Feature/ml stain normalization

.flake8

@@ -0,0 +1,3 @@
+[flake8]
+max-line-length=88
+extend-ignore=E203

.gitignore

@@ -0,0 +1,183 @@
+# 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-project.org/#use-with-ide
+.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
+
+# ruff
+.ruff_cache/
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# VSCode
+.vscode/
+
+# MacOS
+.DS_Store
+
+# Mlflow
+mlruns/
+mlflow_store/
+mlflow_artifacts/
+
+# Pytorch Lightning
+lightning_logs/
+
+# 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/
+
+# Project
+/data
+/demo_*

.gitlab-ci.yml

@@ -0,0 +1,6 @@
+include:
+  project: rationai/digital-pathology/templates/ci-templates
+  file: Python-Lint.gitlab-ci.yml
+
+stages:
+  - lint

.mypy.ini

@@ -0,0 +1,5 @@
+[mypy]
+strict = True
+ignore_missing_imports = True
+disallow_untyped_calls = False
+disable_error_code = no-any-return

.pre-commit-config.yaml

@@ -0,0 +1,23 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: check-yaml
+        args: [--unsafe]
+
+  - repo: https://github.com/commitizen-tools/commitizen
+    rev: v3.30.1
+    hooks:
+      - id: commitizen
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.7.3
+    hooks:
+      # Run the linter.
+      - id: ruff
+        entry: pdm lint --force-exclude
+      # Run the formatter.
+      - id: ruff-format
+        entry: pdm format --force-exclude

.ruff.toml

@@ -0,0 +1,51 @@
+fix = true
+line-length = 88
+target-version = "py311"
+
+[format]
+# Enable reformatting of code snippets in docstrings.
+docstring-code-format = true
+
+[lint]
+unfixable = [
+    "ERA", # do not autoremove commented out code
+]
+extend-select = [
+    "B",   # flake8-bugbear
+    "C4",  # flake8-comprehensions
+    "ERA", # flake8-eradicate/eradicate
+    "I",   # isort
+    "N",   # pep8-naming
+    "PIE", # flake8-pie
+    "PGH", # pygrep
+    "RUF", # ruff checks
+    "SIM", # flake8-simplify
+    "TCH", # flake8-type-checking
+    "TID", # flake8-tidy-imports
+    "UP",  # pyupgrade
+    "D",   # pydocstyle 
+]
+extend-ignore = [
+    "ERA001", # commented out code
+    "D100",   # missing docstring in public module
+    "D101",   # missing docstring in public class
+    "D102",   # missing docstring in public method
+    "D103",   # missing docstring in public function
+    "D104",   # missing docstring in public package
+    "D105",   # missing docstring in magic method
+    "D106",   # missing docstring in public nested class
+    "D107",   # missing docstring in __init__
+    "N812",   # lowercase imported as non lowercase
+    "TCH002", # move third-party into a type-checking block
+    "F722",   # jaxtyping
+]
+
+[lint.flake8-tidy-imports]
+ban-relative-imports = "all"
+
+[lint.isort]
+lines-after-imports = 2
+known-first-party = ["tests"]
+
+[lint.pydocstyle]
+convention = "google"

README.md

@@ -1 +1,34 @@
-# stain-normalization
+# Stain Normalization
+
+Tento repozitár slúži ako doplnkový materiál k bakalárskej práci **"Normalizácia farbenia histopatologických snímkov pomocou neuronových sietí"**.
+
+Celý kód nie je možné spustiť samostatne, pretože vyžaduje prístup k citlivým dátam a k platforme na správu strojového učenia MLflow. Avšak je možné spustiť demo, ku ktorému je pripravených pár vzoriek na demonštráciu.
+
+## Demo
+
+Demo skript umožňuje načítať jeden obrázok alebo celý priečinok, normalizovať ich pomocou predtrénovaného modelu a uložiť výsledné obrázky do určeného priečinka.
+
+## Priložené dáta
+
+- **Originálne obrázky** (v priečinku `./demo_data/original`) – referenčné vzorky.  
+- **Upravené obrázky** (v priečinku `./demo_data/modified`) – referenčné obrázky s modifikovaným sfarbením, ktoré sa následne modelom znormalizujú späť k originálnemu vzhľadu.  
+- **Obrázky z iného datasetu** (v priečinku `./demo_data/to_predict`) – ukazujú, ako model dokáže prispôsobiť farby vstupov tak, aby zodpovedali farebnému štýlu trénovacích dát.  
+- **Model checkpoint** 
+
+## Spustenie dema
+
+Projekt je spravovaný pomocou nástroja **pdm**, ktorý umožňuje jednoduchú správu závislostí a prostredia. Stačí nainštalovať závislosti pomocou:
+
+```bash
+pdm install
+```
+a potom spustiť demo skript:
+
+```bash
+pdm run python demo.py --input ./demo_data/modified
+```
+
+## Dostupné arguemnty:
+- **input**: cesta k obrázku alebo priečinku s obrázkami na normalizáciu (default ./demo_data/modified)
+- **output**: priečinok, kam sa uložia normalizované obrázky (default ./demo_data)
+- **use_cpu**: defaultne nadstavené na použitie GPU ak je dostupná, avšak ak by nastali problémy odporúčam použivať iba CPU