onnxtr 0.1.1__tar.gz → 0.1.2__tar.gz

{onnxtr-0.1.1 → onnxtr-0.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: onnxtr
-Version: 0.1.1
+Version: 0.1.2
 Summary: Onnx Text Recognition (OnnxTR): docTR Onnx-Wrapper for high-performance OCR on documents.
 Author-email: Felix Dittrich <felixdittrich92@gmail.com>
 Maintainer: Felix Dittrich
@@ -227,7 +227,6 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: numpy<2.0.0,>=1.16.0
 Requires-Dist: scipy<2.0.0,>=1.4.0
-Requires-Dist: onnx<2.0.0,>=1.12.0
 Requires-Dist: opencv-python<5.0.0,>=4.5.0
 Requires-Dist: pypdfium2<5.0.0,>=4.0.0
 Requires-Dist: pyclipper<2.0.0,>=1.2.0
@@ -276,9 +275,9 @@ 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-v0.0.1-blue.svg)](https://pypi.org/project/OnnxTR/)
+[![Pypi](https://img.shields.io/badge/pypi-v0.1.1-blue.svg)](https://pypi.org/project/OnnxTR/)
 
-> :warning: Please note that this is 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.
+> :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.
 
 **Optical Character Recognition made seamless & accessible to anyone, powered by Onnx**
 
@@ -300,10 +299,14 @@ Python 3.9 (or higher) and [pip](https://pip.pypa.io/en/stable/) are required to
 
 You can then install the latest release of the package using [pypi](https://pypi.org/project/OnnxTR/) as follows:
 
-**NOTE:** For GPU support please take a look at: [ONNX Runtime](https://onnxruntime.ai/getting-started). Currently supported execution providers by default are: CPU, CUDA
+**NOTE:**
+
+For GPU support please take a look at: [ONNX Runtime](https://onnxruntime.ai/getting-started). Currently supported execution providers by default are: CPU, CUDA
+
+- **Prerequisites:** CUDA & cuDNN needs to be installed before [Version table](https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html).
 
 ```shell
-pip install onnxtr[cpu]
+pip install "onnxtr[cpu]"
 # with gpu support
 pip install "onnxtr[gpu]"
 # with HTML support
@@ -340,13 +343,17 @@ from onnxtr.models import ocr_predictor
 
 model = ocr_predictor(
     det_arch='fast_base',  # detection architecture
-    rec_arch='vitstr_base',  # recognition architecture
+    reco_arch='vitstr_base',  # recognition architecture
     det_bs=4, # detection batch size
     reco_bs=1024, # recognition batch size
     assume_straight_pages=True,  # set to `False` if the pages are not straight (rotation, perspective, etc.) (default: True)
     straighten_pages=False,  # set to `True` if the pages should be straightened before final processing (default: False)
+    # Preprocessing related parameters
     preserve_aspect_ratio=True,  # set to `False` if the aspect ratio should not be preserved (default: True)
     symmetric_pad=True,  # set to `False` to disable symmetric padding (default: True)
+    # Additional parameters - meta information
+    detect_orientation=False,  # set to `True` if the orientation of the pages should be detected (default: False)
+    detect_language=False, # set to `True` if the language of the pages should be detected (default: False)
     # DocumentBuilder specific parameters
     resolve_lines=True,  # whether words should be automatically grouped into lines (default: True)
     resolve_blocks=True,  # whether lines should be automatically grouped into blocks (default: True)
@@ -398,7 +405,7 @@ from onnxtr.models import ocr_predictor, linknet_resnet18, parseq
 
 reco_model = parseq("path_to_custom_model.onnx", vocab="ABC")
 det_model = linknet_resnet18("path_to_custom_model.onnx")
-model = ocr_predictor(det_model=det_model, reco_model=reco_model)
+model = ocr_predictor(det_arch=det_model, reco_arch=reco_model)
 ```
 
 ## Models architectures
@@ -462,7 +469,14 @@ NOTE:
 
 ### Benchmarks
 
-COMING SOON
+The benchmarks was measured on a `i7-14700K Intel CPU`.
+
+MORE BENCHMARKS COMING SOON
+
+|Dataset                         |docTR (CPU) - v0.8.1           |OnnxTR (CPU) - v0.1.1          |
+|--------------------------------|-------------------------------|-------------------------------|
+|FUNSD (199 pages)               | ~1.29s / Page                 | ~0.57s / Page                 |
+|CORD  (900 pages)               | ~0.60s / Page                 | ~0.25s / Page                 |
 
 ## Citation
 

{onnxtr-0.1.1 → onnxtr-0.1.2}/README.md

@@ -7,9 +7,9 @@
 [![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-v0.0.1-blue.svg)](https://pypi.org/project/OnnxTR/)
+[![Pypi](https://img.shields.io/badge/pypi-v0.1.1-blue.svg)](https://pypi.org/project/OnnxTR/)
 
-> :warning: Please note that this is 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.
+> :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.
 
 **Optical Character Recognition made seamless & accessible to anyone, powered by Onnx**
 
@@ -31,10 +31,14 @@ Python 3.9 (or higher) and [pip](https://pip.pypa.io/en/stable/) are required to
 
 You can then install the latest release of the package using [pypi](https://pypi.org/project/OnnxTR/) as follows:
 
-**NOTE:** For GPU support please take a look at: [ONNX Runtime](https://onnxruntime.ai/getting-started). Currently supported execution providers by default are: CPU, CUDA
+**NOTE:**
+
+For GPU support please take a look at: [ONNX Runtime](https://onnxruntime.ai/getting-started). Currently supported execution providers by default are: CPU, CUDA
+
+- **Prerequisites:** CUDA & cuDNN needs to be installed before [Version table](https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html).
 
 ```shell
-pip install onnxtr[cpu]
+pip install "onnxtr[cpu]"
 # with gpu support
 pip install "onnxtr[gpu]"
 # with HTML support
@@ -71,13 +75,17 @@ from onnxtr.models import ocr_predictor
 
 model = ocr_predictor(
     det_arch='fast_base',  # detection architecture
-    rec_arch='vitstr_base',  # recognition architecture
+    reco_arch='vitstr_base',  # recognition architecture
     det_bs=4, # detection batch size
     reco_bs=1024, # recognition batch size
     assume_straight_pages=True,  # set to `False` if the pages are not straight (rotation, perspective, etc.) (default: True)
     straighten_pages=False,  # set to `True` if the pages should be straightened before final processing (default: False)
+    # Preprocessing related parameters
     preserve_aspect_ratio=True,  # set to `False` if the aspect ratio should not be preserved (default: True)
     symmetric_pad=True,  # set to `False` to disable symmetric padding (default: True)
+    # Additional parameters - meta information
+    detect_orientation=False,  # set to `True` if the orientation of the pages should be detected (default: False)
+    detect_language=False, # set to `True` if the language of the pages should be detected (default: False)
     # DocumentBuilder specific parameters
     resolve_lines=True,  # whether words should be automatically grouped into lines (default: True)
     resolve_blocks=True,  # whether lines should be automatically grouped into blocks (default: True)
@@ -129,7 +137,7 @@ from onnxtr.models import ocr_predictor, linknet_resnet18, parseq
 
 reco_model = parseq("path_to_custom_model.onnx", vocab="ABC")
 det_model = linknet_resnet18("path_to_custom_model.onnx")
-model = ocr_predictor(det_model=det_model, reco_model=reco_model)
+model = ocr_predictor(det_arch=det_model, reco_arch=reco_model)
 ```
 
 ## Models architectures
@@ -193,7 +201,14 @@ NOTE:
 
 ### Benchmarks
 
-COMING SOON
+The benchmarks was measured on a `i7-14700K Intel CPU`.
+
+MORE BENCHMARKS COMING SOON
+
+|Dataset                         |docTR (CPU) - v0.8.1           |OnnxTR (CPU) - v0.1.1          |
+|--------------------------------|-------------------------------|-------------------------------|
+|FUNSD (199 pages)               | ~1.29s / Page                 | ~0.57s / Page                 |
+|CORD  (900 pages)               | ~0.60s / Page                 | ~0.25s / Page                 |
 
 ## Citation
 

onnxtr-0.1.2/onnxtr/version.py

@@ -0,0 +1 @@
+__version__ = 'v0.1.2'

{onnxtr-0.1.1 → onnxtr-0.1.2}/onnxtr.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: onnxtr
-Version: 0.1.1
+Version: 0.1.2
 Summary: Onnx Text Recognition (OnnxTR): docTR Onnx-Wrapper for high-performance OCR on documents.
 Author-email: Felix Dittrich <felixdittrich92@gmail.com>
 Maintainer: Felix Dittrich
@@ -227,7 +227,6 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: numpy<2.0.0,>=1.16.0
 Requires-Dist: scipy<2.0.0,>=1.4.0
-Requires-Dist: onnx<2.0.0,>=1.12.0
 Requires-Dist: opencv-python<5.0.0,>=4.5.0
 Requires-Dist: pypdfium2<5.0.0,>=4.0.0
 Requires-Dist: pyclipper<2.0.0,>=1.2.0
@@ -276,9 +275,9 @@ 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-v0.0.1-blue.svg)](https://pypi.org/project/OnnxTR/)
+[![Pypi](https://img.shields.io/badge/pypi-v0.1.1-blue.svg)](https://pypi.org/project/OnnxTR/)
 
-> :warning: Please note that this is 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.
+> :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.
 
 **Optical Character Recognition made seamless & accessible to anyone, powered by Onnx**
 
@@ -300,10 +299,14 @@ Python 3.9 (or higher) and [pip](https://pip.pypa.io/en/stable/) are required to
 
 You can then install the latest release of the package using [pypi](https://pypi.org/project/OnnxTR/) as follows:
 
-**NOTE:** For GPU support please take a look at: [ONNX Runtime](https://onnxruntime.ai/getting-started). Currently supported execution providers by default are: CPU, CUDA
+**NOTE:**
+
+For GPU support please take a look at: [ONNX Runtime](https://onnxruntime.ai/getting-started). Currently supported execution providers by default are: CPU, CUDA
+
+- **Prerequisites:** CUDA & cuDNN needs to be installed before [Version table](https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html).
 
 ```shell
-pip install onnxtr[cpu]
+pip install "onnxtr[cpu]"
 # with gpu support
 pip install "onnxtr[gpu]"
 # with HTML support
@@ -340,13 +343,17 @@ from onnxtr.models import ocr_predictor
 
 model = ocr_predictor(
     det_arch='fast_base',  # detection architecture
-    rec_arch='vitstr_base',  # recognition architecture
+    reco_arch='vitstr_base',  # recognition architecture
     det_bs=4, # detection batch size
     reco_bs=1024, # recognition batch size
     assume_straight_pages=True,  # set to `False` if the pages are not straight (rotation, perspective, etc.) (default: True)
     straighten_pages=False,  # set to `True` if the pages should be straightened before final processing (default: False)
+    # Preprocessing related parameters
     preserve_aspect_ratio=True,  # set to `False` if the aspect ratio should not be preserved (default: True)
     symmetric_pad=True,  # set to `False` to disable symmetric padding (default: True)
+    # Additional parameters - meta information
+    detect_orientation=False,  # set to `True` if the orientation of the pages should be detected (default: False)
+    detect_language=False, # set to `True` if the language of the pages should be detected (default: False)
     # DocumentBuilder specific parameters
     resolve_lines=True,  # whether words should be automatically grouped into lines (default: True)
     resolve_blocks=True,  # whether lines should be automatically grouped into blocks (default: True)
@@ -398,7 +405,7 @@ from onnxtr.models import ocr_predictor, linknet_resnet18, parseq
 
 reco_model = parseq("path_to_custom_model.onnx", vocab="ABC")
 det_model = linknet_resnet18("path_to_custom_model.onnx")
-model = ocr_predictor(det_model=det_model, reco_model=reco_model)
+model = ocr_predictor(det_arch=det_model, reco_arch=reco_model)
 ```
 
 ## Models architectures
@@ -462,7 +469,14 @@ NOTE:
 
 ### Benchmarks
 
-COMING SOON
+The benchmarks was measured on a `i7-14700K Intel CPU`.
+
+MORE BENCHMARKS COMING SOON
+
+|Dataset                         |docTR (CPU) - v0.8.1           |OnnxTR (CPU) - v0.1.1          |
+|--------------------------------|-------------------------------|-------------------------------|
+|FUNSD (199 pages)               | ~1.29s / Page                 | ~0.57s / Page                 |
+|CORD  (900 pages)               | ~0.60s / Page                 | ~0.25s / Page                 |
 
 ## Citation
 

{onnxtr-0.1.1 → onnxtr-0.1.2}/onnxtr.egg-info/requires.txt

@@ -1,6 +1,5 @@
 numpy<2.0.0,>=1.16.0
 scipy<2.0.0,>=1.4.0
-onnx<2.0.0,>=1.12.0
 opencv-python<5.0.0,>=4.5.0
 pypdfium2<5.0.0,>=4.0.0
 pyclipper<2.0.0,>=1.2.0

{onnxtr-0.1.1 → onnxtr-0.1.2}/pyproject.toml

@@ -33,7 +33,6 @@ dependencies = [
     # 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",
     "scipy>=1.4.0,<2.0.0",
-    "onnx>=1.12.0,<2.0.0",
     "opencv-python>=4.5.0,<5.0.0",
     "pypdfium2>=4.0.0,<5.0.0",
     "pyclipper>=1.2.0,<2.0.0",
@@ -117,7 +116,6 @@ module = [
 	"cv2.*",
 	"matplotlib.*",
     "numpy.*",
-    "onnx.*",
 	"pyclipper.*",
 	"shapely.*",
 	"mplcursors.*",

{onnxtr-0.1.1 → onnxtr-0.1.2}/setup.py

@@ -9,7 +9,7 @@ from pathlib import Path
 from setuptools import setup
 
 PKG_NAME = "onnxtr"
-VERSION = os.getenv("BUILD_VERSION", "0.1.1a0")
+VERSION = os.getenv("BUILD_VERSION", "0.1.2a0")
 
 
 if __name__ == "__main__":

onnxtr-0.1.1/onnxtr/version.py

@@ -1 +0,0 @@
-__version__ = 'v0.1.1'