First commit

.gitignore

@@ -0,0 +1,165 @@
+# 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/
+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/
+cover/
+
+# 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
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .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
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__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/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+.cache/
+cc_ocr_src/

README.md

@@ -1,13 +1,14 @@
 ---
-title: Semiocr 1
-emoji: 📈
+title: SEMI OCR
+emoji: 🅰️
 colorFrom: blue
-colorTo: blue
+colorTo: gray
 sdk: gradio
 sdk_version: 5.1.0
-app_file: app.py
+app_file: ocr_demo.py
 pinned: false
 short_description: SEMI OCR
+tags: OCR
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

models/classifier/semidouble_black_20241021093205.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cece38780392ea10294e00c58224724d7ad8f905611b82e8cb2822d0672d28f1
+size 1209362

models/craft/craft_mlt_25k.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63b1e5f1793ccc06128f80e15ece1a24037cc70390cbbf1198fea4668c1df6e3
+size 41520396

ocr_demo.py

@@ -0,0 +1,39 @@
+import gradio as gr
+
+from cc_ocr.predict_wrapper import predict_fn
+
+description = """
+    The <b>SEMI Font</b> (a.k.a. <b>SEMI OCR Font</b>) is specified by SEMI M12/M13 standard, widely used in semiconductor industries.
+
+    Select the examples at the bottom to see it in action.
+"""
+
+def _get_examples():
+    examples = [
+        [f"images/{i}.png",
+        "models/classifier/semidouble_black_20241021093205",
+        0] for i in range(13)
+    ]
+    return examples
+
+def launch():
+    intf = gr.Interface(
+        title="SEMI OCR",
+        description=description,
+        fn=predict_fn,
+        inputs=[
+            gr.Image(label="Image"),
+            gr.Text(label="Model", interactive=False),
+            gr.Slider(label="Threshold", value=0, step=0.01, minimum=0, maximum=1)
+        ],
+        outputs=[
+            gr.Image(label="Detection"),
+            gr.Text(label="Detection", interactive=False)
+        ],
+        examples=_get_examples(),
+        flagging_mode="never"
+    )
+    intf.launch()
+
+if __name__ == "__main__":
+    launch()

setup.py

@@ -0,0 +1,13 @@
+from setuptools import setup, Extension
+from Cython.Build import cythonize
+
+_ext_modules = [
+    Extension("cc_ocr.common.imutils", ["cc_ocr_src/common/imutils.py"]),
+    Extension("cc_ocr.common.inferencer", ["cc_ocr_src/common/inferencer.py"]),
+    Extension("cc_ocr.processing.classifier", ["cc_ocr_src/processing/classifier.py"]),
+    Extension("cc_ocr.processing.craft", ["cc_ocr_src/processing/craft.py"]),
+    Extension("cc_ocr.predict_wrapper", ["cc_ocr_src/predict_wrapper.py"]),
+]
+
+if __name__ == "__main__":
+    setup(ext_modules=cythonize(_ext_modules, cache=False))