Releases: OCR-D/ocrd_calamari
Releases · OCR-D/ocrd_calamari
v2.1.0
v2.0.1
v2.0.0
Changed:
- 🔥 Upgrade calamari API to v2, #118
- 🔥 Upgrade OCR-D API to v3, #118
- 🔥 Switch license from Apache 2.0 to GPLv3 for compatibility with Planet-AI-GmbH/tfaip#12, #118
- Dockerfile: Pre-package ocrd-all-tool.json and update metadata, #118
- CI: Use smaller calamari2-compatible model, #118
ocrd-tool.json
: paramcheckpoint_dir
obligatory now, #118ocrd-tool.json
: update and extend recognition modelresources
, including versioning metadata, #118- Processor API: Use background pipeline to efficiently batch processing tasks, #118
- Tests: Test with all configurations of OCR-D/core's METS caching/page-parallel processing, #118
Removed:
- obsolete
fix-calamari1-models
script, #118
v1.0.6
- Fix: Depend on protobuf < 4.0 (@mikegerber, #89)
- Tested on Python 3.6-3.10
v1.0.5
- README: Do not mention obsolete + unsupported checkpoint parameter (@mikegerber, #80)
- Skip tiny or bin-empty lines (@bertsky, #76)
v1.0.4
- 🚨 Breaking change: There is no
checkpoint
parameter anymore, it was replaced with the new parametercheckpoint_dir
(@bertsky, #70)- e.g.
-P checkpoint "/var/lib/calamari-models/GT4HistOCR/2019-12-11T11_10+0100/*.ckpt.json"
becomes-P checkpoint_dir "/var/lib/calamari-models/GT4HistOCR/2019-12-11T11_10+0100/"
- e.g.
- Descend to all available TextRegions recursively (@bertsky, #75)
- This release is now tested on Python 3.6 → 3.10 (@mikegerber)
v1.0.3
v1.0.2
- Warn if passing raw images to single-channel models (@bertsky)
- Fix word and glyph coordinates (@mikegerber)
v1.0.1
v1.0.0
- Update to support Calamari 1.0
- Major number increase due to needed model update
- New GT4HistOCR model required
- https://qurator-data.de/calamari-models/GT4HistOCR/2019-12-11T11_10+0100/
- This model gives as good results as before (https://gist.github.com/mikegerber/7e16e814bf723f04c47c5a6e2a6ac1d1)
- Calamari 1.0 requires TF 2!