
    sgB              	          d Z ddlZddlZddlZddlmZ ddlmZm	Z	m
Z
 ddlZddlZddlmZ ddlmZmZmZ ddlmZ dd	lmZ dd
lmZ ddlmZmZmZ ddlmZmZmZm Z m!Z!m"Z"m#Z# ddl$m%Z% ddl&m'Z'  e!jP                  e)      Z*dZ+dZ,g dZ-dZ.dZ/e G d de             Z0e G d de             Z1e G d de             Z2e G d de             Z3d Z4d Z5 G d dejl                        Z7 G d  d!ejl                        Z8 G d" d#ejl                        Z9dLd$ejt                  d%e;d&e<d'ejt                  fd(Z= G d) d*ejl                        Z> G d+ d,ejl                        Z? G d- d.ejl                        Z@ G d/ d0ejl                        ZA G d1 d2ejl                        ZB G d3 d4ejl                        ZC G d5 d6ejl                        ZD G d7 d8ejl                        ZE G d9 d:ejl                        ZF G d; d<e      ZGd=ZHd>ZI ed?eHd@       G dA dBeG             ZJ edCeH       G dD dEeG             ZK edFeH       G dG dHeG             ZL edIeH       G dJ dKeGe%             ZMy)MzPyTorch Swin Transformer model.    N)	dataclass)OptionalTupleUnion)nn)BCEWithLogitsLossCrossEntropyLossMSELoss   )ACT2FN)BackboneOutput)PreTrainedModel) find_pruneable_heads_and_indicesmeshgridprune_linear_layer)ModelOutputadd_code_sample_docstringsadd_start_docstrings%add_start_docstrings_to_model_forwardloggingreplace_return_docstrings	torch_int)BackboneMixin   )
SwinConfigr   z&microsoft/swin-tiny-patch4-window7-224)r   1   i   ztabby, tabby catc                       e Zd ZU dZdZej                  ed<   dZe	e
ej                  df      ed<   dZe	e
ej                  df      ed<   dZe	e
ej                  df      ed<   y)SwinEncoderOutputa  
    Swin encoder's outputs, with potential hidden states and attentions.

    Args:
        last_hidden_state (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`):
            Sequence of hidden-states at the output of the last layer of the model.
        hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `torch.FloatTensor` (one for the output of the embeddings + one for the output of each stage) of
            shape `(batch_size, sequence_length, hidden_size)`.

            Hidden-states of the model at the output of each layer plus the initial embedding outputs.
        attentions (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `torch.FloatTensor` (one for each stage) of shape `(batch_size, num_heads, sequence_length,
            sequence_length)`.

            Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
            heads.
        reshaped_hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `torch.FloatTensor` (one for the output of the embeddings + one for the output of each stage) of
            shape `(batch_size, hidden_size, height, width)`.

            Hidden-states of the model at the output of each layer plus the initial embedding outputs reshaped to
            include the spatial dimensions.
    Nlast_hidden_state.hidden_states
attentionsreshaped_hidden_states)__name__
__module____qualname____doc__r   torchFloatTensor__annotations__r    r   r   r!   r"        Y/var/www/html/venv/lib/python3.12/site-packages/transformers/models/swin/modeling_swin.pyr   r   >   sx    2 ,0u((/=AM8E%"3"3S"89:A:>Ju00#567>FJHU5+<+<c+A%BCJr+   r   c                       e Zd ZU dZdZej                  ed<   dZe	ej                     ed<   dZ
e	eej                  df      ed<   dZe	eej                  df      ed<   dZe	eej                  df      ed<   y)	SwinModelOutputaT  
    Swin model's outputs that also contains a pooling of the last hidden states.

    Args:
        last_hidden_state (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`):
            Sequence of hidden-states at the output of the last layer of the model.
        pooler_output (`torch.FloatTensor` of shape `(batch_size, hidden_size)`, *optional*, returned when `add_pooling_layer=True` is passed):
            Average pooling of the last layer hidden-state.
        hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `torch.FloatTensor` (one for the output of the embeddings + one for the output of each stage) of
            shape `(batch_size, sequence_length, hidden_size)`.

            Hidden-states of the model at the output of each layer plus the initial embedding outputs.
        attentions (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `torch.FloatTensor` (one for each stage) of shape `(batch_size, num_heads, sequence_length,
            sequence_length)`.

            Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
            heads.
        reshaped_hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `torch.FloatTensor` (one for the output of the embeddings + one for the output of each stage) of
            shape `(batch_size, hidden_size, height, width)`.

            Hidden-states of the model at the output of each layer plus the initial embedding outputs reshaped to
            include the spatial dimensions.
    Nr   pooler_output.r    r!   r"   )r#   r$   r%   r&   r   r'   r(   r)   r/   r   r    r   r!   r"   r*   r+   r,   r.   r.   _   s    6 ,0u((/15M8E--.5=AM8E%"3"3S"89:A:>Ju00#567>FJHU5+<+<c+A%BCJr+   r.   c                      e Zd ZU dZdZeej                     ed<   dZ	ej                  ed<   dZ
eeej                  df      ed<   dZeeej                  df      ed<   dZeeej                  df      ed<   ed	        Zy)
SwinMaskedImageModelingOutputa  
    Swin masked image model outputs.

    Args:
        loss (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `bool_masked_pos` is provided):
            Masked image modeling (MLM) loss.
        reconstruction (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
            Reconstructed pixel values.
        hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `torch.FloatTensor` (one for the output of the embeddings + one for the output of each stage) of
            shape `(batch_size, sequence_length, hidden_size)`.

            Hidden-states of the model at the output of each layer plus the initial embedding outputs.
        attentions (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `torch.FloatTensor` (one for each stage) of shape `(batch_size, num_heads, sequence_length,
            sequence_length)`.

            Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
            heads.
        reshaped_hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `torch.FloatTensor` (one for the output of the embeddings + one for the output of each stage) of
            shape `(batch_size, hidden_size, height, width)`.

            Hidden-states of the model at the output of each layer plus the initial embedding outputs reshaped to
            include the spatial dimensions.
    Nlossreconstruction.r    r!   r"   c                 N    t        j                  dt               | j                  S )Nzlogits attribute is deprecated and will be removed in version 5 of Transformers. Please use the reconstruction attribute to retrieve the final output instead.)warningswarnFutureWarningr3   selfs    r,   logitsz$SwinMaskedImageModelingOutput.logits   s%    ]	

 """r+   )r#   r$   r%   r&   r2   r   r'   r(   r)   r3   r    r   r!   r"   propertyr:   r*   r+   r,   r1   r1      s    6 )-D(5$$
%,(,NE%%,=AM8E%"3"3S"89:A:>Ju00#567>FJHU5+<+<c+A%BCJ# #r+   r1   c                       e Zd ZU dZdZeej                     ed<   dZ	ej                  ed<   dZ
eeej                  df      ed<   dZeeej                  df      ed<   dZeeej                  df      ed<   y)	SwinImageClassifierOutputa  
    Swin outputs for image classification.

    Args:
        loss (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided):
            Classification (or regression if config.num_labels==1) loss.
        logits (`torch.FloatTensor` of shape `(batch_size, config.num_labels)`):
            Classification (or regression if config.num_labels==1) scores (before SoftMax).
        hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `torch.FloatTensor` (one for the output of the embeddings + one for the output of each stage) of
            shape `(batch_size, sequence_length, hidden_size)`.

            Hidden-states of the model at the output of each layer plus the initial embedding outputs.
        attentions (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
            Tuple of `torch.FloatTensor` (one for each stage) of shape `(batch_size, num_heads, sequence_length,
            sequence_length)`.

            Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
            heads.
        reshaped_hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `torch.FloatTensor` (one for the output of the embeddings + one for the output of each stage) of
            shape `(batch_size, hidden_size, height, width)`.

            Hidden-states of the model at the output of each layer plus the initial embedding outputs reshaped to
            include the spatial dimensions.
    Nr2   r:   .r    r!   r"   )r#   r$   r%   r&   r2   r   r'   r(   r)   r:   r    r   r!   r"   r*   r+   r,   r=   r=      s    6 )-D(5$$
%, $FE$=AM8E%"3"3S"89:A:>Ju00#567>FJHU5+<+<c+A%BCJr+   r=   c                     | j                   \  }}}}| j                  |||z  |||z  ||      } | j                  dddddd      j                         j                  d|||      }|S )z2
    Partitions the given input into windows.
    r   r   r            shapeviewpermute
contiguous)input_featurewindow_size
batch_sizeheightwidthnum_channelswindowss          r,   window_partitionrO      s}     /<.A.A+J|!&&Fk);8Lk[gM ##Aq!Q15@@BGGKYdfrsGNr+   c                     | j                   d   }| j                  d||z  ||z  |||      } | j                  dddddd      j                         j                  d|||      } | S )z?
    Merges windows to produce higher resolution features.
    rB   r   r   r   r?   r@   rA   rC   )rN   rI   rK   rL   rM   s        r,   window_reverserQ      sn     ==$Lll2v4e{6JKYdfrsGooaAq!Q/::<AA"feUabGNr+   c            
            e Zd ZdZd fd	Zdej                  dededej                  fdZ	 	 dde	ej                     d	e	ej                     d
edeej                     fdZ xZS )SwinEmbeddingszW
    Construct the patch and position embeddings. Optionally, also the mask token.
    c                 ~   t         |           t        |      | _        | j                  j                  }| j                  j
                  | _        |r4t        j                  t        j                  dd|j                              nd | _        |j                  r=t        j                  t        j                  d|dz   |j                              | _        nd | _        t        j                  |j                        | _        t        j"                  |j$                        | _        |j(                  | _        || _        y )Nr   )super__init__SwinPatchEmbeddingspatch_embeddingsnum_patches	grid_size
patch_gridr   	Parameterr'   zeros	embed_dim
mask_tokenuse_absolute_embeddingsposition_embeddings	LayerNormnormDropouthidden_dropout_probdropout
patch_sizeconfig)r9   rh   use_mask_tokenrY   	__class__s       r,   rV   zSwinEmbeddings.__init__   s     3F ;++77//99O]",,u{{1a9I9I'JKcg))')||EKK;QR?TZTdTd4e'fD$'+D$LL!1!12	zz&"<"<= ++r+   
embeddingsrK   rL   returnc                    |j                   d   dz
  }| j                  j                   d   dz
  }t        j                  j	                         s||k(  r||k(  r| j                  S | j                  ddddf   }| j                  ddddf   }|j                   d   }|| j
                  z  }	|| j
                  z  }
t        |dz        }|j                  d|||      }|j                  dddd      }t        j                  j                  ||	|
fdd	
      }|j                  dddd      j                  dd|      }t        j                  ||fd      S )a   
        This method allows to interpolate the pre-trained position encodings, to be able to use the model on higher resolution
        images. This method is also adapted to support torch.jit tracing.

        Adapted from:
        - https://github.com/facebookresearch/dino/blob/de9ee3df6cf39fac952ab558447af1fa1365362a/vision_transformer.py#L174-L194, and
        - https://github.com/facebookresearch/dinov2/blob/e1277af2ba9496fbadf7aec6eba56e8d882d1e35/dinov2/models/vision_transformer.py#L179-L211
        r   NrB         ?r   r   r?   bicubicF)sizemodealign_cornersdim)rD   ra   r'   jit
is_tracingrg   r   reshaperF   r   
functionalinterpolaterE   cat)r9   rk   rK   rL   rY   num_positionsclass_pos_embedpatch_pos_embedrt   
new_height	new_widthsqrt_num_positionss               r,   interpolate_pos_encodingz'SwinEmbeddings.interpolate_pos_encoding  s`    !&&q)A-0066q9A= yy##%+*F6UZ?+++221bqb59221ab59r"t.
T__,	&}c'9:)11!5GI[]`a)11!Q1=--33i(	 4 
 *11!Q1=BB1b#Nyy/?;CCr+   pixel_valuesbool_masked_posr   c                    |j                   \  }}}}| j                  |      \  }}	| j                  |      }|j                         \  }
}}|K| j                  j                  |
|d      }|j                  d      j                  |      }|d|z
  z  ||z  z   }| j                  (|r|| j                  |||      z   }n|| j                  z   }| j                  |      }||	fS )NrB         ?)rD   rX   rc   rp   r_   expand	unsqueezetype_asra   r   rf   )r9   r   r   r   _rM   rK   rL   rk   output_dimensionsrJ   seq_lenmask_tokensmasks                 r,   forwardzSwinEmbeddings.forward*  s     *6););&<(,(=(=l(K%
%YYz*
!+!2
GQ&//00WbIK",,R088ED#sTz2[45GGJ##/''$*G*G
TZ\a*bb
'$*B*BB
\\*-
,,,r+   )F)NF)r#   r$   r%   r&   rV   r'   Tensorintr   r   r(   
BoolTensorboolr   r   __classcell__rj   s   @r,   rS   rS      s    &&D5<< &D &DUX &D]b]i]i &DV 7;).	-u001- "%"2"23- #'	-
 
u||	-r+   rS   c                   v     e Zd ZdZ fdZd Zdeej                     de	ej                  e	e   f   fdZ xZS )rW   z
    This class turns `pixel_values` of shape `(batch_size, num_channels, height, width)` into the initial
    `hidden_states` (patch embeddings) of shape `(batch_size, seq_length, hidden_size)` to be consumed by a
    Transformer.
    c                    t         |           |j                  |j                  }}|j                  |j
                  }}t        |t        j                  j                        r|n||f}t        |t        j                  j                        r|n||f}|d   |d   z  |d   |d   z  z  }|| _        || _        || _        || _
        |d   |d   z  |d   |d   z  f| _        t        j                  ||||      | _        y )Nr   r   )kernel_sizestride)rU   rV   
image_sizerg   rM   r^   
isinstancecollectionsabcIterablerY   rZ   r   Conv2d
projection)r9   rh   r   rg   rM   hidden_sizerY   rj   s          r,   rV   zSwinPatchEmbeddings.__init__M  s    !'!2!2F4E4EJ
$*$7$79I9Ik#-j+//:R:R#SZZdfpYq
#-j+//:R:R#SZZdfpYq
!!}
15*Q-:VW=:XY$$(&$Q-:a=8*Q-:VW=:XY))L+:^hir+   c                 n   || j                   d   z  dk7  rDd| j                   d   || j                   d   z  z
  f}t        j                  j                  ||      }|| j                   d   z  dk7  rFddd| j                   d   || j                   d   z  z
  f}t        j                  j                  ||      }|S )Nr   r   )rg   r   rx   pad)r9   r   rK   rL   
pad_valuess        r,   	maybe_padzSwinPatchEmbeddings.maybe_pad\  s    4??1%%*T__Q/%$//!:L2LLMJ==,,\:FLDOOA&&!+Q4??1#5QRAS8S#STJ==,,\:FLr+   r   rl   c                     |j                   \  }}}}| j                  |||      }| j                  |      }|j                   \  }}}}||f}|j                  d      j	                  dd      }||fS )Nr?   r   )rD   r   r   flatten	transpose)r9   r   r   rM   rK   rL   rk   r   s           r,   r   zSwinPatchEmbeddings.forwarde  s}    )5););&<~~lFEB__\2
(..1fe#UO''*44Q:
,,,r+   )r#   r$   r%   r&   rV   r   r   r'   r(   r   r   r   r   r   r   s   @r,   rW   rW   F  sF    j	-HU->->$? 	-E%,,X]^aXbJbDc 	-r+   rW   c            	            e Zd ZdZej
                  fdee   dedej                  ddf fdZ	d Z
d	ej                  d
eeef   dej                  fdZ xZS )SwinPatchMerginga'  
    Patch Merging Layer.

    Args:
        input_resolution (`Tuple[int]`):
            Resolution of input feature.
        dim (`int`):
            Number of input channels.
        norm_layer (`nn.Module`, *optional*, defaults to `nn.LayerNorm`):
            Normalization layer class.
    input_resolutionrt   
norm_layerrl   Nc                     t         |           || _        || _        t	        j
                  d|z  d|z  d      | _         |d|z        | _        y )Nr@   r?   Fbias)rU   rV   r   rt   r   Linear	reductionrc   )r9   r   rt   r   rj   s       r,   rV   zSwinPatchMerging.__init__~  sI     01s7AG%@q3w'	r+   c                     |dz  dk(  xs |dz  dk(  }|r.ddd|dz  d|dz  f}t         j                  j                  ||      }|S )Nr?   r   r   )r   rx   r   )r9   rH   rK   rL   
should_padr   s         r,   r   zSwinPatchMerging.maybe_pad  sU    qjAo:519>
Q519a!<JMM--mZHMr+   rH   input_dimensionsc                    |\  }}|j                   \  }}}|j                  ||||      }| j                  |||      }|d d dd ddd dd d f   }|d d dd ddd dd d f   }	|d d dd ddd dd d f   }
|d d dd ddd dd d f   }t        j                  ||	|
|gd      }|j                  |dd|z        }| j                  |      }| j                  |      }|S )Nr   r?   r   rB   r@   )rD   rE   r   r'   rz   rc   r   )r9   rH   r   rK   rL   rJ   rt   rM   input_feature_0input_feature_1input_feature_2input_feature_3s               r,   r   zSwinPatchMerging.forward  s   ((5(;(;%
C%**:vulS}feD'14a4Aq(89'14a4Aq(89'14a4Aq(89'14a4Aq(89		?O_Ve"fhjk%**:r1|;KL		-0}5r+   )r#   r$   r%   r&   r   rb   r   r   ModulerV   r   r'   r   r   r   r   s   @r,   r   r   q  sr    
 XZWcWc (s (# (299 (hl (U\\ U3PS8_ Y^YeYe r+   r   input	drop_probtrainingrl   c                    |dk(  s|s| S d|z
  }| j                   d   fd| j                  dz
  z  z   }|t        j                  || j                  | j
                        z   }|j                          | j                  |      |z  }|S )aF  
    Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

    Comment by Ross Wightman: This is the same as the DropConnect impl I created for EfficientNet, etc networks,
    however, the original name is misleading as 'Drop Connect' is a different form of dropout in a separate paper...
    See discussion: https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 ... I've opted for changing the
    layer and argument names to 'drop path' rather than mix DropConnect as a layer name and use 'survival rate' as the
    argument.
            r   r   )r   dtypedevice)rD   ndimr'   randr   r   floor_div)r   r   r   	keep_probrD   random_tensoroutputs          r,   	drop_pathr     s     CxII[[^

Q 77E

5ELL YYMYYy!M1FMr+   c                   x     e Zd ZdZd	dee   ddf fdZdej                  dej                  fdZ	de
fdZ xZS )
SwinDropPathzXDrop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).Nr   rl   c                 0    t         |           || _        y N)rU   rV   r   )r9   r   rj   s     r,   rV   zSwinDropPath.__init__  s    "r+   r    c                 D    t        || j                  | j                        S r   )r   r   r   r9   r    s     r,   r   zSwinDropPath.forward  s    FFr+   c                 8    dj                  | j                        S )Nzp={})formatr   r8   s    r,   
extra_reprzSwinDropPath.extra_repr  s    }}T^^,,r+   r   )r#   r$   r%   r&   r   floatrV   r'   r   r   strr   r   r   s   @r,   r   r     sG    b#(5/ #T #GU\\ Gell G-C -r+   r   c                        e Zd Z fdZd Z	 	 	 d	dej                  deej                     deej                     dee	   de
ej                     f
dZ xZS )
SwinSelfAttentionc                    t         |           ||z  dk7  rt        d| d| d      || _        t	        ||z        | _        | j                  | j
                  z  | _        t        |t        j                  j                        r|n||f| _        t        j                  t        j                  d| j                  d   z  dz
  d| j                  d   z  dz
  z  |            | _        t        j"                  | j                  d         }t        j"                  | j                  d         }t        j$                  t'        ||gd            }t        j(                  |d      }|d d d d d f   |d d d d d f   z
  }	|	j+                  ddd      j-                         }	|	d d d d dfxx   | j                  d   dz
  z  cc<   |	d d d d dfxx   | j                  d   dz
  z  cc<   |	d d d d dfxx   d| j                  d   z  dz
  z  cc<   |	j/                  d	      }
| j1                  d
|
       t        j2                  | j                  | j                  |j4                        | _        t        j2                  | j                  | j                  |j4                        | _        t        j2                  | j                  | j                  |j4                        | _        t        j<                  |j>                        | _         y )Nr   zThe hidden size (z6) is not a multiple of the number of attention heads ()r?   r   ij)indexingrB   relative_position_indexr   )!rU   rV   
ValueErrornum_attention_headsr   attention_head_sizeall_head_sizer   r   r   r   rI   r   r\   r'   r]   relative_position_bias_tablearangestackr   r   rF   rG   sumregister_bufferr   qkv_biasquerykeyvaluerd   attention_probs_dropout_probrf   )r9   rh   rt   	num_headsrI   coords_hcoords_wcoordscoords_flattenrelative_coordsr   rj   s              r,   rV   zSwinSelfAttention.__init__  s   ?a#C5(^_h^iijk  $- #&sY#7 !558P8PP%k;??3K3KLKS^`kRl 	 -/LLKKT--a0014T=M=Ma=P9PST9TUW`a-
)
 << 0 0 34<< 0 0 34Xx&:TJKvq1(At4~aqj7QQ)11!Q:EEG1a D$4$4Q$7!$;; 1a D$4$4Q$7!$;; 1a A(8(8(;$;a$?? "1"5"5b"968OPYYt1143E3EFOO\
99T//1C1C&//ZYYt1143E3EFOO\
zz&"E"EFr+   c                     |j                         d d | j                  | j                  fz   }|j                  |      }|j	                  dddd      S )NrB   r   r?   r   r   )rp   r   r   rE   rF   )r9   xnew_x_shapes      r,   transpose_for_scoresz&SwinSelfAttention.transpose_for_scores  sL    ffhsmt'?'?AYAY&ZZFF;yyAq!$$r+   r    attention_mask	head_maskoutput_attentionsrl   c                    |j                   \  }}}| j                  |      }| j                  | j                  |            }	| j                  | j	                  |            }
| j                  |      }t        j                  ||	j                  dd            }|t        j                  | j                        z  }| j                  | j                  j                  d         }|j                  | j                  d   | j                  d   z  | j                  d   | j                  d   z  d      }|j                  ddd      j!                         }||j#                  d      z   }|r|j                   d   }|j                  ||z  || j$                  ||      }||j#                  d      j#                  d      z   }|j                  d| j$                  ||      }t&        j(                  j+                  |d      }| j-                  |      }|||z  }t        j                  ||
      }|j                  dddd      j!                         }|j/                         d d | j0                  fz   }|j                  |      }|r||f}|S |f}|S )NrB   r   r   r?   rs   r   )rD   r   r   r   r   r'   matmulr   mathsqrtr   r   r   rE   rI   rF   rG   r   r   r   rx   softmaxrf   rp   r   )r9   r    r   r   r   rJ   rt   rM   mixed_query_layer	key_layervalue_layerquery_layerattention_scoresrelative_position_bias
mask_shapeattention_probscontext_layernew_context_layer_shapeoutputss                      r,   r   zSwinSelfAttention.forward  s    )6(;(;%
C JJ}5--dhh}.EF	//

=0IJ//0AB !<<Y5H5HR5PQ+dii8P8P.QQ!%!B!B4C_C_CdCdegCh!i!7!<!<Q$"2"21"55t7G7G7JTM]M]^_M`7`bd"
 "8!?!?1a!H!S!S!U+.D.N.Nq.QQ%'--a0J/44j(*d6N6NPSUX   0.2J2J12M2W2WXY2ZZ/44R9Q9QSVX[\ --//0@b/I ,,7  -	9O_kB%--aAq9DDF"/"4"4"6s";t?Q?Q>S"S%**+BC6G=/2 O\M]r+   NNF)r#   r$   r%   rV   r   r'   r   r   r(   r   r   r   r   r   s   @r,   r   r     sv    #GJ% 7;15,16||6 !!2!236 E--.	6
 $D>6 
u||	6r+   r   c                   n     e Zd Z fdZdej
                  dej
                  dej
                  fdZ xZS )SwinSelfOutputc                     t         |           t        j                  ||      | _        t        j
                  |j                        | _        y r   )rU   rV   r   r   denserd   r   rf   r9   rh   rt   rj   s      r,   rV   zSwinSelfOutput.__init__0  s6    YYsC(
zz&"E"EFr+   r    input_tensorrl   c                 J    | j                  |      }| j                  |      }|S r   r  rf   )r9   r    r  s      r,   r   zSwinSelfOutput.forward5  s$    

=1]3r+   r#   r$   r%   rV   r'   r   r   r   r   s   @r,   r
  r
  /  s2    G
U\\  RWR^R^ r+   r
  c                        e Zd Z fdZd Z	 	 	 d	dej                  deej                     deej                     dee	   de
ej                     f
dZ xZS )
SwinAttentionc                     t         |           t        ||||      | _        t	        ||      | _        t               | _        y r   )rU   rV   r   r9   r
  r   setpruned_heads)r9   rh   rt   r   rI   rj   s        r,   rV   zSwinAttention.__init__=  s8    %fc9kJ	$VS1Er+   c                 >   t        |      dk(  ry t        || j                  j                  | j                  j                  | j
                        \  }}t        | j                  j                  |      | j                  _        t        | j                  j                  |      | j                  _        t        | j                  j                  |      | j                  _	        t        | j                  j                  |d      | j                  _        | j                  j                  t        |      z
  | j                  _        | j                  j                  | j                  j                  z  | j                  _        | j
                  j                  |      | _        y )Nr   r   rs   )lenr   r9   r   r   r  r   r   r   r   r   r  r   union)r9   headsindexs      r,   prune_headszSwinAttention.prune_headsC  s   u:?749900$))2O2OQUQbQb
u
 -TYY__eD		*499==%@		,TYY__eD		.t{{/@/@%QO )-		(E(EE
(R		%"&))"?"?$))B_B_"_		 --33E:r+   r    r   r   r   rl   c                 j    | j                  ||||      }| j                  |d   |      }|f|dd  z   }|S )Nr   r   )r9   r   )r9   r    r   r   r   self_outputsattention_outputr  s           r,   r   zSwinAttention.forwardU  sG     yy	K\];;|AF#%QR(88r+   r  )r#   r$   r%   rV   r  r'   r   r   r(   r   r   r   r   r   s   @r,   r  r  <  st    ";* 7;15,1
||
 !!2!23
 E--.	

 $D>
 
u||	
r+   r  c                   V     e Zd Z fdZdej
                  dej
                  fdZ xZS )SwinIntermediatec                    t         |           t        j                  |t	        |j
                  |z              | _        t        |j                  t              rt        |j                     | _        y |j                  | _        y r   )rU   rV   r   r   r   	mlp_ratior  r   
hidden_actr   r   intermediate_act_fnr  s      r,   rV   zSwinIntermediate.__init__c  sa    YYsC(8(83(>$?@
f''-'-f.?.?'@D$'-'8'8D$r+   r    rl   c                 J    | j                  |      }| j                  |      }|S r   )r  r%  r   s     r,   r   zSwinIntermediate.forwardk  s&    

=100?r+   r  r   s   @r,   r!  r!  b  s#    9U\\ ell r+   r!  c                   V     e Zd Z fdZdej
                  dej
                  fdZ xZS )
SwinOutputc                     t         |           t        j                  t	        |j
                  |z        |      | _        t        j                  |j                        | _	        y r   )
rU   rV   r   r   r   r#  r  rd   re   rf   r  s      r,   rV   zSwinOutput.__init__r  sF    YYs6#3#3c#9:C@
zz&"<"<=r+   r    rl   c                 J    | j                  |      }| j                  |      }|S r   r  r   s     r,   r   zSwinOutput.forwardw  s$    

=1]3r+   r  r   s   @r,   r(  r(  q  s#    >
U\\ ell r+   r(  c                        e Zd Zd fd	Zd Zd Zd Z	 	 	 ddej                  de	e
e
f   deej                     dee   d	ee   d
e	ej                  ej                  f   fdZ xZS )	SwinLayerc                    t         |           |j                  | _        || _        |j                  | _        || _        t        j                  ||j                        | _	        t        |||| j                        | _        |dkD  rt        |      nt        j                         | _        t        j                  ||j                        | _        t!        ||      | _        t%        ||      | _        y )Neps)rI   r   )rU   rV   chunk_size_feed_forward
shift_sizerI   r   r   rb   layer_norm_epslayernorm_beforer  	attentionr   Identityr   layernorm_afterr!  intermediater(  r   )r9   rh   rt   r   r   drop_path_rater1  rj   s          r,   rV   zSwinLayer.__init__~  s    '-'E'E$$!-- 0 "Sf6K6K L&vsI4K[K[\9G#9Mn5SUS^S^S`!||CV5J5JK,VS9 -r+   c                    t        |      | j                  k  rgt        d      | _        t        j
                  j                         r(t	        j                   t	        j                  |            n
t        |      | _        y y Nr   )minrI   r   r1  r'   ru   rv   tensor)r9   r   s     r,   set_shift_and_window_sizez#SwinLayer.set_shift_and_window_size  s\     D$4$44'lDO=BYY=Q=Q=S		%,,'789Y\]mYn  5r+   c           	         | j                   dkD  rzt        j                  d||df||      }t        d| j                         t        | j                   | j                          t        | j                    d       f}t        d| j                         t        | j                   | j                          t        | j                    d       f}d}|D ]  }	|D ]  }
||d d |	|
d d f<   |dz  }  t        || j                        }|j                  d| j                  | j                  z        }|j                  d      |j                  d      z
  }|j                  |dk7  t        d            j                  |dk(  t        d            }|S d }|S )Nr   r   r   rB   r?   g      Yr   )
r1  r'   r]   slicerI   rO   rE   r   masked_fillr   )r9   rK   rL   r   r   img_maskheight_sliceswidth_slicescountheight_slicewidth_slicemask_windows	attn_masks                r,   get_attn_maskzSwinLayer.get_attn_mask  s   ??Q{{Avua#8fUHa$***+t'''$//)9:t&-M a$***+t'''$//)9:t&-L
 E - #/ K@EHQk1<=QJE
 ,Hd6F6FGL',,R1A1ADDTDT1TUL$..q1L4J4J14MMI!--i1neFmLXXYbfgYginoristI  Ir+   c                     | j                   || j                   z  z
  | j                   z  }| j                   || j                   z  z
  | j                   z  }ddd|d|f}t        j                  j                  ||      }||fS r:  )rI   r   rx   r   )r9   r    rK   rL   	pad_right
pad_bottomr   s          r,   r   zSwinLayer.maybe_pad  s    %%0@0@(@@DDTDTT	&&$2B2B)BBdFVFVV
Ay!Z8
))-Dj((r+   r    r   r   r   always_partitionrl   c                    |s| j                  |       n	 |\  }}|j                         \  }}	}
|}| j                  |      }|j                  ||||
      }| j	                  |||      \  }}|j
                  \  }	}}}	| j                  dkD  r1t        j                  || j                   | j                   fd      }n|}t        || j                        }|j                  d| j                  | j                  z  |
      }| j                  |||j                  |j                        }| j                  ||||      }|d   }|j                  d| j                  | j                  |
      }t        || j                  ||      }| j                  dkD  r/t        j                  || j                  | j                  fd      }n|}|d   dkD  xs |d   dkD  }|r|d d d |d |d d f   j!                         }|j                  |||z  |
      }|| j#                  |      z   }| j%                  |      }| j'                  |      }|| j)                  |      z   }|r	||d	   f}|S |f}|S )
Nr   )r   r?   )shiftsdimsrB   r   )r   r   rA   r   )r=  rp   r3  rE   r   rD   r1  r'   rollrO   rI   rI  r   r   r4  rQ   rG   r   r6  r7  r   )r9   r    r   r   r   rM  rK   rL   rJ   r   channelsshortcutr   
height_pad	width_padshifted_hidden_stateshidden_states_windowsrH  attention_outputsr  attention_windowsshifted_windows
was_paddedlayer_outputlayer_outputss                            r,   r   zSwinLayer.forward  s     **+;<("/"4"4"6
Ax --m<%**:vuhO %)NN=&%$P!z&3&9&9#:y!??Q$)JJ}tFVY]YhYhXhEipv$w!$1! !11FHXHX Y 5 : :2t?O?ORVRbRb?bdl m&&	)<)<EZEaEa ' 
	 !NN!9iK\ + 
 -Q/,11"d6F6FHXHXZbc():D<L<LjZcd ??Q %

?DOOUYUdUdCelr s /]Q&;*Q-!*;
 1!WfWfufa2G H S S U-22:v~xX 4>>2C#DD++M:((6$t{{<'@@@Q'8';< YeWfr+   )r   r   NFF)r#   r$   r%   rV   r=  rI  r   r'   r   r   r   r   r(   r   r   r   r   s   @r,   r,  r,  }  s    .8) 26,1+0A||A  S/A E--.	A
 $D>A #4.A 
u||U\\)	*Ar+   r,  c                        e Zd Z fdZ	 	 	 d	dej
                  deeef   deej                     dee
   dee
   deej
                     fdZ xZS )
	SwinStagec                 h   t         	|           || _        || _        t	        j
                  t        |      D cg c]-  }t        ||||||   |dz  dk(  rdn|j                  dz        / c}      | _	        |& |||t        j                        | _        d| _        y d | _        d| _        y c c}w )Nr?   r   )rh   rt   r   r   r8  r1  )rt   r   F)rU   rV   rh   rt   r   
ModuleListranger,  rI   blocksrb   
downsamplepointing)
r9   rh   rt   r   depthr   r   re  irj   s
            r,   rV   zSwinStage.__init__  s    mm u
  !%5'#,Q<%&UaZqf6H6HA6M

 !()9sr||\DO  #DO'
s   2B/r    r   r   r   rM  rl   c                    |\  }}t        | j                        D ]  \  }}	|||   nd }
 |	|||
||      }|d   }! |}| j                  )|dz   dz  |dz   dz  }}||||f}| j                  ||      }n||||f}|||f}|r|dd  z  }|S )Nr   r   r?   )	enumeraterd  re  )r9   r    r   r   r   rM  rK   rL   rh  layer_modulelayer_head_maskr]  !hidden_states_before_downsamplingheight_downsampledwidth_downsampledr   stage_outputss                    r,   r   zSwinStage.forward  s     )(5 	-OA|.7.CilO(/BSUeM *!,M	- -:)??&5;aZA4EPQ	VWGW 1!'0BDU V OO,MO_`M!' >&(IK\]]12..Mr+   r^  )r#   r$   r%   rV   r'   r   r   r   r   r(   r   r   r   r   s   @r,   r`  r`    sz    < 26,1+0||  S/ E--.	
 $D> #4. 
u||	r+   r`  c                        e Zd Z fdZ	 	 	 	 	 	 ddej
                  deeef   deej                     dee
   dee
   dee
   dee
   d	ee
   d
eeef   fdZ xZS )SwinEncoderc                    t         |           t        |j                        | _        || _        t        j                  d|j                  t        |j                              D cg c]  }|j                          }}t        j                  t        | j                        D cg c]  }t        |t        |j                   d|z  z        |d   d|z  z  |d   d|z  z  f|j                  |   |j"                  |   |t        |j                  d |       t        |j                  d |dz           || j                  dz
  k  rt$        nd        c}      | _        d| _        y c c}w c c}w )Nr   r?   r   )rh   rt   r   rg  r   r   re  F)rU   rV   r  depths
num_layersrh   r'   linspacer8  r   itemr   rb  rc  r`  r   r^   r   r   layersgradient_checkpointing)r9   rh   rZ   r   dpri_layerrj   s         r,   rV   zSwinEncoder.__init__7  sJ   fmm,!&63H3H#fmmJ\!]^Aqvvx^^mm  %T__5  !F,,q'z9:&/lq'z&BIaLUVX_U_D`%a --0$..w7!#fmmHW&=">V]]S`U\_`U`EaAbc4;dooPQ>Q4Q/X\
 ',#! _s   'E$&B*E)r    r   r   r   output_hidden_states(output_hidden_states_before_downsamplingrM  return_dictrl   c	           	      Z   |rdnd }	|rdnd }
|rdnd }|rE|j                   \  }}} |j                  |g|| }|j                  dddd      }|	|fz  }	|
|fz  }
t        | j                        D ]  \  }}|||   nd }| j
                  r-| j                  r!| j                  |j                  |||||      }n ||||||      }|d   }|d   }|d   }|d   |d   f}|rP|rN|j                   \  }}} |j                  |g|d   |d   f| }|j                  dddd      }|	|fz  }	|
|fz  }
nI|rG|sE|j                   \  }}} |j                  |g|| }|j                  dddd      }|	|fz  }	|
|fz  }
|s||dd  z  } |st        d ||	|fD              S t        ||	||
	      S )
Nr*   r   r   r   r?   r   rB   c              3   &   K   | ]	  }||  y wr   r*   ).0vs     r,   	<genexpr>z&SwinEncoder.forward.<locals>.<genexpr>  s     mq_`_lms   )r   r    r!   r"   )rD   rE   rF   rj  rx  ry  r   _gradient_checkpointing_func__call__tupler   )r9   r    r   r   r   r|  r}  rM  r~  all_hidden_statesall_reshaped_hidden_statesall_self_attentionsrJ   r   r   reshaped_hidden_staterh  rk  rl  r]  rm  r   s                         r,   r   zSwinEncoder.forwardM  s    #7BD+?RT"$5b4)6)<)<&J;$6M$6$6z$bDT$bVa$b!$9$A$A!Q1$M!-!11&+@*BB&(5 *	9OA|.7.CilO**t}} $ A A ))!$#%$! !-!#3_FWYi! *!,M0=a0@- -a 0 1" 57H7LM#(P-N-T-T*
A{ )O(I(N(N)"3A"68I!8L!M)OZ)% )>(E(EaAq(Q%!&G%II!*/D.FF*%.V-:-@-@*
A{(:(:(::(fHX(fZe(f%(=(E(EaAq(Q%!m%55!*/D.FF* #}QR'88#U*	9X m]4EGZ$[mmm ++*#=	
 	
r+   )NFFFFT)r#   r$   r%   rV   r'   r   r   r   r   r(   r   r   r   r   r   r   s   @r,   rr  rr  6  s    ,4 26,1/4CH+0&*K
||K
  S/K
 E--.	K

 $D>K
 'tnK
 3;4.K
 #4.K
 d^K
 
u''	(K
r+   rr  c                   ,    e Zd ZdZeZdZdZdZdgZ	d Z
y)SwinPreTrainedModelz
    An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained
    models.
    swinr   Tr`  c                    t        |t        j                  t        j                  f      rm|j                  j
                  j                  d| j                  j                         |j                  %|j                  j
                  j                          yyt        |t        j                        rJ|j                  j
                  j                          |j                  j
                  j                  d       yy)zInitialize the weightsr   )meanstdNr   )r   r   r   r   weightdatanormal_rh   initializer_ranger   zero_rb   fill_)r9   modules     r,   _init_weightsz!SwinPreTrainedModel._init_weights  s    fryy"))45 MM&&CT[[5R5R&S{{&  &&( '-KK""$MM$$S) .r+   N)r#   r$   r%   r&   r   config_classbase_model_prefixmain_input_namesupports_gradient_checkpointing_no_split_modulesr  r*   r+   r,   r  r    s,    
 L$O&*#$
*r+   r  aG  
    This model is a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) sub-class. Use
    it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and
    behavior.

    Parameters:
        config ([`SwinConfig`]): Model configuration class with all the parameters of the model.
            Initializing with a config file does not load the weights associated with the model, only the
            configuration. Check out the [`~PreTrainedModel.from_pretrained`] method to load the model weights.
a  
    Args:
        pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
            Pixel values. Pixel values can be obtained using [`AutoImageProcessor`]. See [`ViTImageProcessor.__call__`]
            for details.
        head_mask (`torch.FloatTensor` of shape `(num_heads,)` or `(num_layers, num_heads)`, *optional*):
            Mask to nullify selected heads of the self-attention modules. Mask values selected in `[0, 1]`:

            - 1 indicates the head is **not masked**,
            - 0 indicates the head is **masked**.

        output_attentions (`bool`, *optional*):
            Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned
            tensors for more detail.
        output_hidden_states (`bool`, *optional*):
            Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for
            more detail.
        interpolate_pos_encoding (`bool`, *optional*, defaults to `False`):
            Whether to interpolate the pre-trained position encodings.
        return_dict (`bool`, *optional*):
            Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple.
z^The bare Swin Model transformer outputting raw hidden-states without any specific head on top.a  
        add_pooling_layer (`bool`, *optional*, defaults to `True`):
                Whether or not to apply pooling layer.
        use_mask_token (`bool`, *optional*, defaults to `False`):
                Whether or not to create and apply mask tokens in the embedding layer.
    c                       e Zd Zd fd	Zd Zd Z ee       ee	e
ede      	 	 	 	 	 	 	 ddeej                     deej                      deej                     d	ee   d
ee   dedee   deee
f   fd              Z xZS )	SwinModelc                    t         |   |       || _        t        |j                        | _        t        |j                  d| j
                  dz
  z  z        | _        t        ||      | _
        t        || j                  j                        | _        t        j                  | j                  |j                         | _        |rt        j$                  d      nd | _        | j)                          y )Nr?   r   )ri   r.  )rU   rV   rh   r  rt  ru  r   r^   num_featuresrS   rk   rr  r[   encoderr   rb   r2  	layernormAdaptiveAvgPool1dpooler	post_init)r9   rh   add_pooling_layerri   rj   s       r,   rV   zSwinModel.__init__  s     fmm, 0 0119L3M MN(O"64??+E+EFd&7&7V=R=RS1Bb**1- 	r+   c                 .    | j                   j                  S r   rk   rX   r8   s    r,   get_input_embeddingszSwinModel.get_input_embeddings      ///r+   c                     |j                         D ]7  \  }}| j                  j                  |   j                  j	                  |       9 y)z
        Prunes heads of the model. heads_to_prune: dict of {layer_num: list of heads to prune in this layer} See base
        class PreTrainedModel
        N)itemsr  layerr4  r  )r9   heads_to_pruner  r  s       r,   _prune_headszSwinModel._prune_heads  sE    
 +002 	CLE5LLu%//;;EB	Cr+   vision)
checkpointoutput_typer  modalityexpected_outputr   r   r   r   r|  r   r~  rl   c                    ||n| j                   j                  }||n| j                   j                  }||n| j                   j                  }|t	        d      | j                  |t        | j                   j                              }| j                  |||      \  }}	| j                  ||	||||      }
|
d   }| j                  |      }d}| j                  7| j                  |j                  dd            }t        j                  |d      }|s||f|
dd z   }|S t        |||
j                   |
j"                  |
j$                        S )	z
        bool_masked_pos (`torch.BoolTensor` of shape `(batch_size, num_patches)`, *optional*):
            Boolean masked positions. Indicates which patches are masked (1) and which aren't (0).
        Nz You have to specify pixel_values)r   r   )r   r   r|  r~  r   r   r?   )r   r/   r    r!   r"   )rh   r   r|  use_return_dictr   get_head_maskr  rt  rk   r  r  r  r   r'   r   r.   r    r!   r"   )r9   r   r   r   r   r|  r   r~  embedding_outputr   encoder_outputssequence_outputpooled_outputr   s                 r,   r   zSwinModel.forward  sp   , 2C1N-TXT_T_TqTq$8$D $++JjJj 	 &1%<k$++B]B]?@@ &&y#dkk6H6H2IJ	-1__/Tl .= .
** ,,/!5# ' 
 *!,..9;;" KK(A(A!Q(GHM!MM-;M%}58KKFM-')77&11#2#I#I
 	
r+   )TFNNNNNFN)r#   r$   r%   rV   r  r  r   SWIN_INPUTS_DOCSTRINGr   _CHECKPOINT_FOR_DOCr.   _CONFIG_FOR_DOC_EXPECTED_OUTPUT_SHAPEr   r'   r(   r   r   r   r   r   r   r   s   @r,   r  r    s    0C ++@A&#$. 596:15,0/3).&*>
u001>
 "%"2"23>
 E--.	>

 $D>>
 'tn>
 #'>
 d^>
 
uo%	&>
 B>
r+   r  aW  Swin Model with a decoder on top for masked image modeling, as proposed in [SimMIM](https://arxiv.org/abs/2111.09886).

    <Tip>

    Note that we provide a script to pre-train this model on custom data in our [examples
    directory](https://github.com/huggingface/transformers/tree/main/examples/pytorch/image-pretraining).

    </Tip>
    c                        e Zd Z fdZ ee       eee      	 	 	 	 	 	 	 dde	e
j                     de	e
j                     de	e
j                     de	e   de	e   ded	e	e   d
eeef   fd              Z xZS )SwinForMaskedImageModelingc                    t         |   |       t        |dd      | _        t	        |j
                  d|j                  dz
  z  z        }t        j                  t        j                  ||j                  dz  |j                  z  d      t        j                  |j                              | _        | j                          y )NFT)r  ri   r?   r   )in_channelsout_channelsr   )rU   rV   r  r  r   r^   ru  r   
Sequentialr   encoder_striderM   PixelShuffledecoderr  )r9   rh   r  rj   s      r,   rV   z#SwinForMaskedImageModeling.__init__R  s     fdS	6++aF4E4E4I.JJK}}II(v7L7La7ORXReRe7est OOF112	
 	r+   )r  r  r   r   r   r   r|  r   r~  rl   c           	         ||n| j                   j                  }| j                  |||||||      }|d   }	|	j                  dd      }	|	j                  \  }
}}t        j                  |dz        x}}|	j                  |
|||      }	| j                  |	      }d}|| j                   j                  | j                   j                  z  }|j                  d||      }|j                  | j                   j                  d      j                  | j                   j                  d      j                  d      j                         }t        j                  j!                  ||d	      }||z  j#                         |j#                         d
z   z  | j                   j$                  z  }|s|f|dd z   }||f|z   S |S t'        |||j(                  |j*                  |j,                        S )aI  
        bool_masked_pos (`torch.BoolTensor` of shape `(batch_size, num_patches)`):
            Boolean masked positions. Indicates which patches are masked (1) and which aren't (0).

        Returns:

        Examples:
        ```python
        >>> from transformers import AutoImageProcessor, SwinForMaskedImageModeling
        >>> import torch
        >>> from PIL import Image
        >>> import requests

        >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
        >>> image = Image.open(requests.get(url, stream=True).raw)

        >>> image_processor = AutoImageProcessor.from_pretrained("microsoft/swin-base-simmim-window6-192")
        >>> model = SwinForMaskedImageModeling.from_pretrained("microsoft/swin-base-simmim-window6-192")

        >>> num_patches = (model.config.image_size // model.config.patch_size) ** 2
        >>> pixel_values = image_processor(images=image, return_tensors="pt").pixel_values
        >>> # create random boolean mask of shape (batch_size, num_patches)
        >>> bool_masked_pos = torch.randint(low=0, high=2, size=(1, num_patches)).bool()

        >>> outputs = model(pixel_values, bool_masked_pos=bool_masked_pos)
        >>> loss, reconstructed_pixel_values = outputs.loss, outputs.reconstruction
        >>> list(reconstructed_pixel_values.shape)
        [1, 3, 192, 192]
        ```N)r   r   r   r|  r   r~  r   r   r?   rn   rB   none)r   gh㈵>)r2   r3   r    r!   r"   )rh   r  r  r   rD   r   floorrw   r  r   rg   repeat_interleaver   rG   r   rx   l1_lossr   rM   r1   r    r!   r"   )r9   r   r   r   r   r|  r   r~  r  r  rJ   rM   sequence_lengthrK   rL   reconstructed_pixel_valuesmasked_im_lossrp   r   reconstruction_lossr   s                        r,   r   z"SwinForMaskedImageModeling.forwardb  s   R &1%<k$++B]B]))+/!5%=#  
 "!*)33Aq94C4I4I1
L/OS$899)11*lFTYZ &*\\/%B"&;;))T[[-C-CCD-55b$EO11$++2H2H!L""4;;#9#91=1	  #%--"7"7F`lr"7"s1D8==?488:PTCTUX\XcXcXpXppN02WQR[@F3A3M^%.YSYY,5!//))#*#A#A
 	
r+   r  )r#   r$   r%   rV   r   r  r   r1   r  r   r'   r(   r   r   r   r   r   r   r   s   @r,   r  r  E  s      ++@A+HWfg 596:15,0/3).&*T
u001T
 "%"2"23T
 E--.	T

 $D>T
 'tnT
 #'T
 d^T
 
u33	4T
 h BT
r+   r  a  
    Swin Model transformer with an image classification head on top (a linear layer on top of the final hidden state of
    the [CLS] token) e.g. for ImageNet.

    <Tip>

        Note that it's possible to fine-tune Swin on higher resolution images than the ones it has been trained on, by
        setting `interpolate_pos_encoding` to `True` in the forward of the model. This will interpolate the pre-trained
        position embeddings to the higher resolution.

    </Tip>
    c                        e Zd Z fdZ ee       eeee	e
      	 	 	 	 	 	 	 ddeej                     deej                     deej                     dee   dee   ded	ee   d
eeef   fd              Z xZS )SwinForImageClassificationc                 >   t         |   |       |j                  | _        t        |      | _        |j                  dkD  r4t        j                  | j                  j                  |j                        nt        j                         | _	        | j                          y r:  )rU   rV   
num_labelsr  r  r   r   r  r5  
classifierr  )r9   rh   rj   s     r,   rV   z#SwinForImageClassification.__init__  sx      ++f%	 EKDUDUXYDYBIIdii,,f.?.?@_a_j_j_l 	
 	r+   )r  r  r  r  r   r   labelsr   r|  r   r~  rl   c                 .   ||n| j                   j                  }| j                  ||||||      }|d   }	| j                  |	      }
d}|| j                   j                  | j
                  dk(  rd| j                   _        nl| j
                  dkD  rL|j                  t        j                  k(  s|j                  t        j                  k(  rd| j                   _        nd| j                   _        | j                   j                  dk(  rIt               }| j
                  dk(  r& ||
j                         |j                               }n ||
|      }n| j                   j                  dk(  r=t               } ||
j                  d| j
                        |j                  d            }n,| j                   j                  dk(  rt               } ||
|      }|s|
f|dd z   }||f|z   S |S t        ||
|j                   |j"                  |j$                  	      S )
a  
        labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
            Labels for computing the image classification/regression loss. Indices should be in `[0, ...,
            config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
            `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
        N)r   r   r|  r   r~  r   
regressionsingle_label_classificationmulti_label_classificationrB   r?   )r2   r:   r    r!   r"   )rh   r  r  r  problem_typer  r   r'   longr   r
   squeezer	   rE   r   r=   r    r!   r"   )r9   r   r   r  r   r|  r   r~  r  r  r:   r2   loss_fctr   s                 r,   r   z"SwinForImageClassification.forward  s   . &1%<k$++B]B]))/!5%=#  
  
/{{''/??a'/;DKK,__q(fllejj.HFLL\a\e\eLe/LDKK,/KDKK,{{''<7"9??a'#FNN$4fnn6FGD#FF3D))-JJ+-B @&++b/R))-II,./Y,F)-)9TGf$EvE(!//))#*#A#A
 	
r+   r  )r#   r$   r%   rV   r   r  r   _IMAGE_CLASS_CHECKPOINTr=   r  _IMAGE_CLASS_EXPECTED_OUTPUTr   r'   r(   
LongTensorr   r   r   r   r   r   s   @r,   r  r    s      ++@A*-$4	 5915-1,0/3).&*@
u001@
 E--.@
 ))*	@

 $D>@
 'tn@
 #'@
 d^@
 
u//	0@
 B@
r+   r  zM
    Swin backbone, to be used with frameworks like DETR and MaskFormer.
    c                   t     e Zd Zdef fdZd Z	 	 	 d
dej                  dee	   dee	   dee	   de
f
d	Z xZS )SwinBackbonerh   c           	      >   t         |   |       t         | 	  |       |j                  gt	        t        |j                              D cg c]  }t        |j                  d|z  z         c}z   | _        t        |      | _
        t        || j                  j                        | _        i }t        | j                  | j                         D ]  \  }}t#        j$                  |      ||<    t#        j&                  |      | _        | j+                          y c c}w )Nr?   )rU   rV   _init_backboner^   rc  r  rt  r   r  rS   rk   rr  r[   r  zip_out_featuresrR  r   rb   
ModuleDicthidden_states_normsr  )r9   rh   rh  r  stagerM   rj   s         r,   rV   zSwinBackbone.__init__*  s     v&#--.X]^abhbobo^pXq1rST#f6F6FA6M2N1rr(0"64??+E+EF !#&t'9'94==#I 	DE<)+l)C&	D#%==1D#E  	 2ss   "Dc                 .    | j                   j                  S r   r  r8   s    r,   r  z!SwinBackbone.get_input_embeddings;  r  r+   r   r|  r   r~  rl   c           
          ||n| j                   j                  }||n| j                   j                  }||n| j                   j                  }| j	                  |      \  }}| j                  ||d|dddd      }|j                  }d}	t        | j                  |      D ]  \  }
}|
| j                  v s|j                  \  }}}}|j                  dddd      j                         }|j                  |||z  |      } | j                  |
   |      }|j                  ||||      }|j                  dddd      j                         }|	|fz  }	 |s|	f}|r||j                  fz  }|S t!        |	|r|j                  nd|j"                  	      S )
aK  
        Returns:

        Examples:

        ```python
        >>> from transformers import AutoImageProcessor, AutoBackbone
        >>> import torch
        >>> from PIL import Image
        >>> import requests

        >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
        >>> image = Image.open(requests.get(url, stream=True).raw)

        >>> processor = AutoImageProcessor.from_pretrained("shi-labs/nat-mini-in1k-224")
        >>> model = AutoBackbone.from_pretrained(
        ...     "microsoft/swin-tiny-patch4-window7-224", out_features=["stage1", "stage2", "stage3", "stage4"]
        ... )

        >>> inputs = processor(image, return_tensors="pt")
        >>> outputs = model(**inputs)
        >>> feature_maps = outputs.feature_maps
        >>> list(feature_maps[-1].shape)
        [1, 768, 7, 7]
        ```NT)r   r   r|  r}  rM  r~  r*   r   r?   r   r   )feature_mapsr    r!   )rh   r  r|  r   rk   r  r"   r  stage_namesout_featuresrD   rF   rG   rE   r  r    r   r!   )r9   r   r|  r   r~  r  r   r  r    r  r  hidden_staterJ   rM   rK   rL   r   s                    r,   r   zSwinBackbone.forward>  s   @ &1%<k$++B]B]$8$D $++JjJj 	 2C1N-TXT_T_TqTq-1__\-J**,,/!%59!  	
  66#&t'7'7#G 	0E<))):F:L:L7
L&%+33Aq!Q?JJL+00Ve^\Z>t77>|L+00VULY+33Aq!Q?JJL/	0 "_F#70022M%3G'//T))
 	
r+   )NNN)r#   r$   r%   r   rV   r  r'   r   r   r   r   r   r   r   s   @r,   r  r  #  sj    z "0 04,0&*J
llJ
 'tnJ
 $D>	J

 d^J
 
J
r+   r  )r   F)Nr&   collections.abcr   r   r5   dataclassesr   typingr   r   r   r'   torch.utils.checkpointr   torch.nnr   r	   r
   activationsr   modeling_outputsr   modeling_utilsr   pytorch_utilsr   r   r   utilsr   r   r   r   r   r   r   utils.backbone_utilsr   configuration_swinr   
get_loggerr#   loggerr  r  r  r  r  r   r.   r1   r=   rO   rQ   r   rS   rW   r   r   r   r   r   r   r   r
  r  r!  r(  r,  r`  rr  r  SWIN_START_DOCSTRINGr  r  r  r  r  r*   r+   r,   <module>r     s   &    ! ) )    A A ! . - [ [   2 * 
		H	%  ? %  C 1  K K K@  Kk  K  KF )#K )# )#X  K  K  KF	Y-RYY Y-x(-")) (-V3ryy 3nU\\ e T V[VbVb *-299 -a		 aH
RYY 
#BII #Lryy 	 	z		 zz9		 9xb
")) b
J*/ *2	  0 d	a
# a
	a
H  g
!4 g
g
T  V
!4 V
V
r  	_
& _
_
r+   