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

- 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>

conf/gtauav_balanced.gin

@@ -0,0 +1,50 @@
+# GTA-UAV Balanced: GatedFusion with L1/L2/L3 captions on both branches.
+# query = sigma(alpha) * drone + (1-sigma(alpha)) * text -> InfoNCE vs gallery
+# 20 epochs, DINOv3 + DGTRS-CLIP, MONA + LoRA adapters.
+
+import src.losses.multi_infonce
+import src.training.train_gtauav
+
+# ---- Training ----
+TrainConfigGTAUAV.epochs = 10
+TrainConfigGTAUAV.batch_size = 8
+TrainConfigGTAUAV.num_workers = 4
+TrainConfigGTAUAV.learning_rate = 1e-4
+TrainConfigGTAUAV.text_lr_factor = 0.1
+TrainConfigGTAUAV.weight_decay = 1e-4
+TrainConfigGTAUAV.grad_clip = 1.0
+TrainConfigGTAUAV.use_amp = True
+TrainConfigGTAUAV.eval_every = 2
+TrainConfigGTAUAV.warmup_epochs = 2
+TrainConfigGTAUAV.seed = 42
+TrainConfigGTAUAV.device = "cuda"
+
+# ---- Model ----
+TrainConfigGTAUAV.init_gate = 0.7
+TrainConfigGTAUAV.baseline_mode = False
+
+# ---- Loss ----
+TrainConfigGTAUAV.tau_init = 0.07
+TrainConfigGTAUAV.label_smoothing = 0.1
+TrainConfigGTAUAV.weight_q2g = 0.6
+TrainConfigGTAUAV.weight_g2q = 0.4
+TrainConfigGTAUAV.learnable_temperature = True
+
+# ---- Output ----
+TrainConfigGTAUAV.output_dir = "out/gtauav/with_text"
+
+# ---- Tracking ----
+TrainConfigGTAUAV.use_wandb = False
+TrainConfigGTAUAV.use_tb = True
+TrainConfigGTAUAV.use_gradcam = True
+TrainConfigGTAUAV.gradcam_every = 5
+TrainConfigGTAUAV.use_profiler = False
+TrainConfigGTAUAV.log_grad_norms = True
+
+# ---- InfoNCE Loss (gin-configurable) ----
+InfoNCELoss.temperature_init = 0.07
+InfoNCELoss.temperature_final = 0.01
+InfoNCELoss.label_smoothing = 0.1
+InfoNCELoss.weight_q2g = 0.6
+InfoNCELoss.weight_g2q = 0.4
+InfoNCELoss.learnable_temperature = True

conf/gtauav_baseline.gin

@@ -0,0 +1,9 @@
+# GTA-UAV Baseline: no text fusion (gate forced to 1.0).
+# query = drone_only -> InfoNCE vs satellite
+# Reference R@1 for delta computation.
+
+include 'conf/gtauav_balanced.gin'
+
+TrainConfigGTAUAV.baseline_mode = True
+TrainConfigGTAUAV.output_dir = "out/gtauav/baseline"
+TrainConfigGTAUAV.use_gradcam = False

conf/gtauav_image_heavy.gin

@@ -0,0 +1,8 @@
+# GTA-UAV Image-heavy: gate initialized high (more image weight).
+# query = sigma(0.9) * drone + 0.1 * text
+# Minimal text contribution test.
+
+include 'conf/gtauav_balanced.gin'
+
+TrainConfigGTAUAV.init_gate = 0.9
+TrainConfigGTAUAV.output_dir = "out/gtauav/image_heavy"

conf/gtauav_text_heavy.gin

@@ -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"