← Run Index
Run summary · 2026-09-seminar05-milestones M7 (最終スタック確定 + msplat 等価再比較 + Pareto v3)
c1v3-12500-off-prof
M7: per-kernel gpu_ms 再々計測 v2 (submission=per_kernel / forward_submission=per_stage / pipelining=off、M4 radix simd_ballot + A7 refine 3-pass 後の kernel)
partial pass
01
設定
- dataset
- /Users/otkrickey/dev/3dgs-workspace/datasets/nerf_synthetic/lego
- gt_convention
- Premultiplied
- iterations
- 12,500
- seed
- 42
- capacity
- 1,000,000 splats
- sh_degree
- 3
- loss
- L1Ssim
- lambda
- 0.200
- ssim
- window=7 sigma=1
- backend.backward
- Simd
- backend.loss_path
- Gpu
- backend.emit_pairs
- Original
- backend.forward
- F32
- backend.dispatch
- PerStage
- backend.radix_scan
- GpuHierarchical
- backend.radix_scatter
- SimdBallot
- backend.binning
- Resident
- backend.tile_sort
- GlobalRadix
- backend.submission
- PerKernel
- backend.target_cache
- true
- backend.shader_fast_math
- true
- os_build
- 26.6.2 (25G83)
- backend.ssim_clear
- HostMemset
- backend.raster_grad_clear
- HostMemset
- backend.backward_uniform
- HostBuffer
- backend.lazy_c3_scratch
- false
- backend.ssim_walk
- PerChannel
02
結果
Val PSNR
36.19dB
Wallclock
2m 54s
Final splats
409,702
Final loss
5.481522e-3
03
3D ビューワー
学習結果 PLY を .splat 形式に変換し、antimatter15/splat の WebGL ビューワーで対話表示。
04
推移
Loss curve — 反復ごとの training loss
Splat count — refine の発火と最終構成
05
中間ログ抜粋
| iter | 本 run loss |
|---|---|
| 1 | 5.9385e-1 |
| 1,000 | 5.5101e-2 |
| 2,000 | 1.3840e-2 |
| 3,000 | 8.1967e-3 |
| 4,000 | 7.2041e-3 |
| 5,000 | 6.4974e-3 |
| 6,000 | 6.0754e-3 |
| 7,000 | 5.9095e-3 |
| 8,000 | 5.7667e-3 |
| 9,000 | 5.6656e-3 |
| 10,000 | 5.6185e-3 |
| 11,000 | 5.5231e-3 |
| 12,000 | 5.4887e-3 |
| 12,500 | 5.4815e-3 |
06
関連 finding
この run を related_runs に含む finding (Positive / Negative どちらも)。