^js d Z ddlZddlZddlZddlmZ ddlmZ ddlm Z m
Z
m Z m Z m
Z
ddlmZ ddlmZmZ dd lmZ eeeef eeeeeef z eeeeef z eeeeeef z Zeedz eedz eedz eedz z z z Z G d
d e d
Z G d de d
Z G d de
d
Z e G d de Z deeeeef dedeeef fdZ dededefdZ d Z!d Z"d Z#d d Z$dgZ%y) z Processor class for KOSMOS-2. N ) BatchFeature)
ImageInput) ImagesKwargsProcessingKwargsProcessorMixin
TextKwargsUnpack)
AddedToken)
BatchEncoding TextInput)auto_docstringc < e Zd ZU dZedz ed< eed< edz ed< y)Kosmos2ImagesKwargsa
bboxes (`Union[list[tuple[int]], list[tuple[float]], list[list[tuple[int]]], list[list[tuple[float]]]]`, *optional*):
The bounding bboxes associated to `texts`.
num_image_tokens (`int`, *optional* defaults to 64):
The number of (consecutive) places that are used to mark the placeholders to store image information.
This should be the same as `latent_query_num` in the instance of `Kosmos2Config` you are using.
first_image_token_id (`int`, *optional*):
The token id that will be used for the first place of the subsequence that is reserved to store image
information. If unset, will default to `self.tokenizer.unk_token_id + 1`.
Nbboxesnum_image_tokensfirst_image_token_id)__name__
__module__ __qualname____doc__
NestedList__annotations__int y/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/kosmos2/processing_kosmos2.pyr r ' s$
*$r r F)totalc e Zd ZU dZeed< y)Kosmos2TextKwargsz
add_eos_token (`bool`, defaults to `False`):
Whether or not to include `EOS` token id in the encoding when `add_special_tokens=True`.
add_eos_tokenN)r r r r boolr r r r r r 8 s
r r c
D e Zd ZU eed< eed< dddddddddd ddid Zy
) Kosmos2ProcessorKwargs text_kwargs
images_kwargsTFr ) add_special_tokenspaddingstridereturn_overflowing_tokensreturn_special_tokens_maskreturn_offsets_mappingreturn_token_type_idsverboser! r @ )r% r& N)r r r r r r _defaultsr r r r$ r$ A sC ""&& #' ).*/&+%* "
Ir r$ c
> e Zd Zd fd Ze ddedz deee z dee de
fd Z d Z d Z
dd
eee z dedz d ed edz deee z f
d
ZddZddZed Zded eee eee z defdZdeeef eeeeef z deeef fdZ xZS )Kosmos2Processorc d|_ d| _ d| _ d| _ d| _ d| _ d| _ d| _ d | _ d
| _ d | _
d | _ | j | j | j | j | j
| j | j | j | j | j | j g | _ || _
t | j D cg c] }d
t | j! d d" }}g }| j |z D ] }|j# t% |ddd " |j' | t( | U || yc c}w )z
num_patch_index_tokens (`int`, *optional*, defaults to 1024):
The number of tokens that represent patch indices.
Fzzzzzzz z z T)lstriprstrip
normalizedN)r- eod_token boi_token eoi_token eoc_token eol_token bop_token eop_token boo_token eoo_token dom_token grd_token
tag_tokensnum_patch_index_tokensrangestrzfillappendr
add_tokenssuper__init__)
selfimage_processor tokenizerrG kwargsxpatch_index_tokens
tokens_to_addtoken __class__s
r rN zKosmos2Processor.__init__X sO
+0 '!"##"#$#$9&
NN NN NN NN NN NN NN NN NN NN NN
'=#JOPTPkPkJl mQ
c!fll1o->a @ m m
__'99 aE E$uY^!_ ` a ]+
)4 ns 4%E1NimagestextrR returnc
<
|
| t d | j t fd| j j i|}|d j dd }|d j dd }|d j dd }|d j d d
}|d d } |d d }
|d j
d
d } t } |' | j |fi |d }
| j |
|| j |||| }| rd|sbt |t r| j j | }n7t |t r'|D cg c] }| j j | }}|d d xr ||d d < ||
nd
|d d < || nd |d d
< | j dd|i|d }| j | | |d d < |
|d d < | |d d
< | | || j j dz }| }t! | dz }t t# |||z }dgdg|z z dgz }g }g }| d }t |t r |g}| d g| d< |D ]p }|d | |z |||z d z }|j% | t' j& | }|rdg|z }|dgt) | t) | z
z z
}|j% | r t |t rt+ t- j. D cg c] \ }}|t) | f c}}d }|d \ } } |d \ }} |d d xr ||d d < d |d d
< | j dd|| gi|d }t) |j. d } | | k7 r5| j j0 dk( r|D cg c]+ }|| j j2 g| t) | z
z z - }}|D cg c] }|dg| t) | z
z z }}| d D cg c] }|dg| t) | z
z z c}| d< n| j j0 dk( r|D cg c]+ }| j j2 g| t) | z
z |z - }}|D cg c] }dg| t) | z
z |z }}| d D cg c] }dg| t) | z
z |z c}| d< t |t r| |d }| d d | d< |d }| j t5 || d |d| | S c c}w c c}}w c c}w c c}w c c}w c c}w c c}w c c}w ) Nz*You have to specify either images or text.tokenizer_init_kwargsr& r r r/ r r% r! Fr' r( return_tensors)r rY r input_idsattention_maskc | d S Nr )rS s r z+Kosmos2Processor.__call__.. s
defhdi r )keyrc rightleft)r_ r` image_embeds_position_mask)data tensor_typer )
ValueError
_merge_kwargsr$ rQ init_kwargspop
setdefaultr rP updatepreprocess_examples
isinstancerI bos_tokenlist unk_token_idr rH rK copylensorted enumerater_ padding_side pad_token_idr ) rO rX rY rR
output_kwargsr r r r! r' r( r] encodingimage_encodings
text_encodingwith_bos start_indeximage_token_ids base_image_embeds_position_maskr_ rh
all_input_idstext_idsmaskidxrS
sorted_length_min_len_not_paddedmax_len_paddeds r __call__zKosmos2Processor.__call__ sY >dl IJ J*** "
"&.."<"<
/33HdC( 9==>PRTU ,_ = A ABXZ^ _ %m488 %P
*= 9:N O
.y9&}5@@AQSWX > 1T 1 1& [M/D d+FJKt~~ 7 7 8 <KDK m,-ABT}
- ()= > BH gUZM- ( 3OU~^cgM- ()9 : *DNN U U
m8T UM OOM *=O
m$%9:29
m$Y/9G
m$%56 2#+'+~~'B'BQ'F$ *H h-!+K #5)=?SVf?f#g hO/0cQC:J4J.JaS.P + I)+ & $[ 1M$$!.
.67G.H-I)* )
8#L[1OCh{]mOmOoFpp *yy!@A 3:Ds8}s4y 899*11$7
8 $% &1:=;R;R1STvsAc3q6]TZi!
)6a(8%%&r*Q!-01EFX= m,-AB BF
m,-=> . `T#YK `=Q^C_ `
!$]%<% ? ?62 6 JRRbIc6DEA~A'> ? ?6!12 44>lu$vghdnn&A&A%BnWZ[\W]F]%^ab%b$v $vIc6DEQC>CF#: ;a ?62 6 JRRbIc6DEQC>CF#: ;a ?6!12
$$ )? %aL -56F-G-J)*-G-J*
OO %.*23C*D6P
!/
K Lj U %w66 %w66s0 !S5/S:
0T T, T
,0T" T Tc @ |yt |t s t d |D ]{ }|t |t s|g}|D ]^ }t |t rBt | dk( rt d |D r4t | dk( rt d |D rUt d } y)a
Check `bboxes` for a single text example. It could be
- `None`: no bounding box associated to a text.
- A list with each element being the bounding boxes associated to one ` ... ` pair found
in a text. This could be:
- `None`: no bounding box associated to a ` ... ` pair.
- A tuple of 2 integers: A single bounding box specified by patch indices.
- A tuple of 4 float point number: A single bounding box specified by (normalized) coordinates.
- A list containing the above 2 tuple types: Multiple bounding boxes for a
` ... ` pair.
Nz@`bboxes` (for a single text example) should be `None` or a list. c 3 < K | ] }t |t y wN)rr r .0rS s r zAKosmos2Processor._check_bboxes_for_single_text../ s .Saz!S/A.S r6 c 3 < K | ] }t |t y wr )rr floatr s r r zAKosmos2Processor._check_bboxes_for_single_text..0 s 1X1*Q2F1Xr a' Each element in `bboxes` (for a single text example) should be either `None`, a tuple containing 2 integers or 4 float point numbers, or a list containing such tuples. Also make sure the arguments `texts` and `bboxes` passed to `preprocess_text` are both in batches or both for a single example.)rr rt rk tuplerw all)rO r bboxelements r _check_bboxes_for_single_textz.Kosmos2Processor._check_bboxes_for_single_text s > FD) _` ` D| d+ v
!'51\Q&3.S7.S+SG )c1XPW1X.X$@
r c \ |j }|| d| }| j || }|S )N )strip_insert_patch_index_tokens)rO rY imager img_info_tokenss r _preprocess_single_examplez+Kosmos2Processor._preprocess_single_example9 s= zz| %&av.D ..tV< r textsr r c | j g|z }dj | j g|z | j gz }d}t |t rd}|g}|dgt | z }nt |t s|g}t | t | k7 r$t dt | dt | d |s| j | |g}nE|4t |t s t d |D ] }| j | ndgt | z }t | t | k7 r$t d t | dt | d t ||| D
cg c] \ } }
} | j | |
| | } }
} } |s| d
} | S c c} }
} w ) a- Add image and bounding box information to `texts` as image and patch index tokens.
Args:
texts (`Union[TextInput, list[TextInput]]`): The texts to be processed.
images (`ImageInput`, *optional*): The images associated to `texts`.
bboxes (`Union[list[tuple[int]], list[tuple[float]], list[list[tuple[int]]], list[list[tuple[float]]]]`, *optional*):
The bounding bboxes associated to `texts`.
num_image_tokens (`int`, *optional*, defaults to 64):
The number of image tokens (used as latent queries). This should corresponds to the `latent_query_num`
attribute in `Kosmos2Config`.
Returns:
`Union[TextInput, list[TextInput]]`: The processed texts with image and patch index tokens.
r TFNzGThe number of examples in `texts` and `images` should be the same. Got v.s. instead.zS`bboxes` should be `None` or a list (as a batch) when `texts` is passed as a batch.zGThe number of examples in `texts` and `bboxes` should be the same. Got r ) r< joinr= rr rI rw rt rk r zipr )
rO r rX r r
img_tokensr batchedrS rY r r results
r rq z$Kosmos2Processor.preprocess_examplesC s , nn%(88
((DNN#3j#@DNNCS#ST eS !GGE >Vc%j(FFD) XF u:V $ YZ]^cZdYeeklopvlwkx yB C
. .v 6 XF
fd+ !vww
62215
6 Vc%j(F v;#e* $ YZ]^cZdYeeklopvlwkx yB C
&)%?
!eT
+ +D% O
AYF
s F c \ |j | j d }|r t | S |S rb )splitr= +clean_text_and_extract_entities_with_bboxes)rO rY cleanup_and_extractcaptions r post_process_generationz(Kosmos2Processor.post_process_generation s, **T^^,R0 >wG Gr c x | j |fd|i|}|D cg c] }| j |d c}S c c}w )a
Post-process the output of the model to decode the text.
Args:
generated_outputs (`torch.Tensor` or `np.ndarray`):
The output of the model `generate` function. The output is expected to be a tensor of shape `(batch_size, sequence_length)`
or `(sequence_length,)`.
skip_special_tokens (`bool`, *optional*, defaults to `True`):
Whether or not to remove special tokens in the output. Argument passed to the tokenizer's `batch_decode` method.
**kwargs:
Additional arguments to be passed to the tokenizer's `batch_decode method`.
Returns:
`list[str]`: The decoded text.
skip_special_tokensF)r ) batch_decoder )rO generated_outputsr rR generated_textsrY s r post_process_image_text_to_textz0Kosmos2Processor.post_process_image_text_to_text sH ,$++,=qSfqjpqZijRV,,Tu,Mjjjs 7c l | j j }| j j }||z dgz S )Nrh )rQ model_input_namesrP )rO tokenizer_input_namesimage_processor_input_namess r r z"Kosmos2Processor.model_input_names s9 $ @ @ &*&:&:&L&L#$'BBFbEcccr c |t | dk( r|S t t j d| }t | t | k7 r$t dt | dt | d d}g }t || D ] \ }}|j
\ }} |j ||| | }|2t |t r|g}g }
t d |D s t d |D ], } | j | \ } }
|
j | d |
. t |
dk( rd
j |
}|j d | d |t | k r|j ||d d
j | }|S )Nr z.+?)stringzuThe number of elements in `bboxes` should be the same as the number of ` ... ` pairs in `text`. Got r r c 3 $ K | ] }|d u
y wr r )r boxs r r z>Kosmos2Processor._insert_patch_index_tokens.. s 73s$7s zTThe multiple bounding boxes for a single phrase should not contain any `None` value.r z z )
rw rt refinditerrk r spanrK rr r r #_convert_bbox_to_patch_index_tokensr )rO rY r matched_phrasescurr_posbuffermatchedr r endpatch_index_stringsr
patch_index_1
patch_index_2 position_strs r r z+Kosmos2Processor._insert_patch_index_tokens s >S[A -K r{{+B4 PQ 3v; . H IL M\ I] H^ ^d eh io ep dq qz {
& 9 @MGT \\^FAs MM$x, -H|$& v"$ 7$77 j
O/3/W/WX[/\,
}#**m_Am_+MN
O &'1,=BBCVWL MMIl^:> ?/ @2 c$i MM$xy/ *wwv r r c t | dk( r|\ }}n7t t j | j }t || \ }}dt
| j d d}dt
| j d d}||fS )Nr r5 r6 r7 )rw r mathsqrtrG coordinate_to_patch_indexrI rJ )rO r idx_1idx_2num_patches_per_sidetoken_1token_2s r r z4Kosmos2Processor._convert_bbox_to_patch_index_tokens s t9> LE5 $'tyy1L1L'M#N 4T;OPLE5!#e*"2"21"5!6a8!#e*"2"21"5!6a8 r )i )NN)NNr/ )T)r r r rN r r r
rt r
r$ r r r r BboxInputr rI rq r r propertyr r r r r
__classcell__)rW s @r r2 r2 V sa /5b %),0JT!J $y/)J /0 J
J JX!F %) ') @4 ?*@ T!@ @
* @
tCy
@D k& d d
+s +Ds x1 and y2 > y1.
num_patches_per_side (`int`): the number of patches along each side.
Returns:
`tuple[int, int]`: A pair of patch indices representing the upper-left patch and lower-right patch.
zTThe coordinates in `bbox` should be `(x1, y1, x2, y2)` with `x2 > x1` and `y2 > y1`.r^ )rk r floorceil) r r x1y1x2y2ul_xul_ylr_xlr_yul_idxlr_idxs r r r s RR GRopp ::b// 0D ::b// 0D 99R..2 3D 99R..2 3D
(
(4
/F
(
(4
/F 6>r r r c " d|z }| |z }| |z }||z }||z }| |k( r||z }||z } ||z |z }
||z |z } nQ||k( s||k( r||z }||z } ||z |z }
||z |z } n,||z |dz z }||z |dz z } ||z |dz z }
||z |dz z } || |
| fS )a
Given a grid of length `num_patches_per_side` and the indices of the upper-left and lower-right corners of a
bounding box, returns the normalized coordinates of the bounding box, in the form (x1, y1, x2, y2).
Args:
ul_idx (`int`): the index of the grid cell that corresponds to the upper-left corner of the bounding box.
lr_idx (`int`): the index of the grid cell that corresponds to the lower-right corner of the bounding box.
num_patches_per_side (`int`): the number of patches along each side.
Returns:
`tuple[float]`: the normalized coordinates of the bounding box, in the form (x1, y1, x2, y2).
g ?r r ) r r r cell_sizer r r r r r r r s r patch_index_to_coordinater s **I ( (D ) )D ( (D ) )D
I
I
I
)
I
)
I
I
I
)
I
)
I
A
-
I
A
-
I
A
-
I
A
-
r2r>r c
$ d}t j || }g }|D ]o }|j d }|j \ }}}|s*d}|j d d |j d d f}|j d } g }
| D ] } t j
d| } t j
d| dd }
| s5|
s8|rD|
j
t | j d t |
j d f ~|
j
t | j d t |
j d f |r|j
|||
f E|
D ]& }d|d d |d d
}|j
|||gf ( r |S ) a Extract entities contained in `text`. The bounding bboxes is given in the form of patch indices.
This function is only intended to be used within `clean_text_and_extract_entities_with_bboxes` where further
processing happens, including converting to normalized coordinates and whitespace character cleaning up.
Examples:
```python
>>> text = " An image of a snowman warming himself by a fire."
>>> entities = extract_entities_with_patch_indices(text)
>>> entities
[(' a snowman', (31, 41), [(44, 863)]), (' a fire', (130, 137), [(5, 911)])]
```z(?:(([^<]+)))?r Nr r4 zr^ r5 z>r N)rw r sub)r rY entity_namestartr adjusted_start adjusted_endadjusted_entitys r adjust_entity_positionsr i s_ & K %T&5\:;Nrvvgr4:67L"^\$BCO r c | j }t | t | j z
}g }|D ] \ }\ }}}t | t |j z
} t | t |j z
}
||z
| z }||z
|
z
}|j }|j |||f|f ||fS )z9Remove the spaces around the text and the entities in it.)r rw r8 r9 rK ) rY entitiesnew_textleading_spaces new_entitiesr r r r entity_name_leading_spacesentity_name_trailing_spacess r _cleanup_spacesr s s zz|HYT[[]!33NL-5 A) \eS6%(%5K>> text = " An image of a snowman warming himself by a fire."
>>> clean_text, entities = clean_text_and_extract_entities_with_bboxes(text)
>>> clean_text
'An image of a snowman warming himself by a fire.'
>>> entities
[('a snowman', (12, 21), [(0.390625, 0.046875, 0.984375, 0.828125)]), ('a fire', (41, 47), [(0.171875, 0.015625, 0.484375, 0.890625)])]
```r r r r r^ )r r r r r rK r ) rY r processed_textr r itemr r r r bboxes_in_coordss r r r s VVGR.N"Ed"K H+ ? aDG1&$?jpqbf 5d1gtAwH\ ]qq+;*==> ? >8 44 rs B) )&r rv r r image_processing_utilsr image_utilsr processing_utilsr r r r r
tokenization_pythonr tokenization_utils_baser r
utilsr rt r r r r r r r r$ r2 r r r r r r __all__r r r r s $ 2 % b b - ? # sCx
5ue+ ,-.
4c3h !" 4eUE)* +,-
%$,edlT%$,eVZlI[:[5\&\!]]
^
%,e %"
% -U * I ~ I I X E%u*D$E ]` ejknpskset >(c (3 (c (Z7't"*5:
r