docling-ibm-models 0.2.0__py3-none-any.whl → 1.0.0__py3-none-any.whl

docling_ibm_models/tableformer/data_management/tf_predictor.py

@@ -177,7 +177,7 @@ class TFPredictor:
         self._model_type = self._config["model"]["type"]
         # Added import here to avoid loading turbotransformer library unnecessarily
         if self._model_type == "TableModel04_rs":
-            from docling_ibm_models.tableformer.models.table04_rs.tablemodel04_rs import (  # noqa: F401
+            from docling_ibm_models.tableformer.models.table04_rs.tablemodel04_rs import (  # noqa
                 TableModel04_rs,
             )
         for candidate in BaseModel.__subclasses__():
@@ -437,10 +437,10 @@ class TFPredictor:
                 for pdf_cell in pdf_cells:
                     if pdf_cell["id"] == docling_item["cell_id"]:
                         text_cell_bbox = {
-                            "b": pdf_cell["bbox"][1],
+                            "b": pdf_cell["bbox"][3],
                             "l": pdf_cell["bbox"][0],
                             "r": pdf_cell["bbox"][2],
-                            "t": pdf_cell["bbox"][3],
+                            "t": pdf_cell["bbox"][1],
                             "token": pdf_cell["text"],
                         }
                         tf_cells_map[cell_key]["text_cell_bboxes"].append(
@@ -468,10 +468,10 @@ class TFPredictor:
                 for pdf_cell in pdf_cells:
                     if pdf_cell["id"] == docling_item["cell_id"]:
                         text_cell_bbox = {
-                            "b": pdf_cell["bbox"][1],
+                            "b": pdf_cell["bbox"][3],
                             "l": pdf_cell["bbox"][0],
                             "r": pdf_cell["bbox"][2],
-                            "t": pdf_cell["bbox"][3],
+                            "t": pdf_cell["bbox"][1],
                             "token": pdf_cell["text"],
                         }
                         tf_cells_map[cell_key]["text_cell_bboxes"].append(

{docling_ibm_models-0.2.0.dist-info → docling_ibm_models-1.0.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling-ibm-models
-Version: 0.2.0
+Version: 1.0.0
 Summary: This package contains the AI models used by the Docling PDF conversion package
 License: MIT
 Keywords: docling,convert,document,pdf,layout model,segmentation,table structure,table former
@@ -32,7 +32,16 @@ Requires-Dist: torchvision (==0.17.2)
 Requires-Dist: tqdm (>=4.64.0,<5.0.0)
 Description-Content-Type: text/markdown
 
-# Docling-models
+[![PyPI version](https://img.shields.io/pypi/v/docling-ibm-models)](https://pypi.org/project/docling-ibm-models/)
+![Python](https://img.shields.io/badge/python-3.11%20%7C%203.12-blue)
+[![Poetry](https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json)](https://python-poetry.org/)
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+[![Imports: isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat&labelColor=ef8336)](https://pycqa.github.io/isort/)
+[![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit)
+[![Models on Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Model-blue)](https://huggingface.co/ds4sd/docling-models/)
+[![License MIT](https://img.shields.io/github/license/ds4sd/deepsearch-toolkit)](https://opensource.org/licenses/MIT)
+
+# Docling IBM models
 
 AI modules to support the Dockling PDF document conversion project.
 
@@ -41,7 +50,7 @@ AI modules to support the Dockling PDF document conversion project.
 
 
 ## Installation Instructions
- 
+
 ### MacOS / Linux
 
 To install `poetry` locally, use either `pip` or `homebrew`.
@@ -49,8 +58,8 @@ To install `poetry` locally, use either `pip` or `homebrew`.
 To install `poetry` on a docker container, do the following:
 ```
 ENV POETRY_NO_INTERACTION=1 \
-    POETRY_VIRTUALENVS_CREATE=false 
-  
+    POETRY_VIRTUALENVS_CREATE=false
+
 # Install poetry
 RUN curl -sSL 'https://install.python-poetry.org' > install-poetry.py \
     && python install-poetry.py \
@@ -58,7 +67,7 @@ RUN curl -sSL 'https://install.python-poetry.org' > install-poetry.py \
     && rm install-poetry.py
 ```
 
-To install and run the package, simply set up a poetry environment 
+To install and run the package, simply set up a poetry environment
 
 ```
 poetry env use $(which python3.11)
@@ -105,7 +114,7 @@ Example configuration can be seen inside test `tests/test_tf_predictor.py`
 These are the main sections of the configuration file:
 
 - `dataset`: The directory for prepared data and the parameters used during the data loading.
-- `model`: The type, name and hyperparameters of the model. Also the directory to save/load the 
+- `model`: The type, name and hyperparameters of the model. Also the directory to save/load the
   trained checkpoint files.
 - `train`: Parameters for the training of the model.
 - `predict`: Parameters for the evaluation of the model.
@@ -131,7 +140,7 @@ First download the model weights (see above), then run:
 ./devtools/check_code.sh
 ```
 
-This will also generate prediction and matching visualizations that can be found here: 
+This will also generate prediction and matching visualizations that can be found here:
 `tests\test_data\viz\`
 
 Visualization outlines:

{docling_ibm_models-0.2.0.dist-info → docling_ibm_models-1.0.0.dist-info}/RECORD

@@ -7,7 +7,7 @@ docling_ibm_models/tableformer/data_management/functional.py,sha256=UrXsEm4DSc1Q
 docling_ibm_models/tableformer/data_management/matching_post_processor.py,sha256=HYG-wx5PQC38hTQfyXr3zUnZ6--aSs55x8g9PdsROGU,54207
 docling_ibm_models/tableformer/data_management/tf_cell_matcher.py,sha256=DFu428Cr84maT9WehdoZkpkJKeahwe5JlclvTC6fuVY,20870
 docling_ibm_models/tableformer/data_management/tf_dataset.py,sha256=6_qSsYt6qoE2JBzUNrJfCDX3Kgg7tyrv3kimGLdEQ5o,49890
-docling_ibm_models/tableformer/data_management/tf_predictor.py,sha256=I317-qMK13eqUvT4Ix2Q02uzkKQDCoKcf9GqIGVBy70,38508
+docling_ibm_models/tableformer/data_management/tf_predictor.py,sha256=3e7ICgs3r9YclOLWuoOvqSveQHcERvZYmOBMtmslJqU,38502
 docling_ibm_models/tableformer/data_management/transforms.py,sha256=_i1HXkX8LAuHbeGRrg8kF9yFNJRQZOKmWzxKt559ABQ,13268
 docling_ibm_models/tableformer/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling_ibm_models/tableformer/models/common/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -26,7 +26,7 @@ docling_ibm_models/tableformer/utils/app_profiler.py,sha256=13dvwo5byzfP2ejqGBFw
 docling_ibm_models/tableformer/utils/torch_utils.py,sha256=uN0rK9mSXy1ewBnBnILrWebJhhVU4N-XJZBqNiLJwlQ,8893
 docling_ibm_models/tableformer/utils/utils.py,sha256=8Bxf1rEn977lFbY9NX0r5xh9PvxIRipQZX_EZW92XfA,10980
 docling_ibm_models/tableformer/utils/variance.py,sha256=USjRwaMsCmzvc6PeWskaAJnUjbliRVd_MqNKLjMDQw8,4675
-docling_ibm_models-0.2.0.dist-info/LICENSE,sha256=ACwmltkrXIz5VsEQcrqljq-fat6ZXAMepjXGoe40KtE,1069
-docling_ibm_models-0.2.0.dist-info/METADATA,sha256=Sp-I-WgmqMBo4G5kvBwQsVTIjwHpWpa6i0aGevNzG3I,6003
-docling_ibm_models-0.2.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling_ibm_models-0.2.0.dist-info/RECORD,,
+docling_ibm_models-1.0.0.dist-info/LICENSE,sha256=ACwmltkrXIz5VsEQcrqljq-fat6ZXAMepjXGoe40KtE,1069
+docling_ibm_models-1.0.0.dist-info/METADATA,sha256=x4XQzAxVvgbNsVzMTFQGcvEQlDxfqx3l6thHcsL-apg,6968
+docling_ibm_models-1.0.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+docling_ibm_models-1.0.0.dist-info/RECORD,,