363 commits

Author	SHA1	Message	Date
vahidrezanezhad	6ae244bf9b	Fix filename stem extraction using binarization. Restore the CNN-RNN model to its previous version, as setting channels_last alone was insufficient for running on both CPU and GPU. Prevent errors caused by null values in image shape elements.	2026-01-26 15:04:47 +01:00
vahidrezanezhad	30f39e7383	mapregion is added to labels	2026-01-26 13:56:34 +01:00
vahidrezanezhad	c8240905a8	Fix label generation by selecting largest contour when erosion splits shapes	2026-01-26 13:36:24 +01:00
vahidrezanezhad	49261fa99b	CNN–RNN–OCR inference and adaptation of the CNN–RNN–OCR model to support inference on both CPU and GPU	2025-12-17 15:12:39 +01:00
vahidrezanezhad	6ee79c7320	evaluation with a given GT is only possible for segmentation tasks	2025-12-17 13:28:02 +01:00
vahidrezanezhad	4651000191	debuging input shape + enable finetuning a model	2025-12-15 11:36:09 +01:00
vahidrezanezhad	4fc3ff33cb	The cnn-rnn ocr model can be trained now	2025-12-09 17:22:12 +01:00
vahidrezanezhad	84a72a128b	cnn-rnn model can be called - model input height and width are dynamic now - data generator is also callable	2025-12-09 15:30:19 +01:00
vahidrezanezhad	59e5a73654	adding cnn-rnn training script	2025-12-08 19:30:57 +01:00
vahidrezanezhad	7bf5e077d9	Restore correct execution of export_textline_images_and_text	2025-12-03 15:40:52 +01:00
vahidrezanezhad	6ac37af2f8	Fix eynollah ocr --help so it works again	2025-12-03 14:11:47 +01:00
vahidrezanezhad	d687d862d6	Restored correct functionality of the extract_only_images mode and cleaned up the argument handling	2025-12-03 12:01:42 +01:00
kba	51abe9617a	log to STDERR not STDOUT	2025-12-02 15:00:33 +01:00
kba	b161e33854	🔥 refactor eynollah ocr ... .	2025-11-28 15:45:21 +01:00
kba	30f9c695dc	move line-gt extraction out of ocr to eynollah-training	2025-11-28 15:12:31 +01:00
kba	9bcfeab057	💀 remove dead code from eynollah.py	2025-11-28 12:52:28 +01:00
kba	5171e09c2d	eynollah.py: fix kwargs to writer	2025-11-28 12:52:28 +01:00
kba	c24cf94bce	enforce kwargs for writer.build_...	2025-11-28 12:52:28 +01:00
kba	4aa9543a7d	remove more branches after textline_light default true	2025-11-27 11:30:00 +01:00
kba	177d555ded	factor out extract_only_images as eynollah extract-images	2025-11-26 21:37:00 +01:00
kba	83e8b289da	🔥 drop light_version/textline_light (now default and implied)	2025-11-26 20:48:22 +01:00
kba	ca83cf934d	fix imports from src/cli/cli_*/*_cli	2025-11-26 20:48:14 +01:00
kba	095b36c389	models: split into layout, extra and ocr ... layout: Everything not OCR or extra ocr: trocr/cnnrnn models extra: obsolete or niche models	2025-11-26 19:49:59 +01:00
kba	000af16a47	🔥 remove torch pinning	2025-11-26 19:23:49 +01:00
kba	e503c1a0b7	drop obsolete multi-model binarization	2025-11-26 18:51:41 +01:00
kba	82266f8234	reorganize cli	2025-11-26 18:51:20 +01:00
kba	5a1900e664	🔥 remove OCR option from eynollah layout	2025-11-26 18:12:03 +01:00
kba	0f410c2e7c	disable tf/keras logging on first import	2025-11-26 16:37:54 +01:00
kba	9d9d32daed	update OCR-D bindings	2025-11-26 16:20:27 +01:00
vahidrezanezhad	ed5b5c13dd	Add test images; call TrOCR processor from the same directory as the TrOCR model	2025-11-07 12:47:21 +01:00
kba	f902756ce1	try importing torch, then shapely, then tensorflow	2025-11-06 13:10:35 +01:00
kba	d224b0f7e8	try with shapely.set_precision(...mode="keep_collpased")	2025-11-06 11:55:40 +01:00
kba	9ab565fa02	model basedir might be a symlink	2025-10-29 21:02:42 +01:00
kba	4772fd17e2	missed changing override mechanism in eynollah_ocr	2025-10-29 20:47:13 +01:00
kba	29c273685f	fix merge issues	2025-10-29 20:15:19 +01:00
kba	de76eabc1d	Merge branch 'cli-logging' into model-zoo	2025-10-29 19:41:01 +01:00
kba	5e22e9db64	model_zoo: make type str to reduce importing overhead	2025-10-29 19:16:35 +01:00
kba	a913bdf7dc	make --model-basedir and --model-overrides top-level CLI options	2025-10-29 18:48:41 +01:00
kba	b6f82c72b9	refactor cli tests	2025-10-29 17:23:21 +01:00
kba	ef999c8f0a	Merge branch 'model-zoo' of lx0145.sbb.spk-berlin.de:/data/eynollah into model-zoo	2025-10-27 11:45:20 +01:00
kba	294b6356d3	wip	2025-10-27 11:45:16 +01:00
kba	51d2680d9c	wip	2025-10-27 11:44:59 +01:00
kba	ec1fd93dad	wip	2025-10-23 11:58:23 +02:00
kba	883546a6b8	eynollah models package	2025-10-22 17:05:40 +02:00
kba	04bc4a63d0	reorganize model_zoo	2025-10-22 16:04:48 +02:00
kba	d94285b3ea	rewrite model spec data structure	2025-10-22 13:07:35 +02:00
kba	146658f026	eynollah layout: fix trocr_processor model_zoo call	2025-10-22 10:48:26 +02:00
kba	4c8abfe19c	eynollah_ocr: actually replace the model calls	2025-10-22 10:48:26 +02:00
kba	1337461d47	adopt image_enhancer to the zoo	2025-10-21 19:24:55 +02:00
kba	f0c86672f8	adopt mb_ro_on_layout to the zoo	2025-10-21 17:55:08 +02:00