Pikaliov/caption-test
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add ML diagnostics tooling (W&B, TensorBoard, Grad-CAM, profiler) and gin configs

Browse Source 
- Add unified experiment tracker (W&B + TensorBoard) with graceful fallback
- Add gradient norm monitoring per param group (MONA, LoRA, MLP, gates, tau)
- Add Grad-CAM visualization for DINOv3 drone/satellite encoders
- Add PyTorch Profiler wrapper + torchinfo model summary
- Add gin-config support to train_gtauav.py with CLI overrides
- Add v3 gin configs: gtauav_balanced, gtauav_baseline, gtauav_text_heavy, gtauav_image_heavy
- Generate metric plots every epoch (not just on eval)
- Set default epochs to 10
- Update README and CLAUDE.md with new tooling and usage docs

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
pikaliov
2026-04-21 20:30:50 +03:00
parent 83ce04150d
commit 29a09349e7
11 changed files with 1098 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
conf/gtauav_text_heavy.gin Normal file
View File

@@ -0,0 +1,8 @@
# GTA-UAV Text-heavy: gate initialized low (more text weight).
# query = sigma(0.3) * drone + 0.7 * text
# Stress test for text contribution.
include 'conf/gtauav_balanced.gin'
TrainConfigGTAUAV.init_gate = 0.3
TrainConfigGTAUAV.output_dir = "out/gtauav/text_heavy"