5 Commits

Include renames

Author	SHA1	Message	Date
GotthardGandClaude Fable 5.1	62f568b0f6	gate: baseline and candidate measured in the same environment ... The cluster's first run was gated against a baseline measured on the Spark. The same weights score lower there (F1 0.840 vs 0.861, mask score 0.706 vs 0.757 on the 203 gold frames), so the gate failed a model that beats the active one on F1 in 98.7 % of bootstrap draws when both are measured on one machine. Gold reports now record the environment (ultralytics, torch, host). When the active model's report comes from other versions, train_run.py measures its weights again in the job and gates against that; the predictions feed the paired bootstrap. Without the weights there is no verdict and no promotion. The SLURM scripts pull the active model's weights. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>	2026-10-02 13:25:45 +02:00
GotthardGandClaude Fable 5.1	831367d35d	noise-aware gate, frozen core of unseen frames, and a cycle script for the Spark ... A paired bootstrap over the 149 unseen gold frames (2026-10-02) showed that a difference between two models carries about +-0.023 of noise in F1, +-0.018 in the mask score and +-0.10 in crystal F1, while the gate's tolerance was 0.005. - tools/gate_stats.py: per-frame counts and a paired bootstrap (pure Python). - train_run.py: when the baseline's gold predictions exist, the gate requires the candidate to beat it on F1 or the mask score in 90 % of the draws and not to lose the other in more than 90 %; the point rule is the fallback and is always reported (pass_point_rule). - tools/compare_unseen.py replaces the Spark's ~/fair_gate_all.py: all models on the frames none trained on, on the frozen core (data/gold/unseen_core.json, 149 frames) and on all unseen frames once the gold set grows, with the interval and win share against the active model. - measure_weights.py keeps a version's gate verdict when it re-measures it. - tools/spark_cycle.sh: gold growth, export, re-measure, train, gate, compare, push, with what cycles 3 and 4 taught built in. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>	2026-10-02 13:25:45 +02:00
GotthardGandClaude Fable 5.1	3794330fc3	gate: mask term over all gold objects (unmatched = 0), so finding more objects is not punished; tests ... Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>	2026-09-28 19:16:01 +02:00
GotthardGandClaude Fable 5.1	4698dbeaf9	training loop: run ledger, studio export importer with an image pool, train_run with gold gate and auto-promotion, SLURM template, CI ... Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>	2026-09-28 16:06:06 +02:00
duan_j	391c357c84	migration and splitting AareLC	2026-04-14 16:07:31 +02:00