O

ocrd_calamari

Settings | Report Duplicate

0

I Use This!

Low Activity

Commits : Listings

Analyzed about 2 hours ago. based on code collected about 2 hours ago.

Commit Message	Contributor	Files Modified	Lines Added	Lines Removed	Code Location	Date
Sep 14, 2024 — Sep 14, 2025 Showing page 3 of 13 Search / Filter on:
update models (2.1→2.2 for Py3.11 `re` syntax)	Robert Sachunsky	More...				12 months ago
update requirements (Calamari 2.3, remove implied TF)	Robert Sachunsky	More...				12 months ago
avoid overriding itertools.batched, if any	Robert Sachunsky	More...				12 months ago
update models (5→6 HDF5→SavedModel)	Robert Sachunsky	More...				12 months ago
batching: split up batches if too long img widths	Robert Sachunsky	More...				12 months ago
use C2 deep3_fraktur19 model for testing	Robert Sachunsky	More...				12 months ago
add C2 models	Robert Sachunsky	More...				12 months ago
:package: 2.0.0	Robert Sachunsky	More...				12 months ago
expose device parameter, default to GPU	Robert Sachunsky	More...				12 months ago
test with pytest-isolate so TF memory can be freed between tests	Robert Sachunsky	More...				12 months ago
test configs: test metsserver independent of pageparallel	Robert Sachunsky	More...				12 months ago
voter cannot be parallel; shmem is faster	Robert Sachunsky	More...				12 months ago
convert images to input_channels (required TensorShape)	Robert Sachunsky	More...				12 months ago
wait for executor to fully initialize (so we get input_channels)	Robert Sachunsky	More...				12 months ago
:fire: adapt to (and require) Calamari 2…	Robert Sachunsky	More...				12 months ago
CI: increase RAM	Robert Sachunsky	More...				12 months ago
no more need for model fixup	Robert Sachunsky	More...				12 months ago
let GPU memory grow by demand (instead of exclusive reservation)	Robert Sachunsky	More...				12 months ago
require Calamari v1.0.7, no more need for model fixup	Robert Sachunsky	More...				12 months ago
aggregate all lines instead of per region to better utilise batched predictor	Robert Sachunsky	More...				12 months ago
let GPU memory grow by demand (instead of exclusive reservation)	Robert Sachunsky	More...				12 months ago
run prediction in bg thread (shared across pages to interleave CPU/GPU)	Robert Sachunsky	More...				12 months ago
aggregate all lines instead of per region to better utilise batched predictor	Robert Sachunsky	More...				12 months ago
require ocrd 3.0 and calamari-ocr 1.0.7	Robert Sachunsky	More...				12 months ago
tests: adapt to v3, overhaul and add caching+threading modes	Robert Sachunsky	More...				12 months ago
make test: no assumption on OCRD resource location	Robert Sachunsky	More...				12 months ago
adapt to ocrd>=3.0	Robert Sachunsky	More...				about 1 year ago
split up prediction to avoid overly large batches (causing OOM)	Robert Sachunsky	More...				about 1 year ago
Merge pull request #115 from OCR-D/pyproject_toml	Mike Gerber	More...				about 1 year ago
⚙ pyproject.toml: Add license.file	Mike Gerber	More...				about 1 year ago

←
1
2
3
4
5
6
7
8
9
…
12
13
→