fa3f18797b
The SOTA int_hyper vector needs a ~23 MB PTQ model that can't be committed, so
the conformance test skipped without it and CI never exercised the decode. This
adds a SMALL synthetic conditional codec (deterministic random integer weights,
fixed seed) that drives the SAME path end to end — factorized z → integer h_s →
integer-σ entropy bucketing → integer rANS → integer synthesis g_s → RGB — with
a committed expected FNV-1a. ~7 KB total, so it commits and verifies anywhere.
- tools/wai_int_hyper_tiny_vector.py: builds the tiny g_s/h_s (convT/igdn/leaky/
conv) + tiny entropy tables (Gaussian-conditional y + factorized z) + a real
rANS bitstream (CompressAI encoder), reusing the SOTA export's integer-net
runner so the math is identical. Emits JSON + compact-binary models, entropy,
bitstream, and the expected hash.
- tests/vectors/int_hyper/: the committed vector (tiny_{g_s,h_s}.{json,bin},
tiny_entropy.json, tiny_bitstream.json, tiny.json).
- new test decodes_the_committed_tiny_conformance_vector: NEVER skips; decodes
the committed bitstream via BOTH the JSON and the compact-binary model and
asserts both reproduce the committed FNV-1a (7cbe882c42c6725d), byte-for-byte.
The numbers aren't a "real" codec (random weights) — the point is a deterministic,
artifact-free exercise of every integer op, so int_hyper now has the same
committed-conformance footing as the other capabilities.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
1 line
No EOL
285 B
JSON
1 line
No EOL
285 B
JSON
{"m": 4, "sh": 4, "sw": 4, "n_z": 2, "zh": 2, "zw": 2, "z_rans": [136, 237, 63, 227, 12, 43, 114, 0], "rans": [32, 114, 89, 22, 92, 168, 17, 0, 164, 0, 132, 45, 98, 206, 21, 22, 243, 0, 178, 84, 25, 1, 17, 180, 129, 0, 71, 205, 247, 184, 126, 162, 35, 94, 135, 145, 27, 184, 126, 203]} |