doc-page-extractor 0.0.6__py3-none-any.whl → 0.0.7__py3-none-any.whl

doc_page_extractor/extractor.py

@@ -1,5 +1,4 @@
 import os
-import torch
 
 from typing import Literal, Iterable
 from pathlib import Path
@@ -34,10 +33,6 @@ class DocExtractor:
     self._yolo: YOLOv10 | None = None
     self._layout: LayoutLMv3ForTokenClassification | None = None
 
-    if self._device.startswith("cuda") and not torch.cuda.is_available():
-      self._device = "cpu"
-      print("Warn: cuda is not available, use cpu instead")
-
   def extract(
       self,
       image: Image,
@@ -83,7 +78,7 @@ class DocExtractor:
       source=source,
       imgsz=1024,
       conf=0.2,
-      device=self._device    # Device to use (e.g., "cuda:0" or "cpu")
+      device=self._device    # Device to use (e.g., "cuda" or "cpu")
     )
     boxes = det_res[0].__dict__["boxes"]
     layouts: list[Layout] = []

{doc_page_extractor-0.0.6.dist-info → doc_page_extractor-0.0.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: doc-page-extractor
-Version: 0.0.6
+Version: 0.0.7
 Summary: doc page extractor can identify text and format in images and return structured data.
 Home-page: https://github.com/Moskize91/doc-page-extractor
 Author: Tao Zeyu
@@ -10,7 +10,6 @@ License-File: LICENSE
 Requires-Dist: opencv-python<5.0,>=4.11.0
 Requires-Dist: pillow<11.0,>=10.3
 Requires-Dist: pyclipper<2.0,>=1.2.0
-Requires-Dist: onnxruntime<2.0,>=1.19.0
 Requires-Dist: numpy<2.0,>=1.24.0
 Requires-Dist: shapely<3.0,>=2.0.0
 Requires-Dist: transformers<5.0,>=4.48.0
@@ -37,10 +36,20 @@ doc page extractor can identify text and format in images and return structured
 pip install doc-page-extractor
 ```
 
+```shell
+pip install onnxruntime==1.21.0
+```
+
 ## Using CUDA
 
 Please refer to the introduction of [PyTorch](https://pytorch.org/get-started/locally/) and select the appropriate command to install according to your operating system.
 
+In addition, replace the command to install `onnxruntime` in the previous article with the following:
+
+```shell
+pip install onnxruntime-gpu==1.21.0
+```
+
 ## Example
 
 ```python
@@ -49,7 +58,7 @@ from doc_page_extractor import DocExtractor
 
 extractor = DocExtractor(
   model_dir_path=model_path, # Folder address where AI model is downloaded and installed
-  device="cpu", # If you want to use CUDA, please change to device="cuda:0".
+  device="cpu", # If you want to use CUDA, please change to device="cuda".
 )
 with Image.open("/path/to/your/image.png") as image:
   result = extractor.extract(

{doc_page_extractor-0.0.6.dist-info → doc_page_extractor-0.0.7.dist-info}/RECORD

@@ -1,7 +1,7 @@
 doc_page_extractor/__init__.py,sha256=jCf5lo3A9JVDquflYMlvH8nJIs3EjBt8AG5y8mwfS68,210
 doc_page_extractor/clipper.py,sha256=PDafB_9JGwV_dRY7oWe1yf44roSsEaCuEdg3VRMvJNo,3125
 doc_page_extractor/downloader.py,sha256=NbGN9ARnER8-gd4T1uc3W98WMEClVxMrqnShq8HibTw,455
-doc_page_extractor/extractor.py,sha256=aoan_RgSrZiz5LIvjTlr4UpM9ErttpEZ8puqRxwlmDU,10232
+doc_page_extractor/extractor.py,sha256=D3SLWUAciq8jGU6mlkVwIon-4nHJaYoKpPjGCN_YLhQ,10055
 doc_page_extractor/layoutreader.py,sha256=BdC4oPbtpXoLmYhjuSFrKn6SNoT2zWw_gi95sGAUwrk,4031
 doc_page_extractor/ocr.py,sha256=6eLUVx6NSuRAwrq8Mc2zYs3yocxpOgUQS_4LIIqywnQ,5147
 doc_page_extractor/ocr_corrector.py,sha256=RfRA1jESEuqC8_a2kUEvHblT_B4xBjE0OApLMl1JiRg,3917
@@ -26,8 +26,8 @@ doc_page_extractor/onnxocr/rec_postprocess.py,sha256=qZt5Ripal7z9hniKq5e7azOkD9e
 doc_page_extractor/onnxocr/utils.py,sha256=AQoHgQyv-jpPo4BsVzq3r7_ze698EZ-a7LJobm2fwUI,1864
 tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 tests/test_history_bus.py,sha256=WaCUW3U75SESMcLq0f5FKnpVUVRDvmfxLFE7Zo83e48,2517
-doc_page_extractor-0.0.6.dist-info/LICENSE,sha256=TfPDBt3ar0uv_f9cqCDMZ5rIzW3CY8anRRd4PkL6ejs,34522
-doc_page_extractor-0.0.6.dist-info/METADATA,sha256=A2fj-ylx5ug6h_eiTA4C-oFNpzRq8dP3-yQJ9ccyczQ,2046
-doc_page_extractor-0.0.6.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
-doc_page_extractor-0.0.6.dist-info/top_level.txt,sha256=ErNybD_lBzAmw8mVBAK4htsAH_hp14jioZVex-tUqvM,25
-doc_page_extractor-0.0.6.dist-info/RECORD,,
+doc_page_extractor-0.0.7.dist-info/LICENSE,sha256=TfPDBt3ar0uv_f9cqCDMZ5rIzW3CY8anRRd4PkL6ejs,34522
+doc_page_extractor-0.0.7.dist-info/METADATA,sha256=s-ewJAyPQ1I_fgTee91NN99T42HcAaKFu1MAUhZKqdk,2203
+doc_page_extractor-0.0.7.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
+doc_page_extractor-0.0.7.dist-info/top_level.txt,sha256=ErNybD_lBzAmw8mVBAK4htsAH_hp14jioZVex-tUqvM,25
+doc_page_extractor-0.0.7.dist-info/RECORD,,