Sorting

.gitignore

@@ -1 +1,198 @@
-gitignore
+spinnaker_python
+spinnaker_python/*
+spinnaker_sdk
+spinnaker_sdk/*
+spinnaker_python*.tar.gz
+spinnaker-*.tar.gz
+spinnaker.tar.gz
+*.csv
+*.zip
+*.json
+*.record
+*.deb
+Python-3.10.0
+Python-3.10.0/*
+Python-3.9.0
+Python-3.9.0/*
+Python-3.10.0.tar.xz
+Python-3.9.0.tar.xz
+spinnaker_sdk.tar.gz
+models
+models/*
+my-models
+my-models/*
+label-studio
+label-studio/*
+dataset
+dataset/*
+
+**utils/__pycache__
+**old/.venv*
+.venv*
+.venv*/*
+.mypy_cache
+.mypy_cache/*
+label_map.pbtxt
+
+# 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/

.python-version

@@ -0,0 +1 @@
+3.10.20

Dockerfile.train

@@ -0,0 +1,75 @@
+# =============================================================================
+# Sorter end-to-end training image.
+#
+# A single `docker run` performs:
+#   1. TFRecord generation from Label Studio JSONs
+#   2. SSD MobileNet V2 fine-tuning (TF Object Detection API, TF 2.11)
+#   3. TFLite-friendly graph export
+#   4. Full INT8 quantization with a representative dataset
+#   5. Edge TPU compilation
+#
+# Required mounts:
+#   -v <host>/dataset:/dataset       # input  (read-write; nothing is written here)
+#   -v <host>/my-models:/my-models   # output (all artifacts land here)
+#
+# Optional: append `--gpus all` to use the host GPU via the NVIDIA Container Toolkit.
+# =============================================================================
+# NOTE: the `devel` (not `runtime`) CUDA image is required because TensorFlow's
+# XLA JIT needs `libdevice.10.bc`, `ptxas` and friends, which are only present
+# in -devel-. Without them training fails with:
+#   error: Can't find libdevice directory ${CUDA_DIR}/nvvm/libdevice
+#   UNKNOWN: JIT compilation failed.
+FROM nvidia/cuda:11.8.0-cudnn8-devel-ubuntu20.04
+
+ENV DEBIAN_FRONTEND=noninteractive \
+    PYTHONUNBUFFERED=1 \
+    PIP_NO_CACHE_DIR=1 \
+    XLA_FLAGS=--xla_gpu_cuda_data_dir=/usr/local/cuda
+
+# ---- System packages ---------------------------------------------------------
+# libgl1 + libglib2.0-0 are required by opencv-python, which is pulled in by the
+# Object Detection API via the `lvis` evaluator.
+RUN apt-get update && apt-get install -y \
+    python3 python3-pip python3-dev \
+    git curl gnupg protobuf-compiler ca-certificates \
+    libgl1 libglib2.0-0 \
+    && rm -rf /var/lib/apt/lists/*
+
+# ---- Edge TPU compiler -------------------------------------------------------
+RUN curl -fsSL https://packages.cloud.google.com/apt/doc/apt-key.gpg \
+      | gpg --dearmor -o /usr/share/keyrings/coral-edgetpu-archive-keyring.gpg && \
+    echo "deb [signed-by=/usr/share/keyrings/coral-edgetpu-archive-keyring.gpg] https://packages.cloud.google.com/apt coral-edgetpu-stable main" \
+      > /etc/apt/sources.list.d/coral-edgetpu.list && \
+    apt-get update && apt-get install -y edgetpu-compiler && rm -rf /var/lib/apt/lists/*
+
+# ---- Python base -------------------------------------------------------------
+RUN python3 -m pip install --upgrade pip && \
+    python3 -m pip install "tensorflow==2.11.0" "numpy<2" pillow
+
+# ---- TensorFlow Object Detection API -----------------------------------------
+# The OD API setup tends to drag in conflicting TF/Keras pins, so we re-pin
+# tensorflow==2.11.0 and numpy<2 right after installing it.
+RUN git clone --depth 1 https://github.com/tensorflow/models.git /opt/models && \
+    cd /opt/models/research && \
+    protoc object_detection/protos/*.proto --python_out=. && \
+    cp object_detection/packages/tf2/setup.py . && \
+    python3 -m pip install . && \
+    python3 -m pip install --force-reinstall "tensorflow==2.11.0" "numpy<2"
+
+# ---- Pretrained SSD MobileNet V2 checkpoint ----------------------------------
+RUN mkdir -p /opt/sorter/pretrained && \
+    curl -fsSL http://download.tensorflow.org/models/object_detection/tf2/20200711/ssd_mobilenet_v2_320x320_coco17_tpu-8.tar.gz \
+      | tar -xz -C /opt/sorter/pretrained
+
+# ---- Repo-level config + helper scripts --------------------------------------
+COPY pipeline.config        /opt/sorter/pipeline.config
+COPY label_map.pbtxt        /opt/sorter/label_map.pbtxt
+COPY docker/build_tfrecords.py /opt/sorter/build_tfrecords.py
+COPY docker/quantize.py        /opt/sorter/quantize.py
+COPY docker/entrypoint.sh      /usr/local/bin/sorter-train
+RUN chmod +x /usr/local/bin/sorter-train
+
+VOLUME ["/dataset", "/my-models"]
+WORKDIR /my-models
+
+ENTRYPOINT ["/usr/local/bin/sorter-train"]