81c1813822
int_synth's determinism was proven on synthetic/constructed models; this adds a model TRAINED ON REAL IMAGES decoding a REAL PHOTOGRAPH, and proves the same bit-exactness on it. tools/wai_int_synth_real.py trains an autoencoder on real photos, post-training-quantizes the decoder with per-layer activation-scale calibration (the working recipe — pure QAT through the >> shift can't learn), encodes a held-out image to an int8 latent, and decodes it through the EXPORTED integer model in numpy (the same i64 scatter-accumulate / +bias / arithmetic >> shift / clamp that int_synth.rs runs) as the reference. New corpus vector `photo`: a 128×128 macOS Sonoma landscape → a 6,156-byte int8 latent (96×8×8) + a four-layer trained integer decoder, ~21.6 dB at ~3 bpp. Honest scope: a pure integer transposed-conv decoder with no entropy model — quality is modest BY DESIGN; the point is that the decode is bit-identical on every machine. wai_int_synth_vectors `gen` cross-checks the Rust decode against the python integer-forward (ref_rgb.bin) to max|Δ|=0 and freezes the rgb_hash; the four-platform conformance CI then enforces the same bytes everywhere. A real trained model, a real photo, decoded identically on every machine — the int_synth thesis, demonstrated end to end. Co-Authored-By: Claude Opus 4.8 <[email protected]>
37 lines
838 B
JSON
37 lines
838 B
JSON
{
|
|
"gradient": {
|
|
"s_log2": 3,
|
|
"in_channels": 4,
|
|
"layers": 2,
|
|
"width": 38,
|
|
"height": 38,
|
|
"rgb_hash": "1282839b699ad3e79fc810a92ef4220fec7a57a573bb6c844709af4c1fb3f638"
|
|
},
|
|
"bloom": {
|
|
"s_log2": 2,
|
|
"in_channels": 8,
|
|
"layers": 1,
|
|
"width": 18,
|
|
"height": 18,
|
|
"rgb_hash": "29d6d2d8955aa345ff70d12a9bbcafeb0d57b1bf4100c73037855998702e76a6"
|
|
},
|
|
"facade": {
|
|
"s_log2": 4,
|
|
"in_channels": 3,
|
|
"layers": 3,
|
|
"width": 72,
|
|
"height": 72,
|
|
"rgb_hash": "46cb2718a48e273a33d6ec3e561c3e1edfb69dfea1e80c3d670f91d4d5b25562"
|
|
},
|
|
"photo": {
|
|
"trained": true,
|
|
"width": 128,
|
|
"height": 128,
|
|
"layers": 4,
|
|
"rgb_hash": "1677d7112db6cadd70b0eeba8df263f9605cf3875809ce4b26e9c914f62fb582",
|
|
"psnr_db": 21.6,
|
|
"bpp": 3.006,
|
|
"in_channels": 96,
|
|
"s_log2": 3
|
|
}
|
|
}
|