
    hw                     F   d 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 ddlmZ dd	lmZmZ dd
lmZmZ ddlmZ ddlmZmZ ddlmZmZmZmZ ddl m!Z!m"Z" ddl#m$Z$  ejJ                  e&      Z'e ed       G d de                    Z( G d dejR                        Z* G d dejR                        Z+ G d dejR                        Z, G d dejR                        Z-	 d?dejR                  de	j\                  de	j\                  d e	j\                  d!ee	j\                     d"e/d#e/fd$Z0 G d% d&ejR                        Z1 G d' d(ejR                        Z2 G d) d*ejR                        Z3 G d+ d,ejR                        Z4 G d- d.ejR                        Z5 G d/ d0e      Z6 G d1 d2ejR                        Z7e G d3 d4e             Z8e G d5 d6e8             Z9 G d7 d8ejR                        Z: G d9 d:ejR                        Z; ed;       G d< d=e8             Z<g d>Z=y)@zPyTorch YOLOS model.    N)	dataclass)CallableOptionalUnion)nn   )ACT2FN)GradientCheckpointingLayer)BaseModelOutputBaseModelOutputWithPooling)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack) find_pruneable_heads_and_indicesprune_linear_layer)ModelOutputTransformersKwargsauto_docstringlogging)can_return_tuplecheck_model_inputs   )YolosConfigz5
    Output type of [`YolosForObjectDetection`].
    )custom_introc                   <   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)YolosObjectDetectionOutputa0  
    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.
    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   dictr   r    r!   listr"   r#   tupler$        f/var/www/html/eduruby.in/venv/lib/python3.12/site-packages/transformers/models/yolos/modeling_yolos.pyr   r   '   s    , )-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9r0   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$InterpolateInitialPositionEmbeddingsinterpolationr4   )selfr4   rB   	__class__s      r1   r9   zYolosEmbeddings.__init__T   s    ekk!Q8J8J&KL "U[[F<W<WY_YkYk-l m 4V <++77#%<<KK;)D)DDqH&J\J\]$
  zz&"<"<=A&Ir0   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)shaperA   sizer=   expandr?   r)   catrH   rC   rF   )rI   rK   
batch_sizenum_channelsheightwidth
embeddingsseq_len_
cls_tokensr?   rC   s               r1   forwardzYolosEmbeddings.forwardc   s    2>2D2D/
L&%**<8
!+!2
GQ ^^**:r2>
0077
BKYY
J8HIqQ
 #001I1IFTY?["55
\\*-
r0   
r%   r&   r'   r(   r   r9   r)   Tensorr\   __classcell__rJ   s   @r1   r3   r3   N   s6    
{ t ELL U\\ r0   r3   c                   B     e Zd Zd fdZddej
                  fdZ xZS )rG   r5   c                 0    t         |           || _        y Nr8   r9   r4   rI   r4   rJ   s     r1   r9   z-InterpolateInitialPositionEmbeddings.__init__y       r0   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rQ   modealign_cornersrN   )r4   r>   	transposerP   
image_size
patch_sizeviewr   
functionalinterpolateflattenr)   rS   )rI   	pos_embedimg_sizecls_pos_embeddet_pos_embedpatch_pos_embedrT   r<   rY   patch_heightpatch_widthrV   rW   new_patch_heightnew_patch_widthscale_pos_embeds                   r1   r\   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[r0   r5   N)i   i@  r%   r&   r'   r9   r)   r^   r\   r_   r`   s   @r1   rG   rG   x   s    %,, r0   rG   c                   B     e Zd Zd fdZddej
                  fdZ xZS ) InterpolateMidPositionEmbeddingsr5   c                 0    t         |           || _        y rc   rd   re   s     r1   r9   z)InterpolateMidPositionEmbeddings.__init__   rf   r0   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   rh   r   ri   Frj   rN   )r4   r>   rm   rP   rn   ro   rp   r   rq   rr   rs   
contiguousr)   rS   )rI   rt   ru   rv   rw   rx   depthrT   r<   rY   ry   rz   rV   rW   r{   r|   r}   s                    r1   r\   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[r0   r~   r   r   r`   s   @r1   r   r      s    %,, r0   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)r8   r9   rn   ro   rU   r<   
isinstancecollectionsabcIterablerB   r   Conv2d
projection)rI   r4   rn   ro   rU   r<   rB   rJ   s          r1   r9   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r0   rK   r5   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.rh   r   )rP   rU   
ValueErrorr   rs   rm   )rI   rK   rT   rU   rV   rW   rX   s          r1   r\   zYolosPatchEmbeddings.forward   sb    2>2D2D/
L&%4,,,w  __\2::1=GG1M
r0   )	r%   r&   r'   r(   r9   r)   r^   r\   r_   r`   s   @r1   r@   r@      s)    jELL U\\ r0   r@   modulequerykeyvalueattention_maskscalingrF   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 )NrM   )rO   dtype)ptrainingr   rh   )r)   matmulrm   r   rq   softmaxfloat32tor   rF   r   r   )
r   r   r   r   r   r   rF   kwargsattn_weightsattn_outputs
             r1   eager_attention_forwardr      s     <<s}}R'<=GL ==((2U]](SVVW\WbWbcL ==((6??([L !#n4,,|U3K''1-88:K$$r0   c            	            e Zd Zdef fdZ	 ddej                  deej                     deej                  ej                  f   fdZ	 xZ
S )YolosSelfAttentionr4   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 .g      F)bias)r8   r9   r<   num_attention_headshasattrr   r4   intattention_head_sizeall_head_sizeattention_probs_dropout_probdropout_probr   	is_causalr   Linearqkv_biasr   r   r   re   s     r1   r9   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\
r0   r#   	head_maskr5   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                  dk7  rt        | j                  j                     } || ||||| j                  | j                  | j                  sdn| j                        \  }	}
|	j!                         d d | j"                  fz   }|	j%                  |      }	|	|
fS )	Nr   rM   r   rh   eager        )r   r   rF   r   )rP   r   r   r   rp   rm   r   r   r   r4   _attn_implementationr   r   r   r   r   rQ   r   reshape)rI   r#   r   rT   	new_shape	key_layervalue_layerquery_layerattention_interfacecontext_layerattention_probsnew_context_layer_shapes               r1   r\   zYolosSelfAttention.forward  sR    #((+
D$<$<d>V>VV	0DHH]+00)<FFq!L	4djj/44i@JJ1aP4djj/44i@JJ1aP(?;;++w6"9$++:Z:Z"[)<nnLL#}}C$2C2C	*
& #0"4"4"6s";t?Q?Q>S"S%--.EFo--r0   rc   )r%   r&   r'   r   r9   r)   r^   r   r.   r\   r_   r`   s   @r1   r   r      sT    ]{ ]* PT."\\.6>u||6L.	u||U\\)	*.r0   r   c                   x     e Zd ZdZdef fdZdej                  dej                  dej                  fdZ xZ	S )YolosSelfOutputz
    The residual connection is defined in YolosLayer instead of here (as is the case with other models), due to the
    layernorm applied before each block.
    r4   c                     t         |           t        j                  |j                  |j                        | _        t        j                  |j                        | _        y rc   )	r8   r9   r   r   r<   denserD   rE   rF   re   s     r1   r9   zYolosSelfOutput.__init__2  sB    YYv1163E3EF
zz&"<"<=r0   r#   input_tensorr5   c                 J    | j                  |      }| j                  |      }|S rc   r   rF   rI   r#   r   s      r1   r\   zYolosSelfOutput.forward7  s$    

=1]3r0   r]   r`   s   @r1   r   r   ,  s=    
>{ >
U\\  RWR^R^ r0   r   c                        e Zd Zdef fdZdee   fdZd	dej                  de
ej                     dej                  fdZ xZS )
YolosAttentionr4   c                     t         |           t        |      | _        t	        |      | _        t               | _        y rc   )r8   r9   r   	attentionr   outputsetpruned_headsre   s     r1   r9   zYolosAttention.__init__?  s0    +F3%f-Er0   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   rN   )lenr   r   r   r   r   r   r   r   r   r   r   r   union)rI   r   indexs      r1   prune_headszYolosAttention.prune_headsE  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:r0   r#   r   r5   c                 T    | j                  ||      \  }}| j                  ||      }|S rc   )r   r   )rI   r#   r   self_attn_outputrZ   r   s         r1   r\   zYolosAttention.forwardW  s.    "nn]IF!-}=r0   rc   )r%   r&   r'   r   r9   r   r   r   r)   r^   r   r\   r_   r`   s   @r1   r   r   >  sM    "{ ";S ;$U\\ hu||>T `e`l`l r0   r   c                   \     e Zd Zdef fdZdej                  dej                  fdZ xZS )YolosIntermediater4   c                    t         |           t        j                  |j                  |j
                        | _        t        |j                  t              rt        |j                     | _        y |j                  | _        y rc   )r8   r9   r   r   r<   intermediate_sizer   r   
hidden_actstrr	   intermediate_act_fnre   s     r1   r9   zYolosIntermediate.__init___  s]    YYv1163K3KL
f''-'-f.?.?'@D$'-'8'8D$r0   r#   r5   c                 J    | j                  |      }| j                  |      }|S rc   )r   r   )rI   r#   s     r1   r\   zYolosIntermediate.forwardg  s&    

=100?r0   	r%   r&   r'   r   r9   r)   r^   r\   r_   r`   s   @r1   r   r   ^  s*    9{ 9U\\ ell r0   r   c                   t     e Zd Zdef fdZdej                  dej                  dej                  fdZ xZS )YolosOutputr4   c                     t         |           t        j                  |j                  |j
                        | _        t        j                  |j                        | _	        y rc   )
r8   r9   r   r   r   r<   r   rD   rE   rF   re   s     r1   r9   zYolosOutput.__init__o  sB    YYv779K9KL
zz&"<"<=r0   r#   r   r5   c                 T    | j                  |      }| j                  |      }||z   }|S rc   r   r   s      r1   r\   zYolosOutput.forwardt  s.    

=1]3%4r0   r   r`   s   @r1   r   r   n  s8    >{ >
U\\  RWR^R^ r0   r   c                        e Zd ZdZdef fdZddej                  deej                     dej                  fdZ	 xZ
S )	
YolosLayerz?This corresponds to the Block class in the timm implementation.r4   c                 r   t         |           |j                  | _        d| _        t	        |      | _        t        |      | _        t        |      | _	        t        j                  |j                  |j                        | _        t        j                  |j                  |j                        | _        y )Nr   eps)r8   r9   chunk_size_feed_forwardseq_len_dimr   r   r   intermediater   r   r   	LayerNormr<   layer_norm_epslayernorm_beforelayernorm_afterre   s     r1   r9   zYolosLayer.__init__  s    '-'E'E$'/-f5!&) "V-?-?VEZEZ [!||F,>,>FDYDYZr0   r#   r   r5   c                     | j                  |      }| j                  ||      }||z   }| j                  |      }| j                  |      }| j	                  ||      }|S rc   )r   r   r   r   r   )rI   r#   r   hidden_states_normattention_outputlayer_outputs         r1   r\   zYolosLayer.forward  sk    !22=A>>*<iH )=8 ++M:((6 {{<?r0   rc   )r%   r&   r'   r(   r   r9   r)   r^   r   r\   r_   r`   s   @r1   r   r   |  sB    I[{ [U\\ hu||>T `e`l`l r0   r   c                   v     e Zd Zdeddf fdZ	 d
dej                  dededeej                     de	f
d	Z
 xZS )YolosEncoderr4   r5   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   rh   )r8   r9   r4   r   
ModuleListrangenum_hidden_layersr   layergradient_checkpointingrn   ro   r>   use_mid_position_embeddingsr:   r)   r;   r<   mid_position_embeddingsr   rH   )rI   r4   rZ   
seq_lengthrJ   s       r1   r9   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' $as   Dr#   rV   rW   r   c                 X   | j                   j                  r| j                  | j                  ||f      }t	        | j
                        D ]S  \  }}|||   nd } |||      }| j                   j                  s/|| j                   j                  dz
  k  sL||   z   }U t        |      S )Nr   )r"   )r4   r   rH   r  	enumerater   r   r   )	rI   r#   rV   rW   r   $interpolated_mid_position_embeddingsilayer_modulelayer_head_masks	            r1   r\   zYolosEncoder.forward  s     ;;22373E3EdFbFbekmrds3t0(4 	\OA|.7.CilO(HM{{66559:$14XYZ4[$[M	\ ??r0   rc   )r%   r&   r'   r   r9   r)   r^   r   r   r   r\   r_   r`   s   @r1   r   r     sf    v{ vt v: -1@||@ @ 	@
 ELL)@ 
@r0   r   c                       e Zd ZU eed<   dZdZdZg ZdZ	dZ
dZdZeedZdeej$                  ej&                  ej(                  f   ddfd	Zy)
YolosPreTrainedModelr4   vitrK   T)r#   r$   r   r5   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_r4   initializer_ranger   zero_r   fill_)rI   r   s     r1   _init_weightsz"YolosPreTrainedModel._init_weights  s    fryy"))45 MM&&CT[[5R5R&S{{&  &&( '-KK""$MM$$S) .r0   )r%   r&   r'   r   r+   base_model_prefixmain_input_namesupports_gradient_checkpointing_no_split_modules_supports_sdpa_supports_flash_attn_supports_flex_attn_supports_attention_backendr   r   _can_record_outputsr   r   r   r   r   r  r/   r0   r1   r
  r
    sp    $O&*#N"&#(

*E"))RYY*L$M 
*RV 
*r0   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e	 	 dd	eej                      d
eej                      dee   defd              Z xZS )
YolosModelr4   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)r8   r9   r4   r3   rX   r   encoderr   r   r<   r   	layernormYolosPoolerpooler	post_init)rI   r4   r!  rJ   s      r1   r9   zYolosModel.__init__  sk    
 	 )&1#F+f&8&8f>S>ST->k&)D 	r0   r5   c                 .    | j                   j                  S rc   )rX   rA   )rI   s    r1   get_input_embeddingszYolosModel.get_input_embeddings  s    ///r0   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)itemsr#  r   r   r   )rI   r*  r   r   s       r1   _prune_headszYolosModel._prune_heads  sE     +002 	CLE5LLu%//;;EB	Cr0   rK   r   r   c                 j   |t        d      | j                  || j                  j                        }| j	                  |      }|j
                  dd  \  }}| j                  ||||      }|j                  }| j                  |      }| j                  | j                  |      nd }	t        ||	      S )Nz You have to specify pixel_valuesr   )rV   rW   r   )r"   pooler_output)r   get_head_maskr4   r   rX   rP   r#  r"   r$  r&  r   )
rI   rK   r   r   embedding_outputrV   rW   encoder_outputssequence_outputpooled_outputs
             r1   r\   zYolosModel.forward  s     ?@@ &&y$++2O2OP	??<8$**23/+/<<V5I ,8 ,
 *;;..98<8OO4UY)O[hiir0   )TNN)r%   r&   r'   r   boolr9   r@   r)  r,   r   r-   r-  r   r   r   r)   r^   r   r   r   r\   r_   r`   s   @r1   r   r     s    { t "0&: 0
C4T#Y+? 
CD 
C  04,0ju||,j ELL)j +,	j
 
$j  jr0   r   c                   \     e Zd Zdef fdZdej                  dej                  fdZ xZS )r%  r4   c                     t         |           t        j                  |j                  |j                        | _        t        j                         | _        y rc   )r8   r9   r   r   r<   r   Tanh
activationre   s     r1   r9   zYolosPooler.__init__'  s9    YYv1163E3EF
'')r0   r#   r5   c                 \    |d d df   }| j                  |      }| j                  |      }|S )Nr   )r   r:  )rI   r#   first_token_tensorr4  s       r1   r\   zYolosPooler.forward,  s6     +1a40

#566r0   r   r`   s   @r1   r%  r%  &  s*    ${ $
U\\ ell r0   r%  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rc   )r   r   ).0nks      r1   	<genexpr>z2YolosMLPPredictionHead.__init__.<locals>.<genexpr>C  s     #g1BIIaO#gs   #%)r8   r9   
num_layersr   r   ziplayers)rI   	input_dim
hidden_dim
output_dimrE  hrJ   s         r1   r9   zYolosMLPPredictionHead.__init__?  sS    $LJN+mm#gYKRSOUVZdYeUe@f#ggr0   c                     t        | j                        D ]D  \  }}|| j                  dz
  k  r%t        j                  j                   ||            n ||      }F |S r7   )r  rG  rE  r   rq   relu)rI   xr  r   s       r1   r\   zYolosMLPPredictionHead.forwardE  sT    !$++. 	VHAu01DOOa4G0G""58,USTXA	Vr0   )r%   r&   r'   r(   r9   r\   r_   r`   s   @r1   r>  r>  6  s    hr0   r>  zy
    YOLOS Model (consisting of a ViT encoder) with object detection heads on top, for tasks such as COCO detection.
    c                        e Zd Zdef fdZej                  j                  d        Ze	e
	 d	dej                  deee      dee   defd              Z xZS )
YolosForObjectDetectionr4   c                 "   t         |   |       t        |d      | _        t	        |j
                  |j
                  |j                  dz   d      | _        t	        |j
                  |j
                  dd      | _        | j                          y )NF)r!  r   r   )rH  rI  rJ  rE     )
r8   r9   r   r  r>  r<   
num_labelsclass_labels_classifierbbox_predictorr'  re   s     r1   r9   z YolosForObjectDetection.__init__Q  s      f> (>((V5G5GTZTeTehiTivw(
$ 5((V5G5GTUbc

 	r0   c                 ^    t        |d d |d d       D cg c]
  \  }}||d c}}S c c}}w )NrM   )r   r    )rF  )rI   outputs_classoutputs_coordabs        r1   _set_aux_lossz%YolosForObjectDetection._set_aux_lossd  s9    
 <?}Sb?QS`adbdSe;fg41a1A.gggs   )rK   labelsr   r5   c           
      d    | j                   |fi |}|j                  }|dd| j                  j                   dddf   }| j	                  |      }| j                  |      j                         }d\  }}	}
|d\  }}| j                  j                  r<|j                  }| j	                  |      }| j                  |      j                         }| j                  ||| j                  || j                  ||      \  }}	}
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)NNNr5  )r   r   r   r    r!   r"   r#   r$   )r  r"   r4   r>   rT  rU  sigmoidauxiliary_lossr#   loss_functiondevicer   r$   )rI   rK   r\  r   outputsr3  r   r    r   r   r!   rW  rX  r   s                 r1   r\   zYolosForObjectDetection.forwardk  s;   j /7dhh|.Nv.N!33 *!dkk.N.N-N-PRS*ST --o>((9AAC
-=*i*+5(M={{))&44 $ < <\ J $ 3 3L A I I K151C1CZmUb2.D). *!/%77!//))	
 		
r0   rc   )r%   r&   r'   r   r9   r)   jitunusedr[  r   r   r*   r   r-   r,   r   r   r   r\   r_   r`   s   @r1   rP  rP  K  s    { & YYh h  (,Q
''Q
 d$Q
 +,	Q

 
$Q
  Q
r0   rP  )rP  r   r
  )r   )>r(   collections.abcr   dataclassesr   typingr   r   r   r)   torch.utils.checkpointr   activationsr	   modeling_layersr
   modeling_outputsr   r   modeling_utilsr   r   processing_utilsr   pytorch_utilsr   r   utilsr   r   r   r   utils.genericr   r   configuration_yolosr   
get_loggerr%   loggerr   Moduler3   rG   r   r@   r^   floatr   r   r   r   r   r   r   r   r
  r   r%  r>  rP  __all__r/   r0   r1   <module>rw     s&     ! , ,    ! 9 K F & Q M M A , 
		H	% 
: : :B'bii 'T299 :ryy B299 R %II%<<% 
% <<	%
 U\\*% % %>1. 1.jbii $RYY @		  
")) 
+ <+@299 +@\ *? * *8 =j% =j =j@"))  RYY * 
n
2 n

n
b Lr0   