qyi*SrSSKJr SSKrSSKJr SSKJr SSKJ r J r J r SSK J r Jr SS KJrJrJr \(aS S KJr \R*"\5rS rS rSrSr\"SS\55rS/rg)z Image processor class for OwlViT) TYPE_CHECKINGN)TorchvisionBackend)center_to_corners_format)OPENAI_CLIP_MEANOPENAI_CLIP_STDPILImageResampling) ImagesKwargsUnpack) TensorTypeauto_docstringlogging)OwlViTObjectDetectionOutputc,UR5(a@UR[R[R4;aU$UR 5$UR[R [R4;aU$UR5$)N) is_floating_pointdtypetorchfloat32float64floatint32int64int)ts o/home/mande/repo/quber/.venv/lib/python3.13/site-packages/transformers/models/owlvit/image_processing_owlvit.py_upcastr"scGG u}}==qL1779LGG U[[99qFquuwFc[U[[45(aS[R"UVs/sHo"SPM sn5n[R"UVs/sHo"SPM sn5nO>[U[R 5(aUR S5up4O [S5e[R"XCXC/SS9nURS5RUR5nX-nU$s snfs snf)a Scale batch of bounding boxes to the target sizes. Args: boxes (`torch.Tensor` of shape `(batch_size, num_boxes, 4)`): Bounding boxes to scale. Each box is expected to be in (x1, y1, x2, y2) format. target_sizes (`list[tuple[int, int]]` or `torch.Tensor` of shape `(batch_size, 2)`): Target sizes to scale the boxes to. Each target size is expected to be in (height, width) format. Returns: `torch.Tensor` of shape `(batch_size, num_boxes, 4)`: Scaled bounding boxes. rrz4`target_sizes` must be a list, tuple or torch.Tensordim) isinstancelisttuplertensorTensorunbind TypeErrorstack unsqueezetodevice)boxes target_sizesi image_height image_width scale_factors r _scale_boxesr3*s,u ..||<$@SU;aURS5nX!S'[TU]"S0UD6 g)Nrescale do_rescale)popsuper__init__)selfrL rescale_val __class__s rrSOwlViTImageProcessor.__init__ts3   **Y/K#.<  "6"rNoutputsr thresholdr.cURURpT[U5nUb[U5U:wa [S5e[R "USS9n[R "UR5nURn [U5nUb [XS5n/n [XU5H*upn X:nXn Xn Xn U RXU S.5 M, U $)a Converts the raw output of [`OwlViTForObjectDetection`] into final bounding boxes in (top_left_x, top_left_y, bottom_right_x, bottom_right_y) format. Args: outputs ([`OwlViTObjectDetectionOutput`]): Raw outputs of the model. threshold (`float`, *optional*, defaults to 0.1): Score threshold to keep object detection predictions. target_sizes (`torch.Tensor` or `list[tuple[int, int]]`, *optional*): Tensor of shape `(batch_size, 2)` or list of tuples (`tuple[int, int]`) containing the target size `(height, width)` of each image in the batch. If unset, predictions will not be resized. Returns: `list[Dict]`: A list of dictionaries, each dictionary containing the following keys: - "scores": The confidence scores for each predicted box on the image. - "labels": Indexes of the classes predicted by the model on the image. - "boxes": Image bounding boxes in (top_left_x, top_left_y, bottom_right_x, bottom_right_y) format. z9Make sure that you pass in as many target sizes as imagesr scoreslabelsr-) logits pred_boxeslen ValueErrorrr9sigmoidvaluesindicesrr3zipappend)rTrXrYr. batch_logits batch_boxes batch_sizebatch_class_logits batch_scores batch_labelsresultsr]r^r-keeps rpost_process_object_detection2OwlViTImageProcessor.post_process_object_detection~s2%,NNG4F4Fk&  #L(9Z(GXY Y#YY|<}}%7%>%>? )11 /{;   #&{AK%([%Q !FE%D\F\FKE NNfO P &RrcURURpeUb#[U5[U5:wa [S5eUbURSS:wa [S5e[ R "USS9n[ R"UR5n[U5nUS:a[URS 5Hjn [ R"X*5HJn XU (dM[XiU SS24RS 5Xi5S S n S X'S XX:'ML Ml Ub [Xd5n/n [ R"U5n [URS 5Hn XnUR!5R#5(dM,S XU:'[ R "U5S -nXS -- US-- n[ R$"US S5nUX'XS :nXUnXiUnU R'USUS.5 M U $)a5 Converts the output of [`OwlViTForObjectDetection.image_guided_detection`] into the format expected by the COCO api. Args: outputs ([`OwlViTImageGuidedObjectDetectionOutput`]): Raw outputs of the model. threshold (`float`, *optional*, defaults to 0.0): Minimum confidence threshold to use to filter out predicted boxes. nms_threshold (`float`, *optional*, defaults to 0.3): IoU threshold for non-maximum suppression of overlapping boxes. target_sizes (`torch.Tensor`, *optional*): Tensor of shape (batch_size, 2) where each entry is the (height, width) of the corresponding image in the batch. If set, predicted normalized bounding boxes are rescaled to the target sizes. If left to None, predictions will not be unnormalized. Returns: `list[Dict]`: A list of dictionaries, each dictionary containing the scores, labels and boxes for an image in the batch as predicted by the model. All labels are set to None as `OwlViTForObjectDetection.image_guided_detection` perform one-shot object detection. NzTMake sure that you pass in as many target sizes as the batch dimension of the logitsrr5zTEach element of target_sizes must contain the size (h, w) of each image of the batchr[r g?rggư>皙?g?r\)r_target_pred_boxesrarbshaperr9rcrdrrangeargsortrEr*r3 zeros_likenonzeronumelcliprg)rTrXrY nms_thresholdr.r_ target_boxesprobsr]idxr/iousrnalphas query_scores max_score query_alphasmask box_scoresr-s r#post_process_image_guided_detection8OwlViTImageProcessor.post_process_image_guided_detections , '~~w/H/H  #F s<7H(Hst t  # (:(:1(=(Bst t &b)u||,0 =  3 \//23 |4A!;q> "<#4QT#:#D#DQ#GIZ[\]^_`aD"DG8;FK 45 54  #' CL!!&)++A./C!;L'')//1169L 1 2 ,/$6I(O<SQL ::lC=L&FK;?DT*J %d+E NNjD5Q R'0*rrP)rtN)rsg333333?N)__name__ __module__ __qualname____firstlineno__r BICUBICresampler image_meanr image_stdsizedefault_to_square crop_size do_resizedo_center_croprO do_normalizedo_convert_rgbmodel_input_namesr r rSrr r#r$rpr__static_attributes__ __classcell__)rVs@rrGrGes!))H!JIC (D-IINJLN'(# !5#8< 3.33!4;.5 3jKKrrG)__doc__typingrrimage_processing_backendsrimage_transformsr image_utilsrrr processing_utilsr r utilsr r rmodeling_owlvitr get_loggerrloggerrr3r6rErG__all__rPrrrs' ;8PP488<   H %G8 E  X-XXv " "r