Skip to content

update requirements.txt, example.py in DocXChain #181

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

update requirements.txt, example.py in DocXChain #181

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f48a884
modify requirements for DocXChain
jodog0412 Oct 7, 2024
0a1e1a0
modify requirements for DocXChain
jodog0412 Oct 9, 2024
cd0a3aa
modify requirements for DocXChain
jodog0412 Oct 9, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,3 +24,7 @@ tmp*.py
__pycache__
.idea/
*.new
.venv
*.pth
*.onnx
*.json
31 changes: 16 additions & 15 deletions Applications/DocXChain/example.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,10 +94,10 @@ def formula_recognition_example(image):

formula_recognition_configs = dict()
formula_recognition_configs['from_modelscope_flag'] = False
formula_recognition_configs['image_resizer_path'] = '/home/LaTeX-OCR_image_resizer.onnx'
formula_recognition_configs['encoder_path'] = '/home/LaTeX-OCR_encoder.onnx'
formula_recognition_configs['decoder_path'] = '/home/LaTeX-OCR_decoder.onnx'
formula_recognition_configs['tokenizer_json'] = '/home/LaTeX-OCR_tokenizer.json'
formula_recognition_configs['image_resizer_path'] = 'home/LaTeX-OCR_image_resizer.onnx'
formula_recognition_configs['encoder_path'] = 'home/LaTeX-OCR_encoder.onnx'
formula_recognition_configs['decoder_path'] = 'home/LaTeX-OCR_decoder.onnx'
formula_recognition_configs['tokenizer_json'] = 'home/LaTeX-OCR_tokenizer.json'
configs['formula_recognition_configs'] = formula_recognition_configs

# initialize
Expand All @@ -123,7 +123,7 @@ def document_structurization_example(image):

layout_analysis_configs = dict()
layout_analysis_configs['from_modelscope_flag'] = False
layout_analysis_configs['model_path'] = '/home/DocXLayout_231012.pth' # note that: currently the layout analysis model is NOT from modelscope
layout_analysis_configs['model_path'] = 'home/DocXLayout_231012.pth' # note that: currently the layout analysis model is NOT from modelscope
configs['layout_analysis_configs'] = layout_analysis_configs

text_detection_configs = dict()
Expand All @@ -138,10 +138,10 @@ def document_structurization_example(image):

formula_recognition_configs = dict()
formula_recognition_configs['from_modelscope_flag'] = False
formula_recognition_configs['image_resizer_path'] = '/home/LaTeX-OCR_image_resizer.onnx'
formula_recognition_configs['encoder_path'] = '/home/LaTeX-OCR_encoder.onnx'
formula_recognition_configs['decoder_path'] = '/home/LaTeX-OCR_decoder.onnx'
formula_recognition_configs['tokenizer_json'] = '/home/LaTeX-OCR_tokenizer.json'
formula_recognition_configs['image_resizer_path'] = 'home/LaTeX-OCR_image_resizer.onnx'
formula_recognition_configs['encoder_path'] = 'home/LaTeX-OCR_encoder.onnx'
formula_recognition_configs['decoder_path'] = 'home/LaTeX-OCR_decoder.onnx'
formula_recognition_configs['tokenizer_json'] = 'home/LaTeX-OCR_tokenizer.json'
configs['formula_recognition_configs'] = formula_recognition_configs

# initialize
Expand All @@ -168,7 +168,7 @@ def whole_pdf_conversion_example(image_list):

layout_analysis_configs = dict()
layout_analysis_configs['from_modelscope_flag'] = False
layout_analysis_configs['model_path'] = '/home/DocXLayout_231012.pth' # note that: currently the layout analysis model is NOT from modelscope
layout_analysis_configs['model_path'] = 'home/DocXLayout_231012.pth' # note that: currently the layout analysis model is NOT from modelscope
configs['layout_analysis_configs'] = layout_analysis_configs

text_detection_configs = dict()
Expand All @@ -183,10 +183,10 @@ def whole_pdf_conversion_example(image_list):

formula_recognition_configs = dict()
formula_recognition_configs['from_modelscope_flag'] = False
formula_recognition_configs['image_resizer_path'] = '/home/LaTeX-OCR_image_resizer.onnx'
formula_recognition_configs['encoder_path'] = '/home/LaTeX-OCR_encoder.onnx'
formula_recognition_configs['decoder_path'] = '/home/LaTeX-OCR_decoder.onnx'
formula_recognition_configs['tokenizer_json'] = '/home/LaTeX-OCR_tokenizer.json'
formula_recognition_configs['image_resizer_path'] = 'home/LaTeX-OCR_image_resizer.onnx'
formula_recognition_configs['encoder_path'] = 'home/LaTeX-OCR_encoder.onnx'
formula_recognition_configs['decoder_path'] = 'home/LaTeX-OCR_decoder.onnx'
formula_recognition_configs['tokenizer_json'] = 'home/LaTeX-OCR_tokenizer.json'
configs['formula_recognition_configs'] = formula_recognition_configs

# initialize
Expand Down Expand Up @@ -262,9 +262,10 @@ def main():

# dump
name = args.output_path.lower()
if name.endswith('.png'):
if name.endswith('.png') or name.endswith('.jpg'):
if output_image is not None:
cv2.imwrite(args.output_path, output_image)

elif name.endswith('.json'):
if final_result is not None:
with open(args.output_path, 'w') as json_file:
Expand Down
17 changes: 16 additions & 1 deletion Applications/DocXChain/requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,18 @@
opencv-python
pdfplumber
rapid_latex_ocr
rapid_latex_ocr
modelscope
Wand
pytz
addict
datasets == 2.21.0
oss2
ipdb
shapely
simplejson
sortedcontainers
tf_slim
tensorflow <= 2.12.0
torch
pyclipper
matplotlib