
    UhV                     f   d Z ddlZddlmZ ddl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 dd
lmZmZ ddlmZ  ej0                  e      Ze G d de             Z G d dej8                        Z	 d#dej8                  de	j<                  de	j<                  de	j<                  dee	j<                     dedefdZ  G d dej8                        Z! G d dej8                        Z" G d dej8                        Z# G d d ej8                        Z$ G d! d"ej8                        Z%y)$zTPyTorch IdeficsVision model: a copy of CLIPVisionModel using a simpler config object    N)	dataclass)CallableOptionalTupleUnion)nn   )ACT2FN)BaseModelOutputBaseModelOutputWithPooling)ALL_ATTENTION_FUNCTIONS)ModelOutputlogging   )IdeficsVisionConfigc                       e Zd ZU dZdZeej                     ed<   dZ	eej                     ed<   dZ
eeej                  df      ed<   dZeeej                  df      ed<   y)IdeficsVisionModelOutputa  
    Base class for vision model's outputs that also contains image embeddings of the pooling of the last hidden states.

    Args:
        image_embeds (`torch.FloatTensor` of shape `(batch_size, output_dim)` *optional* returned when model is initialized with `with_projection=True`):
            The image embeddings obtained by applying the projection layer to the pooler_output.
        last_hidden_state (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`):
            Sequence of hidden-states at the output of the last layer of the model.
        hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
            Tuple of `torch.FloatTensor` (one for the output of the embeddings, 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image_embedslast_hidden_state.hidden_states
attentions)__name__
__module____qualname____doc__r   r   torchFloatTensor__annotations__r   r   r   r        t/var/www/catia.catastroantioquia-mas.com/valormas/lib/python3.12/site-packages/transformers/models/idefics/vision.pyr   r   &   sr    * 15L(5,,-459x 1 129=AM8E%"3"3S"89:A:>Ju00#567>r    r   c                        e Zd Zdef fdZdej                  dededej                  fdZddej                  d	e
dej                  fd
Z xZS )IdeficsVisionEmbeddingsconfigc                    t         |           || _        |j                  | _        |j
                  | _        |j                  | _        t        j                  t        j                  | j                              | _        t        j                  |j                  | j                  | j                  | j                  d      | _        | j
                  | j                  z  dz  | _        | j                  dz   | _        t        j"                  | j                   | j                        | _        | j'                  dt        j(                  | j                         j+                  d      d       y )NF)in_channelsout_channelskernel_sizestridebias   r   position_ids)r   )
persistent)super__init__r$   hidden_size	embed_dim
image_size
patch_sizer   	Parameterr   randnclass_embeddingConv2dnum_channelspatch_embeddingnum_patchesnum_positions	Embeddingposition_embeddingregister_bufferarangeexpandselfr$   	__class__s     r!   r0   z IdeficsVisionEmbeddings.__init__E   s	   ++ ++ ++!||EKK,GH!yy++?? 
 !OOt>1D!--1"$,,t/A/A4>>"R^U\\$:L:L-M-T-TU\-]jopr    
embeddingsheightwidthreturnc                    |j                   d   dz
  }| j                  | j                        }|j                   d   dz
  }||k(  r||k(  r|S |dddf   }|ddddf   }|j                   d   }	|| j                  j                  z  }
|| j                  j                  z  }|
dz   |dz   }}
t        j                  |      }|j                  dt        |      t        |      |	      }|j                  dddd      }|j                  t        j                  k(  }|r4t        j                  d       |j                  t        j                         }t"        j$                  j'                  ||
|z  ||z  fd	d
      }|r|j                  t        j                        }t        |
      |j                   d   k7  st        |      |j                   d   k7  rBt)        dt        |
      t        |      f d|j                   d   |j                   d   f d      |j                  dddd      j+                  dd|	      }t        j,                  |j/                  d      |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.

        Source:
        https://github.com/facebookresearch/dino/blob/de9ee3df6cf39fac952ab558447af1fa1365362a/vision_transformer.py#L174
        r   Nr   r-   g?r	   r+   zUpcasting patch_pos_embed to fp32 for interpolation since `upsample_bicubic2d_out_frame` in nn.functional.interpolate is not implemented for 'torch.bfloat16' dtype. This will result in a slight overhead.bicubicF)scale_factormodealign_cornerszNumber of patches for images (z/) don't match the shape of position embedding ()dim)shaper>   r,   r$   r4   mathsqrtreshapeintpermutedtyper   bfloat16loggerwarning_oncetofloatr   
functionalinterpolate
ValueErrorviewcat	unsqueeze)rC   rE   rF   rG   r;   	pos_embedr<   class_pos_embedpatch_pos_embedr2   num_h_patchesnum_w_patchessqrt_num_positionsfp32_upcastings                 r!   interpolate_pos_encodingz0IdeficsVisionEmbeddings.interpolate_pos_encoding\   sf    !&&q)A-++D,=,=>	!*Q.-'FeO#AqD/#AqrE*$$R(	$++"8"88!7!77 (5s':MC<O}!YY}5)11!S9K5LcRdNegpq)11!Q1=(..%..@h .00=O--33'*<<mN`>`a	 4 
 -00@O}!6!6r!::c->PTcTiTijlTm>m0]1CSEW1W0X Y00?0E0Eb0I?K`K`acKd0d/eefh  *11!Q1=BB1b)Tyy/33A6HaPPr    pixel_valuesrk   c                 `   |j                   \  }}}}|sJ|| j                  k7  s|| j                  k7  r,t        d| d| d| j                   d| j                   d	      | j                  j                  j
                  }| j                  |j                  |            }|j                  d      j                  dd      }| j                  j                  |dd      }	t        j                  |	|gd	      }
|r|
| j                  |
||      z   }
|
S |
| j                  | j                        z   }
|
S )
NzInput image size (*z) doesn't match model (z8). You should try to set `interpolate_pos_encoding=True`)rX   r+   r   r-   rP   )rR   r3   r`   r:   weightrX   r\   flatten	transposer7   rA   r   rb   rk   r>   r,   )rC   rl   rk   
batch_sizer9   rF   rG   target_dtypepatch_embedsclass_embedsrE   s              r!   forwardzIdeficsVisionEmbeddings.forward   s8   2>2D2D/
L&%'(ET__,D (% 9)4??*;;su 
 ++2288++LOO,O,OP#++A.88A>++22:q"EYYl;C
 $#d&C&CJPVX]&^^J  $d&=&=d>O>O&PPJr    F)r   r   r   r   r0   r   TensorrV   rk   r   boolrv   __classcell__rD   s   @r!   r#   r#   D   sm    q2 q./Q5<< /Q /QUX /Q]b]i]i /QbE$5$5 QU bgbnbn r    r#   modulequerykeyvalueattention_maskscalingdropoutc                    t        j                  ||j                  dd            |z  }|||z   }t        j                  j                  |dt         j                        j                  |j                        }t        j                  j                  ||| j                        }t        j                  ||      }	|	j                  dd      j                         }	|	|fS )Nr-   rN   )rQ   rX   )ptrainingr   r+   )r   matmulrq   r   r^   softmaxfloat32r\   rX   r   r   
contiguous)
r|   r}   r~   r   r   r   r   kwargsattn_weightsattn_outputs
             r!   eager_attention_forwardr      s     <<s}}R'<=GL!#n4==((2U]](SVVW\WbWbcL==((6??([L,,|U3K''1-88:K$$r    c                        e Zd ZdZdef fdZ	 	 	 d
dej                  deej                     deej                     dee	   de
ej                  eej                     f   f
d	Z xZS )IdeficsVisionAttentionz=Multi-headed attention from 'Attention Is All You Need' paperr$   c                    t         |           || _        |j                  | _        |j
                  | _        | j                  | j                  z  | _        | j                  | j                  z  | j                  k7  r&t        d| j                   d| j                   d      | j                  dz  | _	        |j                  | _        d| _        t        j                  | j                  | j                        | _        t        j                  | j                  | j                        | _        t        j                  | j                  | j                        | _        t        j                  | j                  | j                        | _        y )Nz;embed_dim must be divisible by num_heads (got `embed_dim`: z and `num_heads`: z).g      F)r/   r0   r$   r1   r2   num_attention_heads	num_headshead_dimr`   scaleattention_dropoutr   	is_causalr   Lineark_projv_projq_projout_projrB   s     r!   r0   zIdeficsVisionAttention.__init__   s   ++33$..8==4>>)T^^;MdnnM] ^NN#2'  ]]D(
//ii?ii?ii?		$..$..Ar    r   r   causal_attention_maskoutput_attentionsrH   c           
         |j                   \  }}}| j                  |      }| j                  |      }	| j                  |      }
|j	                  ||| j
                  | j                        j                  dd      }|	j	                  ||| j
                  | j                        j                  dd      }	|
j	                  ||| j
                  | j                        j                  dd      }
| j                  j                  dk7  r||||z   }n||}n	|du| _
        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%                  |||      j'                         }| j)                  |      }|sd}||fS )
z#Input shape: Batch x Time x Channelr   r+   flash_attention_2N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   r   )rR   r   r   r   ra   r   r   rq   r$   _attn_implementationr   r   rZ   r[   r   r   r   r   rU   r   r   )rC   r   r   r   r   rr   
seq_lengthr2   querieskeysvaluesattention_interfacer   r   s                 r!   rv   zIdeficsVisionAttention.forward   s    -:,?,?)
J	++m,{{=)]+,,z:t~~t}}U__`acdeyyZOYYZ[]^_ZT^^T]]S]]^_abc ;;++/BB).C.O!/2G!G&2!62$>DN(?;;++w6{{//69>O##L
 '>dkk>^>^&_#$7nnJJ#}}C$,,	%
!\ "))*j)LWWYmmK0 LL((r    )NNF)r   r   r   r   r   r0   r   rx   r   ry   r   rv   rz   r{   s   @r!   r   r      s    GB2 B. 268<,15)||5) !.5)  (5	5)
 $D>5) 
u||Xell33	45)r    r   c                   V     e Zd Z fdZdej
                  dej
                  fdZ xZS )IdeficsVisionMLPc                    t         |           || _        t        |j                     | _        t        j                  |j                  |j                        | _
        t        j                  |j                  |j                        | _        y N)r/   r0   r$   r
   
hidden_actactivation_fnr   r   r1   intermediate_sizefc1fc2rB   s     r!   r0   zIdeficsVisionMLP.__init__  sd    #F$5$5699V//1I1IJ99V55v7I7IJr    r   rH   c                 l    | j                  |      }| j                  |      }| j                  |      }|S r   )r   r   r   )rC   r   s     r!   rv   zIdeficsVisionMLP.forward  s4    /**=9/r    )r   r   r   r0   r   rx   rv   rz   r{   s   @r!   r   r     s$    KU\\ ell r    r   c                        e Zd Zdef fdZ	 d	dej                  dej                  dej                  dee   de	ej                     f
dZ xZS )
IdeficsVisionEncoderLayerr$   c                 D   t         |           |j                  | _        t	        |      | _        t        j                  | j                  |j                        | _	        t        |      | _        t        j                  | j                  |j                        | _        y N)eps)r/   r0   r1   r2   r   	self_attnr   	LayerNormlayer_norm_epslayer_norm1r   mlplayer_norm2rB   s     r!   r0   z"IdeficsVisionEncoderLayer.__init__  sm    ++/7<<F<Q<QR#F+<<F<Q<QRr    r   r   r   r   rH   c                     |}| j                  |      }| j                  ||||      \  }}||z   }|}| j                  |      }| j                  |      }||z   }|f}|r||fz  }|S )aI  
        Args:
            hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
            attention_mask (`torch.FloatTensor`): attention mask of size
                `(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values.
                `(config.encoder_attention_heads,)`.
            output_attentions (`bool`, *optional*):
                Whether or not to return the attentions tensors of all attention layers. See `attentions` under
                returned tensors for more detail.
        )r   r   r   r   )r   r   r   r   )rC   r   r   r   r   residualr   outputss           r!   rv   z!IdeficsVisionEncoderLayer.forward'  s    " !((7&*nn')"7/	 '5 '
#| !=0 ((7/ =0 "&Gr    rw   )r   r   r   r   r0   r   rx   r   ry   r   r   rv   rz   r{   s   @r!   r   r     sg    S2 S -2&||& &  %||	&
 $D>& 
u  	!&r    r   c                        e Zd ZdZdef fdZ	 	 	 	 	 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 )IdeficsVisionEncoderz
    Transformer encoder consisting of `config.num_hidden_layers` self attention layers. Each layer is a
    [`IdeficsVisionEncoderLayer`].

    Args:
        config: IdeficsVisionConfig
    r$   c                     t         |           || _        t        j                  t        |j                        D cg c]  }t        |       c}      | _        d| _	        y c c}w )NF)
r/   r0   r$   r   
ModuleListrangenum_hidden_layersr   layersgradient_checkpointing)rC   r$   _rD   s      r!   r0   zIdeficsVisionEncoder.__init__Z  sQ    mmPUV\VnVnPo$p1%>v%F$pq&+# %qs   A#r   r   r   output_hidden_statesreturn_dictrH   c                    ||n| j                   j                  }||n| j                   j                  }||n| j                   j                  }|rdnd}|rdnd}|}	t	        | j
                        D ]b  \  }
}|r||	fz   }| j                  r,| j                  r | j                  |j                  |	|||      }n ||	|||      }|d   }	|sZ||d   fz   }d |r||	fz   }|st        d |	||fD              S t        |	||      S )a  
        Args:
            inputs_embeds (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`):
                Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation.
                This is useful if you want more control over how to convert `input_ids` indices into associated vectors
                than the model's internal embedding lookup matrix.
            attention_mask (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
                Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

                - 1 for tokens that are **not masked**,
                - 0 for tokens that are **masked**.

                [What are attention masks?](../glossary#attention-mask)
            causal_attention_mask (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
                Causal mask for the text model. Mask values selected in `[0, 1]`:

                - 1 for tokens that are **not masked**,
                - 0 for tokens that are **masked**.

                [What are attention masks?](../glossary#attention-mask)
            output_attentions (`bool`, *optional*):
                Whether or not to return the attentions tensors of all attention layers. See `attentions` under
                returned tensors for more detail.
            output_hidden_states (`bool`, *optional*):
                Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors
                for more detail.
            return_dict (`bool`, *optional*):
                Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple.
        Nr   )r   r   r   c              3   &   K   | ]	  }||  y wr   r   ).0vs     r!   	<genexpr>z/IdeficsVisionEncoder.forward.<locals>.<genexpr>  s     eqWXWdes   )r   r   r   )r$   r   r   use_return_dict	enumerater   r   r   _gradient_checkpointing_func__call__tupler   )rC   inputs_embedsr   r   r   r   r   encoder_statesall_attentionsr   idxencoder_layerlayer_outputss                r!   rv   zIdeficsVisionEncoder.forward`  sH   L 2C1N-TXT_T_TqTq$8$D $++JjJj 	 &1%<k$++B]B]30d%"+DKK"8 	FC#!/=2B!B**t}} $ A A!**!")%! !.!")&7	! *!,M !/=3C2E!E-	F0  +}.>>Ne]NN$Seee+>Vd
 	
r    )NNNNN)r   r   r   r   r   r0   r   r   rx   ry   r   r   r   rv   rz   r{   s   @r!   r   r   Q  s    ,2 , 268<,0/3&*O
 !.O
  (5	O

 $D>O
 'tnO
 d^O
 
uo%	&O
r    r   c                        e Zd Zdef fdZ	 	 	 	 	 d
deej                     dee   dee   dee   dee   de	e
ef   fd	Z xZS )IdeficsVisionTransformerr$   c                     t         |           || _        |j                  }t	        |      | _        t        j                  ||j                        | _	        t        |      | _        t        j                  ||j                        | _        y r   )r/   r0   r$   r1   r#   rE   r   r   r   pre_layrnormr   encoderpost_layernorm)rC   r$   r2   rD   s      r!   r0   z!IdeficsVisionTransformer.__init__  sj    &&	1&9LL8M8MN+F3 ll9&:O:OPr    rl   r   r   rk   r   rH   c                    ||n| j                   j                  }||n| j                   j                  }||n| j                   j                  }|t	        d      | j                  ||      }| j                  |      }| j                  ||||      }|d   }|dddddf   }	| j                  |	      }	|s
||	f|dd z   S t        ||	|j                  |j                        S )z
        Returns:

        Nz You have to specify pixel_values)rk   )r   r   r   r   r   r   )r   pooler_outputr   r   )r$   r   r   r   r`   rE   r   r   r   r   r   r   )
rC   rl   r   r   rk   r   r   encoder_outputsr   pooled_outputs
             r!   rv   z IdeficsVisionTransformer.forward  s    2C1N-TXT_T_TqTq$8$D $++JjJj 	 &1%<k$++B]B]?@@Ogh))-8,,'/!5#	 ' 
 ,A.)!Q'2++M:%}58KKK)/')77&11	
 	
r    )NNNFN)r   r   r   r   r0   r   r   r   ry   r   r   r   rv   rz   r{   s   @r!   r   r     s    Q2 Q 59,0/338&*+
u001+
 $D>+
 'tn	+

 #+4.+
 d^+
 
u00	1+
r    r   )r   )&r   rS   dataclassesr   typingr   r   r   r   r   torch.utils.checkpointr   activationsr
   modeling_outputsr   r   modeling_utilsr   utilsr   r   configuration_ideficsr   
get_loggerr   rZ   r   Moduler#   rx   r]   r   r   r   r   r   r   r   r    r!   <module>r      s1   [  ! 3 3    ! K 5 7 
		H	% ?{ ? ?:`bii `V %II%<<% 
% <<	%
 U\\*% % %,L)RYY L)`ryy  /		 /f^
299 ^
D7
ryy 7
r    