bvandeusen
6e3c5f697f
Slice 1 of milestone #114 (tagging v2). Proves the frozen-embedding + trained- head spine on the operator's own data, reusing the SigLIP embeddings already stored on image_record — no re-embedding, no GPU. Per concept: train a logistic-regression HEAD (positives + negatives = explicit rejections + sampled unlabeled) vs the old single-CENTROID baseline; report cross-validated precision/recall/AP for both, a LEARNING CURVE (AP/F1 as tagged positives grow 10→30→100→300), and example image ids (head-would-suggest / head-doubts-positive) to eyeball. Persisted so the report SURVIVES navigation (operator-flagged): the run + full report live in a new tag_eval_run row (mirrors library_audit_run); the admin card will rehydrate from GET on mount, not transient state. - models.TagEvalRun + migration 0056; runs on the ml queue (only worker with numpy/sklearn) — numpy/sklearn lazy-imported so the API can still enqueue. - services/ml/tag_eval (compute + start helper, one-running guard), tasks.ml .tag_eval_run, api/tag-eval (POST create, GET history light / detail w/ report). - recover_stalled_tag_eval_runs sweep + retention (keep last 20) + 5-min beat (rule 89). scikit-learn added to requirements-ml. - tests: param normalization + the rehydrate read-path + create/conflict. Frontend admin card (trigger + render persisted report) follows next. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
29 lines
1.3 KiB
Plaintext
29 lines
1.3 KiB
Plaintext
-r requirements.txt
|
|
|
|
# ML stack — versions current as of 2026-05-14 with Python 3.14 wheel coverage.
|
|
|
|
# torch + torchvision are NOT listed here: they are installed CPU-only from
|
|
# the PyTorch CPU index in Dockerfile.ml. The default PyPI torch wheel bundles
|
|
# the NVIDIA CUDA runtime (a ~5.6GB image layer); this pipeline is CPU-only,
|
|
# so Dockerfile.ml uses the +cpu wheels from
|
|
# https://download.pytorch.org/whl/cpu instead.
|
|
#
|
|
# IMPORTANT: torchvision 0.27 declares requires_python "!=3.14.1,>=3.10" —
|
|
# Python 3.14.1 specifically is excluded due to a known incompatibility.
|
|
# The python-ci runner pulls python:3.14-bookworm (latest patch); if that
|
|
# resolves to 3.14.1 the install will fail. Pin a specific Python patch in
|
|
# the runner image (CI-Runner/CI-python/Dockerfile) if this becomes a
|
|
# blocker. 3.14.0 and 3.14.2+ are fine.
|
|
|
|
transformers>=5.8,<6.0
|
|
onnxruntime>=1.26,<2.0
|
|
huggingface-hub>=1.14,<2.0
|
|
opencv-python-headless>=4.13,<5.0
|
|
|
|
# scikit-learn powers the tag-eval (#1130) head-vs-centroid comparison: logistic
|
|
# regression + cross-validated precision/recall/AP. Battle-tested metrics matter
|
|
# because that eval's whole purpose is producing trustworthy numbers. numpy is
|
|
# left to resolve transitively (torch/transformers/sklearn all pull it) to avoid
|
|
# pinning against their constraints.
|
|
scikit-learn>=1.7,<2.0
|