§ ³Æj<$ãó’—ddlmZddlmZddlmZddlmZddlm Z ddgZ d#d edede de de de de de de de de de defd„Z d$d edede de de de de de de de de dedefd„Z d#d edede de de de de de de de de de defd „Z d$d edede de de de de de de de de dedefd!„Zd"S)%é)ÚAnyé)Údetection_predictor)Ú KIEPredictor)Ú OCRPredictor)Úrecognition_predictorÚ ocr_predictorÚ kie_predictorTéé€FÚdet_archÚ reco_archÚ pretrainedÚpretrained_backboneÚassume_straight_pagesÚpreserve_aspect_ratioÚ symmetric_padÚdet_bsÚreco_bsÚdetect_orientationÚstraighten_pagesÚdetect_languageÚreturnc ó~—t|||||||¬¦«} t||||¬¦«}t| |f|||| | | dœ| ¤ŽS©N)rrÚ batch_sizerrr)rrr)rrrrrr)rrr©r rrrrrrrrrrrÚkwargsÚ det_predictorÚreco_predictors úS/var/www/html/Carbon-Document/venv/lib/python3.11/site-packages/doctr/models/zoo.pyÚ _predictorr"ó‘€õ (ØØØ/ØØ3Ø3Ø#ðñô€Mõ+ØØØ/Øð ñô€Nõ ØØð ð4Ø3Ø#Ø-Ø)Ø'ð ð ð ð ð ð óÚ fast_baseÚ crnn_vgg16_bnÚexport_as_straight_boxesrc ó2—t|||f||||||| | dœ| ¤ŽS)a`End-to-end OCR architecture using one model for localization, and another for text recognition. >>> import numpy as np >>> from doctr.models import ocr_predictor >>> model = ocr_predictor('db_resnet50', 'crnn_vgg16_bn', pretrained=True) >>> input_page = (255 * np.random.rand(600, 800, 3)).astype(np.uint8) >>> out = model([input_page]) Args: det_arch: name of the detection architecture or the model itself to use (e.g. 'db_resnet50', 'db_mobilenet_v3_large') reco_arch: name of the recognition architecture or the model itself to use (e.g. 'crnn_vgg16_bn', 'sar_resnet31') pretrained: If True, returns a model pre-trained on our OCR dataset pretrained_backbone: If True, returns a model with a pretrained backbone assume_straight_pages: if True, speeds up the inference by assuming you only pass straight pages without rotated textual elements. preserve_aspect_ratio: If True, pad the input document image to preserve the aspect ratio before running the detection model on it. symmetric_pad: if True, pad the image symmetrically instead of padding at the bottom-right. export_as_straight_boxes: when assume_straight_pages is set to False, export final predictions (potentially rotated) as straight bounding boxes. detect_orientation: if True, the estimated general page orientation will be added to the predictions for each page. Doing so will slightly deteriorate the overall latency. straighten_pages: if True, estimates the page general orientation based on the segmentation map median line orientation. Then, rotates page before passing it again to the deep learning detection module. Doing so will improve performances for documents with page-uniform rotations. detect_language: if True, the language prediction will be added to the predictions for each page. Doing so will slightly deteriorate the overall latency. kwargs: keyword args of `OCRPredictor` Returns: OCR predictor ©rrrrr'rrr)r"© r rrrrrrr'rrrrs r!r r ?sN€õb ØØØð ð0Ø3Ø3Ø#Ø!9Ø-Ø)Ø'ð ð ð ð ð ð r$c ó~—t|||||||¬¦«} t||||¬¦«}t| |f|||| | | dœ| ¤ŽSr)rrrrs r!Ú_kie_predictorr,€r#r$c ó2—t|||f||||||| | dœ| ¤ŽS)a`End-to-end KIE architecture using one model for localization, and another for text recognition. >>> import numpy as np >>> from doctr.models import ocr_predictor >>> model = ocr_predictor('db_resnet50', 'crnn_vgg16_bn', pretrained=True) >>> input_page = (255 * np.random.rand(600, 800, 3)).astype(np.uint8) >>> out = model([input_page]) Args: det_arch: name of the detection architecture or the model itself to use (e.g. 'db_resnet50', 'db_mobilenet_v3_large') reco_arch: name of the recognition architecture or the model itself to use (e.g. 'crnn_vgg16_bn', 'sar_resnet31') pretrained: If True, returns a model pre-trained on our OCR dataset pretrained_backbone: If True, returns a model with a pretrained backbone assume_straight_pages: if True, speeds up the inference by assuming you only pass straight pages without rotated textual elements. preserve_aspect_ratio: If True, pad the input document image to preserve the aspect ratio before running the detection model on it. symmetric_pad: if True, pad the image symmetrically instead of padding at the bottom-right. export_as_straight_boxes: when assume_straight_pages is set to False, export final predictions (potentially rotated) as straight bounding boxes. detect_orientation: if True, the estimated general page orientation will be added to the predictions for each page. Doing so will slightly deteriorate the overall latency. straighten_pages: if True, estimates the page general orientation based on the segmentation map median line orientation. Then, rotates page before passing it again to the deep learning detection module. Doing so will improve performances for documents with page-uniform rotations. detect_language: if True, the language prediction will be added to the predictions for each page. Doing so will slightly deteriorate the overall latency. kwargs: keyword args of `OCRPredictor` Returns: KIE predictor r))r,r*s r!r r ¯sN€õb ØØØð ð0Ø3Ø3Ø#Ø!9Ø-Ø)Ø'ð ð ð ð ð ð r$N) TTTTr r FFF) r%r&FTTTTFFFF)ÚtypingrÚ detection.zoorr rÚ predictorrÚrecognition.zoorÚ__all__ÚboolÚintr"r r,©r$r!úr6sTðð ÐÐÐÐÐà.Ð.Ð.Ð.Ð.Ð.Ø'Ð'Ð'Ð'Ð'Ð'Ø#Ð#Ð#Ð#Ð#Ð#Ø2Ð2Ð2Ð2Ð2Ð2à ˜OÐ ,€ð!%Ø"&Ø"&ØØØØ$Ø"Ø!ð,ð,Øð,àð,ðð,ðð ,ð  ð ,ð  ð ,ðð,ð ð,ðð,ðð,ðð,ðð,ðð,ð,ð,ð,ð` Ø$ØØ $Ø"&Ø"&ØØ%*Ø$Ø"Ø!ð>ð>Øð>àð>ðð>ðð >ð  ð >ð  ð >ðð>ð#ð>ðð>ðð>ðð>ðð>ðð>ð>ð>ð>ðJ!%Ø"&Ø"&ØØØØ$Ø"Ø!ð,ð,Øð,àð,ðð,ðð ,ð  ð ,ð  ð ,ðð,ð ð,ðð,ðð,ðð,ðð,ðð,ð,ð,ð,ð` Ø$ØØ $Ø"&Ø"&ØØ%*Ø$Ø"Ø!ð>ð>Øð>àð>ðð>ðð >ð  ð >ð  ð >ðð>ð#ð>ðð>ðð>ðð>ðð>ðð>ð>ð>ð>ð>ð>r$