device: &device cuda:0 max_img_size: [1920,1920] #text det default size: 1280x1280 #[] = originla size, TODO: fix the deskew code to resize the image only for detecting the angle, we want to feed the original size image to the text detection pipeline so that the bounding boxes would be mapped back to the original size extend_bbox: [0, 0.0, 0.0, 0.0] # left, top, right, bottom batch_size: 1 #1 means batch_mode = False detector: # version: /mnt/hdd2T/datnt/datnt_from_ssd1T/mmdetection/wild_receipt_finetune_weights_c_lite.pth version: /workspace/cope2n-ai-fi/weights/models/sdsap_sbt/ocr_engine/sdsvtd/epoch_100_params.pth auto_rotate: True rotator_version: /workspace/cope2n-ai-fi/weights/models/sdsap_sbt/ocr_engine/sdsvtd/best_bbox_mAP_epoch_30_lite.pth device: *device recognizer: # version: satrn-lite-general-pretrain-20230106 version: /workspace/cope2n-ai-fi/weights/models/sdsvtr/hub/jxqhbem4to.pth max_seq_len_overwrite: 24 #default = 12 return_confident: True device: *device #extend the bbox to avoid losing accent mark in vietnames, if using ocr for only english, disable it deskew: enable: True text_detector: config: /workspace/cope2n-ai-fi/modules/ocr_engine/externals/sdsv_dewarp/config/det.yaml weight: /workspace/cope2n-ai-fi/weights/models/sdsap_sbt/ocr_engine/sdsv_dewarp/ch_PP-OCRv3_det_infer text_cls: config: /workspace/cope2n-ai-fi/modules/ocr_engine/externals/sdsv_dewarp/config/cls.yaml weight: /workspace/cope2n-ai-fi/weights/models/sdsap_sbt/ocr_engine/sdsv_dewarp/ch_ppocr_mobile_v2.0_cls_infer device: *device words_to_lines: gradient: 0.6 max_x_dist: 20 max_running_y_shift_degree: 10 #degrees y_overlap_threshold: 0.5 word_formation_mode: line