Photon Memory checkpoints (Rough Flower / PureLight comparison)
Companion weights for the Photon Memory reader that matches / beats PureLight on directional NLL
for the released Rough Flower luminaire. Code: ANABUR920/renderTTT (lightmem/).
Files
| Path | Role | Size |
|---|---|---|
checkpoints/v3_ksched_model.pt |
Meta-trained PhotonKernel reader (k_feat=True) |
~0.7 MB |
checkpoints/big_1e8_k512_ttt.pt |
Reader-only TTT on 1e8 memory (k=512) |
~0.7 MB |
checkpoints/big_match_res2b_best.pt |
Intermediate matched TTT + residual (~NLL β4.54) | ~42 MB |
checkpoints/big_match_res2c_best.pt |
Final matched TTT + residual (NLL β6.00, render default) | ~42 MB |
logs/*.jsonl |
Training / eval logs for the above TTT runs | small |
Download
hf download ANABUR/photon-memory --local-dir ./photon-memory-ckpts
# Photons (separate dataset):
hf download ANABUR/photon-memory-photons --repo-type dataset --local-dir ./photon-memory-photons
Reproduce the β6.00 NLL claim (same protocol as paper)
Needs: CUDA GPU (~40 GB for 1e8 + residual), traced Rough Flower photons (flower_surface_* 11e6 held-out + flowerbig_surface_* 1e8 memory), and this repo's scripts/ttt_big.py.
Winning warm-start chain (do not claim a cold start from the meta reader equals β6.00 in one shot):
- Start from
v3_ksched_model.ptβ reader-only TTT βbig_1e8_k512_ttt.pt(~β0.53). - Joint reader + residual matched TTT β
big_match_res2b_best.pt(~β4.54). - Continue:
python scripts/ttt_big.py \
--data flowerbig_surface --N 100000000 --k 512 --wmult 2 \
--ttt_matched --n_ttt_q 1000000 --steps 8000 --residual \
--res_K 32 --res_log2 19 --res_finest 2048 \
--init_ttt checkpoints/big_match_res2b_best.pt \
--lr 5e-6 --res_lr_grid 5e-3 --res_lr_head 5e-4 \
--name big_match_res2c
Zero-shot (no TTT) with v3_ksched_model.pt at N=1e8, k=512 reaches RGB-mean NLL β β0.460, matching the PureLight teacher plateau (~β0.46). The β6.00 number is matched test-time adaptation on the non-eval remainder of the same 11e6 photon file as the held-out set (memory may be a separately traced 1e8 bank). Leave-one-out TTT on the 1e8 memory alone stalls near β0.53. It is not zero-shot and not a fresh-retrace claim.
Honest notes for reviewers / friends
- Held-out queries are always the last 20k of
default_rng(0).permutation(11_000_000)onflower_surface_*. --ttt_matchedtrains on the non-eval remainder of that same 11e6 file while retrieving from the separately traced 1e8 memory.- A frozen-reader hash residual alone peaks ~β0.38 and does not beat PureLight.
- Photons for Rough Flower are published separately:
ANABUR/photon-memory-photons(flower_surface_*11e6 +flowerbig_surface_*1e8, channels mean/r/g/b). PureLight teacher weights and photon maps remain third-party; otherwise re-trace withscripts/gen_flower.py.
Photons (required for reproduction)
Rough Flower OptiX traces live in ANABUR/photon-memory-photons:
hf download ANABUR/photon-memory-photons --repo-type dataset --local-dir ./photon-memory-photons
Layout: flower_surface_{mean,r,g,b}/val/rough_flower.npz (11e6) and flowerbig_surface_{mean,r,g,b}/val/rough_flower.npz (1e8).
Load in code
import torch
from lightmem.models import PhotonKernel, ResidualLobes
sd = torch.load("checkpoints/big_match_res2c_best.pt", map_location="cpu")
reader = PhotonKernel(k=512, k_feat=True)
reader.load_state_dict(sd["reader"])
residual = ResidualLobes(K=32, finest=2048, log2_table=19)
residual.load_state_dict(sd["residual"])
# sd["nll"] β -6.00, sd["step"] == 8000