+
    	åûjƒC  ã                   ó  € ^ RI Ht ^ RIHt ^ RIHtHtHtHt ^ RI	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 . R8Ot ! R R]
P6                  4      t ! R R]
P:                  4      t ! R R]
P6                  4      t ! R R]
P@                  4      t! ! R R]
P@                  4      t" ! R R]
P:                  4      t# ! R R]
P:                  4      t$ ! R  R]
P@                  4      t%R! R" lt&R#R9R$]R%R&R'R(/t' ! R) R]4      t( ! R* R]4      t) ! R+ R]4      t*]! 4       ]! R,](PV                  3R-7      R.RR/R0/R1 R2 ll4       4       t,]! 4       ]! R,])PV                  3R-7      R.RR/R0/R3 R4 ll4       4       t-]! 4       ]! R,]*PV                  3R-7      R.RR/R0/R5 R6 ll4       4       t.^R7IH/t/ ]/! R](PV                  P`                  R])PV                  P`                  R]*PV                  P`                  /4      t1R# ):é    )ÚSequence)Úpartial)ÚAnyÚCallableÚOptionalÚUnionN©ÚTensor)ÚVideoClassification)Ú_log_api_usage_once)Úregister_modelÚWeightsÚWeightsEnum)Ú_KINETICS400_CATEGORIES)Ú_ovewrite_named_paramÚhandle_legacy_interfaceÚVideoResNetÚR3D_18_WeightsÚMC3_18_WeightsÚR2Plus1D_18_WeightsÚr3d_18Úmc3_18Úr2plus1d_18c                   ó^   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4       tRtVtV ;t	# )ÚConv3DSimplec                óL   <€ V ^8„  d   QhRS[ RS[ RS[S[ ,          RS[ RS[ RR/# ©é   Ú	in_planesÚ
out_planesÚ	midplanesÚstrideÚpaddingÚreturnN©Úintr   )ÚformatÚ__classdict__s   "€Ú[C:\Ai_Coding\apps\studio\ComfyUI\.venv\Lib\site-packages\torchvision\models\video\resnet.pyÚ__annotate__ÚConv3DSimple.__annotate__   óA   ø€ ÷ 
ñ 
Ùð
Ù*-ð
Ù:BÁ3½-ð
ÙX[ð
Ùjmð
à	ñ
ó    c           	     ó2   <€ \         SV `  VVRVVRR7       R# )é   F©Úin_channelsÚout_channelsÚkernel_sizer"   r#   ÚbiasN)r/   r/   r/   ©ÚsuperÚ__init__©Úselfr   r    r!   r"   r#   Ú	__class__s   &&&&&&€r)   r7   ÚConv3DSimple.__init__   s)   ø€ ô 	‰ÑØ!Ø#Ø!ØØØð 	ö 	
r-   c                ó@   <€ V ^8„  d   QhRS[ RS[S[ S[ S[ 3,          /# ©r   r"   r$   ©r&   Útuple)r'   r(   s   "€r)   r*   r+   )   ó&   ø€ ÷ &ñ &¡cð &©e±C¹¹c°MÕ.Bñ &r-   c                ó
   € W V 3# ©N© ©r"   s   &r)   Úget_downsample_strideÚ"Conv3DSimple.get_downsample_stride(   ó   € à˜vÐ%Ð%r-   rC   ©Né   rI   ©
Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__r7   ÚstaticmethodrE   Ú__static_attributes__Ú__classdictcell__Ú__classcell__©r:   r(   s   @@r)   r   r      s(   ù‡ € ÷
õ 
ð ÷&ó ÷&ð &r-   r   c                   ó^   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4       tRtVtV ;t	# )ÚConv2Plus1Dc                ó<   <€ V ^8„  d   QhRS[ RS[ RS[ RS[ RS[ RR/# r   )r&   )r'   r(   s   "€r)   r*   ÚConv2Plus1D.__annotate__.   s:   ø€ ÷ 
ñ 
¡#ð 
±3ð 
Á3ð 
ÑPSð 
Ñbeð 
Ðnrñ 
r-   c                óø   <€ \         SV `  \        P                  ! VVR^WD3^ WU3RR7      \        P                  ! V4      \        P
                  ! RR7      \        P                  ! W2RV^^3V^ ^ 3RR7      4       R# )rI   F©r3   r"   r#   r4   T©ÚinplaceN©rI   r/   r/   ©r/   rI   rI   ©r6   r7   ÚnnÚConv3dÚBatchNorm3dÚReLUr8   s   &&&&&&€r)   r7   ÚConv2Plus1D.__init__.   s{   ø€ Ü‰ÑÜ�IŠIØØØ%Ø˜6Ð*Ø˜GÐ-Øôô �NŠN˜9Ó%Ü�GŠG˜DÔ!Ü�IŠIØ°9ÀfÈaÐQRÀ^Ð^eÐghÐjkÐ]lÐsxôö	
r-   c                ó@   <€ V ^8„  d   QhRS[ RS[S[ S[ S[ 3,          /# r=   r>   )r'   r(   s   "€r)   r*   rW   @   r@   r-   c                ó
   € W V 3# rB   rC   rD   s   &r)   rE   Ú!Conv2Plus1D.get_downsample_stride?   rG   r-   rC   ©rI   rI   rJ   rS   s   @@r)   rU   rU   -   s(   ù‡ € ÷
õ 
ð" ÷&ó ÷&ð &r-   rU   c                   ó^   a a€ ] tR t^Dt oRV3R lV 3R lllt]V3R lR l4       tRtVtV ;t	# )ÚConv3DNoTemporalc                óL   <€ V ^8„  d   QhRS[ RS[ RS[S[ ,          RS[ RS[ RR/# r   r%   )r'   r(   s   "€r)   r*   ÚConv3DNoTemporal.__annotate__E   r,   r-   c           	     ó:   <€ \         SV `  VVR^WD3^ WU3RR7       R# )rI   Fr0   Nr\   r5   r8   s   &&&&&&€r)   r7   ÚConv3DNoTemporal.__init__E   s3   ø€ ô 	‰ÑØ!Ø#Ø!Ø�vÐ&Ø˜Ð)Øð 	ö 	
r-   c                ó@   <€ V ^8„  d   QhRS[ RS[S[ S[ S[ 3,          /# r=   r>   )r'   r(   s   "€r)   r*   rk   S   s&   ø€ ÷ !ñ !¡cð !©e±C¹¹c°MÕ.Bñ !r-   c                ó
   € ^W 3# ©rI   rC   rD   s   &r)   rE   Ú&Conv3DNoTemporal.get_downsample_strideR   s   € à�&Ð Ð r-   rC   rH   rJ   rS   s   @@r)   ri   ri   D   s(   ù‡ € ÷
õ 
ð ÷!ó ÷!ð !r-   ri   c                   óX   a a€ ] tR t^Wt 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
BasicBlockc                óˆ   <€ V ^8„  d   QhRS[ RS[ RS[RS[P                  3,          RS[ RS[S[P                  ,          RR/# ©	r   ÚinplanesÚplanesÚconv_builder.r"   Ú
downsampler$   N©r&   r   r_   ÚModuler   )r'   r(   s   "€r)   r*   ÚBasicBlock.__annotate__[   s]   ø€ ÷ ñ áðñ ðñ ˜s¡B§I¡I˜~Õ.ð	ñ
 ðñ ™RŸY™YÕ'ðð 
ñr-   c                óü  <€ W,          ^,          ^,          ^,          V^,          ^,          ^V,          ,           ,          p\         SV `  4        \        P                  ! V! WWd4      \        P                  ! V4      \        P
                  ! RR7      4      V n        \        P                  ! V! W"V4      \        P                  ! V4      4      V n        \        P
                  ! RR7      V n        WPn	        W@n
        R# )r/   TrZ   N)r6   r7   r_   Ú
Sequentialra   rb   Úconv1Úconv2Úrelury   r"   ©r9   rv   rw   rx   r"   ry   r!   r:   s   &&&&&& €r)   r7   ÚBasicBlock.__init__[   s±   ø€ ð Õ&¨Õ*¨QÕ.°Õ2¸À1½ÀqÕ8HÈ1ÈvÍ:Õ8UÕVˆ	ä‰ÑÔÜ—]’]Ù˜¨9Ó=¼r¿~º~ÈfÓ?UÔWY×W^ÒW^ÐgkÔWló
ˆŒ
ô —]’]¡<°À	Ó#JÌBÏNÊNÐ[aÓLbÓcˆŒ
Ü—G’G DÔ)ˆŒ	Ø$ŒØŽr-   c                ó&   <€ V ^8„  d   QhRS[ RS[ /# ©r   Úxr$   r	   )r'   r(   s   "€r)   r*   r|   n   s   ø€ ÷ ñ ™ð ¡Fñ r-   c                ó¾   € TpV P                  V4      pV P                  V4      pV P                  e   V P                  V4      pW2,          pV P                  V4      pV# rB   )r   r€   ry   r�   ©r9   r†   ÚresidualÚouts   &&  r)   ÚforwardÚBasicBlock.forwardn   sR   € Øˆà�j‰j˜‹mˆØ�j‰j˜‹oˆØ�?‰?Ò&Ø—‘ qÓ)ˆHà�ˆØ�i‰i˜‹nˆàˆ
r-   )r   r€   ry   r�   r"   ©rI   N©
rK   rL   rM   rN   Ú	expansionr7   r‹   rP   rQ   rR   rS   s   @@r)   rs   rs   W   s#   ù‡ € à€I÷õ ÷&÷ ð r-   rs   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
Bottleneckc                óˆ   <€ V ^8„  d   QhRS[ RS[ RS[RS[P                  3,          RS[ RS[S[P                  ,          RR/# ru   rz   )r'   r(   s   "€r)   r*   ÚBottleneck.__annotate__   s]   ø€ ÷ ñ áðñ ðñ ˜s¡B§I¡I˜~Õ.ð	ñ
 ðñ ™RŸY™YÕ'ðð 
ñr-   c           	     ó  <€ \         SV `  4        W,          ^,          ^,          ^,          V^,          ^,          ^V,          ,           ,          p\        P                  ! \        P                  ! W^RR7      \        P
                  ! V4      \        P                  ! RR7      4      V n        \        P                  ! V! W"Wd4      \        P
                  ! V4      \        P                  ! RR7      4      V n        \        P                  ! \        P                  ! W"V P                  ,          ^RR7      \        P
                  ! W P                  ,          4      4      V n
        \        P                  ! RR7      V n        WPn        W@n        R# )r/   F)r3   r4   TrZ   N)r6   r7   r_   r~   r`   ra   rb   r   r€   r�   Úconv3r�   ry   r"   r‚   s   &&&&&& €r)   r7   ÚBottleneck.__init__   s  ø€ ô 	‰ÑÔØÕ&¨Õ*¨QÕ.°Õ2¸À1½ÀqÕ8HÈ1ÈvÍ:Õ8UÕVˆ	ô —]’]Ü�IŠI�h°A¸EÔBÄBÇNÂNÐSYÓDZÔ\^×\cÒ\cÐlpÔ\qó
ˆŒ
ô —]’]Ù˜¨Ó;¼R¿^º^ÈFÓ=SÔUW×U\ÒU\ÐeiÔUjó
ˆŒ
ô
 —]’]Ü�IŠI�f t§~¡~Õ5À1È5ÔQÜ�NŠN˜6§N¡NÕ2Ó3ó
ˆŒ
ô —G’G DÔ)ˆŒ	Ø$ŒØŽr-   c                ó&   <€ V ^8„  d   QhRS[ RS[ /# r…   r	   )r'   r(   s   "€r)   r*   r“   �   s   ø€ ÷ ñ ™ð ¡Fñ r-   c                óà   € TpV P                  V4      pV P                  V4      pV P                  V4      pV P                  e   V P                  V4      pW2,          pV P	                  V4      pV# rB   )r   r€   r•   ry   r�   rˆ   s   &&  r)   r‹   ÚBottleneck.forward�   s_   € Øˆà�j‰j˜‹mˆØ�j‰j˜‹oˆØ�j‰j˜‹oˆà�?‰?Ò&Ø—‘ qÓ)ˆHà�ˆØ�i‰i˜‹nˆàˆ
r-   )r   r€   r•   ry   r�   r"   r�   rŽ   rS   s   @@r)   r‘   r‘   |   s#   ù‡ € Ø€I÷õ ÷<÷ ð r-   r‘   c                   óB   a a€ ] tR t^­t oRtV3R lV 3R lltRtVtV ;t# )Ú	BasicStemz$The default conv-batchnorm-relu stemc                ó   <€ V ^8„  d   QhRR/# ©r   r$   NrC   )r'   r(   s   "€r)   r*   ÚBasicStem.__annotate__°   s   ø€ ÷ 
ñ 
˜$ñ 
r-   c                ó°   <€ \         SV `  \        P                  ! ^^@RRRRR7      \        P                  ! ^@4      \        P
                  ! RR7      4       R# )	r/   FrY   TrZ   N)r/   é   r    ©rI   r   r   r\   r^   ©r9   r:   s   &€r)   r7   ÚBasicStem.__init__°   s?   ø€ Ü‰ÑÜ�IŠI�a˜¨¸9ÈiÐ^cÔdÜ�NŠN˜2ÓÜ�GŠG˜DÔ!ö	
r-   rC   ©	rK   rL   rM   rN   Ú__doc__r7   rP   rQ   rR   rS   s   @@r)   r›   r›   ­   s   ù‡ € Ù.÷
÷ 
ó 
r-   r›   c                   óB   a a€ ] tR t^¸t oRtV3R lV 3R lltRtVtV ;t# )ÚR2Plus1dStemzRR(2+1)D stem is different than the default one as it uses separated 3D convolutionc                ó   <€ V ^8„  d   QhRR/# r�   rC   )r'   r(   s   "€r)   r*   ÚR2Plus1dStem.__annotate__»   s   ø€ ÷ 
ñ 
˜$ñ 
r-   c                ó<  <€ \         SV `  \        P                  ! ^^-RRRRR7      \        P                  ! ^-4      \        P
                  ! RR7      \        P                  ! ^-^@R	R
RRR7      \        P                  ! ^@4      \        P
                  ! RR7      4       R# )r/   FrY   TrZ   N)rI   r    r    r¡   )r   r/   r/   r]   ©rI   rI   rI   )rI   r   r   r^   r¢   s   &€r)   r7   ÚR2Plus1dStem.__init__»   sn   ø€ Ü‰ÑÜ�IŠI�a˜¨¸9ÈiÐ^cÔdÜ�NŠN˜2ÓÜ�GŠG˜DÔ!Ü�IŠI�b˜"¨)¸IÈyÐ_dÔeÜ�NŠN˜2ÓÜ�GŠG˜DÔ!ö	
r-   rC   r¤   rS   s   @@r)   r§   r§   ¸   s   ù‡ € Ù\÷
÷ 
ó 
r-   r§   c                   ój   a a€ ] tR t^Æt oRV3R lV 3R llltV3R lR ltR	V3R lR lltRtVtV ;t	# )
r   c                óÚ   <€ V ^8„  d   QhRS[ S[S[S[3,          ,          RS[S[ S[S[S[S[3,          ,          ,          RS[S[	,          RS[
RS[P                  3,          RS[	RS[RR	/# )
r   ÚblockÚconv_makersÚlayersÚstem.Únum_classesÚzero_init_residualr$   N)Útyper   rs   r‘   r   r   ri   rU   Úlistr&   r   r_   r{   Úbool)r'   r(   s   "€r)   r*   ÚVideoResNet.__annotate__Ç   sˆ   ø€ ÷ 27ñ 27á‘E™*¡jÐ0Õ1Õ2ð27ñ ™d¡5©Ñ7GÉÐ)TÕ#UÕVÕWð27ñ ‘S•	ð	27ñ
 �s™BŸI™I�~Õ&ð27ñ ð27ñ !ð27ð 
ñ27r-   c                ó*  <€ \         SV `  4        \        V 4       ^@V n        V! 4       V n        V P                  W^ ,          ^@V^ ,          ^R7      V n        V P                  W^,          ^€V^,          ^R7      V n        V P                  W^,          RV^,          ^R7      V n        V P                  W^,          RV^,          ^R7      V n	        \        P                  ! R	4      V n        \        P                  ! RVP                  ,          V4      V n        V P!                  4        EF{  p\#        V\        P$                  4      '       di   \        P&                  P)                  VP*                  RRR7       VP,                  e-   \        P&                  P/                  VP,                  ^ 4       KŠ  KŒ  \#        V\        P0                  4      '       dX   \        P&                  P/                  VP*                  ^4       \        P&                  P/                  VP,                  ^ 4       EK  \#        V\        P                  4      '       g   EK&  \        P&                  P3                  VP*                  ^ R4       \        P&                  P/                  VP,                  ^ 4       EK~  	  V'       df   V P!                  4        FO  p\#        V\4        4      '       g   K  \        P&                  P/                  VP6                  P*                  ^ 4       KQ  	  R# R# )
a  Generic resnet video generator.

Args:
    block (Type[Union[BasicBlock, Bottleneck]]): resnet building block
    conv_makers (List[Type[Union[Conv3DSimple, Conv3DNoTemporal, Conv2Plus1D]]]): generator
        function for each layer
    layers (List[int]): number of blocks per layer
    stem (Callable[..., nn.Module]): module specifying the ResNet stem.
    num_classes (int, optional): Dimension of the final FC layer. Defaults to 400.
    zero_init_residual (bool, optional): Zero init bottleneck residual BN. Defaults to False.
rD   é   i   Úfan_outr�   )ÚmodeÚnonlinearityNg{®Gáz„?r«   )r6   r7   r   rv   r²   Ú_make_layerÚlayer1Úlayer2Úlayer3Úlayer4r_   ÚAdaptiveAvgPool3dÚavgpoolÚLinearr�   ÚfcÚmodulesÚ
isinstancer`   ÚinitÚkaiming_normal_Úweightr4   Ú	constant_ra   Únormal_r‘   Úbn3)	r9   r¯   r°   r±   r²   r³   r´   Úmr:   s	   &&&&&&& €r)   r7   ÚVideoResNet.__init__Ç   s  ø€ ô( 	‰ÑÔÜ˜DÔ!ØˆŒá“FˆŒ	à×&Ñ& u¸!­n¸bÀ&ÈÅ)ÐTUÐ&ÓVˆŒØ×&Ñ& u¸!­n¸cÀ6È!Å9ÐUVÐ&ÓWˆŒØ×&Ñ& u¸!­n¸cÀ6È!Å9ÐUVÐ&ÓWˆŒØ×&Ñ& u¸!­n¸cÀ6È!Å9ÐUVÐ&ÓWˆŒä×+Ò+¨IÓ6ˆŒÜ—)’)˜C %§/¡/Õ1°;Ó?ˆŒð —‘—ˆAÜ˜!œRŸY™Y×'Ò'Ü—‘×'Ñ'¨¯©°yÈvÐ'ÔVØ—6‘6Ò%Ü—G‘G×%Ñ% a§f¡f¨aÖ0ñ &ä˜AœrŸ~™~×.Ò.Ü—‘×!Ñ! !§(¡(¨AÔ.Ü—‘×!Ñ! !§&¡&¨!×,Ü˜AœrŸy™y×)Õ)Ü—‘—‘ §¡¨!¨TÔ2Ü—‘×!Ñ! !§&¡&¨!×,ñ  ÷ Ø—\‘\–^�Ü˜a¤×,Ô,Ü—G‘G×%Ñ% a§e¡e§l¡l°AÖ6ó $ñ r-   c                ó&   <€ V ^8„  d   QhRS[ RS[ /# r…   r	   )r'   r(   s   "€r)   r*   r¸   û   s   ø€ ÷ ñ ™ð ¡Fñ r-   c                ó  € V P                  V4      pV P                  V4      pV P                  V4      pV P                  V4      pV P	                  V4      pV P                  V4      pVP                  ^4      pV P                  V4      pV# rp   )r²   r¿   rÀ   rÁ   rÂ   rÄ   ÚflattenrÆ   )r9   r†   s   &&r)   r‹   ÚVideoResNet.forwardû   so   € Ø�I‰I�a‹Lˆà�K‰K˜‹NˆØ�K‰K˜‹NˆØ�K‰K˜‹NˆØ�K‰K˜‹Nˆà�L‰L˜‹Oˆà�I‰I�a‹LˆØ�G‰G�A‹Jˆàˆr-   c                ó¢   <€ V ^8„  d   QhRS[ S[S[S[3,          ,          RS[ S[S[S[S[3,          ,          RS[RS[RS[RS[P                  /# )r   r¯   rx   rw   Úblocksr"   r$   )
rµ   r   rs   r‘   r   ri   rU   r&   r_   r~   )r'   r(   s   "€r)   r*   r¸   
  sl   ø€ ÷ &ñ &á‘E™*¡jÐ0Õ1Õ2ð&ñ ™5¡Ñ/?ÁÐ!LÕMÕNð&ñ ð	&ñ
 ð&ñ ð&ñ 
�‰ñ&r-   c           
     ó^  € R pV^8w  g"   V P                   W1P                  ,          8w  d€   VP                  V4      p\        P                  ! \        P
                  ! V P                   W1P                  ,          ^VRR7      \        P                  ! W1P                  ,          4      4      p. pVP                  V! V P                   W2WV4      4       W1P                  ,          V n         \        ^V4       F%  p	VP                  V! V P                   W24      4       K'  	  \        P                  ! V!  # )NF)r3   r"   r4   )	rv   r�   rE   r_   r~   r`   ra   ÚappendÚrange)
r9   r¯   rx   rw   rÖ   r"   ry   Ú	ds_strider±   Úis
   &&&&&&    r)   r¾   ÚVideoResNet._make_layer
  sÛ   € ð ˆ
à�QŒ;˜$Ÿ-™-¨6·O±OÕ+CÔCØ$×:Ñ:¸6ÓBˆIÜŸšÜ—	’	˜$Ÿ-™-¨·/±/Õ)AÈqÐYbÐinÔoÜ—’˜v¯©Õ7Ó8óˆJð ˆØ�‰‘e˜DŸM™M¨6ÀÓTÔUà§¡Õ0ˆŒÜ�q˜&Ö!ˆAØ�M‰M™% §¡¨vÓDÖEñ "ô �}Š}˜fÑ%Ð%r-   )rÄ   rÆ   rv   r¿   rÀ   rÁ   rÂ   r²   )i�  Frp   )
rK   rL   rM   rN   r7   r‹   r¾   rP   rQ   rR   rS   s   @@r)   r   r   Æ   s)   ù‡ € ÷27õ 27÷hð ÷&÷ &ò &r-   c                ób  € V ^8„  d   QhR\         \        \        \        3,          ,          R\        \         \        \
        \        \        3,          ,          ,          R\        \        ,          R\        R\        P                  3,          R\        \        ,          R\        R\         R	\"        /# )
r   r¯   r°   r±   r²   .ÚweightsÚprogressÚkwargsr$   )rµ   r   rs   r‘   r   r   ri   rU   r¶   r&   r   r_   r{   r   r   r·   r   r   )r'   s   "r)   r*   r*   $  s”   € ÷ ñ Ü””j¤*Ð,Õ-Õ.ðäœ$œu¤\Ô3CÄ[Ð%PÕQÕRÕSðô ”�Iðô �3œŸ	™	�>Õ
"ð	ô
 ”kÕ"ðô ðô ðô ñr-   c                 óÂ   € Ve(   \        VR\        VP                  R,          4      4       \        WW#3/ VB pVe#   VP	                  VP                  VRR7      4       V# )Nr³   Ú
categoriesT)rß   Ú
check_hash)r   ÚlenÚmetar   Úload_state_dictÚget_state_dict)r¯   r°   r±   r²   rÞ   rß   rà   Úmodels   &&&&&&, r)   Ú_video_resnetré   $  s_   € ð ÒÜ˜f m´S¸¿¹ÀlÕ9SÓ5TÔUä˜¨FÑC¸FÑC€EàÒØ×Ñ˜g×4Ñ4¸hÐSWÐ4ÓXÔYà€Lr-   Úmin_sizerâ   ÚrecipezKhttps://github.com/pytorch/vision/tree/main/references/video_classificationÚ_docsz­The weights reproduce closely the accuracy of the paper. The accuracies are estimated on video-level with parameters `frame_rate=15`, `clips_per_video=5`, and `clip_len=16`.c                   óf   € ] tR tRt]! R]! ]RRR7      / ]CRRRRRR	R
R//RRRR/CR7      t]t	Rt
R# )r   iC  z7https://download.pytorch.org/models/r3d_18-b3b3357e.pth©Ú	crop_sizeÚresize_sizeÚ
num_paramsiP5ýÚ_metricsúKinetics-400úacc@1gš™™™™™O@úacc@5g-²�ï§ÞT@Ú_opsgð§ÆK7YD@Ú
_file_sizegåÐ"ÛùÖ_@©ÚurlÚ
transformsrå   rC   N©ép   rü   ©é€   é«   ©rK   rL   rM   rN   r   r   r   Ú_COMMON_METAÚKINETICS400_V1ÚDEFAULTrP   rC   r-   r)   r   r   C  sa   † ÙØEÙÐ.¸*ÐR\Ô]ð
Øð
à˜(ØØØ˜VØ˜Vð!ðð �FØ˜'ñ
ô€Nð  „Gr-   c                   óf   € ] tR tRt]! R]! ]RRR7      / ]CRRRRRR	R
R//RRRR/CR7      t]t	Rt
R# )r   iW  z7https://download.pytorch.org/models/mc3_18-a90a0ba3.pthrî   rñ   iPu² rò   ró   rô   g{®GáúO@rõ   g¸…ëQU@rö   g–C‹lç«E@r÷   g¼t“VF@rø   rC   Nrû   rý   r   rC   r-   r)   r   r   W  sa   † ÙØEÙÐ.¸*ÐR\Ô]ð
Øð
à˜(ØØØ˜VØ˜Vð!ðð �FØ˜&ñ
ô€Nð  „Gr-   c                   óf   € ] tR tRt]! R]! ]RRR7      / ]CRRRRRR	R
R//RRRR/CR7      t]t	Rt
R# )r   ik  z<https://download.pytorch.org/models/r2plus1d_18-91a641e6.pthrî   rñ   i­»àrò   ró   rô   gƒÀÊ¡ÝP@rõ   g33333‹U@rö   gßO�—nBD@r÷   g1¬Z^@rø   rC   Nrû   rý   r   rC   r-   r)   r   r   k  sa   † ÙØJÙÐ.¸*ÐR\Ô]ð
Øð
à˜(ØØØ˜VØ˜Vð!ðð �FØ˜'ñ
ô€Nð  „Gr-   Ú
pretrained)rÞ   rÞ   rß   Tc                ó^   € V ^8„  d   QhR\         \        ,          R\        R\        R\        /# ©r   rÞ   rß   rà   r$   )r   r   r·   r   r   )r'   s   "r)   r*   r*   �  ó/   € ÷  ñ  ”x¤Õ/ð  Ä$ð  ÔY\ð  Ôalñ  r-   c                óz   € \         P                  V 4      p \        \        \        .^,          . RO\
        V V3/ VB # )a”  Construct 18 layer Resnet3D model.

.. betastatus:: video module

Reference: `A Closer Look at Spatiotemporal Convolutions for Action Recognition <https://arxiv.org/abs/1711.11248>`__.

Args:
    weights (:class:`~torchvision.models.video.R3D_18_Weights`, optional): The
        pretrained weights to use. See
        :class:`~torchvision.models.video.R3D_18_Weights`
        below for more details, and possible values. By default, no
        pre-trained weights are used.
    progress (bool): If True, displays a progress bar of the download to stderr. Default is True.
    **kwargs: parameters passed to the ``torchvision.models.video.resnet.VideoResNet`` base class.
        Please refer to the `source code
        <https://github.com/pytorch/vision/blob/main/torchvision/models/video/resnet.py>`_
        for more details about this class.

.. autoclass:: torchvision.models.video.R3D_18_Weights
    :members:
©r   r   r   r   )r   Úverifyré   rs   r   r›   ©rÞ   rß   rà   s   $$,r)   r   r     sD   € ô0 ×#Ñ# GÓ,€GäÜÜ	ˆ˜ÕÚÜØØñð ñð 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                ó’   € \         P                  V 4      p \        \        \        .\
        .^,          ,           . RO\        V V3/ VB # )a¤  Construct 18 layer Mixed Convolution network as in

.. betastatus:: video module

Reference: `A Closer Look at Spatiotemporal Convolutions for Action Recognition <https://arxiv.org/abs/1711.11248>`__.

Args:
    weights (:class:`~torchvision.models.video.MC3_18_Weights`, optional): The
        pretrained weights to use. See
        :class:`~torchvision.models.video.MC3_18_Weights`
        below for more details, and possible values. By default, no
        pre-trained weights are used.
    progress (bool): If True, displays a progress bar of the download to stderr. Default is True.
    **kwargs: parameters passed to the ``torchvision.models.video.resnet.VideoResNet`` base class.
        Please refer to the `source code
        <https://github.com/pytorch/vision/blob/main/torchvision/models/video/resnet.py>`_
        for more details about this class.

.. autoclass:: torchvision.models.video.MC3_18_Weights
    :members:
r  )r   r  ré   rs   r   ri   r›   r  s   $$,r)   r   r   ¤  sM   € ô0 ×#Ñ# GÓ,€GäÜÜ	ˆÔ*Ð+¨aÕ/Õ/ÚÜØØñð ñð r-   c                ó^   € V ^8„  d   QhR\         \        ,          R\        R\        R\        /# r  )r   r   r·   r   r   )r'   s   "r)   r*   r*   Ë  s0   € ÷  ñ  œHÔ%8Õ9ð  ÌDð  Ôcfð  Ôkvñ  r-   c                óz   € \         P                  V 4      p \        \        \        .^,          . RO\
        V V3/ VB # )a®  Construct 18 layer deep R(2+1)D network as in

.. betastatus:: video module

Reference: `A Closer Look at Spatiotemporal Convolutions for Action Recognition <https://arxiv.org/abs/1711.11248>`__.

Args:
    weights (:class:`~torchvision.models.video.R2Plus1D_18_Weights`, optional): The
        pretrained weights to use. See
        :class:`~torchvision.models.video.R2Plus1D_18_Weights`
        below for more details, and possible values. By default, no
        pre-trained weights are used.
    progress (bool): If True, displays a progress bar of the download to stderr. Default is True.
    **kwargs: parameters passed to the ``torchvision.models.video.resnet.VideoResNet`` base class.
        Please refer to the `source code
        <https://github.com/pytorch/vision/blob/main/torchvision/models/video/resnet.py>`_
        for more details about this class.

.. autoclass:: torchvision.models.video.R2Plus1D_18_Weights
    :members:
r  )r   r  ré   rs   rU   r§   r  s   $$,r)   r   r   É  sD   € ô0 "×(Ñ(¨Ó1€GäÜÜ	ˆ˜ÕÚÜØØñð ñð r-   )Ú
_ModelURLs)r   r   r   r   r   r   r   rg   )2Úcollections.abcr   Ú	functoolsr   Útypingr   r   r   r   Útorch.nnr_   Útorchr
   Útransforms._presetsr   Úutilsr   Ú_apir   r   r   Ú_metar   Ú_utilsr   r   Ú__all__r`   r   r~   rU   ri   r{   rs   r‘   r›   r§   r   ré   r  r   r   r   r  r   r   r   r  rù   Ú
model_urlsrC   r-   r)   Ú<module>r     s
  ðÝ $Ý ß 1Ó 1å Ý å 6Ý (ß 7Ñ 7Ý +ß Cò€ô&�2—9‘9ô &ô&&�"—-‘-ô &ô.!�r—y‘yô !ô&"�—‘ô "ôJ.�—‘ô .ôb
�—‘ô 
ô
�2—=‘=ô 
ô[&�"—)‘)ô [&õ|ð* �ØÐ)ØÐ[Øð	Sð€ô�[ô ô(�[ô ô(˜+ô ñ( ÓÙ ,°×0MÑ0MÐ!NÔOð °$ð  Èö  ó Pó ð ñF ÓÙ ,°×0MÑ0MÐ!NÔOð °$ð  Èö  ó Pó ð ñF ÓÙ ,Ð0C×0RÑ0RÐ!SÔTð ¸Dð  ÐSWö  ó Uó ð õH  ñ à�.×/Ñ/×3Ñ3Ø�.×/Ñ/×3Ñ3ØÐ*×9Ñ9×=Ñ=ðó‚
r-   