Merge branch 'feature/reading_order'

mittagessen · Nov 14, 2023 · e9a699c · e9a699c
2 parents 674a772 + 8a39a9a
commit e9a699c
Show file tree

Hide file tree

Showing 55 changed files with 4,943 additions and 1,764 deletions.
diff --git a/conda/meta.yaml b/conda/meta.yaml
@@ -32,6 +32,7 @@ requirements:
      - pyarrow
      - pytorch-lightning~=2.0
      - torchmetrics>=1.1.0
+     - conda-forge::threadpoolctl~=3.2.0
      - albumentations
      - rich
 about:

diff --git a/docs/api_docs.rst b/docs/api_docs.rst
@@ -2,8 +2,11 @@
 API Reference
 *************
 
+Segmentation
+============
+
 kraken.blla module
-==================
+------------------
 
 .. note::
 
@@ -14,7 +17,7 @@ kraken.blla module
 .. autoapifunction:: kraken.blla.segment
 
 kraken.pageseg module
-=====================
+---------------------
 
 .. note::
 
@@ -24,150 +27,141 @@ kraken.pageseg module
 
 .. autoapifunction:: kraken.pageseg.segment
 
-kraken.rpred module
-===================
+Recognition
+===========
 
-.. autoapifunction:: kraken.rpred.bidi_record
+kraken.rpred module
+-------------------
 
 .. autoapiclass:: kraken.rpred.mm_rpred
         :members:
 
-.. autoapiclass:: kraken.rpred.ocr_record
-        :members:
-
 .. autoapifunction:: kraken.rpred.rpred
 
+Serialization
+=============
 
 kraken.serialization module
-===========================
+---------------------------
 
 .. autoapifunction:: kraken.serialization.render_report
 
 .. autoapifunction:: kraken.serialization.serialize
 
 .. autoapifunction:: kraken.serialization.serialize_segmentation
 
-kraken.lib.models module
-========================
+Default templates
+-----------------
 
-.. autoapiclass:: kraken.lib.models.TorchSeqRecognizer
-    :members:
+ALTO 4.4
+^^^^^^^^
 
-.. autoapifunction:: kraken.lib.models.load_any
+.. literalinclude:: ../../templates/alto
+        :language: xml+jinja
 
-kraken.lib.vgsl module
-======================
+PageXML
+^^^^^^^
 
-.. autoapiclass:: kraken.lib.vgsl.TorchVGSLModel
-    :members:
+.. literalinclude:: ../../templates/alto
+        :language: xml+jinja
 
-kraken.lib.xml module
-=====================
+hOCR
+^^^^
 
-.. autoapifunction:: kraken.lib.xml.parse_xml
+.. literalinclude:: ../../templates/alto
+        :language: xml+jinja
 
-.. autoapifunction:: kraken.lib.xml.parse_page
+ABBYY XML
+^^^^^^^^^
 
-.. autoapifunction:: kraken.lib.xml.parse_alto
+.. literalinclude:: ../../templates/abbyyxml
+        :language: xml+jinja
+
+Containers and Helpers
+======================
 
 kraken.lib.codec module
-=======================
+-----------------------
 
 .. autoapiclass:: kraken.lib.codec.PytorchCodec
     :members:
 
-kraken.lib.train module
-=======================
+kraken.containers module
+------------------------
 
-Training Schedulers
--------------------
+.. autoapiclass:: kraken.containers.Segmentation
+        :members:
 
-.. autoapiclass:: kraken.lib.train.TrainScheduler
-    :members:
+.. autoapiclass:: kraken.containers.BaselineLine
+        :members:
 
-.. autoapiclass:: kraken.lib.train.annealing_step
-    :members:
+.. autoapiclass:: kraken.containers.BBoxLine
+        :members:
 
-.. autoapiclass:: kraken.lib.train.annealing_const
-    :members:
+.. autoapiclass:: kraken.containers.ocr_record
+        :members:
 
-.. autoapiclass:: kraken.lib.train.annealing_exponential
-    :members:
+.. autoapiclass:: kraken.containers.BaselineOCRRecord
+        :members:
 
-.. autoapiclass:: kraken.lib.train.annealing_reduceonplateau
-    :members:
+.. autoapiclass:: kraken.containers.BBoxOCRRecord
+        :members:
 
-.. autoapiclass:: kraken.lib.train.annealing_cosine
-    :members:
+.. autoapiclass:: kraken.containers.ProcessingStep
+        :members:
 
-.. autoapiclass:: kraken.lib.train.annealing_onecycle
-    :members:
+kraken.lib.ctc_decoder
+----------------------
 
-Training Stoppers
------------------
+.. autoapifunction:: kraken.lib.ctc_decoder.beam_decoder
 
-.. autoapiclass:: kraken.lib.train.TrainStopper
-    :members:
+.. autoapifunction:: kraken.lib.ctc_decoder.greedy_decoder
 
-.. autoapiclass:: kraken.lib.train.EarlyStopping
-    :members:
+.. autoapifunction:: kraken.lib.ctc_decoder.blank_threshold_decoder
 
-.. autoapiclass:: kraken.lib.train.EpochStopping
-    :members:
+kraken.lib.exceptions
+---------------------
 
-.. autoapiclass:: kraken.lib.train.NoStopping
+.. autoapiclass:: kraken.lib.exceptions.KrakenCodecException
     :members:
 
-Loss and Evaluation Functions
------------------------------
-
-.. autoapifunction:: kraken.lib.train.recognition_loss_fn
-
-.. autoapifunction:: kraken.lib.train.baseline_label_loss_fn
-
-.. autoapifunction:: kraken.lib.train.recognition_evaluator_fn
-
-.. autoapifunction:: kraken.lib.train.baseline_label_evaluator_fn
-
-Trainer
--------
-
-.. autoapiclass:: kraken.lib.train.KrakenTrainer
+.. autoapiclass:: kraken.lib.exceptions.KrakenStopTrainingException
     :members:
 
+.. autoapiclass:: kraken.lib.exceptions.KrakenEncodeException
+    :members:
 
-kraken.lib.dataset module
-=========================
-
-Datasets
---------
+.. autoapiclass:: kraken.lib.exceptions.KrakenRecordException
+    :members:
 
-.. autoapiclass:: kraken.lib.dataset.BaselineSet
+.. autoapiclass:: kraken.lib.exceptions.KrakenInvalidModelException
     :members:
 
-.. autoapiclass:: kraken.lib.dataset.PolygonGTDataset
+.. autoapiclass:: kraken.lib.exceptions.KrakenInputException
     :members:
 
-.. autoapiclass:: kraken.lib.dataset.GroundTruthDataset
+.. autoapiclass:: kraken.lib.exceptions.KrakenRepoException
     :members:
 
-Helpers
--------
+.. autoapiclass:: kraken.lib.exceptions.KrakenCairoSurfaceException
+    :members:
 
-.. autoapifunction:: kraken.lib.dataset.compute_error
+kraken.lib.models module
+------------------------
 
-.. autoapifunction:: kraken.lib.dataset.preparse_xml_data
+.. autoapiclass:: kraken.lib.models.TorchSeqRecognizer
+    :members:
 
-.. autoapifunction:: kraken.lib.dataset.generate_input_transforms
+.. autoapifunction:: kraken.lib.models.load_any
 
 kraken.lib.segmentation module
 ------------------------------
 
 .. autoapifunction:: kraken.lib.segmentation.reading_order
 
-.. autoapifunction:: kraken.lib.segmentation.polygonal_reading_order
+.. autoapifunction:: kraken.lib.segmentation.neural_reading_order
 
-.. autoapifunction:: kraken.lib.segmentation.denoising_hysteresis_thresh
+.. autoapifunction:: kraken.lib.segmentation.polygonal_reading_order
 
 .. autoapifunction:: kraken.lib.segmentation.vectorize_lines
 
@@ -181,43 +175,82 @@ kraken.lib.segmentation module
 
 .. autoapifunction:: kraken.lib.segmentation.extract_polygons
 
+kraken.lib.vgsl module
+----------------------
 
-kraken.lib.ctc_decoder
-======================
+.. autoapiclass:: kraken.lib.vgsl.TorchVGSLModel
+    :members:
 
-.. autoapifunction:: kraken.lib.ctc_decoder.beam_decoder
+kraken.lib.xml module
+---------------------
 
-.. autoapifunction:: kraken.lib.ctc_decoder.greedy_decoder
+.. autoapiclass:: kraken.lib.xml.XMLPage
 
-.. autoapifunction:: kraken.lib.ctc_decoder.blank_threshold_decoder
+Training
+========
 
-kraken.lib.exceptions
-=====================
+kraken.lib.train module
+-----------------------
 
-.. autoapiclass:: kraken.lib.exceptions.KrakenCodecException
-    :members:
+Loss and Evaluation Functions
+-----------------------------
 
-.. autoapiclass:: kraken.lib.exceptions.KrakenStopTrainingException
+.. autoapifunction:: kraken.lib.train.recognition_loss_fn
+
+.. autoapifunction:: kraken.lib.train.baseline_label_loss_fn
+
+.. autoapifunction:: kraken.lib.train.recognition_evaluator_fn
+
+.. autoapifunction:: kraken.lib.train.baseline_label_evaluator_fn
+
+Trainer
+-------
+
+.. autoapiclass:: kraken.lib.train.KrakenTrainer
     :members:
 
-.. autoapiclass:: kraken.lib.exceptions.KrakenEncodeException
+
+kraken.lib.dataset module
+-------------------------
+
+Recognition datasets
+^^^^^^^^^^^^^^^^^^^^
+
+.. autoapiclass:: kraken.lib.dataset.ArrowIPCRecognitionDataset
     :members:
 
-.. autoapiclass:: kraken.lib.exceptions.KrakenRecordException
+.. autoapiclass:: kraken.lib.dataset.BaselineSet
     :members:
 
-.. autoapiclass:: kraken.lib.exceptions.KrakenInvalidModelException
+.. autoapiclass:: kraken.lib.dataset.GroundTruthDataset
     :members:
 
-.. autoapiclass:: kraken.lib.exceptions.KrakenInputException
+Segmentation datasets
+^^^^^^^^^^^^^^^^^^^^^
+
+.. autoapiclass:: kraken.lib.dataset.PolygonGTDataset
     :members:
 
-.. autoapiclass:: kraken.lib.exceptions.KrakenRepoException
+Reading order datasets
+^^^^^^^^^^^^^^^^^^^^^^
+
+.. autoapiclass:: kraken.lib.dataset.PairWiseROSet
     :members:
 
-.. autoapiclass:: kraken.lib.exceptions.KrakenCairoSurfaceException
+.. autoapiclass:: kraken.lib.dataset.PageWiseROSet
     :members:
 
+Helpers
+^^^^^^^
+
+.. autoapiclass:: kraken.lib.dataset.ImageInputTransforms
+   :members:
+
+.. autoapifunction:: kraken.lib.dataset.collate_sequences
+
+.. autoapifunction:: kraken.lib.dataset.global_align
+
+.. autoapifunction:: kraken.lib.dataset.compute_confusions
 
 Legacy modules
 ==============

diff --git a/docs/ketos.rst b/docs/ketos.rst
@@ -142,7 +142,7 @@ option                                                  action
 -F, \--savefreq                                         Model save frequency in epochs during
                                                         training
 -q, \--quit                                             Stop condition for training. Set to `early`
-                                                        for early stopping (default) or `dumb` for fixed
+                                                        for early stopping (default) or `fixed` for fixed
                                                         number of epochs.
 -N, \--epochs                                           Number of epochs to train for.
 \--min-epochs                                           Minimum number of epochs to train for when using early stopping.

diff --git a/environment.yml b/environment.yml
@@ -24,6 +24,7 @@ dependencies:
   - pyarrow
   - conda-forge::pytorch-lightning~=2.0.0
   - conda-forge::torchmetrics>=1.1.0
+  - conda-forge::threadpoolctl~=3.2
   - pip
   - albumentations
   - rich

diff --git a/environment_cuda.yml b/environment_cuda.yml
@@ -25,6 +25,7 @@ dependencies:
   - pyarrow
   - conda-forge::pytorch-lightning~=2.0.0
   - conda-forge::torchmetrics>=1.1.0
+  - conda-forge::threadpoolctl~=3.2
   - pip
   - albumentations
   - rich