Duplicate from lukbl/LaTeX-OCR

Co-authored-by: Lukas Blecher <lukbl@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,142 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+# lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+notebooks/**
+!notebooks/LaTeX_OCR*.ipynb
+.ipynb_checkpoints/
+**/dataset/data/**
+wandb/
+pix2tex/model/checkpoints/**
+!pix2tex/model/checkpoints/*.py
+!**/.gitkeep
+.vscode
+.DS_Store
+test/*
+

README.md

@@ -0,0 +1,14 @@
+---
+title: LaTeX OCR
+emoji: 😻
+colorFrom: gray
+colorTo: red
+sdk: streamlit
+sdk_version: 1.9.0
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: lukbl/LaTeX-OCR
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference

app.py

@@ -0,0 +1,40 @@
+import os
+from PIL import Image
+import streamlit
+os.system('pip install pix2tex')
+from pix2tex.cli import LatexOCR
+from munch import Munch
+
+args = Munch({'config': 'settings/config.yaml',
+              'checkpoint': os.path.realpath(os.path.join(os.path.dirname(__file__), 'checkpoints/weights.pth')),
+              'no_resize': False})
+model = LatexOCR(args)
+
+if __name__ == '__main__':
+    streamlit.set_page_config(page_title='LaTeX-OCR')
+    streamlit.title('LaTeX OCR')
+    streamlit.markdown(
+        'Convert images of equations to corresponding LaTeX code.\n\nThis is based on the `pix2tex` module. Check it out [![github](https://img.shields.io/badge/LaTeX--OCR-visit-a?style=social&logo=github)](https://github.com/lukas-blecher/LaTeX-OCR)')
+
+    uploaded_file = streamlit.file_uploader(
+        'Upload an image an equation',
+        type=['png', 'jpg'],
+    )
+
+    if uploaded_file is not None:
+        image = Image.open(uploaded_file)
+        streamlit.image(image)
+    else:
+        streamlit.text('\n')
+
+    if streamlit.button('Convert'):
+        if uploaded_file is not None and image is not None:
+            with streamlit.spinner('Computing'):
+                try:
+                    latex_code = model(image)
+                    streamlit.code(latex_code, language='latex')
+                    streamlit.markdown(f'$\\displaystyle {latex_code}$')
+                except Exception as e:
+                    streamlit.error(e)
+        else:
+            streamlit.error('Please upload an image.')

checkpoints/image_resizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c3820659985ad142b526490bb25c23d977176ac2073591b3bddada692718458
+size 19441973

checkpoints/weights.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a63d9141c53d266cb682fb5a8bd83bd5cbe283145e0e78ebdc0f895195a1dfaa
+size 102113875

requirements.txt

@@ -0,0 +1,3 @@
+torch
+streamlit
+munch