
    i,b                     .   d Z ddlZddlmZ ddlZddlmZ ddlmZ ddl	m
Z
 ddlmZmZ dd	lmZ dd
lmZmZmZmZ ddlmZmZ ddlmZ ddlmZmZmZmZ ddlm Z m!Z! ddl"m#Z# ddl$m%Z%  ejL                  e'      Z( G d dejR                        Z* G d dejR                        Z+	 	 dBdejR                  dejX                  dejX                  dejX                  dejX                  dz  de-dz  de-dee   fdZ. G d d ejR                        Z/ G d! d"ejR                        Z0 G d# d$ejR                        Z1 G d% d&ejR                        Z2dCd'ejX                  d(e-d)e3d*ejX                  fd+Z4 G d, d-ejR                        Z5 G d. d/ejR                        Z6 G d0 d1ejR                        Z7 G d2 d3e      Z8e G d4 d5e             Z9 G d6 d7e9      Z:e G d8 d9e9             Z; ed:;       G d< d=e9             Z< ed>;       G d? d@ee9             Z=g dAZ>y)DzPyTorch DINOv2 model.    N)Callable)nn   )initialization)ACT2FN)BackboneMixinfilter_output_hidden_states)GradientCheckpointingLayer)BackboneOutputBaseModelOutputBaseModelOutputWithPoolingImageClassifierOutput)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)TransformersKwargsauto_docstringlogging	torch_int)can_return_tuplemerge_with_config_defaults)capture_outputs   )Dinov2Configc                        e Zd ZdZdeddf fdZdej                  dededej                  fd	Z	dd
ej                  dej                  dz  dej                  fdZ
 xZS )Dinov2EmbeddingszM
    Construct the CLS token, mask token, position and patch embeddings.
    configreturnNc                 z   t         |           t        j                  t	        j
                  dd|j                              | _        |j                  r8t        j                  t	        j                  d|j                              | _
        t        |      | _        | j                  j                  }t        j                  t	        j
                  d|dz   |j                              | _        t        j                  |j                         | _        |j$                  | _        |j                  | _        || _        y )Nr   )super__init__r   	Parametertorchrandnhidden_size	cls_tokenuse_mask_tokenzeros
mask_tokenDinov2PatchEmbeddingspatch_embeddingsnum_patchesposition_embeddingsDropouthidden_dropout_probdropout
patch_sizer   )selfr   r,   	__class__s      {/var/www/vps2.regionflexible.com/Desarrollo/venv/lib/python3.12/site-packages/transformers/models/dinov2/modeling_dinov2.pyr!   zDinov2Embeddings.__init__+   s    ekk!Q8J8J&KL   ll5;;q&:L:L+MNDO 5f =++77#%<<A{QPVPbPb0c#d zz&"<"<= ++$33    
embeddingsheightwidthc                    |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      }|j                  }t        j                  j                  |j                  t        j                        |	|
fdd	
      j                  |      }|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 and interpolation at torch.float32 precision.

        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   Ng      ?r   r      bicubicF)sizemodealign_cornersdtypedim)shaper-   r#   jit
is_tracingr1   r   reshapepermuterA   r   
functionalinterpolatetofloat32viewcat)r2   r6   r7   r8   r,   num_positionsclass_pos_embedpatch_pos_embedrC   
new_height	new_widthsqrt_num_positionstarget_dtypes                r4   interpolate_pos_encodingz)Dinov2Embeddings.interpolate_pos_encoding9   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u}}-i(	 4 

 "<"
  	 *11!Q1=BB1b#Nyy/?;CCr5   pixel_valuesbool_masked_posc                 D   |j                   \  }}}}| j                  j                  j                  j                  }| j                  |j                  |            }|d| j                  rXt        j                  |j                  d      | j                  j                  |j                        j                  d      |      }| j                  j                  |dd      }	t        j                  |	|fd      }|| j                  |||      z   }| j                  |      }|S )Nr@   r:   r   r   rB   )rD   r+   
projectionweightrA   rK   r'   r#   where	unsqueezer)   r&   expandrN   rV   r0   )
r2   rW   rX   
batch_size_r7   r8   rU   r6   
cls_tokenss
             r4   forwardzDinov2Embeddings.forwarda   s    '3'9'9$
Avu,,77>>DD**<???+NO
&4+>+>))"-t/A/A*BRBR/S/]/]^_/`blJ
 ^^**:r2>
YY
J7Q?
  $"?"?
FTY"ZZ
\\*-
r5   N)__name__
__module____qualname____doc__r   r!   r#   TensorintrV   rb   __classcell__r3   s   @r4   r   r   &   s}    |  &D5<< &D &DUX &D]b]i]i &DPELL 5<<RVCV bgbnbn r5   r   c                   Z     e Zd ZdZ fdZdej                  dej                  fdZ xZS )r*   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  }|| _        || _        || _        || _
        t        j                  ||||      | _        y )Nr   r   )kernel_sizestride)r    r!   
image_sizer1   num_channelsr%   
isinstancecollectionsabcIterabler,   r   Conv2drZ   )r2   r   rp   r1   rq   r%   r,   r3   s          r4   r!   zDinov2PatchEmbeddings.__init__~   s    !'!2!2F4E4EJ
$*$7$79K9Kk#-j+//:R:R#SZZdfpYq
#-j+//:R:R#SZZdfpYq
!!}
15*Q-:VW=:XY$$(&))L+:^hir5   rW   r   c                     |j                   d   }|| j                  k7  rt        d| j                   d| d      | j                  |      j	                  d      j                  dd      }|S )Nr   zoMake sure that the channel dimension of the pixel values match with the one set in the configuration. Expected z	 but got .r;   )rD   rq   
ValueErrorrZ   flatten	transpose)r2   rW   rq   r6   s       r4   rb   zDinov2PatchEmbeddings.forward   sz    #))!,4,,,!../yaI  __\2::1=GG1M
r5   )	rd   re   rf   rg   r!   r#   rh   rb   rj   rk   s   @r4   r*   r*   w   s)    jELL U\\ r5   r*   modulequerykeyvalueattention_maskscalingr0   kwargsc                    ||j                  d      dz  }t        j                  ||j                  dd            |z  }|||z   }t        j
                  j                  |d      }t        j
                  j                  ||| j                        }t        j                  ||      }	|	j                  dd      j                         }	|	|fS )Nr:         r;   r   rB   )ptrainingr   )
r=   r#   matmulr{   r   rI   softmaxr0   r   
contiguous)
r|   r}   r~   r   r   r   r0   r   attn_weightsattn_outputs
             r4   eager_attention_forwardr      s     **R.D( <<s}}Q':;gEL!#n4==((2(>L==((6??([L,,|U3K''1-88:K$$r5   c                        e Zd Zdef fdZdej                  dee   de	ej                  ej                  f   fdZ
 xZS )Dinov2SelfAttentionr   c                 2   t         |           |j                  |j                  z  dk7  r2t	        |d      s&t        d|j                   d|j                   d      || _        |j                  | _        t        |j                  |j                  z        | _        | j                  | j                  z  | _	        |j                  | _        | j                  dz  | _        d| _        t        j                  |j                  | j                  |j                         | _        t        j                  |j                  | j                  |j                         | _        t        j                  |j                  | j                  |j                         | _        y )	Nr   embedding_sizezThe hidden size z4 is not a multiple of the number of attention heads rx   r   Fbias)r    r!   r%   num_attention_headshasattrry   r   ri   attention_head_sizeall_head_sizeattention_probs_dropout_probdropout_probr   	is_causalr   Linearqkv_biasr}   r~   r   r2   r   r3   s     r4   r!   zDinov2SelfAttention.__init__   sF    : ::a?PVXhHi"6#5#5"6 7334A7 
 #)#=#= #&v'9'9F<V<V'V#W !558P8PP"??//5YYv1143E3EFOO\
99V//1C1C&//ZYYv1143E3EFOO\
r5   hidden_statesr   r   c                    |j                   d   }|d| j                  | j                  f} | j                  |      j                  | j                  dd      } | j                  |      j                  | j                  dd      } | j                  |      j                  | j                  dd      }t        j                  | j                  j                  t              } || |||d f| j                  | j                  | j                  sdn| j                   d|\  }	}
|	j#                         d d | j$                  fz   }|	j'                  |      }	|	|
fS )Nr   r:   r   r;           )r   r   r0   )rD   r   r   r~   rM   r{   r   r}   r   get_interfacer   _attn_implementationr   r   r   r   r   r=   r   rG   )r2   r   r   r_   	new_shape	key_layervalue_layerquery_layerattention_interfacecontext_layerattention_probsnew_context_layer_shapes               r4   rb   zDinov2SelfAttention.forward   sY   
 #((+
D$<$<d>V>VV	0DHH]+00)<FFq!L	4djj/44i@JJ1aP4djj/44i@JJ1aP(?(M(MKK,,.E)
 *=
*
 nnLL#}}C$2C2C
*
 
*
& #0"4"4"6s";t?Q?Q>S"S%--.EFo--r5   )rd   re   rf   r   r!   r#   rh   r   r   tuplerb   rj   rk   s   @r4   r   r      sN    ]| ](.||. +,. 
u||U\\)	*	.r5   r   c                   x     e Zd ZdZdef fdZdej                  dej                  dej                  fdZ xZ	S )Dinov2SelfOutputz
    The residual connection is defined in Dinov2Layer instead of here (as is the case with other models), due to the
    layernorm applied before each block.
    r   c                     t         |           t        j                  |j                  |j                        | _        t        j                  |j                        | _        y rc   )	r    r!   r   r   r%   denser.   r/   r0   r   s     r4   r!   zDinov2SelfOutput.__init__   sB    YYv1163E3EF
zz&"<"<=r5   r   input_tensorr   c                 J    | j                  |      }| j                  |      }|S rc   )r   r0   )r2   r   r   s      r4   rb   zDinov2SelfOutput.forward   s$    

=1]3r5   
rd   re   rf   rg   r   r!   r#   rh   rb   rj   rk   s   @r4   r   r      s=    
>| >
U\\  RWR^R^ r5   r   c                   f     e Zd Zdef fdZdej                  dee   dej                  fdZ	 xZ
S )Dinov2Attentionr   c                 b    t         |           t        |      | _        t	        |      | _        y rc   )r    r!   r   	attentionr   outputr   s     r4   r!   zDinov2Attention.__init__  s&    ,V4&v.r5   r   r   r   c                 V     | j                   |fi |\  }}| j                  ||      }|S rc   )r   r   )r2   r   r   self_attn_outputr`   r   s         r4   rb   zDinov2Attention.forward  s5    
 -dnn]EfE!-}=r5   )rd   re   rf   r   r!   r#   rh   r   r   rb   rj   rk   s   @r4   r   r      s>    /| /
|| +, 
	r5   r   c                   X     e Zd Zd fdZdej
                  dej
                  fdZ xZS )Dinov2LayerScaler   c                     t         |           t        j                  |j                  t        j                  |j                        z        | _        y rc   )	r    r!   r   r"   layerscale_valuer#   onesr%   lambda1r   s     r4   r!   zDinov2LayerScale.__init__  s8    ||F$;$;ejjI[I[>\$\]r5   hidden_statec                      || j                   z  S rc   )r   r2   r   s     r4   rb   zDinov2LayerScale.forward  s    dll**r5   r   Nrd   re   rf   r!   r#   rh   rb   rj   rk   s   @r4   r   r     s$    ^+ELL +U\\ +r5   r   input	drop_probr   r   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 )zc
    Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

    r   r   r   )r   )rA   device)rD   ndimr#   randrA   r   floor_div)r   r   r   	keep_probrD   random_tensorr   s          r4   	drop_pathr     s    
 CxII[[^

Q 77E

5ELL YYMYYy!M1FMr5   c                   x     e Zd ZdZd	dedz  ddf fdZdej                  dej                  fdZde	fdZ
 xZS )
Dinov2DropPathzXDrop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).Nr   r   c                 0    t         |           || _        y rc   )r    r!   r   )r2   r   r3   s     r4   r!   zDinov2DropPath.__init__-  s    "r5   r   c                 D    t        || j                  | j                        S rc   )r   r   r   )r2   r   s     r4   rb   zDinov2DropPath.forward1  s    FFr5   c                      d| j                    S )Nzp=)r   r2   s    r4   
extra_reprzDinov2DropPath.extra_repr4  s    DNN#$$r5   rc   )rd   re   rf   rg   floatr!   r#   rh   rb   strr   rj   rk   s   @r4   r   r   *  sG    b#%$, #$ #GU\\ Gell G%C %r5   r   c                   X     e Zd Zd fdZdej
                  dej
                  fdZ xZS )	Dinov2MLPr   c                 ~   t         |           |j                  x}}t        |j                  |j                  z        }t        j                  ||d      | _        t        |j                  t              rt        |j                     | _        n|j                  | _        t        j                  ||d      | _        y )NTr   )r    r!   r%   ri   	mlp_ratior   r   fc1rr   
hidden_actr   r   
activationfc2r2   r   in_featuresout_featureshidden_featuresr3   s        r4   r!   zDinov2MLP.__init__9  s    %+%7%77lf0063C3CCD99[/Ef''-$V%6%67DO$//DO99_lFr5   r   c                 l    | j                  |      }| j                  |      }| j                  |      }|S rc   )r   r   r   r   s     r4   rb   zDinov2MLP.forwardD  s2    xx-|4xx-r5   r   r   rk   s   @r4   r   r   8  s$    	GELL U\\ r5   r   c                   X     e Zd Zd fdZdej
                  dej
                  fdZ xZS )Dinov2SwiGLUFFNr   c                 0   t         |           |j                  x}}t        |j                  |j                  z        }t        |dz  dz        dz   dz  dz  }t        j                  |d|z  d      | _        t        j                  ||d      | _        y )Nr;   r         Tr   )	r    r!   r%   ri   r   r   r   
weights_inweights_outr   s        r4   r!   zDinov2SwiGLUFFN.__init__L  s    %+%7%77lf0063C3CCD2Q67!;AAE))K_1D4P99_lNr5   r   c                     | j                  |      }|j                  dd      \  }}t        j                  j	                  |      |z  }| j                  |      S )Nr;   r:   rB   )r   chunkr   rI   silur   )r2   r   x1x2hiddens        r4   rb   zDinov2SwiGLUFFN.forwardU  sS    |4##A2#.B##B'",''r5   r   r   rk   s   @r4   r   r   K  s$    O(ELL (U\\ (r5   r   c                   d     e Zd ZdZdeddf fdZdej                  dej                  fdZ xZ	S )Dinov2LayerzCThis corresponds to the Block class in the original implementation.r   r   Nc                    t         |           t        j                  |j                  |j
                        | _        t        |      | _        t        |      | _
        |j                  dkD  rt        |j                        nt        j                         | _        t        j                  |j                  |j
                        | _        |j                   rt#        |      | _        nt'        |      | _        t        |      | _        y )Nepsr   )r    r!   r   	LayerNormr%   layer_norm_epsnorm1r   r   r   layer_scale1drop_path_rater   Identityr   norm2use_swiglu_ffnr   mlpr   layer_scale2r   s     r4   r!   zDinov2Layer.__init___  s    \\&"4"4&:O:OP
(0,V4BHBWBWZ]B](=(=>cecncncp\\&"4"4&:O:OP
  &v.DH (DH,V4r5   r   c                 "   | j                  |      }| j                  |      }| j                  |      }| j                  |      |z   }| j	                  |      }| j                  |      }| j                  |      }| j                  |      |z   }|S rc   )r   r   r   r   r   r   r  )r2   r   hidden_states_normself_attention_outputlayer_outputs        r4   rb   zDinov2Layer.forwardo  s     "ZZ6 $/A B $ 1 12G H '<=M zz-0xx-((6 ~~l3mCr5   r   rk   s   @r4   r   r   \  s8    M5| 5 5 || 
r5   r   c                       e Zd ZU eed<   dZdZdZdZdgZ	dZ
dZdZdZeedZ ej$                         dej(                  ej*                  z  ej,                  z  d	d
fd       Zy
)Dinov2PreTrainedModelr   dinov2rW   )imageTr   )r   
attentionsr|   r   Nc                    t        |t        j                  t        j                  f      rct	        j
                  |j                  d| j                  j                         |j                   t	        j                  |j                         yyt        |t        j                        r?t	        j                  |j                         t	        j                  |j                         yt        |t              rt	        j
                  |j                  d| j                  j                         t	        j
                  |j                  d| j                  j                         | j                  j                   r t	        j                  |j"                         yyt        |t$              r5t	        j&                  |j(                  | j                  j*                         yy)zInitialize the weightsr   )meanstdN)rr   r   r   rv   inittrunc_normal_r[   r   initializer_ranger   zeros_r   ones_r   r-   r&   r'   r)   r   	constant_r   r   )r2   r|   s     r4   _init_weightsz#Dinov2PreTrainedModel._init_weights  s'    fryy"))45v}}3DKK<Y<YZ{{&FKK( '-KK$JJv}}% 01v99IfIfgv//ct{{?\?\]{{))F--. * 01NN6>>4;;+G+GH 2r5   )rd   re   rf   r   __annotations__base_model_prefixmain_input_nameinput_modalitiessupports_gradient_checkpointing_no_split_modules_supports_sdpa_supports_flash_attn_supports_flex_attn_supports_attention_backendr   r   _can_record_outputsr#   no_gradr   r   rv   r   r   r5   r4   r  r    s     $O!&*#&N"&$)
 U]]_IBII		$9BLL$H IT I Ir5   r  c                   t     e Zd Zdef fdZe ed      dej                  de	e
   defd              Z xZS )	Dinov2Encoderr   c                     t         |   |       t        j                  t	        |j
                        D cg c]  }t        |       c}      | _        | j                          y c c}w rc   )	r    r!   r   
ModuleListrangenum_hidden_layersr   layer	post_initr2   r   r`   r3   s      r4   r!   zDinov2Encoder.__init__  sK     ]]vG_G_A`#aAK$7#ab
 $bs   A&F)tie_last_hidden_statesr   r   r   c                 L    | j                   D ]
  } ||      } t        |      S )N)last_hidden_state)r(  r   )r2   r   r   layer_modules       r4   rb   zDinov2Encoder.forward  s.     !JJ 	8L(7M	8 ??r5   )rd   re   rf   r   r!   r   r   r#   rh   r   r   r   rb   rj   rk   s   @r4   r#  r#    sU    | 
  E2@U\\ @VDV=W @\k @ 3  @r5   r#  c                        e Zd Zdef fdZdefdZee	 	 d
de	j                  dz  de	j                  dz  dee   defd	              Z xZS )Dinov2Modelr   c                     t         |   |       || _        t        |      | _        t        |      | _        t        j                  |j                  |j                        | _        | j                          y )Nr   )r    r!   r   r   r6   r#  encoderr   r   r%   r   	layernormr)  r   s     r4   r!   zDinov2Model.__init__  sY     *62$V,f&8&8f>S>ST 	r5   r   c                 .    | j                   j                  S rc   r6   r+   r   s    r4   get_input_embeddingsz Dinov2Model.get_input_embeddings      ///r5   NrW   rX   r   c                     |t        d      | j                  ||      } | j                  |fi |}|j                  }| j	                  |      }|dddddf   }t        |||j                  |j                        S )z
        bool_masked_pos (`torch.BoolTensor` of shape `(batch_size, sequence_length)`):
            Boolean masked positions. Indicates which patches are masked (1) and which aren't (0). Only relevant for
            pre-training.
        Nz You have to specify pixel_values)rX   r   )r-  pooler_outputr   r
  )ry   r6   r2  r-  r3  r   r   r
  )r2   rW   rX   r   embedding_outputencoder_outputssequence_outputpooled_outputs           r4   rb   zDinov2Model.forward  s     ?@@??<?Y+74<<8H+SF+S);;..9'1a0)-')77&11	
 	
r5   NN)rd   re   rf   r   r!   r*   r6  r   r   r#   rh   r   r   r   rb   rj   rk   s   @r4   r0  r0    s~    
| 
0&; 0  -1/3
llT)
 ,
 +,	

 
$
  
r5   r0  z
    Dinov2 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.
    )custom_introc                        e Zd Zdeddf fdZee	 	 d	dej                  dz  dej                  dz  de	e
   defd              Z xZS )
Dinov2ForImageClassificationr   r   Nc                 0   t         |   |       |j                  | _        t        |      | _        |j                  dkD  r-t        j                  |j                  dz  |j                        nt        j                         | _	        | j                          y )Nr   r;   )r    r!   
num_labelsr0  r  r   r   r%   r   
classifierr)  r   s     r4   r!   z%Dinov2ForImageClassification.__init__  sy      ++!&) EKDUDUXYDYBIIf((1,f.?.?@_a_j_j_l 	
 	r5   rW   labelsr   c                 h    | j                   |fi |}|j                  }|dddf   }|ddddf   }t        j                  ||j	                  d      gd      }| j                  |      }	d}
| | j                  ||	| j                  fi |}
t        |
|	|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).
        Nr   r   rB   )losslogitsr   r
  )r  r-  r#   rN   r  rD  loss_functionr   r   r   r
  )r2   rW   rE  r   outputsr<  r&   patch_tokenslinear_inputrH  rG  s              r4   rb   z$Dinov2ForImageClassification.forward  s     /:dkk,.Q&.Q!33#AqD)	&q!"u-yy)\->->1->-E!FAN.%4%%ffdkkLVLD$!//))	
 	
r5   r>  )rd   re   rf   r   r!   r   r   r#   rh   r   r   r   rb   rj   rk   s   @r4   rA  rA    sx    |    -1&*
llT)
 t#
 +,	

 

  
r5   rA  zO
    Dinov2 backbone, to be used with frameworks like DETR and MaskFormer.
    c            	       v     e Zd Z fdZdefdZeeede	j                  dee   defd                     Z xZS )Dinov2Backbonec                 X   t         |   |       t        |j                  dz         D cg c]  }|j                   c}| _        t        |      | _        t        |      | _	        t        j                  |j                  |j                        | _        | j                          y c c}w )Nr   r   )r    r!   r&  r'  r%   num_featuresr   r6   r#  r2  r   r   r   r3  r)  r*  s      r4   r!   zDinov2Backbone.__init__&  s     9>v?W?WZ[?[9\]AV//]*62$V,f&8&8f>S>ST 	 ^s   B'r   c                 .    | j                   j                  S rc   r5  r   s    r4   r6  z#Dinov2Backbone.get_input_embeddings2  r7  r5   rW   r   c                    d|d<   | j                  |      } | j                  |fi |}|j                  }g }t        | j                  |      D ]  \  }}|| j
                  v s| j                  j                  r| j                  |      }| j                  j                  rn|ddddf   }|j                  \  }	}
}}| j                  j                  }|j                  |	||z  ||z  d      }|j                  dddd      j                         }|j                  |        t!        t#        |      ||j$                  	      S )
av  
        Examples:

        ```python
        >>> from transformers import AutoImageProcessor, AutoBackbone
        >>> import torch
        >>> from PIL import Image
        >>> import httpx
        >>> from io import BytesIO

        >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
        >>> with httpx.stream("GET", url) as response:
        ...     image = Image.open(BytesIO(response.read()))

        >>> processor = AutoImageProcessor.from_pretrained("facebook/dinov2-base")
        >>> model = AutoBackbone.from_pretrained(
        ...     "facebook/dinov2-base", out_features=["stage2", "stage5", "stage8", "stage11"]
        ... )

        >>> inputs = processor(image, return_tensors="pt")

        >>> outputs = model(**inputs)
        >>> feature_maps = outputs.feature_maps
        >>> list(feature_maps[-1].shape)
        [1, 768, 16, 16]
        ```Toutput_hidden_statesNr   r:   r   r   r;   )feature_mapsr   r
  )r6   r2  r   zipstage_namesr   r   apply_layernormr3  reshape_hidden_statesrD   r1   rG   rH   r   appendr   r   r
  )r2   rW   r   r:  r   r   rT  stager   r_   r`   r7   r8   r1   s                 r4   rb   zDinov2Backbone.forward5  sE   D *.%&??<8".$,,/?"J6"J,,#&t'7'7#G 	2E<)));;..#'>>,#?L;;44#/12#6L 4@3E3E0J65!%!7!7J#/#7#7
FjDXZ_cmZmoq#rL#/#7#71a#C#N#N#PL##L1	2 |,'((
 	
r5   )rd   re   rf   r!   r*   r6  r   r	   r   r#   rh   r   r   r   rb   rj   rk   s   @r4   rN  rN     s_    
0&; 0  8
ll8
 +,8
 
	8
  ! 8
r5   rN  )rA  r0  r  rN  )Nr   )r   F)?rg   collections.abcrs   r   r#   r    r   r  activationsr   backbone_utilsr   r	   modeling_layersr
   modeling_outputsr   r   r   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   r   utils.genericr   r   utils.output_capturingr   configuration_dinov2r   
get_loggerrd   loggerModuler   r*   rh   r   r   r   r   r   r   boolr   r   r   r   r   r  r#  r0  rA  rN  __all__r!  r5   r4   <module>rl     sB     $   & ! H 9 r r F & K K I 5 . 
		H	%Nryy NbBII P !%II%<<% 
% <<	%
 LL4'% T\% % '(%:4.")) 4.pryy $bii  +ryy +U\\ e T V[VbVb  %RYY %		 &(bii ("&, &R  IO  I  IF@) @ ,
' ,
 ,
^ /
#8 /
/
d 
K
]$9 K

K
\ er5   