Zj8'SSKrSSKrSSKJs Jr SSKJr SSK J r J r SSK J r JrJrJr SSKJrJrJr SSKJrJr SSKJr \R4"\5r"S S \S S 9rS r\"S5Vs/sH nSUSS3PM sn\"S5Vs/sH nSUSS3PM sn-r \\"SS9"SS\555r!S/r"gs snfs snf)N) BatchFeature) ImageInputmake_nested_list_of_images)MultiModalDataProcessingKwargsProcessorMixinUnpack) AddedTokenPreTokenizedInput TextInput)auto_docstringlogging)requiresc*\rSrSrSSSS.SS0S.rS rg ) PI0ProcessorKwargs$ max_length0right)paddingr padding_sidereturn_tensorspt) text_kwargs common_kwargsN)__name__ __module__ __qualname____firstlineno__ _defaults__static_attributes__rw/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/pi0/processing_pi0.pyrr$s#$# +D1 Ir$rF)totalziz4>z3)visiontorch)backendscD^\rSrSrSU4Sjjr\SS\\\-\\\-S-S\\ -\\-\\ -S-S\\ R-\ R-S-S\\ R-\ R-S-S\\S \4 S jj5rSS jr\U4S j5rS rU=r$) PI0Processor3Nc >URSURSsUlUlURS/SQ5nURS/SQ5nURS/SQ5nURS /S Q5n[R "U5Ul[R "U5Ul[R "U5Ul[R "U5Ul URS S 5Ul URS S5Ul [US5(d [S5eURUl[US5(dK[[ SSS9n SU /0n UR#U 5 UR%[ 5Ul[ UlO"UR&UlUR(UlUR+[,5 SUlSUl[2T U]iXUS9 g)Nheightwidth state_mean)ggsgr?g h"l?gW2D@g\ AcgZd;OſgB>٬?g QI state_std)gt$~?gL F%u?g.!u?g/n?g6?gx?g]K=?gF%u? actions_mean)g&S?gX?gW[재gHPsr?gg?g gHPs actions_std)gGz?g`"?g9#J{?gvOjM?g>yX5ͫ?g46unnUR0"U4S S0US D6n[U5nSUUSU24'USUUSU24'M@ 0U EUUS.EnUb[$R2"U5UR4- UR6S-- nUR8SUR::a3[<R>"USUR:UR8S- 45nURASURBUR:5US'Ub[$R2"U5URD- URFS-- nUR8SUR::a3[<R>"USUR:UR8S- 45nURASUR:5US'[IUUS9$)a actions (`list | np.ndarray | torch.Tensor`, *optional*): Actions to be predicted by the model. If provided, padding, mean and std normalization will be applied. state (`list | np.ndarray | torch.Tensor`, *optional*): Robotic states to be predicted by the model. If provided, padding, mean and std normalization will be applied. Returns: [`BatchFeature`]: A [`BatchFeature`] with the following fields: - **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`. If `suffix` is provided, the `input_ids` will also contain the suffix input ids. - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not `None`). - **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`. - **pixel_attention_mask** -- Pixel values padding mask to be fed to a model. Returned when `images` is not `None`. - **state** -- Robot state compatible with model if `state` is not None - **actions** -- Label-actions compatible with training if `actions` is not None tokenizer_init_kwargsNzPYou are using PI0 without a text prefix. The processor will use an empty prompt.z Received z image samples for z\ prompts. Each prompt should be associated with one sample (with one or more camera images).rr images_kwargs c38# UHn[U5v M g7fN)len).0 sample_imagess r% (PI0Processor.__call__..sUn]c-00ns)dtyperrT pixel_values)rhpixel_attention_maskg:0yE>rrXrY)data tensor_type)% _merge_kwargsrrQ init_kwargslogger warning_once isinstancestrrrbrDpopzipr;r: bos_tokenappendmaxr*zerosboolr0r1 enumeraterPrBr4r5shaper6Fpadviewr8r2r3r)rOrVrWrXrYrR output_kwargsbatched_imagesrprompt_stringssample image_list text_inputsmax_num_camerasripadded_pixel_valuesbatchrd processed num_cameras return_datas r%__call__PI0Processor.__call__Xsi8**  6:nn6P6P TZ  <    r sD dC 6D3F; ~ #d) +C/00CCI;Oee  '}599:JDQo&**+;TB"%d"; F##d&;&;;c*oMNt~~OgOgNhiohpprs   ! !& ) #< nn^T}]7ST UnUU${{C,?+QY^YcYcd#kk#n*=PQSWS^S^`d`j`jk$-n$= E=,,]r4rS`apSqrIm,K8<   !4 57@7P | | 3 4 %>  /$8  ||G,t/@/@@TEUEUX]E]^G}}R 4#5#55%%!T-?-?'--PRBS-S)TU%,\\"dootGYGY%ZK "  \\%(4??:t~~PU?UVE{{2!3!33ea););ekk"o)M%NO#(::b$2D2D#EK .IIr$c 0nUb;UR/[U5-nS/[U5-nURXES.5 [S0UD6$)ax Computes the number of placeholder tokens needed for multimodal inputs with the given sizes. Args: image_sizes (list[list[str]], *optional*): The input sizes formatted as (height, width) per each image. Returns: `MultiModalData`: A `MultiModalData` object holding number of tokens per each of the provided input modalities, along with other useful data. )num_image_tokensnum_image_patchesr)r:rbupdater)rO image_sizesrR vision_datarrs r%_get_num_multimodal_tokens'PI0Processor._get_num_multimodal_tokenssZ  " $ 5 56[9II !"c+&6 6    4Dm n, ,,r$c >[TU]S/-$)Nri)rMmodel_input_names)rOrTs r%rPI0Processor.model_input_namessw(,B+CCCr$) r4r5r8r0r:r;rHr6r2r3r1)NNNra)rrr r!rNrrlistr r npndarrayr*Tensorr rrrrpropertyrr# __classcell__)rTs@r%r-r-3s RDbf;?9= WJT*--T*5E0FFMWJ++d9o=EV@WWZ^^WJ "U\\1D8 WJ bjj 5<</$6 WJ +, WJ WJWJr-$DDr$r-)#numpyrr*torch.nn.functionalnn functionalr|feature_extraction_utilsr image_utilsrrprocessing_utilsrrr r tokenization_utils_baser r r utilsrrutils.import_utilsr get_loggerrrorrErangerJr-__all__)is0r%rs* 4AXXOO,*   H %) ).t5A$qgQ5RWX[R\8]R\Q4#waR\8]]  &'QD>QD(QDh  s68]s ,B< C