| |
| |
| """Write assets/nn_golden.json: the release's own network outputs (sha256 of the float32 bytes) for the self-test |
| inputs of python/anuvani_diar/nn/torch_backend.py, on every batch shape the engine uses. |
| |
| The outputs come from the release's code path only: `load_bundle` (frozen package), then |
| `pipeline._segmentation.infer` (segmentation + the softmax conversion) and `pipeline._embedding(...)` (voiceprints). |
| The repacked-voiceprint case is checked against the release's two plain voiceprint batches it replaces. |
| |
| source env/canonical.sh && CUDA_VISIBLE_DEVICES=0 python -s tools/make_nn_goldens.py |
| """ |
| import hashlib |
| import json |
| import os |
| import sys |
| from pathlib import Path |
|
|
| import numpy as np |
|
|
| PROJ = Path(__file__).resolve().parents[1] |
| REL = PROJ.parent / "anuvani_diar_v1" |
| sys.path.insert(0, str(PROJ / "tests")) |
| sys.path.insert(0, str(PROJ / "python")) |
|
|
|
|
| def digest(a): |
| return hashlib.sha256(np.ascontiguousarray(a).tobytes()).hexdigest() |
|
|
|
|
| def main(): |
| if os.environ.get("CUBLAS_WORKSPACE_CONFIG") != ":4096:8" or not sys.flags.no_user_site: |
| raise SystemExit("source env/canonical.sh and run with python -s") |
| import refpkg |
| refpkg.load() |
| import torch |
| from anuvani_diar_ref.frontend import load_bundle |
| from anuvani_diar.nn.torch_backend import golden_inputs |
| model = load_bundle(REL / "bundle", "cuda:0", 8, 2) |
| pipe = model["pipeline"] |
| win, masks = golden_inputs() |
| d = {} |
| with torch.inference_mode(): |
| for b in range(1, 9): |
| d[f"segment_b{b}"] = digest(pipe._segmentation.infer(torch.from_numpy(win[:b].copy()))) |
| pair = np.concatenate([np.repeat(win[0:1], 4, 0), np.repeat(win[1:2], 4, 0)]) |
| w8 = np.concatenate([masks[0], masks[1]]) |
| e8 = pipe._embedding(torch.from_numpy(pair), masks=torch.from_numpy(w8)) |
| d["embed_b8"] = digest(e8) |
| d["embed_b4"] = digest(pipe._embedding(torch.from_numpy(np.repeat(win[2:3], 4, 0)), masks=torch.from_numpy(masks[2].copy()))) |
| pair2 = np.concatenate([np.repeat(win[2:3], 4, 0), np.repeat(win[3:4], 4, 0)]) |
| e8b = pipe._embedding(torch.from_numpy(pair2), masks=torch.from_numpy(np.concatenate([masks[2], masks[3]]))) |
| d["embed_repacked_h2"] = digest(np.concatenate([e8, e8b])) |
| out = dict(source="the reference program's networks (reference/ in the model repository), FP32, deterministic", |
| torch=torch.__version__, cudnn=torch.backends.cudnn.version(), digests=d) |
| (PROJ / "assets/nn_golden.json").write_text(json.dumps(out, indent=1) + "\n") |
| print(json.dumps(out, indent=1)) |
|
|
|
|
| if __name__ == "__main__": |
| main() |
|
|
