+
    þäûj³—  ã                   óN  € ^ RI t ^ RIt^ RIHt ^ RIHu Ht ^ RIHt ^ RI	H
t
HtHt ^RIHt  ! R R]P                  4      tR tR 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]P                  4      t ! R R]P                  4      t ! R R]P4                  4      t ! R R]P4                  4      t]! 4        ! R R]P                  4      4       tR# )é    N)Ústore_hyperparameters)ÚDropPathÚ	to_2tupleÚtrunc_normal_)Úpad_to_multiplec                   óX   a a€ ] tR t^t oRR]P
                  R3V 3R lltR tRtVt	V ;t
# )ÚMlpNç        c                ó  <€ \         SV `  4        T;'       g    TpT;'       g    Tp\        P                  ! W4      V n        V! 4       V n        \        P                  ! W#4      V n        \        P                  ! V4      V n        R # ©N)	ÚsuperÚ__init__ÚnnÚLinearÚfc1ÚactÚfc2ÚDropoutÚdrop)ÚselfÚin_featuresÚhidden_featuresÚout_featuresÚ	act_layerr   Ú	__class__s   &&&&&&€ÚgC:\Ai_Coding\apps\studio\ComfyUI\.venv\Lib\site-packages\spandrel\architectures\SwinIR\__arch\SwinIR.pyr   ÚMlp.__init__   sc   ø€ ô 	‰ÑÔØ#×2Ð2 {ˆØ)×8Ð8¨[ˆÜ—9’9˜[Ó:ˆŒÙ“;ˆŒÜ—9’9˜_Ó;ˆŒÜ—J’J˜tÓ$ˆŽ	ó    c                ó°   € V P                  V4      pV P                  V4      pV P                  V4      pV P                  V4      pV P                  V4      pV# r   )r   r   r   r   ©r   Úxs   &&r   ÚforwardÚMlp.forward$   sH   € Ø�H‰H�Q‹KˆØ�H‰H�Q‹KˆØ�I‰I�a‹LˆØ�H‰H�Q‹KˆØ�I‰I�a‹LˆØˆr   )r   r   r   r   )Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__r   ÚGELUr   r"   Ú__static_attributes__Ú__classdictcell__Ú__classcell__©r   Ú__classdict__s   @@r   r	   r	      s&   ù‡ € ð ØØ—'‘'Ø÷%÷ ò r   r	   c                óÐ   € V P                   w  r#rEV P                  W#V,          WV,          W4      p V P                  ^ ^^^^^4      P                  4       P                  RWV4      pV# )z‚
Args:
    x: (B, H, W, C)
    window_size (int): window size

Returns:
    windows: (num_windows*B, window_size, window_size, C)
éÿÿÿÿ)ÚshapeÚviewÚpermuteÚ
contiguous)r!   Úwindow_sizeÚBÚHÚWÚCÚwindowss   &&     r   Úwindow_partitionr:   -   sh   € ð —‘�J€Aˆ!Ø	�‰ˆq�{Õ" K°kÕ1AÀ;ÓR€Aà	�	‰	�!�Q˜˜1˜a Ó#×.Ñ.Ó0×5Ñ5°b¸+ÐTUÓVð ð €Nr   c                ó   € \        V P                  ^ ,          W#,          V,          V,          ,          4      pV P                  WBV,          W1,          WR4      pVP                  ^ ^^^^^4      P	                  4       P                  WBVR4      pV# )z»
Args:
    windows: (num_windows*B, window_size, window_size, C)
    window_size (int): Window size
    H (int): Height of image
    W (int): Width of image

Returns:
    x: (B, H, W, C)
r/   )Úintr0   r1   r2   r3   )r9   r4   r6   r7   r5   r!   s   &&&&  r   Úwindow_reverser=   >   s~   € ô 	ˆG�M‰M˜!Õ ¥¨Õ 3°kÕ AÕBÓC€AØ�‰Ø	�Õ˜QÕ-¨{Èó	€Að 	
�	‰	�!�Q˜˜1˜a Ó#×.Ñ.Ó0×5Ñ5°a¸A¸rÓB€AØ€Hr   c                   ó\   a a€ ] tR t^Qt oRtRV 3R lltR	R ltV3R lR ltR tRt	Vt
V ;t# )
ÚWindowAttentiona  Window based multi-head self attention (W-MSA) module with relative position bias.
It supports both of shifted and non-shifted window.

Args:
    dim (int): Number of input channels.
    window_size (tuple[int]): The height and width of the window.
    num_heads (int): Number of attention heads.
    qkv_bias (bool, optional):  If True, add a learnable bias to query, key, value. Default: True
    qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set
    attn_drop (float, optional): Dropout ratio of attention weight. Default: 0.0
    proj_drop (float, optional): Dropout ratio of output. Default: 0.0
c                óŒ  <€ \         SV `  4        Wn        W n        W0n        W,          pT;'       g
    VR,          V n        \        P                  ! \        P                  ! ^V^ ,          ,          ^,
          ^V^,          ,          ^,
          ,          V4      4      V n
        \        P                  ! V P                  ^ ,          4      p	\        P                  ! V P                  ^,          4      p
\        P                  ! \        P                  ! Wš.4      4      p\        P                  ! V^4      pVR,          VR	,          ,
          pVP                  ^^^ 4      P!                  4       pVR
;;,          V P                  ^ ,          ^,
          ,          uu&   VR;;,          V P                  ^,          ^,
          ,          uu&   VR
;;,          ^V P                  ^,          ,          ^,
          ,          uu&   VP#                  R4      pV P%                  RV4       \        P&                  ! W^,          VR7      V n        \        P*                  ! V4      V n        \        P&                  ! W4      V n        \        P*                  ! V4      V n        \3        V P                  RR7       \        P4                  ! RR7      V n        R# )g      à?NÚrelative_position_index©Úbiasç{®Gáz”?©Ústd)Údimg      à¿)ºNNNrH   N)rH   NrH   )rH   rH   r   )rH   rH   é   r/   )r   r   rG   r4   Ú	num_headsÚscaler   Ú	ParameterÚtorchÚzerosÚrelative_position_bias_tableÚarangeÚstackÚmeshgridÚflattenr2   r3   ÚsumÚregister_bufferr   Úqkvr   Ú	attn_dropÚprojÚ	proj_dropr   ÚSoftmaxÚsoftmax)r   rG   r4   rJ   Úqkv_biasÚqk_scalerW   rY   Úhead_dimÚcoords_hÚcoords_wÚcoordsÚcoords_flattenÚrelative_coordsrA   r   s   &&&&&&&&       €r   r   ÚWindowAttention.__init___   s  ø€ ô 	‰ÑÔØŒØ&ÔØ"ŒØÕ#ˆØ×/Ð/ ¨4¥ˆŒ
ô -/¯LªLÜ�KŠK˜˜[¨�^Õ+¨aÕ/°A¸ÀA½Õ4FÈÕ4JÕKÈYÓWó-
ˆÔ)ô
 —<’< × 0Ñ 0°Õ 3Ó4ˆÜ—<’< × 0Ñ 0°Õ 3Ó4ˆÜ—’œUŸ^š^¨XÐ,@ÓAÓBˆÜŸš v¨qÓ1ˆà˜:Õ&¨¸
Õ)CÕCð 	ð *×1Ñ1Øˆq�!ó
ç
‰*‹,ð 	ð 	˜×  D×$4Ñ$4°QÕ$7¸!Õ$;Õ;Ó Ø˜×  D×$4Ñ$4°QÕ$7¸!Õ$;Õ;Ó Ø˜×  A¨×(8Ñ(8¸Õ(;Õ$;¸aÕ$?Õ?Ó Ø"1×"5Ñ"5°bÓ"9ÐØ×ÑÐ6Ð8OÔPä—9’9˜S¨¥'°Ô9ˆŒÜŸš IÓ.ˆŒÜ—I’I˜cÓ'ˆŒ	äŸš IÓ.ˆŒä�d×7Ñ7¸TÕBÜ—z’z bÔ)ˆŽr   c                óÎ  € VP                   w  r4pV P                  V4      P                  W4^V P                  WPP                  ,          4      P	                  ^^ ^^^4      pV^ ,          V^,          V^,          r˜pWpP
                  ,          pWxP                  RR4      ,          p
V P                  V P                  P                  R4      ,          P                  V P                  ^ ,          V P                  ^,          ,          V P                  ^ ,          V P                  ^,          ,          R4      pVP	                  ^^ ^4      P                  4       pW«P                  ^ 4      ,           p
Ve‹   VP                   ^ ,          pV
P                  W<,          WÀP                  WD4      VP                  ^4      P                  ^ 4      ,           p
V
P                  RV P                  WD4      p
V P                  V
4      p
MV P                  V
4      p
V P                  V
4      p
W©,          P                  ^^4      P                  W4V4      pV P                  V4      pV P!                  V4      pV# )z‹
Args:
    x: input features with shape of (num_windows*B, N, C)
    mask: (0/-inf) mask with shape of (num_windows, Wh*Ww, Wh*Ww) or None
éþÿÿÿr/   )r0   rV   ÚreshaperJ   r2   rK   Ú	transposerO   rA   r1   r4   r3   Ú	unsqueezer[   rW   rX   rY   )r   r!   ÚmaskÚB_ÚNr8   rV   ÚqÚkÚvÚattnÚrelative_position_biasÚnWs   &&&          r   r"   ÚWindowAttention.forward�   sÿ  € ð —7‘7‰ˆˆqà�H‰H�Q‹Kß‰W�R˜A˜tŸ~™~¨q·N±NÕ/BÓCß‰W�Q˜˜1˜a Ó#ð 	ð ��FØ��FØ��Fð ˆð —
‘
�NˆØ—;‘;˜r 2Ó&Õ&ˆà!%×!BÑ!BØ×(Ñ(×-Ñ-¨bÓ1õ"
ç
‰$Ø×Ñ˜QÕ $×"2Ñ"2°1Õ"5Õ5Ø×Ñ˜QÕ $×"2Ñ"2°1Õ"5Õ5Øó
ð 	ð "8×!?Ñ!?Øˆq�!ó"
ç
‰*‹,ð 	ð ×6Ñ6°qÓ9Õ9ˆàÒØ—‘˜A•ˆBØ—9‘9˜R�X r¯>©>¸1Ó@À4Ç>Á>ØóDç‰i˜‹lõˆDð —9‘9˜R §¡°Ó6ˆDØ—<‘< Ó%‰Dà—<‘< Ó%ˆDà�~‰~˜dÓ#ˆà�X× Ñ   AÓ&×.Ñ.¨r°aÓ8ˆØ�I‰I�a‹LˆØ�N‰N˜1ÓˆØˆr   c                ó    <€ V ^8„  d   QhRS[ /# ©é   Úreturn©Ústr)Úformatr-   s   "€r   Ú__annotate__ÚWindowAttention.__annotate__Á   s   ø€ ÷ ]ñ ]™Cñ ]r   c                óT   € R V P                    RV P                   RV P                   2# )údim=ú, window_size=ú, num_heads=)rG   r4   rJ   ©r   s   &r   Ú
extra_reprÚWindowAttention.extra_reprÁ   s+   € Ø�d—h‘h�Z˜~¨d×.>Ñ.>Ð-?¸|ÈDÏNÉNÐK[Ð\Ð\r   c                óÈ  € ^ pW!V P                   ,          ^,          V P                   ,          ,          pW P                  V,          V P                   V P                  ,          ,          V,          ,          pW P                  V,          V,          V P                   V P                  ,          ,          ,          pW!V P                   ,          V P                   ,          ,          pV# ©r   )rG   rJ   )r   rl   Úflopss   && r   r†   ÚWindowAttention.flopsÄ   s“   € àˆà�T—X‘X• Õ! D§H¡HÕ,Õ,ˆà—‘ !Õ# t§x¡x°4·>±>Õ'AÕBÀQÕFÕFˆà—‘ !Õ# aÕ'¨4¯8©8°t·~±~Õ+EÕFÕFˆà�T—X‘X• §¡Õ(Õ(ˆØˆr   )
rW   rG   rJ   rX   rY   rV   rO   rK   r[   r4   )TNr
   r
   r   )r$   r%   r&   r'   Ú__doc__r   r"   r‚   r†   r)   r*   r+   r,   s   @@r   r?   r?   Q   s,   ù‡ € ñ÷.*ô`0÷d]ð ]÷ò r   r?   c            
       óš   a a€ ] tR t^Òt oRt^^ RRRRRR]P                  ]P                  3
V 3R lltR t	R t
V3R	 lR
 ltR tRtVtV ;t# )ÚSwinTransformerBlockaY  Swin Transformer Block.

Args:
    dim (int): Number of input channels.
    input_resolution (tuple[int]): Input resulotion.
    num_heads (int): Number of attention heads.
    window_size (int): Window size.
    shift_size (int): Shift size for SW-MSA.
    mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
    qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
    qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set.
    drop (float, optional): Dropout rate. Default: 0.0
    attn_drop (float, optional): Attention dropout rate. Default: 0.0
    drop_path (float, optional): Stochastic depth rate. Default: 0.0
    act_layer (nn.Module, optional): Activation layer. Default: nn.GELU
    norm_layer (nn.Module, optional): Normalization layer.  Default: nn.LayerNorm
ç      @TNr
   c           
     ó  <€ \         SV `  4        Wn        W n        W0n        W@n        WPn        W`n        \        V P                  4      V P
                  8:  d"   ^ V n        \        V P                  4      V n        ^ V P                  u;8:  d   V P
                  8  g    Q R4       h Q R4       hV! V4      V n	        \        V\        V P
                  4      VVVV
V	R7      V n        VR8”  d   \        V4      M\        P                  ! 4       V n        V! V4      V n        \%        W,          4      p\'        VVVV	R7      V n        V P                  ^ 8”  d   V P+                  V P                  4      pMRpV P-                  RV4       R# )r   z shift_size must in 0-window_size)r4   rJ   r\   r]   rW   rY   r
   )r   r   r   r   NÚ	attn_mask)r   r   rG   Úinput_resolutionrJ   r4   Ú
shift_sizeÚ	mlp_ratioÚminÚnorm1r?   r   rp   r   r   ÚIdentityÚ	drop_pathÚnorm2r<   r	   ÚmlpÚcalculate_maskrU   )r   rG   rŽ   rJ   r4   r�   r�   r\   r]   r   rW   r”   r   Ú
norm_layerÚmlp_hidden_dimr�   r   s   &&&&&&&&&&&&&&  €r   r   ÚSwinTransformerBlock.__init__å   sW  ø€ ô  	‰ÑÔØŒØ 0ÔØ"ŒØ&ÔØ$ŒØ"ŒÜˆt×$Ñ$Ó%¨×)9Ñ)9Ô9àˆDŒOÜ" 4×#8Ñ#8Ó9ˆDÔà�—‘Ö3 4×#3Ñ#3Õ3ð	.à-ó	.Ù3ð	.à-ó	.Ø3ñ   “_ˆŒ
Ü#ØÜ! $×"2Ñ"2Ó3ØØØØØô
ˆŒ	ð 1:¸C´œ )Ô,ÄRÇ[Â[Ã]ˆŒÙ “_ˆŒ
Ü˜S�_Ó-ˆÜØØ*ØØô	
ˆŒð �?‰?˜QÔØ×+Ñ+¨D×,AÑ,AÓB‰IàˆIà×Ñ˜[¨)Ö4r   c                óæ  € Vw  r#\         P                  ! ^W#^34      p\        ^ V P                  ) 4      \        V P                  ) V P                  ) 4      \        V P                  ) R4      3p\        ^ V P                  ) 4      \        V P                  ) V P                  ) 4      \        V P                  ) R4      3p^ pV F  pV F  p	WtRW‰R3&   V^,          pK  	  K  	  \        W@P                  4      p
V
P                  RV P                  V P                  ,          4      p
V
P                  ^4      V
P                  ^4      ,
          pVP                  V^ 8g  R4      P                  V^ 8H  R4      pV# )rI   NrH   r
   r/   g      YÀ)	rM   rN   Úslicer4   r�   r:   r1   ri   Úmasked_fill)r   Úx_sizer6   r7   Úimg_maskÚh_slicesÚw_slicesÚcntÚhÚwÚmask_windowsr�   s   &&          r   r—   Ú#SwinTransformerBlock.calculate_mask   sg  € à‰ˆÜ—;’;  1¨˜|Ó,ˆä�!�d×&Ñ&Ð&Ó'Ü�4×#Ñ#Ð# d§o¡oÐ%5Ó6Ü�4—?‘?Ð" DÓ)ð
ˆô �!�d×&Ñ&Ð&Ó'Ü�4×#Ñ#Ð# d§o¡oÐ%5Ó6Ü�4—?‘?Ð" DÓ)ð
ˆð
 ˆÛˆAÛ�Ø'*˜˜A !˜Ñ$Ø�q•’ó ñ ô
 (Ø×&Ñ&ó
ˆð $×(Ñ(¨¨T×-=Ñ-=À×@PÑ@PÕ-PÓQˆØ ×*Ñ*¨1Ó-°×0FÑ0FÀqÓ0IÕIˆ	Ø×)Ñ)¨)°q©.¸&ÓA×MÑMØ˜‰N˜Có
ˆ	ð Ðr   c                ó  € Vw  r4VP                   w  rVpTpV P                  V4      pVP                  WSWG4      pV P                  ^ 8”  d2   \        P
                  ! WP                  ) V P                  ) 3RR7      p	MTp	\        W�P                  4      p
V
P                  RV P                  V P                  ,          V4      p
V P                  V8X  d   V P                  W P                  R7      pM:V P                  W P                  V4      P                  VP                  4      R7      pVP                  RV P                  V P                  V4      p\        W°P                  W44      p	V P                  ^ 8”  d0   \        P
                  ! W�P                  V P                  3RR7      pMT	pVP                  WSV,          V4      pW€P                  V4      ,           pWP                  V P!                  V P#                  V4      4      4      ,           pV# )r   )ÚshiftsÚdims)rj   )rI   rv   r/   )r0   r’   r1   r�   rM   Úrollr:   r4   rŽ   rp   r�   r—   ÚtoÚdevicer=   r”   r–   r•   )r   r!   rž   r6   r7   r5   ÚLr8   ÚshortcutÚ	shifted_xÚ	x_windowsÚattn_windowss   &&&         r   r"   ÚSwinTransformerBlock.forward?  sÈ  € Ø‰ˆØ—'‘'‰ˆˆað ˆØ�J‰J�q‹MˆØ�F‰F�1˜Óˆð �?‰?˜QÔÜŸ
š
ØŸO™OÐ+¨d¯o©oÐ-=Ð>ÀVô‰Ið ˆIô %Ø×'Ñ'ó
ˆ	ð —N‘NØ�× Ñ  4×#3Ñ#3Õ3°Qó
ˆ	ð
 × Ñ  FÔ*ØŸ9™9Ø§¡ð %ó ‰Lð  Ÿ9™9Ø× 3Ñ 3°FÓ ;× >Ñ >¸q¿x¹xÓ Hð %ó ˆLð
 $×(Ñ(¨¨T×-=Ñ-=¸t×?OÑ?OÐQRÓSˆÜ" <×1AÑ1AÀ1ÓHˆ	ð �?‰?˜QÔÜ—
’
Ø§?¡?°D·O±OÐ"DÈ6ô‰Að ˆAØ�F‰F�1˜!•e˜QÓˆð —~‘~ aÓ(Õ(ˆØ—‘˜tŸx™x¨¯
©
°1«Ó6Ó7Õ7ˆàˆr   c                ó    <€ V ^8„  d   QhRS[ /# ru   rx   )rz   r-   s   "€r   r{   Ú!SwinTransformerBlock.__annotate__u  s   ø€ ÷ 
ñ 
™Cñ 
r   c                ó¢   € R V P                    RV P                   RV P                   RV P                   RV P                   RV P
                   2# )r~   ú, input_resolution=r€   r   z, shift_size=z, mlp_ratio=)rG   rŽ   rJ   r4   r�   r�   r�   s   &r   r‚   ÚSwinTransformerBlock.extra_repru  s_   € à�4—8‘8�*Ð/°×0EÑ0EÐ/FÀlÐSW×SaÑSaÐRbð cØ×+Ñ+Ð,¨M¸$¿/¹/Ð9JÈ,ÐW[×WeÑWeÐVfðhð	
r   c                ó  € ^ pV P                   w  r#WP                  V,          V,          ,          pW#,          V P                  ,          V P                  ,          pWV P                  P	                  V P                  V P                  ,          4      ,          ,          pV^V,          V,          V P                  ,          V P                  ,          V P
                  ,          ,          pWP                  V,          V,          ,          pV# r…   )rŽ   rG   r4   rp   r†   r�   )r   r†   r6   r7   rr   s   &    r   r†   ÚSwinTransformerBlock.flops{  s¸   € ØˆØ×$Ñ$‰ˆà—‘˜A• Õ!Õ!ˆà�U�T×%Ñ%Õ%¨×(8Ñ(8Õ8ˆØ�d—i‘i—o‘o d×&6Ñ&6¸×9IÑ9IÕ&IÓJÕJÕJˆà��Q•˜•˜TŸX™XÕ%¨¯©Õ0°4·>±>ÕAÕAˆà—‘˜A• Õ!Õ!ˆØˆr   )rp   rG   r”   rŽ   r–   r�   r’   r•   rJ   r�   r4   )r$   r%   r&   r'   rˆ   r   r(   Ú	LayerNormr   r—   r"   r‚   r†   r)   r*   r+   r,   s   @@r   rŠ   rŠ   Ò   sW   ù‡ € ñð. ØØØØØØØØ—'‘'Ø—<‘<÷95òvò>4÷l
ð 
÷ò r   rŠ   c                   ón   a a€ ] tR tRt oRt]P                  3V 3R lltR tV3R lR lt	R t
RtVtV ;t# )	ÚPatchMergingiŠ  z×Patch Merging Layer.

Args:
    input_resolution (tuple[int]): Resolution of input feature.
    dim (int): Number of input channels.
    norm_layer (nn.Module, optional): Normalization layer.  Default: nn.LayerNorm
c                ó¼   <€ \         SV `  4        Wn        W n        \        P
                  ! ^V,          ^V,          RR7      V n        V! ^V,          4      V n        R# )é   FrB   N)r   r   rŽ   rG   r   r   Ú	reductionÚnorm)r   rŽ   rG   r˜   r   s   &&&&€r   r   ÚPatchMerging.__init__“  sE   ø€ Ü‰ÑÔØ 0ÔØŒÜŸš 1 s¥7¨A°­G¸%Ô@ˆŒÙ˜q 3�wÓ'ˆŽ	r   c                óÒ  € V P                   w  r#VP                  w  rEpWRV,          8X  g   Q R4       hV^,          ^ 8X  d   V^,          ^ 8X  g   Q RV RV R24       hVP                  WBW64      pVR,          pVR,          pVR,          p	VR,          p
\        P                  ! WxWš.R	4      pVP                  VR	^V,          4      pV P                  V4      pV P                  V4      pV# )
z
x: B, H*W, C
zinput feature has wrong sizezx size (Ú*z) are not even.)rH   ºr   Nrv   rÄ   rH   )rH   ºrI   Nrv   rÄ   rH   )rH   rÄ   rÅ   rH   )rH   rÅ   rÅ   rH   r/   )rŽ   r0   r1   rM   ÚcatrÀ   r¿   )r   r!   r6   r7   r5   r­   r8   Úx0Úx1Úx2Úx3s   &&         r   r"   ÚPatchMerging.forwardš  sè   € ð ×$Ñ$‰ˆØ—'‘'‰ˆˆaØ˜•EŒzÐ9Ð9Ó9ˆzØ�1�u˜Œz˜a !�e qœjÐK¨H°Q°C°q¸¸¸?Ð*KÓKÐ(à�F‰F�1˜ÓˆàÐÕ ˆØÐÕ ˆØÐÕ ˆØÐÕ ˆÜ�IŠI�r˜rÐ&¨Ó+ˆØ�F‰F�1�b˜!˜a�%Ó ˆà�I‰I�a‹LˆØ�N‰N˜1Óˆàˆr   c                ó    <€ V ^8„  d   QhRS[ /# ru   rx   )rz   r-   s   "€r   r{   ÚPatchMerging.__annotate__±  s   ø€ ÷ Kñ K™Cñ Kr   c                ó:   € R V P                    RV P                   2# )zinput_resolution=z, dim=©rŽ   rG   r�   s   &r   r‚   ÚPatchMerging.extra_repr±  s    € Ø" 4×#8Ñ#8Ð"9¸ÀÇÁ¸zÐJÐJr   c                óî   € V P                   w  rW,          V P                  ,          pW1^,          V^,          ,          ^,          V P                  ,          ^,          V P                  ,          ,          pV# ©rv   rÏ   ©r   r6   r7   r†   s   &   r   r†   ÚPatchMerging.flops´  sU   € Ø×$Ñ$‰ˆØ•˜Ÿ™Õ ˆØ�q•&˜Q !�VÕ$ qÕ(¨4¯8©8Õ3°aÕ7¸$¿(¹(ÕBÕBˆØˆr   )rG   rŽ   rÀ   r¿   ©r$   r%   r&   r'   rˆ   r   rº   r   r"   r‚   r†   r)   r*   r+   r,   s   @@r   r¼   r¼   Š  s3   ù‡ € ñð :<¿¹÷ (ò÷.Kð K÷ò r   r¼   c            	       ó~   a a€ ] tR tRt oRtRRRRRR]P                  RR3	V 3R lltR	 tV3R
 lR lt	R t
RtVtV ;t# )Ú
BasicLayeri»  aî  A basic Swin Transformer layer for one stage.

Args:
    dim (int): Number of input channels.
    input_resolution (tuple[int]): Input resolution.
    depth (int): Number of blocks.
    num_heads (int): Number of attention heads.
    window_size (int): Local window size.
    mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
    qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
    qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set.
    drop (float, optional): Dropout rate. Default: 0.0
    attn_drop (float, optional): Attention dropout rate. Default: 0.0
    drop_path (float | tuple[float], optional): Stochastic depth rate. Default: 0.0
    norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm
    downsample (nn.Module | None, optional): Downsample layer at the end of the layer. Default: None
    use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False.
r‹   TNr
   Fc                ó’  <€ \         SV `  4        Wn        W n        W0n        Wàn        \        P                  ! \        V4       Uu. uFO  p\        TTTTV^,          ^ 8X  d   ^ MV^,          TTTT	T
\        V\        4      '       d	   W¿,          MTVR7      NKQ  	  up4      V n        Ve   V! W!VR7      V n        R# RV n        R# u upi )rv   )rG   rŽ   rJ   r4   r�   r�   r\   r]   r   rW   r”   r˜   N)rG   r˜   )r   r   rG   rŽ   ÚdepthÚuse_checkpointr   Ú
ModuleListÚrangerŠ   Ú
isinstanceÚlistÚblocksÚ
downsample)r   rG   rŽ   rÙ   rJ   r4   r�   r\   r]   r   rW   r”   r˜   rà   rÚ   Úir   s   &&&&&&&&&&&&&&& €r   r   ÚBasicLayer.__init__Ï  sÒ   ø€ ô" 	‰ÑÔØŒØ 0ÔØŒ
Ø,Ôô —m’mô$ ˜uœó#ñ" &�Aô! %ØØ%5Ø'Ø +Ø%&¨¥U¨a¤Z™q°kÀQÕ6FØ'Ø%Ø%ØØ'ä! )¬T×2Ò2ð (žlà"Ø)÷ñ  &ñ#ó
ˆŒð. Ò!Ù(Ø °jôˆDŽOð #ˆDŽOùò7s   ÁACc                óÐ   € V P                    F6  pV P                  '       d   \        P                  ! W1V4      pK.  V! W4      pK8  	  V P                  e   V P                  V4      pV# r   )rß   rÚ   Ú
checkpointrà   )r   r!   rž   Úblks   &&& r   r"   ÚBasicLayer.forward  sV   € Ø—;”;ˆCØ×"×"Ð"Ü×)Ò)¨#°&Ó9’á˜“N’ñ	 ð
 �?‰?Ò&Ø—‘ Ó"ˆAØˆr   c                ó    <€ V ^8„  d   QhRS[ /# ru   rx   )rz   r-   s   "€r   r{   ÚBasicLayer.__annotate__  s   ø€ ÷ _ñ _™Cñ _r   c                óT   € R V P                    RV P                   RV P                   2# )r~   r¶   z, depth=)rG   rŽ   rÙ   r�   s   &r   r‚   ÚBasicLayer.extra_repr  s/   € Ø�d—h‘h�ZÐ2°4×3HÑ3HÐ2IÈÐRV×R\ÑR\ÐQ]Ð^Ð^r   c                ó¸   € ^ pV P                    F  pWP                  4       ,          pK  	  V P                  e!   WP                  P                  4       ,          pV# r…   )rß   r†   rà   )r   r†   rå   s   &  r   r†   ÚBasicLayer.flops  sG   € ØˆØ—;”;ˆCØ—Y‘Y“[Õ ŠEñ à�?‰?Ò&Ø—_‘_×*Ñ*Ó,Õ,ˆEØˆr   )rß   rÙ   rG   rà   rŽ   rÚ   rÕ   r,   s   @@r   r×   r×   »  sL   ù‡ € ñð4 ØØØØØØ—<‘<ØØ÷4#òl÷_ð _÷ò r   r×   c                   ór   a a€ ] tR tRt oRtRRRRRR]P                  RR^à^R3V 3R	 lltR
 tR t	Rt
VtV ;t# )ÚRSTBi  am  Residual Swin Transformer Block (RSTB).

Args:
    dim (int): Number of input channels.
    input_resolution (tuple[int]): Input resolution.
    depth (int): Number of blocks.
    num_heads (int): Number of attention heads.
    window_size (int): Local window size.
    mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
    qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True
    qk_scale (float | None, optional): Override default qk scale of head_dim ** -0.5 if set.
    drop (float, optional): Dropout rate. Default: 0.0
    attn_drop (float, optional): Attention dropout rate. Default: 0.0
    drop_path (float | tuple[float], optional): Stochastic depth rate. Default: 0.0
    norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm
    downsample (nn.Module | None, optional): Downsample layer at the end of the layer. Default: None
    use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False.
    img_size: Input image size.
    patch_size: Patch size.
    resi_connection: The convolutional block before residual connection.
r‹   TNr
   FÚ1convc                ó‚  <€ \         SV `  4        Wn        W n        \	        VVVVVVVVV	V
VVVVR 7      V n        VR8X  d    \        P                  ! W^^^4      V n        MµVR8X  d¯   \        P                  ! \        P                  ! W^,          ^^^4      \        P                  ! RRR7      \        P                  ! V^,          V^,          ^^^ 4      \        P                  ! RRR7      \        P                  ! V^,          V^^^4      4      V n        \        VV^ VRR7      V n        \        VV^ VRR7      V n        R# ))rG   rŽ   rÙ   rJ   r4   r�   r\   r]   r   rW   r”   r˜   rà   rÚ   rï   Ú3convçš™™™™™É?T©Únegative_slopeÚinplaceN©Úimg_sizeÚ
patch_sizeÚin_chansÚ	embed_dimr˜   )r   r   rG   rŽ   r×   Úresidual_groupr   ÚConv2dÚconvÚ
SequentialÚ	LeakyReLUÚ
PatchEmbedÚpatch_embedÚPatchUnEmbedÚpatch_unembed)r   rG   rŽ   rÙ   rJ   r4   r�   r\   r]   r   rW   r”   r˜   rà   rÚ   r÷   rø   Úresi_connectionr   s   &&&&&&&&&&&&&&&&&&€r   r   ÚRSTB.__init__2  s,  ø€ ô( 	‰ÑÔàŒØ 0Ôä(ØØ-ØØØ#ØØØØØØØ!Ø!Ø)ô
ˆÔð" ˜gÔ%ÜŸ	š	 #¨A¨q°!Ó4ˆD�IØ Ô'äŸšÜ—	’	˜# a�x¨¨A¨qÓ1Ü—’¨C¸Ô>Ü—	’	˜# �( C¨1¥H¨a°°AÓ6Ü—’¨C¸Ô>Ü—	’	˜# �( C¨¨A¨qÓ1óˆDŒIô &ØØ!ØØØô
ˆÔô *ØØ!ØØØô
ˆÖr   c           
     óŽ   € V P                  V P                  V P                  V P                  W4      V4      4      4      V,           # r   )r  rý   r  rû   )r   r!   rž   s   &&&r   r"   ÚRSTB.forwardx  sC   € à×ÑØ—	‘	˜$×,Ñ,¨T×-@Ñ-@ÀÓ-KÈVÓTÓUóð õð	
r   c                óV  € ^ pWP                   P                  4       ,          pV P                  w  r#WV,          V P                  ,          V P                  ,          ^	,          ,          pWP                  P                  4       ,          pWP
                  P                  4       ,          pV# r…   )rû   r†   rŽ   rG   r  r  ©r   r†   r6   r7   s   &   r   r†   Ú
RSTB.flops€  s�   € ØˆØ×$Ñ$×*Ñ*Ó,Õ,ˆØ×$Ñ$‰ˆØ�Q•˜Ÿ™Õ! D§H¡HÕ,¨qÕ0Õ0ˆØ×!Ñ!×'Ñ'Ó)Õ)ˆØ×#Ñ#×)Ñ)Ó+Õ+ˆàˆr   )rý   rG   rŽ   r  r  rû   )r$   r%   r&   r'   rˆ   r   rº   r   r"   r†   r)   r*   r+   r,   s   @@r   rî   rî     sJ   ù‡ € ñð: ØØØØØØ—<‘<ØØØØØ÷%D
òL
÷ò r   rî   c                   óF   a a€ ] tR tRt oRtRV 3R lltR tR tRtVt	V ;t
# )r   i‹  a[  Image to Patch Embedding

Args:
    img_size (int): Image size.  Default: 224.
    patch_size (int): Patch token size. Default: 4.
    in_chans (int): Number of input image channels. Default: 3.
    embed_dim (int): Number of linear projection output channels. Default: 96.
    norm_layer (nn.Module, optional): Normalization layer. Default: None
c                óT  <€ \         SV `  4        \        V4      p\        V4      pV^ ,          V^ ,          ,          V^,          V^,          ,          .pWn        W n        W`n        V^ ,          V^,          ,          V n        W0n        W@n        Ve   V! V4      V n	        R# RV n	        R# ©r   N)
r   r   r   r÷   rø   Úpatches_resolutionÚnum_patchesrù   rú   rÀ   ©r   r÷   rø   rù   rú   r˜   r  r   s   &&&&&& €r   r   ÚPatchEmbed.__init__–  s™   ø€ ô 	‰ÑÔÜ˜XÓ&ˆÜ˜zÓ*ˆ
à�Q�K˜: a�=Õ(Ø�Q�K˜: a�=Õ(ð
Ðð !ŒØ$ŒØ"4ÔØ-¨aÕ0Ð3EÀaÕ3HÕHˆÔà ŒØ"ŒàÒ!Ù" 9Ó-ˆDŽIàˆDŽIr   c                ó†   € VP                  ^4      P                  ^^4      pV P                  e   V P                  V4      pV# rÒ   )rS   rh   rÀ   r    s   &&r   r"   ÚPatchEmbed.forward­  s8   € Ø�I‰I�a‹L×"Ñ" 1 aÓ(ˆØ�9‰9Ò Ø—	‘	˜!“ˆAØˆr   c                ó‚   € ^ pV P                   w  r#V P                  e!   WV,          V P                  ,          ,          pV# r…   )r÷   rÀ   rú   r	  s   &   r   r†   ÚPatchEmbed.flops³  s6   € ØˆØ�}‰}‰ˆØ�9‰9Ò Ø˜•U˜TŸ^™^Õ+Õ+ˆEØˆr   )rú   r÷   rù   rÀ   r  rø   r  ©éà   r¾   é   é`   N©r$   r%   r&   r'   rˆ   r   r"   r†   r)   r*   r+   r,   s   @@r   r   r   ‹  s   ù‡ € ñ÷ò.÷ò r   r   c                   óF   a a€ ] tR tRt oRtRV 3R lltR tR tRtVt	V ;t
# )r  i»  a]  Image to Patch Unembedding

Args:
    img_size (int): Image size.  Default: 224.
    patch_size (int): Patch token size. Default: 4.
    in_chans (int): Number of input image channels. Default: 3.
    embed_dim (int): Number of linear projection output channels. Default: 96.
    norm_layer (nn.Module, optional): Normalization layer. Default: None
c                ó   <€ \         SV `  4        \        V4      p\        V4      pV^ ,          V^ ,          ,          V^,          V^,          ,          .pWn        W n        W`n        V^ ,          V^,          ,          V n        W0n        W@n        R# r  )	r   r   r   r÷   rø   r  r  rù   rú   r  s   &&&&&& €r   r   ÚPatchUnEmbed.__init__Æ  s€   ø€ ô 	‰ÑÔÜ˜XÓ&ˆÜ˜zÓ*ˆ
à�Q�K˜: a�=Õ(Ø�Q�K˜: a�=Õ(ð
Ðð !ŒØ$ŒØ"4ÔØ-¨aÕ0Ð3EÀaÕ3HÕHˆÔà ŒØ"Žr   c                óš   € VP                   w  r4pVP                  ^^4      P                  W0P                  V^ ,          V^,          4      pV# )rI   )r0   rh   r1   rú   )r   r!   rž   r5   ÚHWr8   s   &&&   r   r"   ÚPatchUnEmbed.forwardØ  s?   € Ø—7‘7‰ˆˆqØ�K‰K˜˜1Ó×"Ñ" 1§n¡n°f¸QµiÀÈÅÓKˆØˆr   c                ó
   € ^ pV# r…   © )r   r†   s   & r   r†   ÚPatchUnEmbed.flopsÝ  s   € ØˆØˆr   )rú   r÷   rù   r  rø   r  r  r  r,   s   @@r   r  r  »  s   ù‡ € ñ÷#ò$÷
ò r   r  c                   ó6   a a€ ] tR tRt oRtV 3R ltRtVtV ;t# )ÚUpsampleiâ  z‘Upsample module.

Args:
    scale (int): Scale factor. Supported scales: 2^n and 3.
    num_feat (int): Channel number of intermediate features.
c           
     ó4  <€ . pW^,
          ,          ^ 8X  d‡   \        \        \        P                  ! V^4      4      4       FX  pVP	                  \
        P                  ! V^V,          ^^^4      4       VP	                  \
        P                  ! ^4      4       KZ  	  MlV^8X  dW   VP	                  \
        P                  ! V^	V,          ^^^4      4       VP	                  \
        P                  ! ^4      4       M\        RV R24      h\        SV `(  ! V!   R# )rI   zscale z/ is not supported. Supported scales: 2^n and 3.N)rÜ   r<   ÚmathÚlogÚappendr   rü   ÚPixelShuffleÚ
ValueErrorr   r   )r   rK   Únum_featÚmÚ_r   s   &&&  €r   r   ÚUpsample.__init__ê  sÔ   ø€ ØˆØ˜Q•YÕ AÔ%Üœ3œtŸxšx¨¨qÓ1Ó2Ö3�Ø—‘œŸš 8¨Q°­\¸1¸aÀÓCÔDØ—‘œŸš¨Ó+Ö,ò 4ð �aŒZØ�H‰H”R—Y’Y˜x¨¨X­°q¸!¸QÓ?Ô@Ø�H‰H”R—_’_ QÓ'Õ(äØ˜˜ÐRÐRóð ô 	‰Ò˜!Ôr   r"  )	r$   r%   r&   r'   rˆ   r   r)   r*   r+   r,   s   @@r   r%  r%  â  s   ù‡ € ñ÷õ r   r%  c                   ó@   a a€ ] tR tRt oRtRV 3R lltR tRtVtV ;t	# )ÚUpsampleOneStepiú  a  UpsampleOneStep module (the difference with Upsample is that it always only has 1conv + 1pixelshuffle)
   Used in lightweight SR to save parameters.

Args:
    scale (int): Scale factor. Supported scales: 2^n and 3.
    num_feat (int): Channel number of intermediate features.

c           	     óö   <€ W n         W@n        . pVP                  \        P                  ! W!^,          V,          ^^^4      4       VP                  \        P
                  ! V4      4       \        SV `  ! V!   R# )rv   N)r,  rŽ   r)  r   rü   r*  r   r   )r   rK   r,  Ú
num_out_chrŽ   r-  r   s   &&&&& €r   r   ÚUpsampleOneStep.__init__  sY   ø€ Ø ŒØ 0ÔØˆØ	�‰”—’˜8¨Q¥h°*Õ%<¸aÀÀAÓFÔGØ	�‰”—’ Ó'Ô(Ü‰Ò˜!Ôr   c                óp   € V P                   w  rW,          V P                  ,          ^,          ^	,          pV# )r  ©rŽ   r,  rÓ   s   &   r   r†   ÚUpsampleOneStep.flops  s.   € Ø×$Ñ$‰ˆØ•˜Ÿ™Õ%¨Õ)¨AÕ-ˆØˆr   r6  r   )
r$   r%   r&   r'   rˆ   r   r†   r)   r*   r+   r,   s   @@r   r1  r1  ú  s   ù‡ € ñ÷÷ò r   r1  c            ,       ó@  a a€ ] tR tRt oRt/ tR^@R^R^R^`R. R+OR. R+OR	^R
RRRRRRRRRRRR]P                  RRRRRRR^RRRRRR R!^/V 3R" lltR# t	]
P                  P                  R$ 4       t]
P                  P                  R% 4       tR& tR' tR( tR) tR*tVtV ;t# ),ÚSwinIRi  aw  SwinIR
    A PyTorch impl of : `SwinIR: Image Restoration Using Swin Transformer`, based on Swin Transformer.

Args:
    img_size (int | tuple(int)): Input image size. Default 64
    patch_size (int | tuple(int)): Patch size. Default: 1
    in_chans (int): Number of input image channels. Default: 3
    embed_dim (int): Patch embedding dimension. Default: 96
    depths (tuple(int)): Depth of each Swin Transformer layer.
    num_heads (tuple(int)): Number of attention heads in different layers.
    window_size (int): Window size. Default: 7
    mlp_ratio (float): Ratio of mlp hidden dim to embedding dim. Default: 4
    qkv_bias (bool): If True, add a learnable bias to query, key, value. Default: True
    qk_scale (float): Override default qk scale of head_dim ** -0.5 if set. Default: None
    drop_rate (float): Dropout rate. Default: 0
    attn_drop_rate (float): Attention dropout rate. Default: 0
    drop_path_rate (float): Stochastic depth rate. Default: 0.1
    norm_layer (nn.Module): Normalization layer. Default: nn.LayerNorm.
    ape (bool): If True, add absolute position embedding to the patch embedding. Default: False
    patch_norm (bool): If True, add normalization after patch embedding. Default: True
    use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False
    upscale: Upscale factor. 2/3/4/8 for image SR, 1 for denoising and compress artifact reduction
    img_range: Image range. 1. or 255.
    upsampler: The reconstruction reconstruction module. 'pixelshuffle'/'pixelshuffledirect'/'nearest+conv'/None
    resi_connection: The convolutional block before residual connection. '1conv'/'3conv'
r÷   rø   rù   rú   ÚdepthsrJ   r4   r�   r‹   r\   Tr]   NÚ	drop_rater
   Úattn_drop_rateÚdrop_path_rategš™™™™™¹?r˜   ÚapeFÚ
patch_normrÚ   ÚupscaleÚ	img_rangeç      ð?Ú	upsamplerÚ r  rï   Ústart_unshufflec               óš  <€ \         S!V `  4        VV n        W0P                  ^,          ,          pTp^@pVV n        V^8X  d1   R p\        P
                  ! V4      P                  ^^^^4      V n        M\        P                  ! ^^^^4      V n        VV n	        VV n
        Wpn        \        P                  ! VV^^^4      V n        \        V4      V n        W@n        Wðn        VV n        W@n        W€n        \-        TTTTV P&                  '       d   TMRR7      V n        V P.                  P0                  pV P.                  P2                  pVV n        \5        TTTTV P&                  '       d   TMRR7      V n        V P$                  '       dI   \        P8                  ! \        P                  ! ^VV4      4      V n        \=        V P:                  RR7       \        P>                  ! VR7      V n         \        PB                  ! ^ V\E        V4      4       Uu. uF  pVPG                  4       NK  	  pp\        PH                  ! 4       V n%        \M        V P                   4       F¤  p\O        R!/ RVbRV^ ,          V^,          3bRVV,          bR	VV,          bR
VbRV P*                  bRV	bRV
bRVbRVbRV\E        VRV 4      \E        VRV^,            4       bRVbRRbRVbRVbRVbRVb p V PJ                  PQ                  V 4       K¦  	  V! V P(                  4      V n)        VR8X  d    \        P                  ! WD^^^4      V n*        MµVR8X  d¯   \        PV                  ! \        P                  ! WD^,          ^^^4      \        PX                  ! RRR7      \        P                  ! V^,          V^,          ^^^ 4      \        PX                  ! RRR7      \        P                  ! V^,          V^^^4      4      V n*        V P                  R8X  d|   \        PV                  ! \        P                  ! VV^^^4      \        PX                  ! RR7      4      V n-        \]        VV4      V n/        \        P                  ! VV^^^4      V n0        EM«V P                  R8X  d&   \c        VVVV^ ,          V^,          34      V n/        EMuV P                  R8X  EdE   \        PV                  ! \        P                  ! VV^^^4      \        PX                  ! RR7      4      V n-        \        P                  ! VV^^^4      V n2        V P                  ^8X  d!   \        P                  ! VV^^^4      V n3        MOV P                  ^8X  d?   \        P                  ! VV^^^4      V n3        \        P                  ! VV^^^4      V n4        \        P                  ! VV^^^4      V n5        \        P                  ! VV^^^4      V n0        \        PX                  ! RRR7      V n6        M\        P                  ! VV^^^4      V n0        V Po                  V Pp                  4       R# u upi )"rv   Nrö   rD   rE   )ÚprG   rŽ   rÙ   rJ   r4   r�   r\   r]   r   rW   r”   r˜   rà   rÚ   r÷   rø   r  rï   rñ   rò   Tró   Úpixelshuffle)rõ   Úpixelshuffledirectúnearest+conv)gšwœ¢#¹Ü?gï8EGrùÛ?gB`åÐ"ÛÙ?r"  )9r   r   rE  rA  rM   ÚTensorr1   ÚmeanrN   r@  rC  r4   r   rü   Ú
conv_firstÚlenÚ
num_layersrú   r>  r?  Únum_featuresr�   r   r  r  r  r  r  rL   Úabsolute_pos_embedr   r   Úpos_dropÚlinspacerT   ÚitemrÛ   ÚlayersrÜ   rî   r)  rÀ   Úconv_after_bodyrþ   rÿ   Úconv_before_upsampler%  ÚupsampleÚ	conv_lastr1  Úconv_up1Úconv_up2Úconv_up3Úconv_hrÚlreluÚapplyÚ_init_weights)"r   r÷   rø   rù   rú   r:  rJ   r4   r�   r\   r]   r;  r<  r=  r˜   r>  r?  rÚ   r@  rA  rC  r  rE  Ú	num_in_chr3  r,  Úrgb_meanr  r  r!   ÚdprÚi_layerÚlayerr   s"   &$$$$$$$$$$$$$$$$$$$$$$          €r   r   ÚSwinIR.__init__1  s~  ø€ ô4 	‰ÑÔØ.ˆÔØ×3Ñ3°QÕ6Õ6ˆ	Øˆ
ØˆØ"ˆŒØ�qŒ=Ø/ˆHÜŸš XÓ.×3Ñ3°A°q¸!¸QÓ?ˆD�IäŸš A q¨!¨QÓ/ˆDŒIØˆŒØ"ˆŒØ&Ôô Ÿ)š) I¨y¸!¸QÀÓBˆŒô ˜f›+ˆŒØ"ŒØŒØ$ˆŒØ%ÔØ"Œô &ØØ!ØØØ%)§_§_ _‘z¸$ô
ˆÔð ×&Ñ&×2Ñ2ˆØ!×-Ñ-×@Ñ@ÐØ"4ˆÔô *ØØ!ØØØ%)§_§_ _‘z¸$ô
ˆÔð �8�8ˆ8Ü&(§l¢lÜ—’˜A˜{¨IÓ6ó'ˆDÔ#ô ˜$×1Ñ1°tÕ<äŸ
š
 YÔ/ˆŒô $Ÿnšn¨Q°ÄÀFÃÔLó
ÙL˜ˆA�F‰FŽHÑLð 	ð 
ô
 —m’m“oˆŒÜ˜TŸ_™_Ö-ˆGÜò Ùðà"4°QÕ"7Ð9KÈAÕ9NÑ!Oðð ˜W–oðð $ GÖ,ð	ñ
 (ðð Ÿ.š.ðñ "ðñ "ðñ ðñ )ðð Ü˜˜x Ð(Ó)¬CØ˜} ¨1¥Ð-ó-ñðñ  &ð!ñ"  ð#ñ$  .ð%ñ& "ð'ñ( &ð)ñ* !0ð+ˆEð. �K‰K×Ñ˜uÖ%ñ1 .ñ2 ˜t×0Ñ0Ó1ˆŒ	ð ˜gÔ%Ü#%§9¢9¨YÀ1ÀaÈÓ#KˆDÕ Ø Ô'ä#%§=¢=Ü—	’	˜)°!¥^°Q¸¸1Ó=Ü—’¨C¸Ô>Ü—	’	˜) q�.¨)°q­.¸!¸QÀÓBÜ—’¨C¸Ô>Ü—	’	˜) q�.¨)°Q¸¸1Ó=ó$ˆDÔ ð �>‰>˜^Ô+ä(*¯ªÜ—	’	˜) X¨q°!°QÓ7¼¿ºÈdÔ9Só)ˆDÔ%ô % W¨hÓ7ˆDŒMÜŸYšY x°¸QÀÀ1ÓEˆDŽNØ�^‰^Ð3Ô3ä+ØØØØ# AÕ&Ð(:¸1Õ(=Ð>ó	ˆDŽMð �^‰^˜~Õ-ä(*¯ªÜ—	’	˜) X¨q°!°QÓ7¼¿ºÈdÔ9Só)ˆDÔ%ô ŸIšI h°¸!¸QÀÓBˆDŒMØ�|‰|˜qÔ Ü "§	¢	¨(°H¸aÀÀAÓ F�•Ø—‘ Ô"Ü "§	¢	¨(°H¸aÀÀAÓ F�”Ü "§	¢	¨(°H¸aÀÀAÓ F�”ÜŸ9š9 X¨x¸¸A¸qÓAˆDŒLÜŸYšY x°¸QÀÀ1ÓEˆDŒNÜŸš°SÀ$ÔGˆD�Jô  ŸYšY y°*¸aÀÀAÓFˆDŒNà�
‰
�4×%Ñ%Ö&ùòc
s   ÈYc                ó  € \        V\        P                  4      '       dv   \        VP                  R R7       \        V\        P                  4      '       d=   VP
                  e-   \        P                  P                  VP
                  ^ 4       R# R# R# \        V\        P                  4      '       dW   \        P                  P                  VP
                  ^ 4       \        P                  P                  VP                  R4       R# R# )rD   rE   NrB  )	rÝ   r   r   r   ÚweightrC   ÚinitÚ	constant_rº   )r   r-  s   &&r   r`  ÚSwinIR._init_weightsÙ  s¡   € Ü�aœŸ™×#Ò#Ü˜!Ÿ(™(¨Õ-Ü˜!œRŸY™Y×'Ò'¨A¯F©FÒ,>Ü—‘×!Ñ! !§&¡&¨!Ö,ñ -?Ñ'ä˜œ2Ÿ<™<×(Ò(Ü�G‰G×Ñ˜aŸf™f aÔ(Ü�G‰G×Ñ˜aŸh™h¨Ö,ñ )r   c                ó   € R 0# )rQ  r"  r�   s   &r   Úno_weight_decayÚSwinIR.no_weight_decayâ  s   € à$Ð%Ð%r   c                ó   € R 0# )rO   r"  r�   s   &r   Úno_weight_decay_keywordsÚSwinIR.no_weight_decay_keywordsæ  s   € à.Ð/Ð/r   c                ó0   € \        WP                  R R7      # )Úreflect)Úmode)r   r4   r    s   &&r   Úcheck_image_sizeÚSwinIR.check_image_sizeê  s   € Ü˜q×"2Ñ"2¸ÔCÐCr   c                óX  € VP                   ^,          VP                   ^,          3pV P                  V4      pV P                  '       d   WP                  ,           pV P	                  V4      pV P
                   F  pV! W4      pK  	  V P                  V4      pV P                  W4      pV# rÒ   )r0   r  r>  rQ  rR  rU  rÀ   r  )r   r!   rž   re  s   &&  r   Úforward_featuresÚSwinIR.forward_featuresí  s�   € Ø—'‘'˜!•*˜aŸg™g a�jÐ)ˆØ×Ñ˜QÓˆØ�8�8ˆ8Ø×+Ñ+Õ+ˆAØ�M‰M˜!Óˆà—[”[ˆEÙ�aÓ ŠAñ !ð �I‰I�a‹LˆØ×Ñ˜qÓ)ˆàˆr   c           
     óþ  € VP                   R ,          w  r#V P                  V4      pV P                  P                  V4      V n        WP                  ,
          V P                  ,          pV P
                  ^8”  d4   \        P                  P                  P                  WP
                  4      pV P                  R8X  dl   V P                  V4      pV P                  V P                  V4      4      V,           pV P                  V4      pV P                  V P!                  V4      4      pEM�V P                  R8X  dL   V P                  V4      pV P                  V P                  V4      4      V,           pV P!                  V4      pEM%V P                  R8X  EdÅ   V P                  V4      pV P                  V P                  V4      4      V,           pV P                  V4      pV P#                  V P%                  \        P                  P                  P'                  V^RR7      4      4      pV P(                  ^8X  dL   V P#                  V P+                  \        P                  P                  P'                  V^RR7      4      4      pM¥V P(                  ^8X  d•   V P#                  V P+                  \        P                  P                  P'                  V^RR7      4      4      pV P#                  V P-                  \        P                  P                  P'                  V^RR7      4      4      pV P                  V P#                  V P/                  V4      4      4      pMOV P                  V4      pV P                  V P                  V4      4      V,           pWP                  V4      ,           pWP                  ,          V P                  ,           pVRRRW P(                  ,          1RW0P(                  ,          13,          # ):rv   NNrH  rI  rJ  Únearest)Úscale_factorrt  rH   N)r0   ru  rL  Útype_asrA  rE  rM   r   Ú
functionalÚpixel_unshufflerC  rM  rV  rx  rW  rY  rX  r^  rZ  Úinterpolater@  r[  r\  r]  )r   r!   r6   r7   Úx_firstÚress   &&    r   r"   ÚSwinIR.forwardü  s#  € Ø�w‰w�r�{‰ˆØ×!Ñ! !Ó$ˆà—I‘I×%Ñ% aÓ(ˆŒ	Ø—‘�]˜dŸn™nÕ,ˆà×Ñ !Ô#Ü—‘×#Ñ#×3Ñ3°A×7KÑ7KÓLˆAà�>‰>˜^Ô+à—‘ Ó"ˆAØ×$Ñ$ T×%:Ñ%:¸1Ó%=Ó>ÀÕBˆAØ×)Ñ)¨!Ó,ˆAØ—‘˜tŸ}™}¨QÓ/Ó0ŠAØ�^‰^Ð3Ô3à—‘ Ó"ˆAØ×$Ñ$ T×%:Ñ%:¸1Ó%=Ó>ÀÕBˆAØ—‘˜aÓ ŠAØ�^‰^˜~Õ-à—‘ Ó"ˆAØ×$Ñ$ T×%:Ñ%:¸1Ó%=Ó>ÀÕBˆAØ×)Ñ)¨!Ó,ˆAØ—
‘
Ø—‘Ü—H‘H×'Ñ'×3Ñ3°AÀAÈIÐ3ÓVóóˆAð
 �|‰|˜qÔ Ø—J‘JØ—M‘MÜŸ™×+Ñ+×7Ñ7Ø¨A°Ið 8ó óó‘ð —‘ Ô"Ø—J‘JØ—M‘MÜŸ™×+Ñ+×7Ñ7Ø¨A°Ið 8ó óó�ð —J‘JØ—M‘MÜŸ™×+Ñ+×7Ñ7Ø¨A°Ið 8ó óó�ð —‘˜tŸz™z¨$¯,©,°q«/Ó:Ó;‰Að —o‘o aÓ(ˆGØ×&Ñ& t×'<Ñ'<¸WÓ'EÓFÈÕPˆCØ—N‘N 3Ó'Õ'ˆAà—‘Õ §¡Õ*ˆà��AÐ)˜Ÿ\™\Õ)Ð)Ð+=¨Q·±Õ-=Ð+=Ð=Õ>Ð>r   c                óÚ  € ^ pV P                   w  r#WV,          ^,          V P                  ,          ^	,          ,          pWP                  P                  4       ,          p\	        V P
                  4       F  w  rEWP                  4       ,          pK  	  WV,          ^,          V P                  ,          V P                  ,          ,          pWP                  P                  4       ,          pV# r…   )r  rú   r  r†   Ú	enumeraterU  rX  )r   r†   r6   r7   rá   re  s   &     r   r†   ÚSwinIR.flops=  s¨   € ØˆØ×&Ñ&‰ˆØ�Q•˜•˜TŸ^™^Õ+¨aÕ/Õ/ˆØ×!Ñ!×'Ñ'Ó)Õ)ˆÜ! $§+¡+Ö.‰HˆAØ—[‘[“]Õ"ŠEñ /à�Q•˜•˜TŸ^™^Õ+¨d¯n©nÕ<Õ<ˆØ—‘×$Ñ$Ó&Õ&ˆØˆr   )rQ  r>  rV  rW  rM  r]  rY  rZ  r[  r\  rú   rA  rU  r^  rL  r�   rÀ   rP  rO  r  r?  r  r  rR  rE  rX  rC  r@  r4   )é   r‡  r‡  r‡  )r$   r%   r&   r'   rˆ   Úhyperparametersr   rº   r   r`  rM   ÚjitÚignorerm  rp  ru  rx  r"   r†   r)   r*   r+   r,   s   @@r   r9  r9    sj  ù‡ € ñð6 €Oðf'ð ðf'ð ð	f'ð
 ðf'ð ðf'ò ðf'ò ðf'ð ðf'ð ðf'ð ðf'ð ðf'ð ðf'ð ðf'ð ðf'ð  —<‘<ð!f'ð" ð#f'ð$ ð%f'ð& ð'f'ð( ð)f'ð* ð+f'ð, ð-f'ð.  ð/f'ð0 ÷1f'òP-ð ‡Y�Y×Ññ&ó ð&ð ‡Y�Y×Ññ0ó ð0òDòò??÷B	ò 	r   r9  )r'  rM   Útorch.nnr   Útorch.utils.checkpointÚutilsrä   Úspandrel.utilr   Úspandrel.util.timmr   r   r   Ú__arch_helpers.paddingr   ÚModuler	   r:   r=   r?   rŠ   r¼   r×   rî   r   r  rþ   r%  r1  r9  r"  r   r   Ú<module>r’     s   ðó ã Ý ß +Ð +å /ß AÑ Aå 5ôˆ"�)‰)ô ò4ò"ô&~�b—i‘iô ~ôBu˜2Ÿ9™9ô uôp.�2—9‘9ô .ôb]�—‘ô ]ô@mˆ2�9‰9ô mô`-�—‘ô -ô`$�2—9‘9ô $ôNˆr�}‰}ô ô0�b—m‘mô ñ0 ÓôsˆR�Y‰Yó só òsr   