Files
caption-test/conf/gtauav_balanced_sofia.gin
2026-04-29 08:04:33 +03:00

40 lines
2.0 KiB
Plaintext
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# GTA-UAV Balanced (SOFIA-Tiny backbone): SOFIA v7.1 student trained from scratch
# с двухуровневой text fusion:
# 1. Mid-level: Text-FiLM в SAT и UAV heads (модулирует feature map перед GGeM/CHP).
# 2. Late-level: GatedFusion на дескрипторах (как в DINOv3/StripNet вариантах).
#
# Trainable (~5-7M):
# - SOFIA backbone (Tiny, ~5M, from scratch — нет pretrained)
# - SOFIA heads (SatHead GGeM+BN+Linear, UAVHead AltitudeFiLM+CHP+BN+Linear, +Text-FiLM)
# - DGTRS-CLIP LoRA (rank=4, ~147K)
# - TextFusionMLP (3*768 -> 1024 -> 1024, ~3.4M, shared)
# - Gates α_q, α_g + learnable τ
#
# Altitude (drone_height метры) подаётся в UAVHead.AltitudeFiLM из dataset meta CSV.
# Для sat — altitude=None → FiLM passthrough (γ=1, β=0).
#
# Note: SOFIA from scratch — нужно больше эпох или warmup, чем frozen DINOv3/StripNet.
# Mamba-2 backend (mamba_ssm) даёт 2-8x speedup vs torch fallback.
include 'conf/gtauav_balanced.gin'
# ---- Backbone ----
TrainConfigGTAUAV.backbone = "sofia"
TrainConfigGTAUAV.sofia_preset = "Tiny"
TrainConfigGTAUAV.sofia_d_descriptor = 1024
TrainConfigGTAUAV.sofia_use_text_film_uav = True
TrainConfigGTAUAV.sofia_use_text_film_sat = True
TrainConfigGTAUAV.sofia_lora_rank = 4
# Mamba-1 used for Tiny (Mamba-2 torch fallback has a pre-existing reshape bug
# with channels not divisible by default headdim; switch to "mamba2" for M/L
# presets where channels % 64 == 0 OR install mamba_ssm CUDA kernels).
TrainConfigGTAUAV.sofia_mamba_variant = "mamba1"
TrainConfigGTAUAV.sofia_mamba_backend = "auto" # mamba_ssm if installed else torch fallback
# ---- Training overrides ----
TrainConfigGTAUAV.gradient_checkpointing = False # SOFIA from-scratch — keep activations live
TrainConfigGTAUAV.shared_encoder = True # ignored by SOFIA but kept for logging compat
# ---- Output ----
TrainConfigGTAUAV.output_dir = "out/gtauav/with_text_sofia"