
    Uh|              	       \   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mZmZ ddlmZ dd	lmZ dd
lmZ ddlmZmZ ddlmZmZmZmZmZmZ ddlm Z  ddl!m"Z"  e       r	ddl#m$Z$m%Z% nd Z%d Z$ ejL                  e'      Z(e G d de             Z)e G d de             Z*e G d de             Z+ G d de
jX                        Z- G d de
jX                        Z. G d de
jX                        Z/dBdej`                  d e1d!e2d"ej`                  fd#Z3 G d$ d%e
jX                        Z4 G d& d'e
jX                        Z5 G d( d)e
jX                        Z6 G d* d+e
jX                        Z7 G d, d-e
jX                        Z8 G d. d/e
jX                        Z9 G d0 d1e
jX                        Z: G d2 d3e
jX                        Z; G d4 d5e
jX                        Z<e G d6 d7e             Z=e G d8 d9e=             Z> ed:;       G d< d=e=             Z? ed>;       G d? d@e=e              Z@g dAZAy)Cz9PyTorch Dilated Neighborhood Attention Transformer model.    N)	dataclass)OptionalTupleUnion)nn)BCEWithLogitsLossCrossEntropyLossMSELoss   )ACT2FN)BackboneOutput)PreTrainedModel) find_pruneable_heads_and_indicesprune_linear_layer)ModelOutputOptionalDependencyNotAvailableauto_docstringis_natten_availableloggingrequires_backends)BackboneMixin   )DinatConfig)
natten2davnatten2dqkrpbc                      t               Nr   argskwargss     z/var/www/catia.catastroantioquia-mas.com/valormas/lib/python3.12/site-packages/transformers/models/dinat/modeling_dinat.pyr   r   .       ,..    c                      t               r   r   r   s     r"   r   r   1   r#   r$   c                       e Zd ZU dZdZeej                     ed<   dZ	ee
ej                  df      ed<   dZee
ej                  df      ed<   dZee
ej                  df      ed<   y)DinatEncoderOutputa  
    Dinat encoder's outputs, with potential hidden states and attentions.

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

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

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

            Hidden-states of the model at the output of each layer plus the initial embedding outputs reshaped to
            include the spatial dimensions.
    Nlast_hidden_state.hidden_states
attentionsreshaped_hidden_states)__name__
__module____qualname____doc__r(   r   torchFloatTensor__annotations__r)   r   r*   r+    r$   r"   r'   r'   ;   s}    2 6:x 1 129=AM8E%"3"3S"89:A:>Ju00#567>FJHU5+<+<c+A%BCJr$   r'   c                       e Zd ZU dZdZeej                     ed<   dZ	eej                     ed<   dZ
eeej                  df      ed<   dZeeej                  df      ed<   dZeeej                  df      ed<   y)	DinatModelOutputaU  
    Dinat model's outputs that also contains a pooling of the last hidden states.

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

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

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

            Hidden-states of the model at the output of each layer plus the initial embedding outputs reshaped to
            include the spatial dimensions.
    Nr(   pooler_output.r)   r*   r+   )r,   r-   r.   r/   r(   r   r0   r1   r2   r6   r)   r   r*   r+   r3   r$   r"   r5   r5   \   s    6 6:x 1 12915M8E--.5=AM8E%"3"3S"89:A:>Ju00#567>FJHU5+<+<c+A%BCJr$   r5   c                       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<   dZeeej                  df      ed<   y)	DinatImageClassifierOutputa  
    Dinat outputs for image classification.

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

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

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

            Hidden-states of the model at the output of each layer plus the initial embedding outputs reshaped to
            include the spatial dimensions.
    Nlosslogits.r)   r*   r+   )r,   r-   r.   r/   r9   r   r0   r1   r2   r:   r)   r   r*   r+   r3   r$   r"   r8   r8      s    6 )-D(5$$
%,*.FHU&&'.=AM8E%"3"3S"89:A:>Ju00#567>FJHU5+<+<c+A%BCJr$   r8   c                   f     e Zd ZdZ fdZdeej                     deej                     fdZ
 xZS )DinatEmbeddingsz6
    Construct the patch and position embeddings.
    c                     t         |           t        |      | _        t	        j
                  |j                        | _        t	        j                  |j                        | _
        y r   )super__init__DinatPatchEmbeddingspatch_embeddingsr   	LayerNorm	embed_dimnormDropouthidden_dropout_probdropoutselfconfig	__class__s     r"   r?   zDinatEmbeddings.__init__   sG     4V <LL!1!12	zz&"<"<=r$   pixel_valuesreturnc                 l    | j                  |      }| j                  |      }| j                  |      }|S r   )rA   rD   rG   )rI   rL   
embeddingss      r"   forwardzDinatEmbeddings.forward   s4    **<8
YYz*
\\*-
r$   )r,   r-   r.   r/   r?   r   r0   r1   r   TensorrP   __classcell__rK   s   @r"   r<   r<      s4    >HU->->$? E%,,DW r$   r<   c                   `     e Zd ZdZ fdZde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, height, width, hidden_size)` to be consumed by a
    Transformer.
    c           
      P   t         |           |j                  }|j                  |j                  }}|| _        |dk(  rnt        d      t        j                  t        j                  | j                  |dz  ddd      t        j                  |dz  |ddd            | _	        y )N   z2Dinat only supports patch size of 4 at the moment.   r   r   rW   rW   r   r   )kernel_sizestridepadding)
r>   r?   
patch_sizenum_channelsrC   
ValueErrorr   
SequentialConv2d
projection)rI   rJ   r^   r_   hidden_sizerK   s        r"   r?   zDinatPatchEmbeddings.__init__   s    &&
$*$7$79I9Ik(? QRR--IId'')9vV\flmIIkQ&PV`fg
r$   rL   rM   c                     |j                   \  }}}}|| j                  k7  rt        d      | j                  |      }|j	                  dddd      }|S )NzeMake sure that the channel dimension of the pixel values match with the one set in the configuration.r   rW   r   r   )shaper_   r`   rc   permute)rI   rL   _r_   heightwidthrO   s          r"   rP   zDinatPatchEmbeddings.forward   s`    )5););&<4,,,w  __\2
''1a3
r$   )r,   r-   r.   r/   r?   r   r0   r1   rQ   rP   rR   rS   s   @r"   r@   r@      s/    
"	HU->->$? 	ELL 	r$   r@   c                        e Zd ZdZej
                  fdedej                  ddf fdZde	j                  de	j                  fdZ xZS )	DinatDownsamplerz
    Convolutional Downsampling Layer.

    Args:
        dim (`int`):
            Number of input channels.
        norm_layer (`nn.Module`, *optional*, defaults to `nn.LayerNorm`):
            Normalization layer class.
    dim
norm_layerrM   Nc                     t         |           || _        t        j                  |d|z  dddd      | _         |d|z        | _        y )NrW   rX   rY   rZ   F)r[   r\   r]   bias)r>   r?   rm   r   rb   	reductionrD   )rI   rm   rn   rK   s      r"   r?   zDinatDownsampler.__init__   sE    3CVF\binoq3w'	r$   input_featurec                     | j                  |j                  dddd            j                  dddd      }| j                  |      }|S )Nr   r   r   rW   )rq   rg   rD   )rI   rr   s     r"   rP   zDinatDownsampler.forward   sJ    }'<'<Q1a'HIQQRSUVXY[\]		-0r$   )r,   r-   r.   r/   r   rB   intModuler?   r0   rQ   rP   rR   rS   s   @r"   rl   rl      sJ     :< (C (RYY ($ (U\\ ell r$   rl   input	drop_probtrainingrM   c                    |dk(  s|s| S d|z
  }| j                   d   fd| j                  dz
  z  z   }|t        j                  || j                  | j
                        z   }|j                          | j                  |      |z  }|S )aF  
    Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

    Comment by Ross Wightman: This is the same as the DropConnect impl I created for EfficientNet, etc networks,
    however, the original name is misleading as 'Drop Connect' is a different form of dropout in a separate paper...
    See discussion: https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 ... I've opted for changing the
    layer and argument names to 'drop path' rather than mix DropConnect as a layer name and use 'survival rate' as the
    argument.
            r   r   )r   )dtypedevice)rf   ndimr0   randr{   r|   floor_div)rv   rw   rx   	keep_probrf   random_tensoroutputs          r"   	drop_pathr      s     CxII[[^

Q 77E

5ELL YYMYYy!M1FMr$   c                   x     e Zd ZdZd	dee   ddf fdZdej                  dej                  fdZ	de
fdZ xZS )
DinatDropPathzXDrop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).Nrw   rM   c                 0    t         |           || _        y r   )r>   r?   rw   )rI   rw   rK   s     r"   r?   zDinatDropPath.__init__  s    "r$   r)   c                 D    t        || j                  | j                        S r   )r   rw   rx   rI   r)   s     r"   rP   zDinatDropPath.forward  s    FFr$   c                 8    dj                  | j                        S )Nzp={})formatrw   rI   s    r"   
extra_reprzDinatDropPath.extra_repr  s    }}T^^,,r$   r   )r,   r-   r.   r/   r   floatr?   r0   rQ   rP   strr   rR   rS   s   @r"   r   r     sG    b#(5/ #T #GU\\ Gell G-C -r$   r   c                   p     e Zd Z fdZd Z	 ddej                  dee   de	ej                     fdZ
 xZS )NeighborhoodAttentionc                 *   t         |           ||z  dk7  rt        d| d| d      || _        t	        ||z        | _        | j                  | j
                  z  | _        || _        || _        t        j                  t        j                  |d| j                  z  dz
  d| j                  z  dz
              | _        t        j                  | j                  | j                  |j                        | _        t        j                  | j                  | j                  |j                        | _        t        j                  | j                  | j                  |j                        | _        t        j&                  |j(                        | _        y )Nr   zThe hidden size (z6) is not a multiple of the number of attention heads ()rW   r   )rp   )r>   r?   r`   num_attention_headsrt   attention_head_sizeall_head_sizer[   dilationr   	Parameterr0   zerosrpbLinearqkv_biasquerykeyvaluerE   attention_probs_dropout_probrG   rI   rJ   rm   	num_headsr[   r   rK   s         r"   r?   zNeighborhoodAttention.__init__  sD   ?a#C5(^_h^iijk  $- #&sY#7 !558P8PP&  <<ID<L<L8Lq8PTUX\XhXhThklTl noYYt1143E3EFOO\
99T//1C1C&//ZYYt1143E3EFOO\
zz&"E"EFr$   c                     |j                         d d | j                  | j                  fz   }|j                  |      }|j	                  ddddd      S )Nr   r   r   rW   rV   )sizer   r   viewrg   )rI   xnew_x_shapes      r"   transpose_for_scoresz*NeighborhoodAttention.transpose_for_scores0  sN    ffhsmt'?'?AYAY&ZZFF;yyAq!Q''r$   r)   output_attentionsrM   c                    | j                  | j                  |            }| j                  | j                  |            }| j                  | j                  |            }|t	        j
                  | j                        z  }t        ||| j                  | j                  | j                        }t        j                  j                  |d      }| j                  |      }t        ||| j                  | j                        }|j!                  ddddd      j#                         }|j%                         d d | j&                  fz   }	|j)                  |	      }|r||f}
|
S |f}
|
S )	Nr   rm   r   rW   r   r   rV   )r   r   r   r   mathsqrtr   r   r   r[   r   r   
functionalsoftmaxrG   r   rg   
contiguousr   r   r   )rI   r)   r   query_layer	key_layervalue_layerattention_scoresattention_probscontext_layernew_context_layer_shapeoutputss              r"   rP   zNeighborhoodAttention.forward5  sQ   
 //

=0IJ--dhh}.EF	//

=0IJ
 "DIId.F.F$GG )i4K[K[]a]j]jk --//0@b/I ,,7"?KAQAQSWS`S`a%--aAq!<GGI"/"4"4"6s";t?Q?Q>S"S%**+BC6G=/2 O\M]r$   F)r,   r-   r.   r?   r   r0   rQ   r   boolr   rP   rR   rS   s   @r"   r   r     sE    G,( -2|| $D> 
u||		r$   r   c                   n     e Zd Z fdZdej
                  dej
                  dej
                  fdZ xZS )NeighborhoodAttentionOutputc                     t         |           t        j                  ||      | _        t        j
                  |j                        | _        y r   )r>   r?   r   r   denserE   r   rG   rI   rJ   rm   rK   s      r"   r?   z$NeighborhoodAttentionOutput.__init__X  s6    YYsC(
zz&"E"EFr$   r)   input_tensorrM   c                 J    | j                  |      }| j                  |      }|S r   r   rG   )rI   r)   r   s      r"   rP   z#NeighborhoodAttentionOutput.forward]  s$    

=1]3r$   r,   r-   r.   r?   r0   rQ   rP   rR   rS   s   @r"   r   r   W  s2    G
U\\  RWR^R^ r$   r   c                   p     e Zd Z fdZd Z	 ddej                  dee   de	ej                     fdZ
 xZS )NeighborhoodAttentionModulec                     t         |           t        |||||      | _        t	        ||      | _        t               | _        y r   )r>   r?   r   rI   r   r   setpruned_headsr   s         r"   r?   z$NeighborhoodAttentionModule.__init__e  s:    )&#y+xX	1&#>Er$   c                 >   t        |      dk(  ry t        || j                  j                  | j                  j                  | j
                        \  }}t        | j                  j                  |      | j                  _        t        | j                  j                  |      | j                  _        t        | j                  j                  |      | j                  _	        t        | j                  j                  |d      | j                  _        | j                  j                  t        |      z
  | j                  _        | j                  j                  | j                  j                  z  | j                  _        | j
                  j                  |      | _        y )Nr   r   r   )lenr   rI   r   r   r   r   r   r   r   r   r   r   union)rI   headsindexs      r"   prune_headsz'NeighborhoodAttentionModule.prune_headsk  s   u:?749900$))2O2OQUQbQb
u
 -TYY__eD		*499==%@		,TYY__eD		.t{{/@/@%QO )-		(E(EE
(R		%"&))"?"?$))B_B_"_		 --33E:r$   r)   r   rM   c                 f    | j                  ||      }| j                  |d   |      }|f|dd  z   }|S Nr   r   )rI   r   )rI   r)   r   self_outputsattention_outputr   s         r"   rP   z#NeighborhoodAttentionModule.forward}  sC    
 yy0AB;;|AF#%QR(88r$   r   )r,   r-   r.   r?   r   r0   rQ   r   r   r   rP   rR   rS   s   @r"   r   r   d  sD    ";* -2|| $D> 
u||		r$   r   c                   V     e Zd Z fdZdej
                  dej
                  fdZ xZS )DinatIntermediatec                    t         |           t        j                  |t	        |j
                  |z              | _        t        |j                  t              rt        |j                     | _        y |j                  | _        y r   )r>   r?   r   r   rt   	mlp_ratior   
isinstance
hidden_actr   r   intermediate_act_fnr   s      r"   r?   zDinatIntermediate.__init__  sa    YYsC(8(83(>$?@
f''-'-f.?.?'@D$'-'8'8D$r$   r)   rM   c                 J    | j                  |      }| j                  |      }|S r   )r   r   r   s     r"   rP   zDinatIntermediate.forward  s&    

=100?r$   r   rS   s   @r"   r   r     s#    9U\\ ell r$   r   c                   V     e Zd Z fdZdej
                  dej
                  fdZ xZS )DinatOutputc                     t         |           t        j                  t	        |j
                  |z        |      | _        t        j                  |j                        | _	        y r   )
r>   r?   r   r   rt   r   r   rE   rF   rG   r   s      r"   r?   zDinatOutput.__init__  sF    YYs6#3#3c#9:C@
zz&"<"<=r$   r)   rM   c                 J    | j                  |      }| j                  |      }|S r   r   r   s     r"   rP   zDinatOutput.forward  s$    

=1]3r$   r   rS   s   @r"   r   r     s#    >
U\\ ell r$   r   c            	            e Zd Zd fd	Zd Z	 ddej                  dee   de	ej                  ej                  f   fdZ
 xZS )	
DinatLayerc                    t         |           |j                  | _        |j                  | _        || _        | j                  | j                  z  | _        t        j                  ||j                        | _	        t        |||| j                  | j                        | _        |dkD  rt        |      nt        j                         | _        t        j                  ||j                        | _        t!        ||      | _        t%        ||      | _        |j(                  dkD  r?t        j*                  |j(                  t-        j.                  d|f      z  d      | _        y d | _        y )Neps)r[   r   rz   r   rW   T)requires_grad)r>   r?   chunk_size_feed_forwardr[   r   window_sizer   rB   layer_norm_epslayernorm_beforer   	attentionr   Identityr   layernorm_afterr   intermediater   r   layer_scale_init_valuer   r0   oneslayer_scale_parameters)rI   rJ   rm   r   r   drop_path_raterK   s         r"   r?   zDinatLayer.__init__  s(   '-'E'E$!-- ++dmm; "Sf6K6K L4C0@0@4==
 ;I3:N~6TVT_T_Ta!||CV5J5JK-fc:!&#. ,,q0 LL66QH9MM]ab 	#  	#r$   c                     | j                   }d}||k  s||k  rJdx}}t        d||z
        }t        d||z
        }	dd||||	f}t        j                  j	                  ||      }||fS )N)r   r   r   r   r   r   r   )r   maxr   r   pad)
rI   r)   ri   rj   r   
pad_valuespad_lpad_tpad_rpad_bs
             r"   	maybe_padzDinatLayer.maybe_pad  s    &&'
K5;#6EE;./E;/0EQueU;JMM--mZHMj((r$   r)   r   rM   c                    |j                         \  }}}}|}| j                  |      }| j                  |||      \  }}|j                  \  }	}
}}	| j	                  ||      }|d   }|d   dkD  xs |d   dkD  }|r|d d d |d |d d f   j                         }| j                  | j                  d   |z  }|| j                  |      z   }| j                  |      }| j                  | j                  |            }| j                  | j                  d   |z  }|| j                  |      z   }|r	||d   f}|S |f}|S )N)r   r   r      r   )r   r   r   rf   r   r   r   r   r   r   r   )rI   r)   r   
batch_sizeri   rj   channelsshortcutr   rh   
height_pad	width_padattention_outputsr   
was_paddedlayer_outputlayer_outputss                    r"   rP   zDinatLayer.forward  s|   
 /<.@.@.B+
FE8 --m<$(NN=&%$P!z&3&9&9#:y! NN=L]N^,Q/]Q&;*Q-!*;
/7F7FUFA0EFQQS&&2#::1=@PP 4>>2B#CC++M:{{4#4#4\#BC&&266q9LHL$t~~l'CC@Q'8';< YeWfr$   )rz   r   )r,   r-   r.   r?   r   r0   rQ   r   r   r   rP   rR   rS   s   @r"   r   r     sM    
(	) -2$||$ $D>$ 
u||U\\)	*	$r$   r   c                   j     e Zd Z fdZ	 ddej
                  dee   deej
                     fdZ	 xZ
S )
DinatStagec                 <   t         	|           || _        || _        t	        j
                  t        |      D cg c]  }t        |||||   ||          c}      | _        |% ||t        j                        | _
        d| _        y d | _
        d| _        y c c}w )N)rJ   rm   r   r   r   )rm   rn   F)r>   r?   rJ   rm   r   
ModuleListranger   layersrB   
downsamplepointing)
rI   rJ   rm   depthr   	dilationsr   r  irK   s
            r"   r?   zDinatStage.__init__  s    mm u	  !'&q\#1!#4	
 !(SR\\JDO  #DO%	s   Br)   r   rM   c                     |j                         \  }}}}t        | j                        D ]  \  }} |||      }|d   } |}	| j                  | j                  |	      }||	f}
|r|
dd  z  }
|
S r   )r   	enumerater  r  )rI   r)   r   rh   ri   rj   r  layer_moduler  !hidden_states_before_downsamplingstage_outputss              r"   rP   zDinatStage.forward  s    
 ,00265!(5 	-OA|(8IJM)!,M	- -:)??& OO,MNM&(IJ]12..Mr$   r   )r,   r-   r.   r?   r0   rQ   r   r   r   rP   rR   rS   s   @r"   r  r    s?    8 -2|| $D> 
u||		r$   r  c                   ~     e Zd Z fdZ	 	 	 	 d	d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 )
DinatEncoderc                    t         |           t        |j                        | _        || _        t        j                  d|j                  t        |j                        d      D cg c]  }|j                          }}t        j                  t        | j                        D cg c]  }t        |t        |j                   d|z  z        |j                  |   |j"                  |   |j$                  |   |t        |j                  d |       t        |j                  d |dz           || j                  dz
  k  rt&        nd        c}      | _        y c c}w c c}w )Nr   cpu)r|   rW   r   )rJ   rm   r  r   r  r   r  )r>   r?   r   depths
num_levelsrJ   r0   linspacer   sumitemr   r
  r  r  rt   rC   r   r  rl   levels)rI   rJ   r   dpri_layerrK   s        r"   r?   zDinatEncoder.__init__  s,   fmm,!&63H3H#fmmJ\ej!klAqvvxllmm  %T__5  !F,,q'z9: --0$..w7$..w7#&s6=='+B'Cc&--XeZadeZeJfFg#h4;dooPQ>Q4Q/X\
 ms   )E(B#Er)   r   output_hidden_states(output_hidden_states_before_downsamplingreturn_dictrM   c                    |rdnd }|rdnd }|rdnd }|r |j                  dddd      }	||fz  }||	fz  }t        | j                        D ]l  \  }
} |||      }|d   }|d   }|r#|r!|j                  dddd      }	||fz  }||	fz  }n$|r"|s |j                  dddd      }	||fz  }||	fz  }|se||dd  z  }n |st        d |||fD              S t	        ||||      S )Nr3   r   r   r   rW   c              3   &   K   | ]	  }||  y wr   r3   ).0vs     r"   	<genexpr>z'DinatEncoder.forward.<locals>.<genexpr>U  s     mq_`_lms   )r(   r)   r*   r+   )rg   r  r   tupler'   )rI   r)   r   r#  r$  r%  all_hidden_statesall_reshaped_hidden_statesall_self_attentionsreshaped_hidden_stater  r  r  r  s                 r"   rP   zDinatEncoder.forward.  s]    #7BD+?RT"$5b4$1$9$9!Q1$E!-!11&+@*BB&(5 	9OA|(8IJM)!,M0=a0@-#(P(I(Q(QRSUVXY[\(]%!&G%II!*/D.FF*%.V(5(=(=aAq(I%!m%55!*/D.FF* #}QR'88#%	9( m]4EGZ$[mmm!++*#=	
 	
r$   )FFFT)r,   r-   r.   r?   r0   rQ   r   r   r   r   r'   rP   rR   rS   s   @r"   r  r    st    
. -2/4CH&*.
||.
 $D>.
 'tn	.

 3;4..
 d^.
 
u((	).
r$   r  c                       e Zd ZeZdZdZd Zy)DinatPreTrainedModeldinatrL   c                    t        |t        j                  t        j                  f      rm|j                  j
                  j                  d| j                  j                         |j                  %|j                  j
                  j                          yyt        |t        j                        rJ|j                  j
                  j                          |j                  j
                  j                  d       yy)zInitialize the weightsrz   )meanstdNg      ?)r   r   r   rb   weightdatanormal_rJ   initializer_rangerp   zero_rB   fill_)rI   modules     r"   _init_weightsz"DinatPreTrainedModel._init_weightse  s    fryy"))45 MM&&CT[[5R5R&S{{&  &&( '-KK""$MM$$S) .r$   N)r,   r-   r.   r   config_classbase_model_prefixmain_input_namer=  r3   r$   r"   r1  r1  _  s    L$O
*r$   r1  c                        e Zd Zd
 fd	Zd Zd Ze	 	 	 	 ddeej                     dee
   dee
   dee
   deeef   f
d	       Z xZS )
DinatModelc                    t         |   |       t        | dg       || _        t	        |j
                        | _        t        |j                  d| j                  dz
  z  z        | _	        t        |      | _        t        |      | _        t        j                  | j                  |j                         | _        |rt        j$                  d      nd| _        | j)                          y)zv
        add_pooling_layer (bool, *optional*, defaults to `True`):
            Whether to add a pooling layer
        nattenrW   r   r   N)r>   r?   r   rJ   r   r  r  rt   rC   num_featuresr<   rO   r  encoderr   rB   r   	layernormAdaptiveAvgPool1dpooler	post_init)rI   rJ   add_pooling_layerrK   s      r"   r?   zDinatModel.__init__t  s    
 	 $
+fmm, 0 0119L3M MN)&1#F+d&7&7V=R=RS1Bb**1- 	r$   c                 .    | j                   j                  S r   rO   rA   r   s    r"   get_input_embeddingszDinatModel.get_input_embeddings      ///r$   c                     |j                         D ]7  \  }}| j                  j                  |   j                  j	                  |       9 y)z
        Prunes heads of the model. heads_to_prune: dict of {layer_num: list of heads to prune in this layer} See base
        class PreTrainedModel
        N)itemsrF  layerr   r   )rI   heads_to_prunerR  r   s       r"   _prune_headszDinatModel._prune_heads  sE    
 +002 	CLE5LLu%//;;EB	Cr$   rL   r   r#  r%  rM   c                 R   ||n| j                   j                  }||n| j                   j                  }||n| j                   j                  }|t	        d      | j                  |      }| j                  ||||      }|d   }| j                  |      }d }| j                  G| j                  |j                  dd      j                  dd            }t        j                  |d      }|s||f|dd  z   }	|	S t        |||j                  |j                  |j                        S )Nz You have to specify pixel_valuesr   r#  r%  r   r   rW   )r(   r6   r)   r*   r+   )rJ   r   r#  use_return_dictr`   rO   rF  rG  rI  flatten	transposer0   r5   r)   r*   r+   )
rI   rL   r   r#  r%  embedding_outputencoder_outputssequence_outputpooled_outputr   s
             r"   rP   zDinatModel.forward  sA    2C1N-TXT_T_TqTq$8$D $++JjJj 	 &1%<k$++B]B]?@@??<8,,/!5#	 ' 
 *!,..9;;" KK(?(?1(E(O(OPQST(UVM!MM-;M%}58KKFM-')77&11#2#I#I
 	
r$   )T)NNNN)r,   r-   r.   r?   rN  rT  r   r   r0   r1   r   r   r   r5   rP   rR   rS   s   @r"   rB  rB  r  s    ,0C  59,0/3&*,
u001,
 $D>,
 'tn	,

 d^,
 
u&&	',
 ,
r$   rB  z
    Dinat Model transformer with an image classification head on top (a linear layer on top of the final hidden state
    of the [CLS] token) e.g. for ImageNet.
    )custom_introc                        e Zd Z fdZe	 	 	 	 	 d	deej                     deej                     dee	   dee	   dee	   de
eef   fd       Z xZS )
DinatForImageClassificationc                 X   t         |   |       t        | dg       |j                  | _        t	        |      | _        |j                  dkD  r4t        j                  | j
                  j                  |j                        nt        j                         | _
        | j                          y )NrD  r   )r>   r?   r   
num_labelsrB  r2  r   r   rE  r   
classifierrJ  rH   s     r"   r?   z$DinatForImageClassification.__init__  s     $
+ ++'
 FLEVEVYZEZBIIdjj--v/@/@A`b`k`k`m 	
 	r$   rL   labelsr   r#  r%  rM   c                 *   ||n| j                   j                  }| j                  ||||      }|d   }| j                  |      }d}	|| j                   j                  | j
                  dk(  rd| j                   _        nl| j
                  dkD  rL|j                  t        j                  k(  s|j                  t        j                  k(  rd| j                   _        nd| j                   _        | j                   j                  dk(  rIt               }
| j
                  dk(  r& |
|j                         |j                               }	n |
||      }	n| j                   j                  dk(  r=t               }
 |
|j                  d| j
                        |j                  d            }	n,| j                   j                  dk(  rt               }
 |
||      }	|s|f|dd z   }|	|	f|z   S |S t        |	||j                   |j"                  |j$                  	      S )
a  
        labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
            Labels for computing the image classification/regression loss. Indices should be in `[0, ...,
            config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
            `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
        NrV  r   
regressionsingle_label_classificationmulti_label_classificationr   rW   )r9   r:   r)   r*   r+   )rJ   rW  r2  rc  problem_typerb  r{   r0   longrt   r
   squeezer	   r   r   r8   r)   r*   r+   )rI   rL   rd  r   r#  r%  r   r]  r:   r9   loss_fctr   s               r"   rP   z#DinatForImageClassification.forward  s    &1%<k$++B]B]**/!5#	  
  
/{{''/??a'/;DKK,__q(fllejj.HFLL\a\e\eLe/LDKK,/KDKK,{{''<7"9??a'#FNN$4fnn6FGD#FF3D))-JJ+-B @&++b/R))-II,./Y,F)-)9TGf$EvE)!//))#*#A#A
 	
r$   )NNNNN)r,   r-   r.   r?   r   r   r0   r1   
LongTensorr   r   r   r8   rP   rR   rS   s   @r"   r`  r`    s       59-1,0/3&*<
u001<
 ))*<
 $D>	<

 'tn<
 d^<
 
u00	1<
 <
r$   r`  zL
    NAT backbone, to be used with frameworks like DETR and MaskFormer.
    c                   x     e Zd Z fdZd Ze	 	 	 d	dej                  dee	   dee	   dee	   de
f
d       Z xZS )
DinatBackbonec           	      .   t         |   |       t         | 	  |       t        | dg       t	        |      | _        t        |      | _        |j                  gt        t        |j                              D cg c]  }t        |j                  d|z  z         c}z   | _        i }t        | j                  | j                         D ]  \  }}t#        j$                  |      ||<    t#        j&                  |      | _        | j+                          y c c}w )NrD  rW   )r>   r?   _init_backboner   r<   rO   r  rF  rC   r  r   r  rt   rE  zip_out_featuresr   r   rB   
ModuleDicthidden_states_normsrJ  )rI   rJ   r  ru  stager_   rK   s         r"   r?   zDinatBackbone.__init__"  s     v&$
+)&1#F+#--.X]^abhbobo^pXq1rST#f6F6FA6M2N1rr !#&t'9'94==#I 	DE<)+l)C&	D#%==1D#E  	 2ss   9"Dc                 .    | j                   j                  S r   rM  r   s    r"   rN  z"DinatBackbone.get_input_embeddings5  rO  r$   rL   r#  r   r%  rM   c                    ||n| j                   j                  }||n| j                   j                  }||n| j                   j                  }| j	                  |      }| j                  ||ddd      }|j                  }d}t        | j                  |      D ]  \  }	}
|	| j                  v s|
j                  \  }}}}|
j                  dddd      j                         }
|
j                  |||z  |      }
 | j                  |	   |
      }
|
j                  ||||      }
|
j                  dddd      j                         }
||
fz  } |s|f}|r||j                  fz  }|S t!        ||r|j                  nd|j"                  	      S )
a/  
        Examples:

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

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

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

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

        >>> outputs = model(**inputs)

        >>> feature_maps = outputs.feature_maps
        >>> list(feature_maps[-1].shape)
        [1, 512, 7, 7]
        ```NT)r   r#  r$  r%  r3   r   rW   r   r   )feature_mapsr)   r*   )rJ   rW  r#  r   rO   rF  r+   rr  stage_namesout_featuresrf   rg   r   r   ru  r)   r   r*   )rI   rL   r#  r   r%  rZ  r   r)   ry  rv  hidden_stater   r_   ri   rj   r   s                   r"   rP   zDinatBackbone.forward8  s   B &1%<k$++B]B]$8$D $++JjJj 	 2C1N-TXT_T_TqTq??<8,,/!%59  
  66#&t'7'7#G 	0E<))):F:L:L7
L&%+33Aq!Q?JJL+00Ve^\Z>t77>|L+00VULY+33Aq!Q?JJL/	0 "_F#70022M%3G'//T))
 	
r$   )NNN)r,   r-   r.   r?   rN  r   r0   rQ   r   r   r   rP   rR   rS   s   @r"   ro  ro    ss    &0  04,0&*G
llG
 'tnG
 $D>	G

 d^G
 
G
 G
r$   ro  )r`  rB  r1  ro  )rz   F)Br/   r   dataclassesr   typingr   r   r   r0   torch.utils.checkpointr   torch.nnr   r	   r
   activationsr   modeling_outputsr   modeling_utilsr   pytorch_utilsr   r   utilsr   r   r   r   r   r   utils.backbone_utilsr   configuration_dinatr   natten.functionalr   r   
get_loggerr,   loggerr'   r5   r8   ru   r<   r@   rl   rQ   r   r   r   r   r   r   r   r   r   r   r  r  r1  rB  r`  ro  __all__r3   r$   r"   <module>r     s\   @  ! ) )    A A ! . - Q  2 , ;;// 
		H	% K K K@  K{  K  KF  K  K  KFbii ,!299 !Hryy 0U\\ e T V[VbVb *-BII -;BII ;|
")) 
!")) !H		 	")) 	D DN, ,^C
299 C
L *? * *$ O
% O
 O
d N
"6 N
N
b 
_
(- _

_
D ar$   