qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-10-26 23:34:13 +01:00
Code Issues Projects Releases Wiki Activity

update docs/makefile to point to v0.6.0 models

Browse source
This commit is contained in:
kba 2025-10-21 13:15:57 +02:00
parent c6b863b13f
commit a53d5fc452
4 changed files with 17 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

16
Makefile
View file

@ -6,21 +6,23 @@ EXTRAS ?=
DOCKER_BASE_IMAGE ?= docker.io/ocrd/core-cuda-tf2:latest DOCKER_BASE_IMAGE ?= docker.io/ocrd/core-cuda-tf2:latest
DOCKER_TAG ?= ocrd/eynollah DOCKER_TAG ?= ocrd/eynollah
DOCKER ?= docker DOCKER ?= docker
WGET = wget -O
#SEG_MODEL := https://qurator-data.de/eynollah/2021-04-25/models_eynollah.tar.gz #SEG_MODEL := https://qurator-data.de/eynollah/2021-04-25/models_eynollah.tar.gz
#SEG_MODEL := https://qurator-data.de/eynollah/2022-04-05/models_eynollah_renamed.tar.gz #SEG_MODEL := https://qurator-data.de/eynollah/2022-04-05/models_eynollah_renamed.tar.gz
# SEG_MODEL := https://qurator-data.de/eynollah/2022-04-05/models_eynollah.tar.gz # SEG_MODEL := https://qurator-data.de/eynollah/2022-04-05/models_eynollah.tar.gz
#SEG_MODEL := https://github.com/qurator-spk/eynollah/releases/download/v0.3.0/models_eynollah.tar.gz #SEG_MODEL := https://github.com/qurator-spk/eynollah/releases/download/v0.3.0/models_eynollah.tar.gz
#SEG_MODEL := https://github.com/qurator-spk/eynollah/releases/download/v0.3.1/models_eynollah.tar.gz #SEG_MODEL := https://github.com/qurator-spk/eynollah/releases/download/v0.3.1/models_eynollah.tar.gz
SEG_MODEL := https://zenodo.org/records/17194824/files/models_layout_v0_5_0.tar.gz?download=1 #SEG_MODEL := https://zenodo.org/records/17194824/files/models_layout_v0_5_0.tar.gz?download=1
SEG_MODEL := https://zenodo.org/records/17295988/files/models_layout_v0_6_0.tar.gz?download=1
SEG_MODELFILE = $(notdir $(patsubst %?download=1,%,$(SEG_MODEL))) SEG_MODELFILE = $(notdir $(patsubst %?download=1,%,$(SEG_MODEL)))
SEG_MODELNAME = $(SEG_MODELFILE:%.tar.gz=%) SEG_MODELNAME = $(SEG_MODELFILE:%.tar.gz=%)
BIN_MODEL := https://github.com/qurator-spk/sbb_binarization/releases/download/v0.0.11/saved_model_2021_03_09.zip BIN_MODEL := https://zenodo.org/records/17295988/files/models_binarization_v0_6_0.tar.gz?download=1
BIN_MODELFILE = $(notdir $(BIN_MODEL)) BIN_MODELFILE = $(notdir $(BIN_MODEL))
BIN_MODELNAME := default-2021-03-09 BIN_MODELNAME := default-2021-03-09
OCR_MODEL := https://zenodo.org/records/17236998/files/models_ocr_v0_5_1.tar.gz?download=1 OCR_MODEL := https://zenodo.org/records/17295988/files/models_ocr_v0_6_0.tar.gz?download=1
OCR_MODELFILE = $(notdir $(patsubst %?download=1,%,$(OCR_MODEL))) OCR_MODELFILE = $(notdir $(patsubst %?download=1,%,$(OCR_MODEL)))
OCR_MODELNAME = $(OCR_MODELFILE:%.tar.gz=%) OCR_MODELNAME = $(OCR_MODELFILE:%.tar.gz=%)
@ -55,18 +57,18 @@ help:
# END-EVAL # END-EVAL
# Download and extract models to $(PWD)/models_layout_v0_5_0 # Download and extract models to $(PWD)/models_layout_v0_6_0
models: $(BIN_MODELNAME) $(SEG_MODELNAME) $(OCR_MODELNAME) models: $(BIN_MODELNAME) $(SEG_MODELNAME) $(OCR_MODELNAME)
# do not download these files if we already have the directories # do not download these files if we already have the directories
.INTERMEDIATE: $(BIN_MODELFILE) $(SEG_MODELFILE) $(OCR_MODELFILE) .INTERMEDIATE: $(BIN_MODELFILE) $(SEG_MODELFILE) $(OCR_MODELFILE)
$(BIN_MODELFILE): $(BIN_MODELFILE):
wget -O $@ $(BIN_MODEL) $(WGET) $@ $(BIN_MODEL)
$(SEG_MODELFILE): $(SEG_MODELFILE):
wget -O $@ $(SEG_MODEL) $(WGET) $@ $(SEG_MODEL)
$(OCR_MODELFILE): $(OCR_MODELFILE):
wget -O $@ $(OCR_MODEL) $(WGET) $@ $(OCR_MODEL)
$(BIN_MODELNAME): $(BIN_MODELFILE) $(BIN_MODELNAME): $(BIN_MODELFILE)
mkdir $@ mkdir $@

6
README.md
View file

@ -55,7 +55,7 @@ make install EXTRAS=OCR
## Models ## Models
Pretrained models can be downloaded from [zenodo](https://zenodo.org/records/17194824) or [huggingface](https://huggingface.co/SBB?search_models=eynollah). Pretrained models can be downloaded from [zenodo](https://doi.org/10.5281/zenodo.17194823) or [huggingface](https://huggingface.co/SBB?search_models=eynollah).
For documentation on models, have a look at [`models.md`](https://github.com/qurator-spk/eynollah/tree/main/docs/models.md). For documentation on models, have a look at [`models.md`](https://github.com/qurator-spk/eynollah/tree/main/docs/models.md).
Model cards are also provided for our trained models. Model cards are also provided for our trained models.
@ -162,7 +162,7 @@ formally described in [`ocrd-tool.json`](https://github.com/qurator-spk/eynollah
In this case, the source image file group with (preferably) RGB images should be used as input like this: In this case, the source image file group with (preferably) RGB images should be used as input like this:
ocrd-eynollah-segment -I OCR-D-IMG -O OCR-D-SEG -P models eynollah_layout_v0_5_0 ocrd-eynollah-segment -I OCR-D-IMG -O OCR-D-SEG -P models eynollah_layout_v0_6_0
If the input file group is PAGE-XML (from a previous OCR-D workflow step), Eynollah behaves as follows: If the input file group is PAGE-XML (from a previous OCR-D workflow step), Eynollah behaves as follows:
- existing regions are kept and ignored (i.e. in effect they might overlap segments from Eynollah results) - existing regions are kept and ignored (i.e. in effect they might overlap segments from Eynollah results)
@ -174,7 +174,7 @@ If the input file group is PAGE-XML (from a previous OCR-D workflow step), Eynol
(because some other preprocessing step was in effect like `denoised`), then (because some other preprocessing step was in effect like `denoised`), then
the output PAGE-XML will be based on that as new top-level (`@imageFilename`) the output PAGE-XML will be based on that as new top-level (`@imageFilename`)
ocrd-eynollah-segment -I OCR-D-XYZ -O OCR-D-SEG -P models eynollah_layout_v0_5_0 ocrd-eynollah-segment -I OCR-D-XYZ -O OCR-D-SEG -P models eynollah_layout_v0_6_0
In general, it makes more sense to add other workflow steps **after** Eynollah. In general, it makes more sense to add other workflow steps **after** Eynollah.

6
src/eynollah/ocrd-tool.json
View file

@ -83,10 +83,10 @@
}, },
"resources": [ "resources": [
{ {
"url": "https://zenodo.org/records/17194824/files/models_layout_v0_5_0.tar.gz?download=1", "url": "https://zenodo.org/records/17295988/files/models_layout_v0_6_0.tar.gz?download=1",
"name": "models_layout_v0_5_0", "name": "models_layout_v0_6_0",
"type": "archive", "type": "archive",
"path_in_archive": "models_layout_v0_5_0", "path_in_archive": "models_layout_v0_6_0",
"size": 3525684179, "size": 3525684179,
"description": "Models for layout detection, reading order detection, textline detection, page extraction, column classification, table detection, binarization, image enhancement", "description": "Models for layout detection, reading order detection, textline detection, page extraction, column classification, table detection, binarization, image enhancement",
"version_range": ">= v0.5.0" "version_range": ">= v0.5.0"

4
train/README.md
View file

@ -22,14 +22,14 @@ Download our pretrained weights and add them to a `train/pretrained_model` folde
```sh ```sh
cd train cd train
wget -O pretrained_model.tar.gz https://zenodo.org/records/17243320/files/pretrained_model_v0_5_1.tar.gz?download=1 wget -O pretrained_model.tar.gz "https://zenodo.org/records/17295988/files/pretrained_model_v0_6_0.tar.gz?download=1"
tar xf pretrained_model.tar.gz tar xf pretrained_model.tar.gz
``` ```
### Binarization training data ### Binarization training data
A small sample of training data for binarization experiment can be found [on A small sample of training data for binarization experiment can be found [on
zenodo](https://zenodo.org/records/17243320/files/training_data_sample_binarization_v0_5_1.tar.gz?download=1), zenodo](https://zenodo.org/records/17295988/files/training_data_sample_binarization_v0_6_0.tar.gz?download=1),
which contains `images` and `labels` folders. which contains `images` and `labels` folders.
### Helpful tools ### Helpful tools