onnxtr 0.1.0__py3-none-any.whl → 0.1.2__py3-none-any.whl

onnxtr/version.py

@@ -1 +1 @@
-__version__ = 'v0.1.0'
+__version__ = 'v0.1.2'

{onnxtr-0.1.0.dist-info → onnxtr-0.1.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: onnxtr
-Version: 0.1.0
+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
@@ -227,8 +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: onnxruntime >=1.11.0
 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
@@ -239,7 +237,10 @@ Requires-Dist: Pillow >=9.2.0
 Requires-Dist: defusedxml >=0.7.0
 Requires-Dist: anyascii >=0.3.2
 Requires-Dist: tqdm >=4.30.0
+Provides-Extra: cpu
+Requires-Dist: onnxruntime >=1.11.0 ; extra == 'cpu'
 Provides-Extra: dev
+Requires-Dist: onnxruntime >=1.11.0 ; extra == 'dev'
 Requires-Dist: weasyprint >=55.0 ; extra == 'dev'
 Requires-Dist: matplotlib >=3.1.0 ; extra == 'dev'
 Requires-Dist: mplcursors >=0.3 ; extra == 'dev'
@@ -274,9 +275,9 @@ Requires-Dist: mplcursors >=0.3 ; extra == 'viz'
 [![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**
 
@@ -298,18 +299,22 @@ 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
+pip install "onnxtr[cpu]"
 # with gpu support
-pip install "OnnxTR[gpu]"
+pip install "onnxtr[gpu]"
 # with HTML support
-pip install "OnnxTR[html]"
+pip install "onnxtr[html]"
 # with support for visualization
-pip install "OnnxTR[viz]"
+pip install "onnxtr[viz]"
 # with support for all dependencies
-pip install "OnnxTR[html, gpu, viz]"
+pip install "onnxtr[html, gpu, viz]"
 ```
 
 ### Reading files
@@ -338,13 +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)
@@ -396,7 +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
@@ -460,7 +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-0.1.0.dist-info → onnxtr-0.1.2.dist-info}/RECORD

@@ -1,6 +1,6 @@
 onnxtr/__init__.py,sha256=h7Wc2tuHLsaoCk5xNpEFEK-g11A6SJA7nAasA76TQ_Y,100
 onnxtr/file_utils.py,sha256=WjUKalEdR53aoeIY4e-ihy3r7J_C9qFxL40JHGPfutc,1107
-onnxtr/version.py,sha256=wC2oqFtrOUdONUyrZY5FqyMyRDiF3ryABp7mW73C87o,23
+onnxtr/version.py,sha256=t2ZLy6eqIRREzP9MNv-0UaNqpTXYFxlbMzz0JwDxS9I,23
 onnxtr/contrib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 onnxtr/contrib/artefacts.py,sha256=tdmfhvfXVRYEH7uj4_hqf2cuUGoTieyNK8bXsD3zHwo,5383
 onnxtr/contrib/base.py,sha256=PoCKtOIgj7u4xl-V0eBVh-QmVeTyk_eEggFHQ8R34AI,3445
@@ -62,9 +62,9 @@ onnxtr/utils/reconstitution.py,sha256=Hx1_ddLevKLzuxXc19UelPdsGlAwqi4f6vRSYKHDUB
 onnxtr/utils/repr.py,sha256=kfbjGL6KymGT8spo2UL4FJXZ0XRwa7CO7Y1dTVR8dIk,2129
 onnxtr/utils/visualization.py,sha256=CX09qvDnNIw3BFW5F3jM4R9OcpLWAeZyoDyTAOGRvls,9925
 onnxtr/utils/vocabs.py,sha256=SCQ4XQjbHSxunj1tg2iHRiPfE8OaTAMhcJbKq5BNvFs,3138
-onnxtr-0.1.0.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-onnxtr-0.1.0.dist-info/METADATA,sha256=k4DicngL3zLNaAWV2yRaF82MbJ6XdpAh9D3X0OWBS3Y,24645
-onnxtr-0.1.0.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-onnxtr-0.1.0.dist-info/top_level.txt,sha256=48aR9EH095hmgye7CNuxAW3o_cj4TjhWmuw3jEMdTs0,12
-onnxtr-0.1.0.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-onnxtr-0.1.0.dist-info/RECORD,,
+onnxtr-0.1.2.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+onnxtr-0.1.2.dist-info/METADATA,sha256=hg64djJ-sUVObh4t9QYB3PJSjZgYxrPne2aS_lEtWcI,25645
+onnxtr-0.1.2.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+onnxtr-0.1.2.dist-info/top_level.txt,sha256=48aR9EH095hmgye7CNuxAW3o_cj4TjhWmuw3jEMdTs0,12
+onnxtr-0.1.2.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+onnxtr-0.1.2.dist-info/RECORD,,