
    UhP                     &   d Z ddlZddlmZ ddlmZmZmZm	Z	m
Z
mZmZ ddlZddlZddlmZ ddlmZ ddlmZmZ dd	lmZmZ dd
lmZmZ ddlmZmZmZ ddlm Z   ejB                  e"      Z#e G d de             Z$ G d dejJ                        Z& G d dejJ                        Z' G d dejJ                        Z( G d dejJ                        Z)	 d;dejJ                  dejT                  dejT                  dejT                  de	ejT                     de+de+fdZ, G d  d!ejJ                        Z- G d" d#ejJ                        Z. G d$ d%ejJ                        Z/ G d& d'ejJ                        Z0 G d( d)ejJ                        Z1 G d* d+ejJ                        Z2 G d, d-ejJ                        Z3e G d. d/e             Z4e G d0 d1e4             Z5 G d2 d3ejJ                        Z6 G d4 d5ejJ                        Z7 ed67       G d8 d9e4             Z8g d:Z9y)<zPyTorch YOLOS model.    N)	dataclass)CallableDictListOptionalSetTupleUnion)nn   )ACT2FN)BaseModelOutputBaseModelOutputWithPooling)ALL_ATTENTION_FUNCTIONSPreTrainedModel) find_pruneable_heads_and_indicesprune_linear_layer)ModelOutputauto_docstringlogging   )YolosConfigc                   <   e Zd ZU dZdZeej                     ed<   dZ	ee
   ed<   dZeej                     ed<   dZeej                     ed<   dZeee
      ed<   dZeej                     ed<   dZeeej                        ed	<   dZeeej                        ed
<   y)YolosObjectDetectionOutputaH
  
    Output type of [`YolosForObjectDetection`].

    Args:
        loss (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` are provided)):
            Total loss as a linear combination of a negative log-likehood (cross-entropy) for class prediction and a
            bounding box loss. The latter is defined as a linear combination of the L1 loss and the generalized
            scale-invariant IoU loss.
        loss_dict (`Dict`, *optional*):
            A dictionary containing the individual losses. Useful for logging.
        logits (`torch.FloatTensor` of shape `(batch_size, num_queries, num_classes + 1)`):
            Classification logits (including no-object) for all queries.
        pred_boxes (`torch.FloatTensor` of shape `(batch_size, num_queries, 4)`):
            Normalized boxes coordinates for all queries, represented as (center_x, center_y, width, height). These
            values are normalized in [0, 1], relative to the size of each individual image in the batch (disregarding
            possible padding). You can use [`~YolosImageProcessor.post_process`] to retrieve the unnormalized bounding
            boxes.
        auxiliary_outputs (`list[Dict]`, *optional*):
            Optional, only returned when auxiliary losses are activated (i.e. `config.auxiliary_loss` is set to `True`)
            and labels are provided. It is a list of dictionaries containing the two above keys (`logits` and
            `pred_boxes`) for each decoder layer.
        last_hidden_state (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*):
            Sequence of hidden-states at the output of the last layer of the decoder 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, if the model has an embedding layer, +
            one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of
            the model at the output of each layer plus the optional 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 layer) 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.
    Nloss	loss_dictlogits
pred_boxesauxiliary_outputslast_hidden_statehidden_states
attentions)__name__
__module____qualname____doc__r   r   torchFloatTensor__annotations__r   r   r   r   r   r   r    r!   r	   r"        z/var/www/catia.catastroantioquia-mas.com/valormas/lib/python3.12/site-packages/transformers/models/yolos/modeling_yolos.pyr   r   $   s    B )-D(5$$
%, $Ix~$*.FHU&&'..2J**+2.2xT
+259x 1 1298<M8E%"3"345<59Ju00129r+   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 )YolosEmbeddingszT
    Construct the CLS token, detection tokens, position and patch embeddings.

    configreturnNc                 n   t         |           t        j                  t	        j
                  dd|j                              | _        t        j                  t	        j
                  d|j                  |j                              | _	        t        |      | _        | j                  j                  }t        j                  t	        j
                  d||j                  z   dz   |j                              | _        t        j                  |j                        | _        t#        |      | _        || _        y Nr   )super__init__r   	Parameterr'   zeroshidden_size	cls_tokennum_detection_tokensdetection_tokensYolosPatchEmbeddingspatch_embeddingsnum_patchesposition_embeddingsDropouthidden_dropout_probdropout$InterpolateInitialPositionEmbeddingsinterpolationr/   )selfr/   r=   	__class__s      r,   r4   zYolosEmbeddings.__init__W   s    ekk!Q8J8J&KL "U[[F<W<WY_YkYk-l m 4V <++77#%<<KK;)D)DDqH&J\J\]$
  zz&"<"<=A&Ir+   pixel_valuesc                    |j                   \  }}}}| j                  |      }|j                         \  }}}| j                  j	                  |dd      }	| j
                  j	                  |dd      }
t        j                  |	||
fd      }| j                  | j                  ||f      }||z   }| j                  |      }|S )Nr   dim)shaper<   sizer8   expandr:   r'   catrC   r>   rA   )rD   rF   
batch_sizenum_channelsheightwidth
embeddingsseq_len_
cls_tokensr:   r>   s               r,   forwardzYolosEmbeddings.forwardf   s    2>2D2D/
L&%**<8
!+!2
GQ ^^**:r2>
0077
BKYY
J8HIqQ
 #001I1IFTY?["55
\\*-
r+   
r#   r$   r%   r&   r   r4   r'   TensorrW   __classcell__rE   s   @r,   r.   r.   Q   s6    
{ t ELL U\\ r+   r.   c                   B     e Zd Zd fdZddej
                  fdZ xZS )rB   r0   c                 0    t         |           || _        y Nr3   r4   r/   rD   r/   rE   s     r,   r4   z-InterpolateInitialPositionEmbeddings.__init__}       r+   c                    |d d dd d f   }|d d d f   }|d d | j                   j                   d d d f   }|d d d| j                   j                   d d f   }|j                  dd      }|j                  \  }}}| j                   j                  d   | j                   j
                  z  | j                   j                  d   | j                   j
                  z  }
}	|j                  |||	|
      }|\  }}|| j                   j
                  z  || j                   j
                  z  }}t        j                  j                  |||fdd      }|j                  d      j                  dd      }t        j                  |||fd      }|S )Nr   r      bicubicFrL   modealign_cornersrI   )r/   r9   	transposerK   
image_size
patch_sizeviewr   
functionalinterpolateflattenr'   rN   )rD   	pos_embedimg_sizecls_pos_embeddet_pos_embedpatch_pos_embedrO   r7   rT   patch_heightpatch_widthrQ   rR   new_patch_heightnew_patch_widthscale_pos_embeds                   r,   rW   z,InterpolateInitialPositionEmbeddings.forward   s   !!Q'*%ag.!!dkk&F&F%F%H!"KL#AqDKK,L,L+L'La$OP)33Aq9+:+@+@(
K KK""1%)?)??KK""1%)?)?? " *..z;Vab ,2dkk6L6L,LeW[WbWbWmWmNm/--33#3_"EIej 4 
 *11!4>>q!D))]O]$SYZ[r+   r0   N)i   i@  r#   r$   r%   r4   r'   rY   rW   rZ   r[   s   @r,   rB   rB   |   s    %,, r+   rB   c                   B     e Zd Zd fdZddej
                  fdZ xZS ) InterpolateMidPositionEmbeddingsr0   c                 0    t         |           || _        y r^   r_   r`   s     r,   r4   z)InterpolateMidPositionEmbeddings.__init__   ra   r+   c                 v   |d d d d dd d f   }|d d d f   }|d d d d | j                   j                   d d d f   }|d d d d d| j                   j                   d d f   }|j                  dd      }|j                  \  }}}}	| j                   j                  d   | j                   j
                  z  | j                   j                  d   | j                   j
                  z  }}
|j                  ||z  ||
|      }|\  }}|| j                   j
                  z  || j                   j
                  z  }}t        j                  j                  |||fdd      }|j                  d      j                  dd      j                         j                  ||||z  |      }t        j                  |||fd      }|S )	Nr   r   rc   r   rd   Fre   rI   )r/   r9   rh   rK   ri   rj   rk   r   rl   rm   rn   
contiguousr'   rN   )rD   ro   rp   rq   rr   rs   depthrO   r7   rT   rt   ru   rQ   rR   rv   rw   rx   s                    r,   rW   z(InterpolateMidPositionEmbeddings.forward   s   !!Q1*-%ag.!!Q)I)I(I(KQ"NO#Aq!t{{/O/O.O*OQR$RS)33Aq92A2G2G/z; KK""1%)?)??KK""1%)?)?? " *..uz/A;P\^ij ,2dkk6L6L,LeW[WbWbWmWmNm/--33#3_"EIej 4 
 ##A&Yq!_Z\T%%5%GU	 	  ))]O]$SYZ[r+   ry   rz   r{   r[   s   @r,   r}   r}      s    %,, r+   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)r3   r4   ri   rj   rP   r7   
isinstancecollectionsabcIterabler=   r   Conv2d
projection)rD   r/   ri   rj   rP   r7   r=   rE   s          r,   r4   zYolosPatchEmbeddings.__init__   s    !'!2!2F4E4EJ
$*$7$79K9Kk#-j+//:R:R#SZZdfpYq
#-j+//:R:R#SZZdfpYq
!!}
15*Q-:VW=:XY$$(&))L+:^hir+   rF   r0   c                     |j                   \  }}}}|| j                  k7  rt        d      | j                  |      j	                  d      j                  dd      }|S )NzeMake sure that the channel dimension of the pixel values match with the one set in the configuration.rc   r   )rK   rP   
ValueErrorr   rn   rh   )rD   rF   rO   rP   rQ   rR   rS   s          r,   rW   zYolosPatchEmbeddings.forward   sb    2>2D2D/
L&%4,,,w  __\2::1=GG1M
r+   )	r#   r$   r%   r&   r4   r'   rY   rW   rZ   r[   s   @r,   r;   r;      s)    jELL U\\ r+   r;   modulequerykeyvalueattention_maskscalingrA   c                    t        j                  ||j                  dd            |z  }t        j                  j                  |dt         j                        j                  |j                        }t        j                  j                  ||| j                        }|||z  }t        j                  ||      }	|	j                  dd      j                         }	|	|fS )NrH   )rJ   dtype)ptrainingr   rc   )r'   matmulrh   r   rl   softmaxfloat32tor   rA   r   r   )
r   r   r   r   r   r   rA   kwargsattn_weightsattn_outputs
             r,   eager_attention_forwardr      s     <<s}}R'<=GL ==((2U]](SVVW\WbWbcL ==((6??([L !#n4,,|U3K''1-88:K$$r+   c            
            e Zd Zdeddf fdZdej                  dej                  fdZ	 d
deej                     de	de
eej                  ej                  f   eej                     f   fd	Z xZS )YolosSelfAttentionr/   r0   Nc                 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 .g      F)bias)r3   r4   r7   num_attention_headshasattrr   r/   intattention_head_sizeall_head_sizeattention_probs_dropout_probdropout_probr   	is_causalr   Linearqkv_biasr   r   r   r`   s     r,   r4   zYolosSelfAttention.__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\
r+   xc                     |j                         d d | j                  | j                  fz   }|j                  |      }|j	                  dddd      S )NrH   r   rc   r   r   )rL   r   r   rk   permute)rD   r   new_x_shapes      r,   transpose_for_scoresz'YolosSelfAttention.transpose_for_scores  sL    ffhsmt'?'?AYAY&ZZFF;yyAq!$$r+   	head_maskoutput_attentionsc           
         | j                  | j                  |            }| j                  | j                  |            }| j                  | j                  |            }t        }| j
                  j                  dk7  rN| j
                  j                  dk(  r|rt        j                  d       nt        | j
                  j                     } || ||||| j                  | j                  | j                  sdn| j                        \  }}	|j                         d d | j                  fz   }
|j!                  |
      }|r||	f}|S |f}|S )Neagersdpaz`torch.nn.functional.scaled_dot_product_attention` does not support `output_attentions=True`. Falling back to eager attention. This warning can be removed using the argument `attn_implementation="eager"` when loading the model.        )r   r   rA   r   )r   r   r   r   r   r/   _attn_implementationloggerwarning_oncer   r   r   r   r   rL   r   reshape)rD   r!   r   r   	key_layervalue_layerquery_layerattention_interfacecontext_layerattention_probsnew_context_layer_shapeoutputss               r,   rW   zYolosSelfAttention.forward  s=    --dhh}.EF	//

=0IJ//

=0IJ(?;;++w6{{//69>O##L
 '>dkk>^>^&_#)<nnLL#}}C$2C2C	*
& #0"4"4"6s";t?Q?Q>S"S%--.EF6G=/2 O\M]r+   NF)r#   r$   r%   r   r4   r'   rY   r   r   boolr
   r	   rW   rZ   r[   s   @r,   r   r      s    ]{ ]t ](%ell %u|| % bg!(0(>!Z^!	uU\\5<</0%2EE	F!r+   r   c                   |     e Zd ZdZdeddf fdZdej                  dej                  dej                  fdZ xZ	S )	YolosSelfOutputz
    The residual connection is defined in YolosLayer instead of here (as is the case with other models), due to the
    layernorm applied before each block.
    r/   r0   Nc                     t         |           t        j                  |j                  |j                        | _        t        j                  |j                        | _        y r^   )	r3   r4   r   r   r7   denser?   r@   rA   r`   s     r,   r4   zYolosSelfOutput.__init__@  sB    YYv1163E3EF
zz&"<"<=r+   r!   input_tensorc                 J    | j                  |      }| j                  |      }|S r^   r   rA   rD   r!   r   s      r,   rW   zYolosSelfOutput.forwardE  s$    

=1]3r+   rX   r[   s   @r,   r   r   :  sD    
>{ >t >
U\\  RWR^R^ r+   r   c                        e Zd Zdeddf fdZdee   ddfdZ	 	 ddej                  de
ej                     d	edeeej                  ej                  f   eej                     f   fd
Z xZS )YolosAttentionr/   r0   Nc                     t         |           t        |      | _        t	        |      | _        t               | _        y r^   )r3   r4   r   	attentionr   outputsetpruned_headsr`   s     r,   r4   zYolosAttention.__init__N  s0    +F3%f-Er+   headsc                 >   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   rI   )lenr   r   r   r   r   r   r   r   r   r   r   r   union)rD   r   indexs      r,   prune_headszYolosAttention.prune_headsT  s   u:?74>>55t~~7Y7Y[_[l[l
u
  2$..2F2FN/0B0BEJ1$..2F2FN.t{{/@/@%QO .2^^-O-ORUV[R\-\*'+~~'I'IDNNLnLn'n$ --33E:r+   r!   r   r   c                 h    | j                  |||      }| j                  |d   |      }|f|dd  z   }|S )Nr   r   )r   r   )rD   r!   r   r   self_outputsattention_outputr   s          r,   rW   zYolosAttention.forwardf  sE     ~~mY@QR;;|AF#%QR(88r+   r   )r#   r$   r%   r   r4   r   r   r   r'   rY   r   r   r
   r	   rW   rZ   r[   s   @r,   r   r   M  s    "{ "t ";S ;d ;* -1"'	|| ELL)  	
 
uU\\5<</0%2EE	Fr+   r   c                   `     e Zd Zdeddf fdZdej                  dej                  fdZ xZS )YolosIntermediater/   r0   Nc                    t         |           t        j                  |j                  |j
                        | _        t        |j                  t              rt        |j                     | _        y |j                  | _        y r^   )r3   r4   r   r   r7   intermediate_sizer   r   
hidden_actstrr   intermediate_act_fnr`   s     r,   r4   zYolosIntermediate.__init__v  s]    YYv1163K3KL
f''-'-f.?.?'@D$'-'8'8D$r+   r!   c                 J    | j                  |      }| j                  |      }|S r^   )r   r   )rD   r!   s     r,   rW   zYolosIntermediate.forward~  s&    

=100?r+   	r#   r$   r%   r   r4   r'   rY   rW   rZ   r[   s   @r,   r   r   u  s1    9{ 9t 9U\\ ell r+   r   c                   x     e Zd Zdeddf fdZdej                  dej                  dej                  fdZ xZS )YolosOutputr/   r0   Nc                     t         |           t        j                  |j                  |j
                        | _        t        j                  |j                        | _	        y r^   )
r3   r4   r   r   r   r7   r   r?   r@   rA   r`   s     r,   r4   zYolosOutput.__init__  sB    YYv779K9KL
zz&"<"<=r+   r!   r   c                 T    | j                  |      }| j                  |      }||z   }|S r^   r   r   s      r,   rW   zYolosOutput.forward  s.    

=1]3%4r+   r   r[   s   @r,   r   r     s?    >{ >t >
U\\  RWR^R^ r+   r   c                        e Zd ZdZdeddf fdZ	 	 d
dej                  deej                     de	de
eej                  ej                  f   eej                     f   fd	Z xZS )
YolosLayerz?This corresponds to the Block class in the timm implementation.r/   r0   Nc                 r   t         |           |j                  | _        d| _        t	        |      | _        t        |      | _        t        |      | _	        t        j                  |j                  |j                        | _        t        j                  |j                  |j                        | _        y )Nr   eps)r3   r4   chunk_size_feed_forwardseq_len_dimr   r   r   intermediater   r   r   	LayerNormr7   layer_norm_epslayernorm_beforelayernorm_afterr`   s     r,   r4   zYolosLayer.__init__  s    '-'E'E$'/-f5!&) "V-?-?VEZEZ [!||F,>,>FDYDYZr+   r!   r   r   c                     | j                  | j                  |      ||      }|d   }|dd  }||z   }| j                  |      }| j                  |      }| j	                  ||      }|f|z   }|S )N)r   r   r   )r   r   r   r   r   )rD   r!   r   r   self_attention_outputsr   r   layer_outputs           r,   rW   zYolosLayer.forward  s     "&!!-0/ "0 "

 2!4(, )=8 ++M:((6 {{<?/G+r+   r   )r#   r$   r%   r&   r   r4   r'   rY   r   r   r
   r	   rW   rZ   r[   s   @r,   r   r     s    I[{ [t [ -1"'	|| ELL)  	
 
uU\\5<</0%2EE	Fr+   r   c                        e Zd Zdeddf fdZ	 	 	 	 ddej                  deej                     deded	ede	e
ef   fd
Z xZS )YolosEncoderr/   r0   Nc                 @   t         |           || _        t        j                  t        |j                        D cg c]  }t        |       c}      | _        d| _	        d|j                  d   |j                  d   z  |j                  dz  z  z   |j                  z   }|j                  rBt        j                  t        j                   |j                  dz
  d||j"                              nd | _        |j                  rt'        |      | _        y d | _        y c c}w )NFr   r   rc   )r3   r4   r/   r   
ModuleListrangenum_hidden_layersr   layergradient_checkpointingri   rj   r9   use_mid_position_embeddingsr5   r'   r6   r7   mid_position_embeddingsr}   rC   )rD   r/   rU   
seq_lengthrE   s       r,   r4   zYolosEncoder.__init__  s   ]]fF^F^@_#`1Jv$6#`a
&+# ""1%(9(9!(<<@Q@QST@TTUX^XsXss 	 11 LL,,q0&&	  	$ JPIkIk=fEqu' $as   Dr!   r   r   output_hidden_statesreturn_dictc                 P   |rdnd }|rdnd }	| j                   j                  r| j                  | j                  ||f      }
t	        | j
                        D ]  \  }}|r||fz   }|||   nd }| j                  r+| j                  r| j                  |j                  |||      }n
 ||||      }|d   }| j                   j                  r$|| j                   j                  dz
  k  r|
|   z   }|s|	|d   fz   }	 |r||fz   }|st        d |||	fD              S t        |||	      S )Nr*   r   r   c              3   &   K   | ]	  }||  y wr^   r*   ).0vs     r,   	<genexpr>z'YolosEncoder.forward.<locals>.<genexpr>  s     mq_`_lms   )r    r!   r"   )r/   r  rC   r  	enumerater  r  r   _gradient_checkpointing_func__call__r  tupler   )rD   r!   rQ   rR   r   r   r	  r
  all_hidden_statesall_self_attentions$interpolated_mid_position_embeddingsilayer_modulelayer_head_masklayer_outputss                  r,   rW   zYolosEncoder.forward  sa    #7BD$5b4;;22373E3EdFbFbekmrds3t0(4 	POA|#$58H$H!.7.CilO**t}} $ A A ))!#%	! !-]OM^ _)!,M{{66559:$14XYZ4[$[M &9]1=M<O&O#/	P2   1]4D Dm]4EGZ$[mmm++*
 	
r+   )NFFT)r#   r$   r%   r   r4   r'   rY   r   r   r
   r  r   rW   rZ   r[   s   @r,   r   r     s}    v{ vt v: -1"'%* 2
||2

 ELL)2
  2
 #2
 2
 
uo%	&2
r+   r   c                       e Zd ZeZdZdZdZg ZdZ	dZ
deej                  ej                  ej                  f   ddfdZy)YolosPreTrainedModelvitrF   Tr   r0   Nc                    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stdNg      ?)r   r   r   r   weightdatanormal_r/   initializer_ranger   zero_r   fill_)rD   r   s     r,   _init_weightsz"YolosPreTrainedModel._init_weights  s    fryy"))45 MM&&CT[[5R5R&S{{&  &&( '-KK""$MM$$S) .r+   )r#   r$   r%   r   config_classbase_model_prefixmain_input_namesupports_gradient_checkpointing_no_split_modules_supports_sdpa_supports_flash_attn_2r
   r   r   r   r   r'  r*   r+   r,   r  r    sU    L$O&*#N!
*E"))RYY*L$M 
*RV 
*r+   r  c                        e Zd Zddedef fdZdefdZdee	e
e	   f   ddfdZe	 	 	 	 	 dd	eej                     d
eej                     dee   dee   dee   deeef   fd       Z xZS )
YolosModelr/   add_pooling_layerc                    t         |   |       || _        t        |      | _        t        |      | _        t        j                  |j                  |j                        | _        |rt        |      nd| _        | j                          y)zv
        add_pooling_layer (bool, *optional*, defaults to `True`):
            Whether to add a pooling layer
        r   N)r3   r4   r/   r.   rS   r   encoderr   r   r7   r   	layernormYolosPoolerpooler	post_init)rD   r/   r1  rE   s      r,   r4   zYolosModel.__init__'  sk    
 	 )&1#F+f&8&8f>S>ST->k&)D 	r+   r0   c                 .    | j                   j                  S r^   )rS   r<   )rD   s    r,   get_input_embeddingszYolosModel.get_input_embeddings8  s    ///r+   heads_to_pruneNc                     |j                         D ]7  \  }}| j                  j                  |   j                  j	                  |       9 y)a	  
        Prunes heads of the model.

        Args:
            heads_to_prune (`dict`):
                See base class `PreTrainedModel`. The input dictionary must have the following format: {layer_num:
                list of heads to prune in this layer}
        N)itemsr3  r  r   r   )rD   r:  r  r   s       r,   _prune_headszYolosModel._prune_heads;  sE     +002 	CLE5LLu%//;;EB	Cr+   rF   r   r   r	  r
  c           	      `   ||n| j                   j                  }||n| j                   j                  }||n| j                   j                  }|t	        d      | j                  || j                   j                        }| j                  |      }| j                  ||j                  d   |j                  d   ||||      }|d   }| j                  |      }| j                  | j                  |      nd }	|s|	||	fn|f}
|
|dd  z   S t        ||	|j                  |j                        S )Nz You have to specify pixel_valuesr   rH   )rQ   rR   r   r   r	  r
  r   r   )r    pooler_outputr!   r"   )r/   r   r	  use_return_dictr   get_head_maskr  rS   r3  rK   r4  r6  r   r!   r"   )rD   rF   r   r   r	  r
  embedding_outputencoder_outputssequence_outputpooled_outputhead_outputss              r,   rW   zYolosModel.forwardG  sR    2C1N-TXT_T_TqTq$8$D $++JjJj 	 &1%<k$++B]B]?@@ &&y$++2O2OP	??<8,,%%b)$$R(/!5# ' 
 *!,..98<8OO4UY?L?XO];_n^pL/!""555)-')77&11	
 	
r+   )T)NNNNN)r#   r$   r%   r   r   r4   r;   r9  r   r   r   r=  r   r   r'   rY   r
   r	   r   rW   rZ   r[   s   @r,   r0  r0  %  s    { t "0&: 0
C4T#Y+? 
CD 
C  04,0,0/3&*0
u||,0
 ELL)0
 $D>	0

 'tn0
 d^0
 
u00	10
 0
r+   r0  c                   *     e Zd Zdef fdZd Z xZS )r5  r/   c                     t         |           t        j                  |j                  |j                        | _        t        j                         | _        y r^   )r3   r4   r   r   r7   r   Tanh
activationr`   s     r,   r4   zYolosPooler.__init__|  s9    YYv1163E3EF
'')r+   c                 \    |d d df   }| j                  |      }| j                  |      }|S )Nr   )r   rJ  )rD   r!   first_token_tensorrE  s       r,   rW   zYolosPooler.forward  s6     +1a40

#566r+   )r#   r$   r%   r   r4   rW   rZ   r[   s   @r,   r5  r5  {  s    ${ $
r+   r5  c                   (     e Zd ZdZ fdZd Z xZS )YolosMLPPredictionHeada  
    Very simple multi-layer perceptron (MLP, also called FFN), used to predict the normalized center coordinates,
    height and width of a bounding box w.r.t. an image.

    Copied from https://github.com/facebookresearch/detr/blob/master/models/detr.py

    c                     t         |           || _        |g|dz
  z  }t        j                  d t        |g|z   ||gz         D              | _        y )Nr   c              3   N   K   | ]  \  }}t        j                  ||        y wr^   )r   r   )r  nks      r,   r  z2YolosMLPPredictionHead.__init__.<locals>.<genexpr>  s     #g1BIIaO#gs   #%)r3   r4   
num_layersr   r  ziplayers)rD   	input_dim
hidden_dim
output_dimrS  hrE   s         r,   r4   zYolosMLPPredictionHead.__init__  sS    $LJN+mm#gYKRSOUVZdYeUe@f#ggr+   c                     t        | j                        D ]D  \  }}|| j                  dz
  k  r%t        j                  j                   ||            n ||      }F |S r2   )r  rU  rS  r   rl   relu)rD   r   r  r  s       r,   rW   zYolosMLPPredictionHead.forward  sT    !$++. 	VHAu01DOOa4G0G""58,USTXA	Vr+   )r#   r$   r%   r&   r4   rW   rZ   r[   s   @r,   rN  rN    s    hr+   rN  zy
    YOLOS Model (consisting of a ViT encoder) with object detection heads on top, for tasks such as COCO detection.
    )custom_introc                        e Zd Zdef fdZej                  j                  d        Ze		 	 	 	 ddej                  deee      dee   dee   dee   d	eeef   fd
       Z xZS )YolosForObjectDetectionr/   c                 "   t         |   |       t        |d      | _        t	        |j
                  |j
                  |j                  dz   d      | _        t	        |j
                  |j
                  dd      | _        | j                          y )NF)r1  r   r   )rV  rW  rX  rS     )
r3   r4   r0  r  rN  r7   
num_labelsclass_labels_classifierbbox_predictorr7  r`   s     r,   r4   z YolosForObjectDetection.__init__  s      f> (>((V5G5GTZTeTehiTivw(
$ 5((V5G5GTUbc

 	r+   c                 ^    t        |d d |d d       D cg c]
  \  }}||d c}}S c c}}w )NrH   )r   r   )rT  )rD   outputs_classoutputs_coordabs        r,   _set_aux_lossz%YolosForObjectDetection._set_aux_loss  s9    
 <?}Sb?QS`adbdSe;fg41a1A.gggs   )rF   labelsr   r	  r
  r0   c           
         ||n| j                   j                  }| j                  ||||      }|d   }|dd| j                   j                   dddf   }| j	                  |      }| j                  |      j                         }	d\  }
}}|d\  }}| j                   j                  rC|r|j                  n|d   }| j	                  |      }| j                  |      j                         }| j                  ||| j                  |	| j                   ||      \  }
}}|s|||	f|z   |z   }n||	f|z   }|
|
|f|z   S |S t        |
|||	||j                  |j                  |j                        S )a	  
        labels (`List[Dict]` of len `(batch_size,)`, *optional*):
            Labels for computing the bipartite matching loss. List of dicts, each dictionary containing at least the
            following 2 keys: `'class_labels'` and `'boxes'` (the class labels and bounding boxes of an image in the
            batch respectively). The class labels themselves should be a `torch.LongTensor` of len `(number of bounding
            boxes in the image,)` and the boxes a `torch.FloatTensor` of shape `(number of bounding boxes in the image,
            4)`.

        Examples:

        ```python
        >>> from transformers import AutoImageProcessor, AutoModelForObjectDetection
        >>> 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("hustvl/yolos-tiny")
        >>> model = AutoModelForObjectDetection.from_pretrained("hustvl/yolos-tiny")

        >>> inputs = image_processor(images=image, return_tensors="pt")
        >>> outputs = model(**inputs)

        >>> # convert outputs (bounding boxes and class logits) to Pascal VOC format (xmin, ymin, xmax, ymax)
        >>> target_sizes = torch.tensor([image.size[::-1]])
        >>> results = image_processor.post_process_object_detection(outputs, threshold=0.9, target_sizes=target_sizes)[
        ...     0
        ... ]

        >>> for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
        ...     box = [round(i, 2) for i in box.tolist()]
        ...     print(
        ...         f"Detected {model.config.id2label[label.item()]} with confidence "
        ...         f"{round(score.item(), 3)} at location {box}"
        ...     )
        Detected remote with confidence 0.991 at location [46.48, 72.78, 178.98, 119.3]
        Detected remote with confidence 0.908 at location [336.48, 79.27, 368.23, 192.36]
        Detected cat with confidence 0.934 at location [337.18, 18.06, 638.14, 373.09]
        Detected cat with confidence 0.979 at location [10.93, 53.74, 313.41, 470.67]
        Detected remote with confidence 0.974 at location [41.63, 72.23, 178.09, 119.99]
        ```N)r   r	  r
  r   )NNN)NNr`  )r   r   r   r   r   r    r!   r"   )r/   r@  r  r9   rb  rc  sigmoidauxiliary_lossintermediate_hidden_statesloss_functiondevicer   r    r!   r"   )rD   rF   rj  r   r	  r
  r   rD  r   r   r   r   r   re  rf  r   r   s                    r,   rW   zYolosForObjectDetection.forward  s   h &1%<k$++B]B] ((/!5#	  
 "!* *!dkk.N.N-N-PRS*ST --o>((9AAC
-=*i*+5(M={{))EPwAAV]^_V` $ < <\ J $ 3 3L A I I K151C1CZmUb2.D).  , *-0AAGK *-7373CT9%.OO)!/%77!//))	
 		
r+   )NNNN)r#   r$   r%   r   r4   r'   jitunusedri  r   r(   r   r   r   r   r
   r	   r   rW   rZ   r[   s   @r,   r^  r^    s    { & YYh h  (,,0/3&*a
''a
 d$a
 $D>	a

 'tna
 d^a
 
u00	1a
 a
r+   r^  )r^  r0  r  )r   ):r&   collections.abcr   dataclassesr   typingr   r   r   r   r   r	   r
   r'   torch.utils.checkpointr   activationsr   modeling_outputsr   r   modeling_utilsr   r   pytorch_utilsr   r   utilsr   r   r   configuration_yolosr   
get_loggerr#   r   r   Moduler.   rB   r}   r;   rY   floatr   r   r   r   r   r   r   r   r  r0  r5  rN  r^  __all__r*   r+   r,   <module>r     s     ! D D D    ! K F Q 9 9 , 
		H	% ): ): ):X(bii (V299 :ryy B299 R %II%<<% 
% <<	%
 U\\*% % %>; ;~bii &$RYY $P		 ""))  ' 'TK
299 K
\ *? * *, R
% R
 R
j"))  RYY * 
}
2 }

}
@ Lr+   