onnxtr 0.4.0__tar.gz → 0.4.1__tar.gz

{onnxtr-0.4.0 → onnxtr-0.4.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: onnxtr
-Version: 0.4.0
+Version: 0.4.1
 Summary: Onnx Text Recognition (OnnxTR): docTR Onnx-Wrapper for high-performance OCR on documents.
 Author-email: Felix Dittrich <felixdittrich92@gmail.com>
 Maintainer: Felix Dittrich
@@ -225,7 +225,7 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: <4,>=3.9.0
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: numpy<2.0.0,>=1.16.0
+Requires-Dist: numpy<3.0.0,>=1.16.0
 Requires-Dist: scipy<2.0.0,>=1.4.0
 Requires-Dist: opencv-python<5.0.0,>=4.5.0
 Requires-Dist: pypdfium2<5.0.0,>=4.11.0
@@ -276,7 +276,7 @@ Requires-Dist: pre-commit>=2.17.0; extra == "dev"
 [![codecov](https://codecov.io/gh/felixdittrich92/OnnxTR/graph/badge.svg?token=WVFRCQBOLI)](https://codecov.io/gh/felixdittrich92/OnnxTR)
 [![Codacy Badge](https://app.codacy.com/project/badge/Grade/4fff4d764bb14fb8b4f4afeb9587231b)](https://app.codacy.com/gh/felixdittrich92/OnnxTR/dashboard?utm_source=gh&utm_medium=referral&utm_content=&utm_campaign=Badge_grade)
 [![CodeFactor](https://www.codefactor.io/repository/github/felixdittrich92/onnxtr/badge)](https://www.codefactor.io/repository/github/felixdittrich92/onnxtr)
-[![Pypi](https://img.shields.io/badge/pypi-v0.3.2-blue.svg)](https://pypi.org/project/OnnxTR/)
+[![Pypi](https://img.shields.io/badge/pypi-v0.4.1-blue.svg)](https://pypi.org/project/OnnxTR/)
 
 > :warning: Please note that this is a wrapper around the [doctr](https://github.com/mindee/doctr) library to provide a Onnx pipeline for docTR. For feature requests, which are not directly related to the Onnx pipeline, please refer to the base project.
 
@@ -589,8 +589,8 @@ The smallest combination in OnnxTR (docTR) of `db_mobilenet_v3_large` and `crnn_
 |Library                          |FUNSD (199 pages)              |CORD  (900 pages)              |
 |---------------------------------|-------------------------------|-------------------------------|
 |docTR (CPU) - v0.8.1             | ~1.29s / Page                 | ~0.60s / Page                 |
-|**OnnxTR (CPU)** - v0.1.2        | ~0.57s / Page                 | **~0.25s / Page**             |
-|**OnnxTR (CPU) 8-bit** - v0.1.2  | **~0.38s / Page**             | **~0.14s / Page**             |
+|**OnnxTR (CPU)** - v0.4.1        | ~0.57s / Page                 | **~0.25s / Page**             |
+|**OnnxTR (CPU) 8-bit** - v0.4.1  | **~0.38s / Page**             | **~0.14s / Page**             |
 |EasyOCR (CPU) - v1.7.1           | ~1.96s / Page                 | ~1.75s / Page                 |
 |**PyTesseract (CPU)** - v0.3.10  | **~0.50s / Page**             | ~0.52s / Page                 |
 |Surya (line) (CPU) - v0.4.4      | ~48.76s / Page                | ~35.49s / Page                |
@@ -602,7 +602,7 @@ The smallest combination in OnnxTR (docTR) of `db_mobilenet_v3_large` and `crnn_
 |-------------------------------------|-------------------------------|-------------------------------|
 |docTR (GPU) - v0.8.1                 | ~0.07s / Page                 | ~0.05s / Page                 |
 |**docTR (GPU) float16** - v0.8.1     | **~0.06s / Page**             | **~0.03s / Page**             |
-|OnnxTR (GPU) - v0.1.2                | **~0.06s / Page**             | ~0.04s / Page                 |
+|OnnxTR (GPU) - v0.4.1                | **~0.06s / Page**             | ~0.04s / Page                 |
 |EasyOCR (GPU) - v1.7.1               | ~0.31s / Page                 | ~0.19s / Page                 |
 |Surya (GPU) float16 - v0.4.4         | ~3.70s / Page                 | ~2.81s / Page                 |
 |**PaddleOCR (GPU) - no cls - v2.7.3**| ~0.08s / Page                 | **~0.03s / Page**             |
@@ -621,6 +621,16 @@ If you wish to cite please refer to the base project citation, feel free to use
 }
 ```
 
+```bibtex
+@misc{onnxtr2024,
+    title={OnnxTR: Optical Character Recognition made seamless & accessible to anyone, powered by Onnx},
+    author={Felix Dittrich},
+    year={2024},
+    publisher = {GitHub},
+    howpublished = {\url{https://github.com/felixdittrich92/OnnxTR}}
+}
+```
+
 ## License
 
 Distributed under the Apache 2.0 License. See [`LICENSE`](https://github.com/felixdittrich92/OnnxTR?tab=Apache-2.0-1-ov-file#readme) for more information.

{onnxtr-0.4.0 → onnxtr-0.4.1}/README.md

@@ -7,7 +7,7 @@
 [![codecov](https://codecov.io/gh/felixdittrich92/OnnxTR/graph/badge.svg?token=WVFRCQBOLI)](https://codecov.io/gh/felixdittrich92/OnnxTR)
 [![Codacy Badge](https://app.codacy.com/project/badge/Grade/4fff4d764bb14fb8b4f4afeb9587231b)](https://app.codacy.com/gh/felixdittrich92/OnnxTR/dashboard?utm_source=gh&utm_medium=referral&utm_content=&utm_campaign=Badge_grade)
 [![CodeFactor](https://www.codefactor.io/repository/github/felixdittrich92/onnxtr/badge)](https://www.codefactor.io/repository/github/felixdittrich92/onnxtr)
-[![Pypi](https://img.shields.io/badge/pypi-v0.3.2-blue.svg)](https://pypi.org/project/OnnxTR/)
+[![Pypi](https://img.shields.io/badge/pypi-v0.4.1-blue.svg)](https://pypi.org/project/OnnxTR/)
 
 > :warning: Please note that this is a wrapper around the [doctr](https://github.com/mindee/doctr) library to provide a Onnx pipeline for docTR. For feature requests, which are not directly related to the Onnx pipeline, please refer to the base project.
 
@@ -320,8 +320,8 @@ The smallest combination in OnnxTR (docTR) of `db_mobilenet_v3_large` and `crnn_
 |Library                          |FUNSD (199 pages)              |CORD  (900 pages)              |
 |---------------------------------|-------------------------------|-------------------------------|
 |docTR (CPU) - v0.8.1             | ~1.29s / Page                 | ~0.60s / Page                 |
-|**OnnxTR (CPU)** - v0.1.2        | ~0.57s / Page                 | **~0.25s / Page**             |
-|**OnnxTR (CPU) 8-bit** - v0.1.2  | **~0.38s / Page**             | **~0.14s / Page**             |
+|**OnnxTR (CPU)** - v0.4.1        | ~0.57s / Page                 | **~0.25s / Page**             |
+|**OnnxTR (CPU) 8-bit** - v0.4.1  | **~0.38s / Page**             | **~0.14s / Page**             |
 |EasyOCR (CPU) - v1.7.1           | ~1.96s / Page                 | ~1.75s / Page                 |
 |**PyTesseract (CPU)** - v0.3.10  | **~0.50s / Page**             | ~0.52s / Page                 |
 |Surya (line) (CPU) - v0.4.4      | ~48.76s / Page                | ~35.49s / Page                |
@@ -333,7 +333,7 @@ The smallest combination in OnnxTR (docTR) of `db_mobilenet_v3_large` and `crnn_
 |-------------------------------------|-------------------------------|-------------------------------|
 |docTR (GPU) - v0.8.1                 | ~0.07s / Page                 | ~0.05s / Page                 |
 |**docTR (GPU) float16** - v0.8.1     | **~0.06s / Page**             | **~0.03s / Page**             |
-|OnnxTR (GPU) - v0.1.2                | **~0.06s / Page**             | ~0.04s / Page                 |
+|OnnxTR (GPU) - v0.4.1                | **~0.06s / Page**             | ~0.04s / Page                 |
 |EasyOCR (GPU) - v1.7.1               | ~0.31s / Page                 | ~0.19s / Page                 |
 |Surya (GPU) float16 - v0.4.4         | ~3.70s / Page                 | ~2.81s / Page                 |
 |**PaddleOCR (GPU) - no cls - v2.7.3**| ~0.08s / Page                 | **~0.03s / Page**             |
@@ -352,6 +352,16 @@ If you wish to cite please refer to the base project citation, feel free to use
 }
 ```
 
+```bibtex
+@misc{onnxtr2024,
+    title={OnnxTR: Optical Character Recognition made seamless & accessible to anyone, powered by Onnx},
+    author={Felix Dittrich},
+    year={2024},
+    publisher = {GitHub},
+    howpublished = {\url{https://github.com/felixdittrich92/OnnxTR}}
+}
+```
+
 ## License
 
 Distributed under the Apache 2.0 License. See [`LICENSE`](https://github.com/felixdittrich92/OnnxTR?tab=Apache-2.0-1-ov-file#readme) for more information.

{onnxtr-0.4.0 → onnxtr-0.4.1}/onnxtr/models/predictor/base.py

@@ -112,8 +112,8 @@ class _OCRPredictor:
             ]
         )
         return [
-            # We exapnd if the page is wider than tall and the angle is 90 or -90
-            rotate_image(page, angle, expand=page.shape[1] > page.shape[0] and abs(angle) == 90)
+            # expand if height and width are not equal
+            rotate_image(page, angle, expand=page.shape[0] != page.shape[1])
             for page, angle in zip(pages, origin_pages_orientations)
         ]
 

{onnxtr-0.4.0 → onnxtr-0.4.1}/onnxtr/models/predictor/predictor.py

@@ -100,6 +100,8 @@ class OCRPredictor(NestedObject, _OCRPredictor):
             origin_pages_orientations = None
         if self.straighten_pages:
             pages = self._straighten_pages(pages, seg_maps, general_pages_orientations, origin_pages_orientations)
+            # update page shapes after straightening
+            origin_page_shapes = [page.shape[:2] for page in pages]
 
             # forward again to get predictions on straight pages
             loc_preds = self.det_predictor(pages, **kwargs)  # type: ignore[assignment]

onnxtr-0.4.1/onnxtr/version.py

@@ -0,0 +1 @@
+__version__ = 'v0.4.1'

{onnxtr-0.4.0 → onnxtr-0.4.1}/onnxtr.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: onnxtr
-Version: 0.4.0
+Version: 0.4.1
 Summary: Onnx Text Recognition (OnnxTR): docTR Onnx-Wrapper for high-performance OCR on documents.
 Author-email: Felix Dittrich <felixdittrich92@gmail.com>
 Maintainer: Felix Dittrich
@@ -225,7 +225,7 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: <4,>=3.9.0
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: numpy<2.0.0,>=1.16.0
+Requires-Dist: numpy<3.0.0,>=1.16.0
 Requires-Dist: scipy<2.0.0,>=1.4.0
 Requires-Dist: opencv-python<5.0.0,>=4.5.0
 Requires-Dist: pypdfium2<5.0.0,>=4.11.0
@@ -276,7 +276,7 @@ Requires-Dist: pre-commit>=2.17.0; extra == "dev"
 [![codecov](https://codecov.io/gh/felixdittrich92/OnnxTR/graph/badge.svg?token=WVFRCQBOLI)](https://codecov.io/gh/felixdittrich92/OnnxTR)
 [![Codacy Badge](https://app.codacy.com/project/badge/Grade/4fff4d764bb14fb8b4f4afeb9587231b)](https://app.codacy.com/gh/felixdittrich92/OnnxTR/dashboard?utm_source=gh&utm_medium=referral&utm_content=&utm_campaign=Badge_grade)
 [![CodeFactor](https://www.codefactor.io/repository/github/felixdittrich92/onnxtr/badge)](https://www.codefactor.io/repository/github/felixdittrich92/onnxtr)
-[![Pypi](https://img.shields.io/badge/pypi-v0.3.2-blue.svg)](https://pypi.org/project/OnnxTR/)
+[![Pypi](https://img.shields.io/badge/pypi-v0.4.1-blue.svg)](https://pypi.org/project/OnnxTR/)
 
 > :warning: Please note that this is a wrapper around the [doctr](https://github.com/mindee/doctr) library to provide a Onnx pipeline for docTR. For feature requests, which are not directly related to the Onnx pipeline, please refer to the base project.
 
@@ -589,8 +589,8 @@ The smallest combination in OnnxTR (docTR) of `db_mobilenet_v3_large` and `crnn_
 |Library                          |FUNSD (199 pages)              |CORD  (900 pages)              |
 |---------------------------------|-------------------------------|-------------------------------|
 |docTR (CPU) - v0.8.1             | ~1.29s / Page                 | ~0.60s / Page                 |
-|**OnnxTR (CPU)** - v0.1.2        | ~0.57s / Page                 | **~0.25s / Page**             |
-|**OnnxTR (CPU) 8-bit** - v0.1.2  | **~0.38s / Page**             | **~0.14s / Page**             |
+|**OnnxTR (CPU)** - v0.4.1        | ~0.57s / Page                 | **~0.25s / Page**             |
+|**OnnxTR (CPU) 8-bit** - v0.4.1  | **~0.38s / Page**             | **~0.14s / Page**             |
 |EasyOCR (CPU) - v1.7.1           | ~1.96s / Page                 | ~1.75s / Page                 |
 |**PyTesseract (CPU)** - v0.3.10  | **~0.50s / Page**             | ~0.52s / Page                 |
 |Surya (line) (CPU) - v0.4.4      | ~48.76s / Page                | ~35.49s / Page                |
@@ -602,7 +602,7 @@ The smallest combination in OnnxTR (docTR) of `db_mobilenet_v3_large` and `crnn_
 |-------------------------------------|-------------------------------|-------------------------------|
 |docTR (GPU) - v0.8.1                 | ~0.07s / Page                 | ~0.05s / Page                 |
 |**docTR (GPU) float16** - v0.8.1     | **~0.06s / Page**             | **~0.03s / Page**             |
-|OnnxTR (GPU) - v0.1.2                | **~0.06s / Page**             | ~0.04s / Page                 |
+|OnnxTR (GPU) - v0.4.1                | **~0.06s / Page**             | ~0.04s / Page                 |
 |EasyOCR (GPU) - v1.7.1               | ~0.31s / Page                 | ~0.19s / Page                 |
 |Surya (GPU) float16 - v0.4.4         | ~3.70s / Page                 | ~2.81s / Page                 |
 |**PaddleOCR (GPU) - no cls - v2.7.3**| ~0.08s / Page                 | **~0.03s / Page**             |
@@ -621,6 +621,16 @@ If you wish to cite please refer to the base project citation, feel free to use
 }
 ```
 
+```bibtex
+@misc{onnxtr2024,
+    title={OnnxTR: Optical Character Recognition made seamless & accessible to anyone, powered by Onnx},
+    author={Felix Dittrich},
+    year={2024},
+    publisher = {GitHub},
+    howpublished = {\url{https://github.com/felixdittrich92/OnnxTR}}
+}
+```
+
 ## License
 
 Distributed under the Apache 2.0 License. See [`LICENSE`](https://github.com/felixdittrich92/OnnxTR?tab=Apache-2.0-1-ov-file#readme) for more information.

{onnxtr-0.4.0 → onnxtr-0.4.1}/onnxtr.egg-info/requires.txt

@@ -1,4 +1,4 @@
-numpy<2.0.0,>=1.16.0
+numpy<3.0.0,>=1.16.0
 scipy<2.0.0,>=1.4.0
 opencv-python<5.0.0,>=4.5.0
 pypdfium2<5.0.0,>=4.11.0

{onnxtr-0.4.0 → onnxtr-0.4.1}/pyproject.toml

@@ -31,7 +31,7 @@ dynamic = ["version"]
 dependencies = [
     # For proper typing, mypy needs numpy>=1.20.0 (cf. https://github.com/numpy/numpy/pull/16515)
     # Additional typing support is brought by numpy>=1.22.4, but core build sticks to >=1.16.0
-    "numpy>=1.16.0,<2.0.0",
+    "numpy>=1.16.0,<3.0.0",
     "scipy>=1.4.0,<2.0.0",
     "opencv-python>=4.5.0,<5.0.0",
     "pypdfium2>=4.11.0,<5.0.0",

{onnxtr-0.4.0 → onnxtr-0.4.1}/setup.py

@@ -9,7 +9,7 @@ from pathlib import Path
 from setuptools import setup
 
 PKG_NAME = "onnxtr"
-VERSION = os.getenv("BUILD_VERSION", "0.4.0a0")
+VERSION = os.getenv("BUILD_VERSION", "0.4.1a0")
 
 
 if __name__ == "__main__":

onnxtr-0.4.0/onnxtr/version.py

@@ -1 +0,0 @@
-__version__ = 'v0.4.0'