Releases: Calamari-OCR/calamari
Releases · Calamari-OCR/calamari
v2.3.1
2.3.0.post1
(without tests, docs and other non-resource data files)
2.3.0
- 🔥 Switched from Apache 2 to GPL 3 license (which was effectively the case ever since Calamari 2.0)
- 🔥 Update to
ocrd-fork-tfaip==1.2.7(supporting Tensorflow up to and including 2.15) - Adapt to changes in Numpy, Pillow, Python 3.9 and 3.11
- 🔥 Switch to Tensorflow SavedModel format as backend for models (because they are compatible across Python versions)
new checkpoint format version identifier is6, updates will happen automatically (as usual), if possible
to migrate older models, you might need to go back to Python 3.8 once - Implement
--non_existing_pred_handling_modeevaluator param (providing newskipanderror, in addition to current and now defaultempty)
(fixes missing--non_existing_file_handling_modefrom Calamari 1) - Fix warmstarting: keep network architecture
- Introduce new model parameter
temperature(inactive by default, can be applied ex post)
for pre-scaling the logits, controlling steepness of probability distribution prior to CTC) - Respect directory of
PageXMLdatasets: output as input, unless--output-diris given - Change label
PERCENTtoPERCENT_CERin evaluator's confusion table - Fully git-controlled versioning (via
setuptools_scm)
1.0.7
1.0.6
2.2.2
2.2.1
2.1.5
2.2.0
- Upgrade to tfaip 1.2.6
- PageXML: Emit Glyphs, Words and confidence