# GTA-UAV Balanced (StripNet backbone): StripNet-small + Conv-MONA in last 2 stages.
# Replaces DINOv3 ViT-L/16 with strip-shaped DWConv hierarchical CNN (~28M params,
# 10× smaller than DINOv3). Output 512-dim → projected to 1024 to match retrieval space.
#
# Trainable:
#   - Projection (Linear 512→1024): ~525K
#   - Conv-MONA in stages 3 & 4 (2 adapters per Block × 6 blocks total): ~2-3M
#   - LoRA on DGTRS-CLIP: 147K
#   - TextFusionMLP (shared): ~3.4M
#   - GatedFusion gates + tau: 3 scalars
#
# StripNet pretrained on ImageNet-1K (head dropped); state-dict naming follows
# upstream Strip-R-CNN repo (`conv_spatial1/2`).

include 'conf/gtauav_balanced.gin'

# ---- Backbone ----
TrainConfigGTAUAV.backbone = "stripnet"
TrainConfigGTAUAV.stripnet_path = "nn_models/STRIPNET/stripnet_s.pth"
TrainConfigGTAUAV.stripnet_mona_last_n_stages = 2  # Conv-MONA in stages 3 & 4 (deepest)

# ---- Model overrides ----
TrainConfigGTAUAV.shared_encoder = True   # StripNet always shared (one CNN for both branches)
TrainConfigGTAUAV.mona_bottleneck = 64    # Conv-MONA bottleneck channels

# ---- Output ----
TrainConfigGTAUAV.output_dir = "out/gtauav/with_text_stripnet"