mirror of
https://github.com/ruvnet/RuView
synced 2026-07-20 17:03:24 +00:00
ruv
42b261f807
Edge optimization (ADR-152 optimize track): ONNX Runtime fp32 is the CPU latency win (3.2 ms/window, ~3.4x faster than torch, parity 2.4e-7); ORT dynamic int8 reaches 2.44 MB (paper's ~2.2 MB claim plausible only via conv-capable toolchains; -0.16pt PCK@20, +18% MPJPE, 2x slower); torch dynamic quant converts 0% of this conv-only model; fp16 halves storage free but is slower on CPU. Measurement (b) BLOCKED-ON-DATA: only 1,077 paired ESP32 windows exist (stop rule <2k). Forensic recheck of the surviving April holdout RETRACTS the ADR-079 '92.9% PCK@20' figure: constant-output model, absolute (not torso) threshold, 69 near-static frames — mean predictor scores 100% under that protocol; torso-PCK@20 is 19.1%. Corroborates PR #535. Stale citations removed from user-guide, readme-details, ADR-152 §2.1.3; no-citation rule extended to ADR-079 accuracy claims. Unblock: >=2k-window multi-pose paired session + torso-PCK re-baseline. Co-Authored-By: claude-flow <ruv@ruv.net>
239 lines
6.9 KiB
JSON
239 lines
6.9 KiB
JSON
{
|
|
"torch": {
|
|
"env": {
|
|
"torch": "2.12.0+cpu",
|
|
"platform": "Windows-11-10.0.26200-SP0",
|
|
"processor": "Intel64 Family 6 Model 197 Stepping 2, GenuineIntel",
|
|
"num_threads": 16,
|
|
"checkpoint": "results\\retrained_best_pose_model.pth",
|
|
"params": 2225042
|
|
},
|
|
"variants": {
|
|
"fp32": {
|
|
"file": "retrained_fp32_resaved.pth",
|
|
"size_bytes": 9068948,
|
|
"size_mb": 9.068948,
|
|
"latency_batch1": {
|
|
"batch_size": 1,
|
|
"runs": 100,
|
|
"median_ms_per_batch": 24.903650000851485,
|
|
"median_ms_per_window": 24.903650000851485,
|
|
"windows_per_second": 40.15475642991324
|
|
},
|
|
"latency_batch64": {
|
|
"batch_size": 64,
|
|
"runs": 30,
|
|
"median_ms_per_batch": 184.02919999789447,
|
|
"median_ms_per_window": 2.875456249967101,
|
|
"windows_per_second": 347.77089723115813
|
|
},
|
|
"accuracy": {
|
|
"samples": 10000,
|
|
"pck@20": 0.9668200004577636,
|
|
"pck@50": 0.9915333324432373,
|
|
"mpjpe": 0.00936222033649683,
|
|
"wall_seconds": 37.85407733917236
|
|
}
|
|
},
|
|
"fp16": {
|
|
"file": "retrained_fp16.pth",
|
|
"size_bytes": 4580332,
|
|
"size_mb": 4.580332,
|
|
"latency_batch1": {
|
|
"batch_size": 1,
|
|
"runs": 100,
|
|
"median_ms_per_batch": 23.936699999467237,
|
|
"median_ms_per_window": 23.936699999467237,
|
|
"windows_per_second": 41.776853117691964
|
|
},
|
|
"latency_batch64": {
|
|
"batch_size": 64,
|
|
"runs": 30,
|
|
"median_ms_per_batch": 102.32584999903338,
|
|
"median_ms_per_window": 1.5988414062348966,
|
|
"windows_per_second": 625.4529036465817
|
|
},
|
|
"accuracy": {
|
|
"samples": 10000,
|
|
"pck@20": 0.966773332977295,
|
|
"pck@50": 0.9915066654205322,
|
|
"mpjpe": 0.009460017587244511,
|
|
"wall_seconds": 21.632277250289917
|
|
}
|
|
},
|
|
"int8_dynamic": {
|
|
"file": "retrained_int8_dynamic.pth",
|
|
"size_bytes": 9068948,
|
|
"size_mb": 9.068948,
|
|
"latency_batch1": {
|
|
"batch_size": 1,
|
|
"runs": 100,
|
|
"median_ms_per_batch": 18.105350000041653,
|
|
"median_ms_per_window": 18.105350000041653,
|
|
"windows_per_second": 55.23229321707117
|
|
},
|
|
"latency_batch64": {
|
|
"batch_size": 64,
|
|
"runs": 30,
|
|
"median_ms_per_batch": 168.77549999844632,
|
|
"median_ms_per_window": 2.6371171874757238,
|
|
"windows_per_second": 379.20195763359703
|
|
},
|
|
"accuracy": {
|
|
"samples": 10000,
|
|
"pck@20": 0.9668200004577636,
|
|
"pck@50": 0.9915333324432373,
|
|
"mpjpe": 0.00936222033649683,
|
|
"wall_seconds": 45.35376596450806
|
|
}
|
|
}
|
|
},
|
|
"int8_dynamic_quant_report": {
|
|
"eligible_module_counts": {
|
|
"nn.Linear": 0,
|
|
"nn.Conv1d": 21,
|
|
"nn.Conv2d": 22
|
|
},
|
|
"modules_actually_quantized": [],
|
|
"n_modules_quantized": 0,
|
|
"params_total": 2225042,
|
|
"params_quantized": 0,
|
|
"params_quantized_fraction": 0.0
|
|
},
|
|
"accuracy_subset": {
|
|
"description": "seed-42 file-level 70/15/15 test split, corrupted windows (files 487-499) excluded, seed-42 random subset",
|
|
"subset_size": 10000,
|
|
"clean_test_total": 10000
|
|
}
|
|
},
|
|
"onnx": {
|
|
"env": {
|
|
"torch": "2.12.0+cpu",
|
|
"onnxruntime": "1.26.0",
|
|
"platform": "Windows-11-10.0.26200-SP0"
|
|
},
|
|
"export": {
|
|
"mode": "dynamic-batch",
|
|
"exporter": "torchscript",
|
|
"file": "retrained_fp32_dynamic.onnx",
|
|
"size_mb": 8.971781
|
|
},
|
|
"parity": {
|
|
"fixture": "results/parity_fixture.npz (batch 2, seed 42)",
|
|
"max_abs_diff_vs_stored_fixture": 2.384185791015625e-07,
|
|
"max_abs_diff_vs_torch_now": 2.384185791015625e-07,
|
|
"pass_lt_1e-4": true
|
|
},
|
|
"latency": {
|
|
"batch1": {
|
|
"batch_size": 1,
|
|
"runs": 100,
|
|
"median_ms_per_batch": 2.5410999987798277,
|
|
"median_ms_per_window": 2.5410999987798277,
|
|
"windows_per_second": 393.5303610563043
|
|
},
|
|
"batch64": {
|
|
"batch_size": 64,
|
|
"runs": 30,
|
|
"median_ms_per_batch": 181.95204999938142,
|
|
"median_ms_per_window": 2.8430007812403346,
|
|
"windows_per_second": 351.7410218803118
|
|
}
|
|
},
|
|
"ort_int8_dynamic_supplementary": {
|
|
"file": "retrained_int8_ort_dynamic.onnx",
|
|
"size_mb": 2.438794,
|
|
"runs": true,
|
|
"max_abs_diff_vs_fp32_fixture": 0.00827130675315857
|
|
}
|
|
},
|
|
"onnx_accuracy": {
|
|
"onnx_fp32": {
|
|
"samples": 10000,
|
|
"pck@20": 0.9668200004577636,
|
|
"pck@50": 0.9915333324432373,
|
|
"mpjpe": 0.00936222568154335,
|
|
"wall_seconds": 22.34790802001953
|
|
},
|
|
"onnx_int8_ort_dynamic": {
|
|
"samples": 10000,
|
|
"pck@20": 0.965240001964569,
|
|
"pck@50": 0.9915466655731201,
|
|
"mpjpe": 0.01108054072111845,
|
|
"wall_seconds": 55.742953062057495
|
|
}
|
|
},
|
|
"latency_controlled_rerun": {
|
|
"note": "3 interleaved repetitions per variant, median ms/window; quiet box",
|
|
"fp32": {
|
|
"batch1_ms_per_window_median": 10.969150001983508,
|
|
"batch1_reps": [
|
|
10.969150001983508,
|
|
12.646450000829645,
|
|
10.49820000116597
|
|
],
|
|
"batch64_ms_per_window_median": 2.2734187500077496,
|
|
"batch64_reps": [
|
|
2.377234374989712,
|
|
2.124126562478068,
|
|
2.2734187500077496
|
|
]
|
|
},
|
|
"fp16": {
|
|
"batch1_ms_per_window_median": 24.313550000442774,
|
|
"batch1_reps": [
|
|
25.1078499986761,
|
|
21.856999999727122,
|
|
24.313550000442774
|
|
],
|
|
"batch64_ms_per_window_median": 2.414695312495496,
|
|
"batch64_reps": [
|
|
2.5705156249955508,
|
|
1.7137437499741281,
|
|
2.414695312495496
|
|
]
|
|
},
|
|
"int8_dynamic": {
|
|
"batch1_ms_per_window_median": 15.627150000000256,
|
|
"batch1_reps": [
|
|
17.67525000104797,
|
|
14.627999998992891,
|
|
15.627150000000256
|
|
],
|
|
"batch64_ms_per_window_median": 2.0546906250160646,
|
|
"batch64_reps": [
|
|
2.0546906250160646,
|
|
2.03407343752815,
|
|
2.9325796875241394
|
|
]
|
|
},
|
|
"onnx_fp32": {
|
|
"batch1_ms_per_window_median": 3.186650001225644,
|
|
"batch1_reps": [
|
|
2.7332500012562377,
|
|
3.1995500012271805,
|
|
3.186650001225644
|
|
],
|
|
"batch64_ms_per_window_median": 1.9893374999924163,
|
|
"batch64_reps": [
|
|
1.5590843750032946,
|
|
1.9893374999924163,
|
|
2.2144343749914697
|
|
]
|
|
},
|
|
"onnx_int8_ort_dynamic": {
|
|
"batch1_ms_per_window_median": 6.50984999811044,
|
|
"batch1_reps": [
|
|
6.50984999811044,
|
|
6.455249998907675,
|
|
6.789299999581999
|
|
],
|
|
"batch64_ms_per_window_median": 5.770093750015803,
|
|
"batch64_reps": [
|
|
5.770093750015803,
|
|
3.912374999970325,
|
|
7.8067296875019565
|
|
]
|
|
}
|
|
}
|
|
} |