# syntax=docker/dockerfile:1.7
# Parking TRAINER image: the phase-B body-type classifier job. Build CONTEXT is apps/trainer
# (self-contained Python package). A ONE-OFF JOB on the reviewer's host (art-docker-station),
# never a booth service: it reads the wash collector's volume (collector.sqlite + crops/)
# and writes a versioned model folder. CPU-only PyTorch — the host has no usable GPU and a
# few thousand crops train in minutes/an hour on four Xeon cores.
# See wiki/decisions/bodytype-classifier-training.md.

FROM ghcr.io/astral-sh/uv:python3.12-bookworm-slim AS base
WORKDIR /app
ENV UV_LINK_MODE=copy \
    UV_COMPILE_BYTECODE=1 \
    PYTHONUNBUFFERED=1

RUN apt-get update \
    && apt-get install -y --no-install-recommends libgl1 libglib2.0-0 \
    && rm -rf /var/lib/apt/lists/*

COPY pyproject.toml uv.lock .python-version ./
RUN --mount=type=cache,target=/root/.cache/uv \
    uv sync --frozen --no-install-project --no-dev --extra train

COPY trainer/ ./trainer/
COPY README.md ./
RUN --mount=type=cache,target=/root/.cache/uv \
    uv sync --frozen --no-dev --extra train

# Pre-warm the ImageNet backbone weights INTO the image so a run needs no network (the
# host has one, but a job that fetches at run time is a job that fails at 2 am). Best-effort:
# without network at build time torchvision fetches lazily on the first run.
ENV TORCH_HOME=/app/torch-home
RUN uv run python -c "import torchvision.models as m; m.resnet18(weights=m.ResNet18_Weights.IMAGENET1K_V1); m.mobilenet_v3_small(weights=m.MobileNet_V3_Small_Weights.IMAGENET1K_V1)" \
    || echo "[build] backbone weights not pre-warmed (no network) — fetched on first run"

RUN useradd --system --create-home --uid 999 trainer \
    && mkdir -p /data /out && chown -R trainer:trainer /app /out
USER trainer

ENV TRAINER_DATA_DIR=/data \
    TRAINER_OUT_DIR=/out
VOLUME ["/out"]
ENTRYPOINT ["uv", "run", "--no-sync", "parking-trainer"]
CMD ["inspect"]