c25bd64357
Previous baseline run collapsed to ~random retrieval (R@1 0.6% at epoch 8, train loss trending up 4.2 → 4.5). Hypothesis: at bs=8, DSS packs visually-identical drones into a batch where InfoNCE asks the model to discriminate them, and the hard-mining queue amplifies that hardness — together they prevent convergence from a near-random start. Override the new baseline config to run with the simpler regime: sampler_type = "mutex" (disable DSS, keep only the no-false-negative guarantee) hard_mining_k = 0 (use full queue as uniform negatives, no per-query top-K) Fresh `out/gtauav/baseline_mutex` output dir so results stay separate from the failed run's mixed logs. Other architecture changes (shared DINOv3 WEB, MONA in last 12 blocks, grad_accum=8) kept — verify they work with simple sampling before layering DSS/mining back on. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
22 lines
990 B
Plaintext
22 lines
990 B
Plaintext
# GTA-UAV Baseline: no text fusion (gate forced to 1.0).
|
|
# query = drone_only -> InfoNCE vs satellite
|
|
# Reference R@1 for delta computation.
|
|
#
|
|
# Diagnostic mode (2026-04-24): DSS and hard-negative mining disabled after
|
|
# the previous run collapsed (R@1 = 0.6% at epoch 8, train loss growing).
|
|
# Hypothesis: DSS packs visually-identical drones at bs=8 and the hard-mining
|
|
# queue amplifies that hardness — together they prevent convergence from a
|
|
# nearly-random start. Run with mutex-only sampling and the full queue as
|
|
# uniform negatives first, restore the extras incrementally once baseline
|
|
# converges.
|
|
|
|
include 'conf/gtauav_balanced.gin'
|
|
|
|
TrainConfigGTAUAV.baseline_mode = True
|
|
TrainConfigGTAUAV.output_dir = "out/gtauav/baseline_mutex"
|
|
TrainConfigGTAUAV.use_gradcam = False
|
|
|
|
# ---- Diagnostic overrides ----
|
|
TrainConfigGTAUAV.sampler_type = "mutex" # was "dss" — disable hard-batch construction
|
|
InfoNCELoss.hard_mining_k = 0 # was 512 — use full queue without per-query top-K
|