S#.r, " S$ S%\5      r- " S& S'\5      r. " S( S)\5      r/ " S* S+\5      r0\" 5       \" S,\-Rb                  4S-9SS.S/.S\\-   S\'S\S\&4S0 jj5       5       r2\" 5       \" S,\.Rb                  4S-9SS.S/.S\\.   S\'S\S\&4S1 jj5       5       r3\" 5       \" S,\/Rb                  4S-9SS.S/.S\\/   S\'S\S\&4S2 jj5       5       r4\" 5       \" S,\0Rb                  4S-9SS.S/.S\\0   S\'S\S\&4S3 jj5       5       r5g)4é    N)ÚOrderedDict)Úpartial)ÚAnyÚOptional)ÚTensoré   )ÚImageClassification)Ú_log_api_usage_onceé   )Úregister_modelÚWeightsÚWeightsEnum)Ú_IMAGENET_CATEGORIES)Ú_ovewrite_named_paramÚhandle_legacy_interface)	ÚDenseNetÚDenseNet121_WeightsÚDenseNet161_WeightsÚDenseNet169_WeightsÚDenseNet201_WeightsÚdensenet121Údensenet161Údensenet169Údensenet201c                   ód  ^ • \ rS rSr SS\S\S\S\S\SS4U 4S	 jjjrS
\\	   S\	4S jr
S\\	   S\4S jr\R                  R                  S\\	   S\	4S j5       r\R                  R                   S\\	   S\	4S j5       r\R                  R                   S\	S\	4S j5       rS\	S\	4S jrSrU =r$ )Ú_DenseLayeré   Únum_input_featuresÚgrowth_rateÚbn_sizeÚ	drop_rateÚmemory_efficientÚreturnNc           	      ó   >• [         TU ]  5         [        R                  " U5      U l        [        R
                  " SS9U l        [        R                  " XU-  SSSS9U l        [        R                  " X2-  5      U l	        [        R
                  " SS9U l
        [        R                  " X2-  USSSSS9U l        [        U5      U l        XPl        g )NT©Úinplacer   F©Úkernel_sizeÚstrideÚbiasé   ©r(   r)   Úpaddingr*   )ÚsuperÚ__init__ÚnnÚBatchNorm2dÚnorm1ÚReLUÚrelu1ÚConv2dÚconv1Únorm2Úrelu2Úconv2Úfloatr!   r"   )Úselfr   r   r    r!   r"   Ú	__class__s         €ÚX/home/mande/repo/quber/.venv/lib/python3.13/site-packages/torchvision/models/densenet.pyr/   Ú_DenseLayer.__init__    s¥   ø€ ô 	‰ÑÔÜ—^’^Ð$6Ó7ˆŒ
Ü—W’W TÑ*ˆŒ
Ü—Y’YÐ1¸[Ñ3HÐVWÐ`aÐhmÑnˆŒ
ä—^’^ GÑ$9Ó:ˆŒ
Ü—W’W TÑ*ˆŒ
Ü—Y’Y˜wÑ4°kÈqÐYZÐdeÐlqÑrˆŒ
ä˜yÓ)ˆŒØ 0Õó    Úinputsc                 ó’   • [         R                  " US5      nU R                  U R                  U R	                  U5      5      5      nU$ ©Nr   )ÚtorchÚcatr6   r4   r2   )r;   r@   Úconcated_featuresÚbottleneck_outputs       r=   Úbn_functionÚ_DenseLayer.bn_function/   s;   € Ü!ŸIšI f¨aÓ0ÐØ ŸJ™J t§z¡z°$·*±*Ð=NÓ2OÓ'PÓQÐØ Ð r?   Úinputc                 ó<   • U H  nUR                   (       d  M    g   g)NTF)Úrequires_grad)r;   rI   Útensors      r=   Úany_requires_gradÚ_DenseLayer.any_requires_grad5   s    € ÛˆFØ×#×#Ñ#Ùñ ð r?   c                 óD   ^ • U 4S jn[         R                  " U/UQ7SS06$ )Nc                  ó&   >• TR                  U 5      $ ©N)rG   )r@   r;   s    €r=   ÚclosureÚ7_DenseLayer.call_checkpoint_bottleneck.<locals>.closure=   s   ø€ Ø×#Ñ# FÓ+Ð+r?   Úuse_reentrantF)ÚcpÚ
checkpoint)r;   rI   rR   s   `  r=   Úcall_checkpoint_bottleneckÚ&_DenseLayer.call_checkpoint_bottleneck;   s#   ø€ õ	,ô �}Š}˜WÐB uÒB¸EÑBÐBr?   c                 ó   • g rQ   © ©r;   rI   s     r=   ÚforwardÚ_DenseLayer.forwardB   ó   € àr?   c                 ó   • g rQ   rZ   r[   s     r=   r\   r]   F   r^   r?   c                 óü  • [        U[        5      (       a  U/nOUnU R                  (       aV  U R                  U5      (       a@  [        R
                  R                  5       (       a  [        S5      eU R                  U5      nOU R                  U5      nU R                  U R                  U R                  U5      5      5      nU R                  S:”  a)  [        R                  " X@R                  U R                   S9nU$ )Nz%Memory Efficient not supported in JITr   )ÚpÚtraining)Ú
isinstancer   r"   rM   rC   ÚjitÚis_scriptingÚ	ExceptionrW   rG   r9   r8   r7   r!   ÚFÚdropoutrb   )r;   rI   Úprev_featuresrF   Únew_featuress        r=   r\   r]   L   sÀ   € Ü�eœV×$Ñ$Ø"˜G‰Mà!ˆMà× ×  T×%;Ñ%;¸M×%JÑ%JÜ�y‰y×%Ñ%×'Ñ'ÜÐ GÓHÐHà $× ?Ñ ?ÀÓ NÑà $× 0Ñ 0°Ó ?Ðà—z‘z $§*¡*¨T¯Z©ZÐ8IÓ-JÓ"KÓLˆØ�>‰>˜AÓÜŸ9š9 \·^±^ÈdÏmÉmÑ\ˆLØÐr?   )r6   r9   r!   r"   r2   r7   r4   r8   ©F)Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Úintr:   Úboolr/   Úlistr   rG   rM   rC   rd   ÚunusedrW   Ú_overload_methodr\   Ú__static_attributes__Ú__classcell__©r<   s   @r=   r   r      s  ø† àrwñ1Ø"%ð1Ø47ð1ØBEð1ØRWð1Økoð1à	÷1ð 1ð! $ v¡,ð !°6ô !ð t¨F¡|ð ¸ô ð ‡Y�Y×ÑðC°°V±ð CÀó Có ðCð ‡Y�Y×Ñð˜T &™\ð ¨fó ó  ðð ‡Y�Y×Ñð˜Vð ¨ó ó  ðð
˜Vð ¨÷ ò r?   r   c                   ód   ^ • \ rS rSrSr SS\S\S\S\S\S\S	S
4U 4S jjjrS\	S	\	4S jr
SrU =r$ )Ú_DenseBlocké`   r   Ú
num_layersr   r    r   r!   r"   r#   Nc           	      óš   >• [         T	U ]  5         [        U5       H-  n[        X'U-  -   UUUUS9nU R	                  SUS-   -  U5        M/     g )N)r   r    r!   r"   zdenselayer%dr   )r.   r/   Úranger   Ú
add_module)
r;   r{   r   r    r   r!   r"   ÚiÚlayerr<   s
            €r=   r/   Ú_DenseBlock.__init__c   sX   ø€ ô 	‰ÑÔÜ�zÖ"ˆAÜØ"¨¡_Ñ4Ø'ØØ#Ø!1ñˆEð �O‰O˜N¨a°!©eÑ4°eÖ<ò #r?   Úinit_featuresc                 óš   • U/nU R                  5        H  u  p4U" U5      nUR                  U5        M      [        R                  " US5      $ rB   )ÚitemsÚappendrC   rD   )r;   r‚   ÚfeaturesÚnamer€   rj   s         r=   r\   Ú_DenseBlock.forwardw   sC   € Ø!�?ˆØŸ:™:ž<‰KˆDÙ  ›?ˆLØ�O‰O˜LÖ)ñ (ô �yŠy˜ 1Ó%Ð%r?   rZ   rk   )rl   rm   rn   ro   Ú_versionrp   r:   rq   r/   r   r\   ru   rv   rw   s   @r=   ry   ry   `   ss   ø† Ø€Hð "'ñ=àð=ð  ð=ð ð	=ð
 ð=ð ð=ð ð=ð 
÷=ð =ð(& Vð &°÷ &ò &r?   ry   c                   ó8   ^ • \ rS rSrS\S\SS4U 4S jjrSrU =r$ )Ú_Transitioné   r   Únum_output_featuresr#   Nc                 óö   >• [         TU ]  5         [        R                  " U5      U l        [        R
                  " SS9U l        [        R                  " XSSSS9U l        [        R                  " SSS9U l
        g )NTr%   r   Fr'   r   )r(   r)   )r.   r/   r0   r1   Únormr3   Úrelur5   ÚconvÚ	AvgPool2dÚpool)r;   r   r�   r<   s      €r=   r/   Ú_Transition.__init__€   s[   ø€ Ü‰ÑÔÜ—N’NÐ#5Ó6ˆŒ	Ü—G’G DÑ)ˆŒ	Ü—I’IÐ0ÐSTÐ]^ÐejÑkˆŒ	Ü—L’L¨Q°qÑ9ˆ�	r?   )r‘   r�   r“   r�   )rl   rm   rn   ro   rp   r/   ru   rv   rw   s   @r=   r‹   r‹      s"   ø† ð:¨3ð :ÀSð :ÈT÷ :õ :r?   r‹   c                   ó‚   ^ • \ rS rSrSr       SS\S\\\\\4   S\S\S\S\S	\S
S4U 4S jjjr	S\
S
\
4S jrSrU =r$ )r   éˆ   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>`_.
r   Úblock_configÚnum_init_featuresr    r!   Únum_classesr"   r#   Nc                 ó>  >• [         TU ]  5         [        U 5        [        R                  " [        S[        R                  " SUSSSSS94S[        R                  " U5      4S[        R                  " S	S
94S[        R                  " SSSS94/5      5      U l
        Un[        U5       Hƒ  u  pš[        U
UUUUUS9nU R                  R                  SU	S-   -  U5        XŠU-  -   nU	[        U5      S-
  :w  d  MP  [        XˆS-  S9nU R                  R                  SU	S-   -  U5        US-  nM…     U R                  R                  S[        R                  " U5      5        [        R                   " X†5      U l        U R%                  5        GH  n['        U[        R                  5      (       a+  [        R(                  R+                  UR,                  5        MN  ['        U[        R                  5      (       aV  [        R(                  R/                  UR,                  S5        [        R(                  R/                  UR0                  S5        MÃ  ['        U[        R                   5      (       d  Mä  [        R(                  R/                  UR0                  S5        GM     g )NÚconv0r+   é   r   Fr,   Únorm0Úrelu0Tr%   Úpool0r   )r(   r)   r-   )r{   r   r    r   r!   r"   zdenseblock%d)r   r�   ztransition%dÚnorm5r   )r.   r/   r
   r0   Ú
Sequentialr   r5   r1   r3   Ú	MaxPool2dr†   Ú	enumeratery   r~   Úlenr‹   ÚLinearÚ
classifierÚmodulesrc   ÚinitÚkaiming_normal_ÚweightÚ	constant_r*   )r;   r   r—   r˜   r    r!   r™   r"   Únum_featuresr   r{   ÚblockÚtransÚmr<   s                 €r=   r/   ÚDenseNet.__init__˜   s  ø€ ô 	‰ÑÔÜ˜DÔ!ô ŸšÜàœbŸiši¨Ð+<È!ÐTUÐ_`ÐglÑmÐnØœbŸnšnÐ->Ó?Ð@ØœbŸgšg¨dÑ3Ð4ØœbŸlšl°qÀÈAÑNÐOð	óó	
ˆŒð )ˆÜ& |Ö4‰MˆAÜØ%Ø#/ØØ'Ø#Ø!1ñˆEð �M‰M×$Ñ$ ^°q¸1±uÑ%=¸uÔEØ'°{Ñ*BÑBˆLØ”C˜Ó%¨Ñ)Õ)Ü#°|ÐijÑYjÑk�Ø—‘×(Ñ(¨¸1¸q¹5Ñ)AÀ5ÔIØ+¨qÑ0’ñ 5ð" 	�‰× Ñ  ¬"¯.ª.¸Ó*FÔGô Ÿ)š) LÓ>ˆŒð —‘—ˆAÜ˜!œRŸY™Y×'Ñ'Ü—‘×'Ñ'¨¯©Ö1Ü˜AœrŸ~™~×.Ñ.Ü—‘×!Ñ! !§(¡(¨AÔ.Ü—‘×!Ñ! !§&¡&¨!Ö,Ü˜AœrŸy™y×)Ó)Ü—‘×!Ñ! !§&¡&¨!×,ò  r?   Úxc                 óÐ   • U R                  U5      n[        R                  " USS9n[        R                  " US5      n[        R
                  " US5      nU R                  U5      nU$ )NTr%   )r   r   r   )r†   rg   r�   Úadaptive_avg_pool2drC   Úflattenr¦   )r;   r±   r†   Úouts       r=   r\   ÚDenseNet.forwardÔ   sU   € Ø—=‘= Ó#ˆÜ�fŠf�X tÑ,ˆÜ×#Ò# C¨Ó0ˆÜ�mŠm˜C Ó#ˆØ�o‰o˜cÓ"ˆØˆ
r?   )r¦   r†   )é    ©é   é   é   é   é@   é   r   iè  F)rl   rm   rn   ro   Ú__doc__rp   Útupler:   rq   r/   r   r\   ru   rv   rw   s   @r=   r   r   ˆ   sž   ø† ñð" Ø2AØ!#ØØØØ!&ñ:-àð:-ð ˜C  c¨3Ð.Ñ/ð:-ð ð	:-ð
 ð:-ð ð:-ð ð:-ð ð:-ð 
÷:-ð :-ðx˜ð  F÷ ò r?   r   ÚmodelÚweightsÚprogressr#   c                 ó<  • [         R                  " S5      nUR                  USS9n[        UR	                  5       5       HH  nUR                  U5      nU(       d  M  UR                  S5      UR                  S5      -   nXE   XG'   XE	 MJ     U R                  U5        g )Nz]^(.*denselayer\d+\.(?:norm|relu|conv))\.((?:[12])\.(?:weight|bias|running_mean|running_var))$T)rÃ   Ú
check_hashr   r   )ÚreÚcompileÚget_state_dictrr   ÚkeysÚmatchÚgroupÚload_state_dict)rÁ   rÂ   rÃ   ÚpatternÚ
state_dictÚkeyÚresÚnew_keys           r=   Ú_load_state_dictrÒ   Ý   sŽ   € ô
 �jŠjØhó€Gð ×'Ñ'°ÀdÐ'ÐK€JÜ�J—O‘OÓ%Ö&ˆØ�m‰m˜CÓ ˆßˆ3Ø—i‘i “l S§Y¡Y¨q£\Ñ1ˆGØ",¡/ˆJÑØ’ñ 'ð 
×Ñ˜*Õ%r?   r   r—   r˜   Úkwargsc                 ó†   • Ub#  [        US[        UR                  S   5      5        [        XU40 UD6nUb
  [	        XcUS9  U$ )Nr™   Ú
categories)rÁ   rÂ   rÃ   )r   r¤   Úmetar   rÒ   )r   r—   r˜   rÂ   rÃ   rÓ   rÁ   s          r=   Ú	_densenetr×   ð   sK   € ð ÑÜ˜f m´S¸¿¹ÀlÑ9SÓ5TÔUä�[Ð0AÑLÀVÑL€EàÑÜ˜uÀÒIà€Lr?   )é   rØ   z*https://github.com/pytorch/vision/pull/116z'These weights are ported from LuaTorch.)Úmin_sizerÕ   ÚrecipeÚ_docsc            
       óN   • \ rS rSr\" S\" \SS90 \ESSSSS	.0S
SS.ES9r\r	Sr
g)r   i  z<https://download.pytorch.org/models/densenet121-a639ec97.pthéà   ©Ú	crop_sizeih¿y úImageNet-1Kg²�ï§Æ›R@g‘í|?5þV@©zacc@1zacc@5gyé&1¬@g¸…ëQØ>@©Ú
num_paramsÚ_metricsÚ_opsÚ
_file_size©ÚurlÚ
transformsrÖ   rZ   N©rl   rm   rn   ro   r   r   r	   Ú_COMMON_METAÚIMAGENET1K_V1ÚDEFAULTru   rZ   r?   r=   r   r     sQ   † ÙØJÙÐ.¸#Ñ>ð
Øð
à!àØ#Ø#ñ ðð Ø ò
ñ€Mð  ƒGr?   r   c            
       óN   • \ rS rSr\" S\" \SS90 \ESSSSS	.0S
SS.ES9r\r	Sr
g)r   i  z<https://download.pytorch.org/models/densenet161-8d451a50.pthrÝ   rÞ   i(£µrà   gF¶óýÔHS@g¤p=
×cW@rá   g¶óýÔxé@gV-²�—[@râ   rç   rZ   Nrê   rZ   r?   r=   r   r     sQ   † ÙØJÙÐ.¸#Ñ>ð
Øð
à"àØ#Ø#ñ ðð Ø!ò
ñ€Mð  ƒGr?   r   c            
       óN   • \ rS rSr\" S\" \SS90 \ESSSSS	.0S
SS.ES9r\r	Sr
g)r   i3  z<https://download.pytorch.org/models/densenet169-b2777c0a.pthrÝ   rÞ   ihç× rà   gfffffæR@gÝ$�•3W@rá   gáz®Gá
@g´Èv¾ŸZK@râ   rç   rZ   Nrê   rZ   r?   r=   r   r   3  sQ   † ÙØJÙÐ.¸#Ñ>ð
Øð
à"àØ#Ø#ñ ðð Ø ò
ñ€Mð  ƒGr?   r   c            
       óN   • \ rS rSr\" S\" \SS90 \ESSSSS	.0S
SS.ES9r\r	Sr
g)r   iG  z<https://download.pytorch.org/models/densenet201-c1103571.pthrÝ   rÞ   ihc1rà   gÓMbX9S@gHáz®WW@rá   gD‹lçû)@gZd;ßWS@râ   rç   rZ   Nrê   rZ   r?   r=   r   r   G  sQ   † ÙØJÙÐ.¸#Ñ>ð
Øð
à"àØ#Ø#ñ ðð Ø ò
ñ€Mð  ƒGr?   r   Ú
pretrained)rÂ   T)rÂ   rÃ   c                 óJ   • [         R                  U 5      n [        SSSX40 UD6$ )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:
r·   r¸   r½   )r   Úverifyr×   ©rÂ   rÃ   rÓ   s      r=   r   r   [  ó*   € ô* "×(Ñ(¨Ó1€Gä�R˜¨"¨gÑJÀ6ÑJÐJr?   c                 óJ   • [         R                  U 5      n [        SSSX40 UD6$ )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:
é0   )r¹   rº   é$   r»   rz   )r   ró   r×   rô   s      r=   r   r   u  rõ   r?   c                 óJ   • [         R                  U 5      n [        SSSX40 UD6$ )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:
r·   )r¹   rº   r·   r·   r½   )r   ró   r×   rô   s      r=   r   r   �  rõ   r?   c                 óJ   • [         R                  U 5      n [        SSSX40 UD6$ )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:
r·   )r¹   rº   r÷   r·   r½   )r   ró   r×   rô   s      r=   r   r   ©  rõ   r?   )6rÆ   Úcollectionsr   Ú	functoolsr   Útypingr   r   rC   Útorch.nnr0   Útorch.nn.functionalÚ
functionalrg   Útorch.utils.checkpointÚutilsrV   rU   r   Útransforms._presetsr	   r
   Ú_apir   r   r   Ú_metar   Ú_utilsr   r   Ú__all__ÚModuler   Ú
ModuleDictry   r¡   r‹   r   rq   rÒ   rp   rÀ   r×   rë   r   r   r   r   rì   r   r   r   r   rZ   r?   r=   Ú<module>r
     sÌ  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ðj&˜BŸI™Ið &°ð &Àtð &ÐPTô &ð&Øðà˜˜S # sÐ*Ñ+ðð ðð �kÑ"ð	ð
 ðð ðð ôð( Ø&Ø:Ø:ñ	€ô˜+ô ô(˜+ô ô(˜+ô ô(˜+ô ñ( ÓÙ ,Ð0C×0QÑ0QÐ!RÑSØ<@ÐSWò K˜HÐ%8Ñ9ð KÈDð KÐcfð KÐksô Kó Tó ðKñ0 ÓÙ ,Ð0C×0QÑ0QÐ!RÑSØ<@ÐSWò K˜HÐ%8Ñ9ð KÈDð KÐcfð KÐksô Kó Tó ðKñ0 ÓÙ ,Ð0C×0QÑ0QÐ!RÑSØ<@ÐSWò K˜HÐ%8Ñ9ð KÈDð KÐcfð KÐksô Kó Tó ðKñ0 ÓÙ ,Ð0C×0QÑ0QÐ!RÑSØ<@ÐSWò K˜HÐ%8Ñ9ð KÈDð KÐcfð KÐksô Kó Tó ñKr?   