Preview

1. 1e-4 - 1e-6 WarmupCosineAnnealing W/ Restart + Small DT (time issue)
2. large w/ March/ablation/exp7

Dataset의 RIR이 길어짐 (유의미한 샘플 수 증가) + DT 전체 데이터 쌍 (4배)

loss 설명 (ratio)

context: Entire Depth (1) (exp1, 2 → 0.4)

recon: Target Depth (0.2)

structural: SSIM Depth (exp1, 2 → Entire Depth) (0.1)

latent: MSE(latent, GT_depth) (0.005)

DepthGAN: PatchGAN Target Depth (0.01)

Summary

• main.py

exp1 | large vs. small DT (RIR Qaulity++)