v0.10.0

Note: docTR 0.10.0 requires python >= 3.9
Note: docTR 0.10.0 requires either TensorFlow >= 2.15.0 or PyTorch >= 2.0.0

What's Changed

Soft Breaking Changes (TensorFlow backend only) 🛠

• Changed the saving format from /weights to .weights.h5

NOTE: Please update your custom trained models and HuggingFace hub uploaded models, this will be the last release supporting manual loading from /weights.

New features

• Added numpy 2.0 support @felixdittrich92
• New and updated notebooks was added @felixdittrich92 --> notebooks
• Custom orientation model loading @felixdittrich92
• Additional functionality to control the pipeline when dealing with rotated documents @milosacimovic @felixdittrich92
• Bulit-in datasets can now be loaded directly for detection with detection_task=True comparable to the existing recognition_task=True @felixdittrich92

Disable page orientation classification

• If you deal with documents which contains only small rotations (~ -45 to 45 degrees), you can disable the page orientation classification to speed up the inference.
• This will only have an effect with assume_straight_pages=False and/or straighten_pages=True and/or detect_orientation=True.

from doctr.models import ocr_predictor

model = ocr_predictor(pretrained=True, assume_straight_pages=False, disable_page_orientation=True)

Disable crop orientation classification

• If you deal with documents which contains only horizontal text, you can disable the crop orientation classification to speed up the inference.
• This will only have an effect with assume_straight_pages=False and/or straighten_pages=True.

from doctr.models import ocr_predictor

model = ocr_predictor(pretrained=True, assume_straight_pages=False, disable_crop_orientation=True)

Loading custom exported orientation classification models

You can now load your custom trained orientation models, the following snippet demonstrates how:

from doctr.io import DocumentFile
from doctr.models import ocr_predictor, mobilenet_v3_small_page_orientation, mobilenet_v3_small_crop_orientation
from doctr.models.classification.zoo import crop_orientation_predictor, page_orientation_predictor

custom_page_orientation_model = mobilenet_v3_small_page_orientation("<PATH_TO_CUSTOM_EXPORTED_ONNX_MODEL>")
custom_crop_orientation_model = mobilenet_v3_small_crop_orientation("<PATH_TO_CUSTOM_EXPORTED_ONNX_MODEL>"))

predictor = ocr_predictor(pretrained=True, assume_straight_pages=False, detect_orientation=True)

# Overwrite the default orientation models
predictor.crop_orientation_predictor = crop_orientation_predictor(custom_crop_orientation_model)
predictor.page_orientation_predictor = page_orientation_predictor(custom_page_orientation_model)

What's Changed

Breaking Changes 🛠

• [TF] First changes on the road to Keras v3 by @felixdittrich92 in #1724
• [Build] update minor version & update torch to >= 2.0 by @felixdittrich92 in #1747

New Features

• Disable page and crop orientation by @milosacimovic in #1735

Bug Fixes

• [Bug] fix straighten pages by @felixdittrich92 in #1697
• [Fix] Remove image padding after rotation correction with straighten_pages=True by @felixdittrich92 in #1731
• [datasets] Allow detection task for built-in datasets by @felixdittrich92 in #1717
• [Bug] Fix eval scripts + possible overflow in Resize by @felixdittrich92 in #1715
• [demo] Add missing viz dep for demo by @felixT2K in #1751

Improvements

• [Datasets] Add Vietnamese letters by @MinhChien9 in #1693
• feat: added ukrainian vocab by @holyCowMp3 in #1700
• [orientation] Enable usage of custom trained orientation models by @felixdittrich92 in #1708
• [demo] Automate doctr demo update via CI job by @felixdittrich92 in #1742
• [TF] Move model building & unify train scripts by @felixdittrich92 in #1744
• [demo/docs] Update notebook docs & minor demo update / fix by @felixT2K in #1755
• [Reconstitution] Improve reconstitution by @felixdittrich92 in #1750

Miscellaneous

• [misc] post release 0.9.1 by @felixT2K in #1689
• [build] NumPy 2.0 support by @felixdittrich92 in #1709

New Contributors

• @MinhChien9 made their first contribution in #1693
• @holyCowMp3 made their first contribution in #1700
• @milosacimovic made their first contribution in #1735

Full Changelog: v0.9.0...v0.10.0