You can deploy this model and start earning money today!

VuNgocDuong/
depose-fi-onnx

Name: depose-fi-onnx
Availability: InStock

Views

No views yet

DePose-Fi: Dual-CP (Amplitude + Phase) S-AFF ONNX Models

Decomposition-first WiFi human pose estimation. Each CSI frame's amplitude and phase are separately CP-factorized (phase sanitized via cross-antenna phase linking + linear-trend removal), then fused by Selective Component-Adaptive Fusion (S-AFF). See the paper/code: https://github.com/Duongvu05/DePose-Fi

Both models take two inputs (cp_factors_amp, cp_factors_phase), each the canonicalized + zero-padded CP factors at the model's R_max, produced by deploy/run_inference.py in the repo above (do not feed raw CSI directly -- these models start after CP decomposition).

Files

File	Dataset	R_max	Params	Headline N-MPJPE
`saff_dualcp_rmax.onnx` (+ `.onnx.data`)	MM-Fi (single-person)	20	190.9K	36.35% (at R=10)
`saff_dualcp_piw3d_rmax.onnx` (+ `.onnx.data`)	Person-in-WiFi 3D (single-person)	24	1.68M	21.35% (at R=16)

N-MPJPE is torso-normalized (%), not raw millimeters.

Usage

See deploy/README.md in the GitHub repo for the full edge-deployment pipeline (Raspberry Pi / Jetson Nano / Qualcomm QCS6490, PRA rank/iteration adaptation). Quick local test:

bash

python deploy/run_inference.py --device raspberry_pi \
    --model saff_dualcp_rmax.onnx \
    --deadline-ms 30 \
    --frames "path/to/wifi-csi/*.mat"

VuNgocDuong/depose-fi-onnx

DePose-Fi: Dual-CP (Amplitude + Phase) S-AFF ONNX Models

Files

Usage

VuNgocDuong/
depose-fi-onnx