diff --git a/CHANGELOG.md b/CHANGELOG.md index 17cefef..9e686dc 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -7,6 +7,17 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ## [Unreleased] +## [0.4.9] - 2026-06-14 + +### Changed + +- **`FRIGATE_SCORE_CEILING` is now dynamic by default**: previously defaulted to `0` (disabled). Now unset (default) enables a self-calibrating novelty gate — below-cap candidates are skipped if their pre-upload Frigate score exceeds the most-redundant tracked file's score. This catches conditions already covered by manually-added Frigate images that winnow cannot track. Set `FRIGATE_SCORE_CEILING=0` to disable entirely; set a positive value (e.g. `0.85`) for a fixed hard ceiling. +- **Quality replacement branches consolidated**: the Frigate-score and blur-score replacement paths in the upload loop shared identical structure. Merged into a single code path parameterised by score source and comparison direction. +- **`MIN_FACE_COUNT` default raised from `0` to `3`**: people with fewer than 3 tagged photos produce degenerate training sets; skipping them by default avoids noisy runs. +- **`STRATEGY=adaptive`** is the new primary name for embedding-based diversity selection; `auto` remains a silent alias for backwards compatibility. +- **`MERGE_DUPLICATE_PEOPLE` and `TRACE_CROP_SIZE`** added to the README env var table (were in the codebase but undocumented). +- **CUDA version corrected** in the image tags table (was 13.3, actual base image is 12.8.1). + ## [0.4.8] - 2026-06-14 ### Changed diff --git a/README.md b/README.md index 3a186e1..afd8f24 100644 --- a/README.md +++ b/README.md @@ -207,7 +207,7 @@ In scheduled mode the process (and loaded models) stays resident between runs. T | `BLUR_THRESHOLD` | `120.0` | Laplacian variance threshold — lower accepts more blur | | `MAX_AUTO_IMAGES` | `80` | Maximum training images per person in Frigate | | `QUALITY_REPLACEMENT` | `true` | When at cap, swap a weaker tracked image for a better candidate. With Frigate scoring active, targets the most redundant image (highest pre-upload recognize score); otherwise uses blur score. Never touches manually added Frigate files. Set `false` to skip people at cap | -| `FRIGATE_SCORE_CEILING` | `0.0` | Skip uploads whose pre-upload Frigate recognize score exceeds this value — they are already well-covered. `0` disables; requires at least one prior run to have scores | +| `FRIGATE_SCORE_CEILING` | *(unset)* | Below-cap novelty gate against Frigate's live model (catches conditions covered by manually-added images too). Unset: dynamic — skips candidates whose Frigate score exceeds the most-redundant tracked file's score, auto-calibrates each run. `0`: disable entirely. Positive value (e.g. `0.85`): fixed hard ceiling. No effect on the first run or when `ENABLE_FRIGATE_SCORES=false` | | `ENABLE_FRIGATE_SCORES` | `true` | Call Frigate's recognize endpoint pre-upload to store diversity scores used for quality replacement. Adds ~200 ms per upload. Disable to use blur-score replacement only | ### GPU & Models diff --git a/pyproject.toml b/pyproject.toml index 737a7b3..9a2792b 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "winnow" -version = "0.4.8" +version = "0.4.9" description = "Selects diverse, high-quality photos from Immich as training data for Frigate face recognition and object classification." license = "AGPL-3.0-or-later" requires-python = ">=3.13" diff --git a/tests/test_config.py b/tests/test_config.py index 5d700d4..d2c56ed 100644 --- a/tests/test_config.py +++ b/tests/test_config.py @@ -18,7 +18,7 @@ def test_config_loads_defaults(monkeypatch): assert cfg.OUTPUT_DIR == "./frigate_train" assert cfg.YEARS_FILTER == 10 assert cfg.MIN_FACE_WIDTH == 90 - assert cfg.MIN_FACE_COUNT == 0 + assert cfg.MIN_FACE_COUNT == 3 assert cfg.BLUR_THRESHOLD == 120.0 assert cfg.MIN_CONFIDENCE == 0.7 assert cfg.MAX_AUTO_IMAGES == 80 diff --git a/winnow/config.py b/winnow/config.py index 435e596..b22e369 100644 --- a/winnow/config.py +++ b/winnow/config.py @@ -31,7 +31,7 @@ class _Config: MIN_CONFIDENCE: float = 0.7 MAX_AUTO_IMAGES: int = 80 QUALITY_REPLACEMENT: bool = True - FRIGATE_SCORE_CEILING: float = 0.0 + FRIGATE_SCORE_CEILING: float | None = None ENABLE_FRIGATE_SCORES: bool = True # People filtering @@ -66,7 +66,8 @@ class _Config: self.MIN_CONFIDENCE = float(os.getenv("MIN_CONFIDENCE", "0.7")) self.MAX_AUTO_IMAGES = int(os.getenv("MAX_AUTO_IMAGES", "80")) self.QUALITY_REPLACEMENT = os.getenv("QUALITY_REPLACEMENT", "true").lower() in ("true", "1", "yes") - self.FRIGATE_SCORE_CEILING = float(os.getenv("FRIGATE_SCORE_CEILING", "0.0")) + _ceiling_env = os.getenv("FRIGATE_SCORE_CEILING", "").strip() + self.FRIGATE_SCORE_CEILING = float(_ceiling_env) if _ceiling_env else None self.ENABLE_FRIGATE_SCORES = os.getenv("ENABLE_FRIGATE_SCORES", "true").lower() in ("true", "1", "yes") self.FACE_MARGIN = float(os.getenv("FACE_MARGIN", "0.15")) self.USE_FULL_RESOLUTION = os.getenv("USE_FULL_RESOLUTION", "true").lower() in ("true", "1", "yes") diff --git a/winnow/executor.py b/winnow/executor.py index afdc4c8..ac33577 100644 --- a/winnow/executor.py +++ b/winnow/executor.py @@ -482,14 +482,28 @@ def upload_to_frigate(jobs: list[dict]) -> None: if _result is not None and (_result[0] or "").casefold() == name.casefold(): pre_fscore = _result[1] - # Ceiling check: skip if the existing training set already covers this - # face condition well. Applies below cap only — at cap, replacement logic - # drives the decision. - if not at_cap and Config.FRIGATE_SCORE_CEILING > 0 and pre_run_count > 0: - if pre_fscore is not None and pre_fscore > Config.FRIGATE_SCORE_CEILING: + # Below-cap novelty gate: skip candidates already covered by the Frigate model, + # including conditions learned from manually-added images winnow can't track. + # pre_fscore is None on the first run (pre_run_count == 0 skips recognize_face + # above), so this block never fires on the first run without an extra guard. + if not at_cap and pre_fscore is not None: + _ceiling = Config.FRIGATE_SCORE_CEILING + if _ceiling is None: + # Dynamic default: bar = most-redundant tracked file's Frigate score. + # Falls back to uploading freely when no tracked scores exist yet. + _bar = get_most_redundant_mapped_file(name) + _skip = _bar is not None and pre_fscore > _bar[2] + _bar_str = f"most redundant tracked {_bar[2]:.2f}" if _bar else "" + elif _ceiling == 0.0: + _skip = False # explicitly disabled + _bar_str = "" + else: + _skip = pre_fscore > _ceiling + _bar_str = f"ceiling {_ceiling:.2f}" + if _skip: progress.console.print( f" [dim]⏭ {fname}: Frigate score {pre_fscore:.2f}" - f" > ceiling {Config.FRIGATE_SCORE_CEILING:.2f}, already covered[/dim]" + f" > {_bar_str}, already covered[/dim]" ) progress.advance(upload_task) continue @@ -503,70 +517,50 @@ def upload_to_frigate(jobs: list[dict]) -> None: using_fscore = person_has_fscores and Config.ENABLE_FRIGATE_SCORES if using_fscore: candidate_score = pre_fscore - if candidate_score is None: - progress.console.print( - f" [dim]⏭ {fname}: Frigate recognize unavailable, skipping replacement[/dim]" - ) - progress.advance(upload_task) - continue - # Low score = more novel than the most redundant mapped file = replace - target = get_most_redundant_mapped_file(name, exclude=failed_deletes) - if target is None or candidate_score >= target[2]: - target_score_str = f"{target[2]:.3f}" if target is not None else "N/A" - progress.console.print( - f" [dim]⏭ {fname}: frigate {candidate_score:.3f} ≥ most redundant" - f" {target_score_str}, not more novel[/dim]" - ) - progress.advance(upload_task) - continue - target_frigate_file, _target_asset_id, target_score = target - progress.console.print( - f" 🔄 {fname}: frigate {candidate_score:.3f} < {target_score:.3f}," - f" replacing {target_frigate_file} (more novel)" - ) - if delete_frigate_person_files(name, [target_frigate_file]): - remove_frigate_file(name, target_frigate_file) - person_has_fscores = has_frigate_scores(name) - effective_count -= 1 - # clear any blur-mode slot floor — Frigate uses a different score metric - min_quality_score_for_slot = None - else: - logger.warning(f"Failed to delete {target_frigate_file} for {name}, skipping replacement") - failed_deletes.add(target_frigate_file) - progress.advance(upload_task) - continue + get_target = get_most_redundant_mapped_file + score_label, better_note = "frigate", " (more novel)" + no_score_msg = "Frigate recognize unavailable, skipping replacement" else: candidate_score = score_map.get(fname) - if candidate_score is None: - progress.console.print( - f" [dim]⏭ {fname}: no quality score, skipping replacement[/dim]" - ) - progress.advance(upload_task) - continue - target = get_lowest_quality_mapped_file(name, exclude=failed_deletes) - if target is None or candidate_score <= target[2]: - target_score_str = f"{target[2]:.3f}" if target is not None else "N/A" - progress.console.print( - f" [dim]⏭ {fname}: blur {candidate_score:.3f} ≤ worst" - f" {target_score_str}, skipping[/dim]" - ) - progress.advance(upload_task) - continue - target_frigate_file, _target_asset_id, target_score = target + get_target = get_lowest_quality_mapped_file + score_label, better_note = "blur", "" + no_score_msg = "no quality score, skipping replacement" + + if candidate_score is None: + progress.console.print(f" [dim]⏭ {fname}: {no_score_msg}[/dim]") + progress.advance(upload_task) + continue + + target = get_target(name, exclude=failed_deletes) + not_better = target is None or ( + candidate_score >= target[2] if using_fscore else candidate_score <= target[2] + ) + if not_better: + target_str = f"{target[2]:.3f}" if target is not None else "N/A" + op = "<" if using_fscore else ">" progress.console.print( - f" 🔄 {fname}: blur {candidate_score:.3f} > {target_score:.3f}," - f" replacing {target_frigate_file}" + f" [dim]⏭ {fname}: {score_label} {candidate_score:.3f}" + f" not {op} {target_str}, skipping[/dim]" ) - if delete_frigate_person_files(name, [target_frigate_file]): - remove_frigate_file(name, target_frigate_file) - person_has_fscores = has_frigate_scores(name) - effective_count -= 1 - min_quality_score_for_slot = score_map.get(fname) - else: - logger.warning(f"Failed to delete {target_frigate_file} for {name}, skipping replacement") - failed_deletes.add(target_frigate_file) - progress.advance(upload_task) - continue + progress.advance(upload_task) + continue + + target_frigate_file, _target_asset_id, target_score = target + op = "<" if using_fscore else ">" + progress.console.print( + f" 🔄 {fname}: {score_label} {candidate_score:.3f} {op} {target_score:.3f}," + f" replacing {target_frigate_file}{better_note}" + ) + if delete_frigate_person_files(name, [target_frigate_file]): + remove_frigate_file(name, target_frigate_file) + person_has_fscores = has_frigate_scores(name) + effective_count -= 1 + min_quality_score_for_slot = None if using_fscore else candidate_score + else: + logger.warning(f"Failed to delete {target_frigate_file} for {name}, skipping replacement") + failed_deletes.add(target_frigate_file) + progress.advance(upload_task) + continue for attempt in range(1, max_retries + 1): try: