Commit graph

Select branches

Hide pull requests

master

unifying-training-models

#15

#16

#16

#18

#2

#21

#23

#24

#25

#25

#7

Mono Color

• cf63bd92bc
  Update README.md: how to train model using docker image unifying-training-models vahidrezanezhad 2025-06-25 18:33:55 +02:00
• ce4219e517 docker file to train model with desired cuda and cudnn vahidrezanezhad 2025-06-25 18:24:16 +02:00
• d6ccb83bf5
  Merge pull request #24 from johnlockejrr/unifying-training-models Clemens Neudecker 2025-06-03 09:00:56 +02:00
• 834cf19cb9 layout visualization updated vahidrezanezhad 2025-06-02 18:23:34 +02:00
• 13c6d28aaa visualizing ro for single xml file vahidrezanezhad 2025-05-23 18:30:51 +02:00
• e9738886ac
  Merge f298643fcf into 02b1436f39 johnlockejrr 2025-05-17 20:24:46 +00:00
• f298643fcf
  Fix ReduceONPlateau wrong logic johnlockejrr 2025-05-17 23:24:40 +03:00
• 7661080899
  LR Warmup and Optimization Implementation johnlockejrr 2025-05-17 16:17:38 +03:00
• 110e077ee2 updating inference for mb reading order vahidrezanezhad 2025-05-17 02:18:27 +02:00
• 1bf801985b
  Update gt_gen_utils.py johnlockejrr 2025-05-14 03:34:51 -07:00
• 26a1964357
  Update utils.py johnlockejrr 2025-05-14 03:29:00 -07:00
• 0c919d17db
  Update utils.py johnlockejrr 2025-05-14 03:27:12 -07:00
• 3de24243fc visuliazation layout from eynollah page-xml output vahidrezanezhad 2025-05-12 22:39:47 +02:00
• fc75770b73 visulizing textline detection from eynollah page-xml output vahidrezanezhad 2025-05-12 18:31:40 +02:00
• 102b04c84d
  Update utils.py johnlockejrr 2025-05-11 06:09:17 -07:00
• be57f137d7
  Update utils.py johnlockejrr 2025-05-11 05:31:34 -07:00
• 479a6705c1
  Update utils.py johnlockejrr 2025-05-10 14:58:40 -07:00
• d554d26739 resolving issued with saving model by steps vahidrezanezhad 2025-05-05 16:13:38 +02:00
• 1454bc4f58 saving model by steps is added to reading order and pixel wise segmentation use cases training vahidrezanezhad 2025-05-05 15:39:05 +02:00
• 8ae42b7c6e adding min_early parameter for generating training dataset for machine based reading order model vahidrezanezhad 2025-05-03 19:25:32 +02:00
• d57de478eb
  Merge pull request #18 from johnlockejrr/unifying-training-models Clemens Neudecker 2025-04-17 15:43:28 +02:00
• 4cc5aea166 updating:rotation augmentation is provided for machine based reading order vahidrezanezhad 2025-04-17 00:12:30 +02:00
• 77ef68a1ec updating:rotation augmentation is provided for machine based reading order vahidrezanezhad 2025-04-17 00:05:59 +02:00
• 22f82c5448 rotation augmentation is provided for machine based reading order vahidrezanezhad 2025-04-16 23:36:41 +02:00
• 872e5b0b3a visualising reaidng order- Overlaying on image is provided vahidrezanezhad 2025-03-17 20:09:48 +01:00
• 822d9292de this enables to visualize reading order of textregions provided in page-xml files vahidrezanezhad 2025-03-14 17:20:33 +01:00
• bd4160408e artificial_class_label for table region vahidrezanezhad 2024-11-18 16:34:53 +01:00
• 98868e4a9e update resizing in inference vahidrezanezhad 2024-11-14 16:26:19 +01:00
• 3ef865e0b5 addinh shifting augmentation vahidrezanezhad 2024-10-29 17:06:22 +01:00
• 4150675621 early_erosion is added vahidrezanezhad 2024-10-25 14:01:39 +02:00
• 451188c3b9
  Changed deprecated lr to learning_rate and model.fit_generator to model.fit johnlockejrr 2024-10-19 13:25:50 -07:00
• df4a47ae6f
  Update inference.py to check if save_layout was passed as argument otherwise can give an cv2 error johnlockejrr 2024-10-19 13:21:29 -07:00
• cca4d17823 new augmentations for patchwise training vahidrezanezhad 2024-08-30 15:30:18 +02:00
• 5f456cf508 fixing artificial class bug vahidrezanezhad 2024-08-28 17:34:06 +02:00
• c502e67c14 adding foreground rgb to augmentation vahidrezanezhad 2024-08-28 02:09:27 +02:00
• 4f0e3efa2b early dilation for textline artificial class vahidrezanezhad 2024-08-28 00:04:19 +02:00
• 9904846776 using prepared binarized images in the case of augmentation vahidrezanezhad 2024-08-22 21:58:09 +02:00
• f31219b1c9 scaling, channels shuffling, rgb background and red content added to no patch augmentation vahidrezanezhad 2024-08-21 19:33:23 +02:00
• 95bbdf8040 updating augmentations vahidrezanezhad 2024-08-21 16:17:59 +02:00
• 7be326d689 augmentation function for red textlines, rgb background and scaling for no patch case vahidrezanezhad 2024-08-21 00:48:30 +02:00
• 85dd59f23e update vahidrezanezhad 2024-08-09 13:20:09 +02:00
• f4bad09083 save only layout output. different from overlayed layout on image vahidrezanezhad 2024-08-09 12:46:18 +02:00
• b6bdf942fd
  add documentation from wiki as markdown file to the codebase Clemens Neudecker 2024-08-08 16:35:06 +02:00
• 59e5892f25 erosion rate changed vahidrezanezhad 2024-08-01 14:30:51 +02:00
• 5fbe941f53 inference updated vahidrezanezhad 2024-07-24 18:00:39 +02:00
• 30894ddc75 erosion and dilation parameters are changed & separators are written in label images after artificial label vahidrezanezhad 2024-07-24 16:52:05 +02:00
• c340fbb721 increasing margin in the case of pixelwise inference b-vr103 2024-07-23 11:29:05 +02:00
• f2692cf8dd brightness augmentation modified b-vr103 2024-07-17 18:20:24 +02:00
• 9521768774 adding degrading and brightness augmentation to no patches case training vahidrezanezhad 2024-07-17 17:14:20 +02:00
• 55f3cb9a84 printspace_as_class_in_layout is integrated. Printspace can be defined as a class for layout segmentation vahidrezanezhad 2024-07-16 18:29:27 +02:00
• 647a3f8cc4 resolving typo vahidrezanezhad 2024-07-09 03:04:29 +02:00
• c0faecec2c update inference vahidrezanezhad 2024-06-21 23:42:25 +02:00
• 033cf6734b update reading order machine based vahidrezanezhad 2024-06-21 13:06:26 +02:00
• 9358657a0d update config vahidrezanezhad 2024-06-12 17:40:40 +02:00
• 743f2e97d6 Transformer+CNN structure is added to vision transformer type vahidrezanezhad 2024-06-12 17:39:57 +02:00
• f1fd74c7eb transformer patch size is dynamic now. vahidrezanezhad 2024-06-12 13:26:27 +02:00
• 2aa216e388 binarization as a separate task of segmentation vahidrezanezhad 2024-06-11 17:48:30 +02:00
• 41a0e15e79 updating train.py nontransformer backend vahidrezanezhad 2024-06-10 22:15:30 +02:00
• 815e5a1d35 updating train.py vahidrezanezhad 2024-06-07 16:24:31 +02:00
• dc356a5f42 just defined graphic region types can be extracted as label vahidrezanezhad 2024-06-06 18:55:22 +02:00
• b1d971a200 just defined textregion types can be extracted as label vahidrezanezhad 2024-06-06 18:47:30 +02:00
• 1c8873ffa3 just defined textregion types can be extracted as label vahidrezanezhad 2024-06-06 18:45:47 +02:00
• e25a925169
  Update README.md vahidrezanezhad 2024-06-06 14:46:06 +02:00
• b9cbc0edb7 replacement in a list done correctly vahidrezanezhad 2024-06-06 14:38:29 +02:00
• 821290c464 scaling and cropping of labels and org images vahidrezanezhad 2024-05-30 16:59:50 +02:00
• 4640d9f2dc modifying xml parsing vahidrezanezhad 2024-05-30 12:56:56 +02:00
• 785033536a min_area size of regions considered for reading order detection passed as an argument for inference vahidrezanezhad 2024-05-29 13:07:06 +02:00
• f6abefb0a8 reading order detection on xml with layout + result will be written in an output directory with the same file name vahidrezanezhad 2024-05-29 11:18:35 +02:00
• 2e7c69f2ac inference for reading order vahidrezanezhad 2024-05-28 16:48:51 +02:00
• 356da4cc53 min area size of text region passes as an argument for machine based reading order vahidrezanezhad 2024-05-28 10:14:16 +02:00
• 29ddd4d909 pass degrading scales for image enhancement as a json file vahidrezanezhad 2024-05-28 10:01:17 +02:00
• 5aa6ee0010 adding rest_as_paragraph and rest_as_graphic to elements vahidrezanezhad 2024-05-27 17:23:49 +02:00
• 4e4490d740 machine based reading order training is integrated vahidrezanezhad 2024-05-24 16:39:48 +02:00
• bf1468391a machine based reading order training dataset generator is added vahidrezanezhad 2024-05-24 14:42:58 +02:00
• f5746011f6 use case printspace is added vahidrezanezhad 2024-05-23 17:36:23 +02:00
• 4b7f7da07c use cases like textline, word and glyph are added vahidrezanezhad 2024-05-23 17:14:31 +02:00
• 947a0e06f8 missing text types are added vahidrezanezhad 2024-05-23 15:43:31 +02:00
• d687f5328f dynamic layout decorated with artificial class on text elements boundry vahidrezanezhad 2024-05-23 11:14:14 +02:00
• f7dda078d2 page2label with a dynamic layout vahidrezanezhad 2024-05-22 12:38:24 +02:00
• 5f06a02441 update requirements vahidrezanezhad 2024-05-17 09:08:25 +02:00
• 2623113b0c
  page to label enable textline new concept vahidrezanezhad 2024-05-17 09:10:13 +02:00
• 6ef86585c0 adding page xml to label generator vahidrezanezhad 2024-05-16 15:03:23 +02:00
• 45aba32351
  Update utils.py vahidrezanezhad 2024-05-12 08:32:28 +02:00
• a7e1f255f3
  Update train.py vahidrezanezhad 2024-05-08 14:47:16 +02:00
• ce1108aca0 modifications vahidrezanezhad 2024-05-07 16:24:12 +02:00
• 8d1050ec30 inference script is added vahidrezanezhad 2024-05-07 13:34:03 +02:00
• 38db3e9289 adding enhancement training vahidrezanezhad 2024-05-06 18:31:48 +02:00
• dbb84507ed integrating first working classification training model vahidrezanezhad 2024-04-29 20:59:36 +02:00
• d27647a0f1 first working update of branch vahidrezanezhad 2024-04-16 01:00:48 +02:00
• 02b1436f39 code formatting with black; typos master cneud 2024-04-10 22:20:23 +02:00
• 5f84938839 update parameter config docs (fix #11) cneud 2024-04-10 21:40:23 +02:00
• 0103e14f44 add info on helpful tools (fix #14) cneud 2024-04-10 20:26:26 +02:00
• c4bcfc1fc0 use headless cv2 cneud 2024-04-10 20:03:02 +02:00
• 7dfaafefc6 adding requirements vahidrezanezhad 2024-04-04 11:30:12 +02:00
• 522f00ab99 adjusting to tf2 vahidrezanezhad 2024-04-04 11:26:28 +02:00
• e070e88794
  Merge 3098700dc9 into dbb404030e Herbert 2024-01-11 18:21:26 +00:00
• 3098700dc9 tf.keras version that allows any input resolution H.T. Kruitbosch 2024-01-11 19:04:42 +01:00
• dbb404030e supposed to solve https://github.com/qurator-spk/sbb_binarization/issues/41 vahid 2022-08-22 13:03:10 +02:00
• da558061ab
  Update README.md vahidrezanezhad 2021-07-14 06:01:33 -04:00
• 31b010269a
  Update README.md vahidrezanezhad 2021-06-29 07:22:34 -04:00