mcap/modules/OCR/models.config

49 lines
2.1 KiB
Plaintext

@version 1
# OCR models. Each [model NAME] names the files it needs from this folder (fetch_models.jai
# downloads them) and how it is run; ocr_create takes the NAME. Changes apply to engines created
# after the file is saved.
#
# title shown to people
# detector, recognizer, dictionary file names, quoted
# textline_ori optional: a text line orientation classifier's file name, quoted; lines it
# finds upside down are read both ways and the more confident reading kept
# det_max_side wider images are scaled down to this width for detection (px)
# det_tile_height taller images are detected in overlapping strips this high (px, after scaling)
# det_threshold a pixel is text when its probability is above this
# box_threshold a text region is kept when its mean probability is at least this
# unclip_ratio how far each region is grown, as DB detection networks expect
# rec_height each text line is scaled to this height for recognition (px)
# rec_batch_gpu text lines recognized together in one run, on the GPU
# rec_batch_cpu the same on the CPU, where one at a time is fastest: a batch is padded to its
# widest line, and the padding costs time and changes what is read a little
[model ppocr-v5-mobile]
title: "PP-OCRv5 mobile (light)"
detector: "ch_PP-OCRv5_det_mobile.onnx"
recognizer: "ch_PP-OCRv5_rec_mobile.onnx"
dictionary: "ppocrv5_dict.txt"
textline_ori: "ch_PP-LCNet_x0_25_textline_ori_cls_mobile.onnx"
det_max_side: 2560
det_tile_height: 1536
det_threshold: 0.3
box_threshold: 0.6
unclip_ratio: 1.5
rec_height: 48
rec_batch_gpu: 16
rec_batch_cpu: 1
[model ppocr-v5-server]
title: "PP-OCRv5 server (heavy)"
detector: "ch_PP-OCRv5_det_server.onnx"
recognizer: "ch_PP-OCRv5_rec_server.onnx"
dictionary: "ppocrv5_dict.txt"
textline_ori: "ch_PP-LCNet_x0_25_textline_ori_cls_mobile.onnx"
det_max_side: 2560
det_tile_height: 1536
det_threshold: 0.3
box_threshold: 0.6
unclip_ratio: 1.5
rec_height: 48
rec_batch_gpu: 8
rec_batch_cpu: 1