Files

rUv 9bbe95648c feat: ADR-024 Contrastive CSI Embedding Model — all 7 phases (#52 )

Full implementation of Project AETHER — Contrastive CSI Embedding Model.

## Phases Delivered
1. ProjectionHead (64→128→128) + L2 normalization
2. CsiAugmenter (5 physically-motivated augmentations)
3. InfoNCE contrastive loss + SimCLR pretraining
4. FingerprintIndex (4 index types: env, activity, temporal, person)
5. RVF SEG_EMBED (0x0C) + CLI integration
6. Cross-modal alignment (PoseEncoder + InfoNCE)
7. Deep RuVector: MicroLoRA, EWC++, drift detection, hard-negative mining, SEG_LORA

## Stats
- 276 tests passing (191 lib + 51 bin + 16 rvf + 18 vitals)
- 3,342 additions across 8 files
- Zero unsafe/unwrap/panic/todo stubs
- ~55KB INT8 model for ESP32 edge deployment

Also fixes deprecated GitHub Actions (v3→v4) and adds feat/* branch CI triggers.

Closes #50

2026-03-01 01:44:38 -05:00

3.7 KiB

Raw Blame History

wifi-densepose-nn

Multi-backend neural network inference for WiFi-based DensePose estimation.

Overview

wifi-densepose-nn provides the inference engine that maps processed WiFi CSI features to DensePose body surface predictions. It supports three backends -- ONNX Runtime (default), PyTorch via tch-rs, and Candle -- so models can run on CPU, CUDA GPU, or TensorRT depending on the deployment target.

The crate implements two key neural components:

DensePose Head -- Predicts 24 body part segmentation masks and per-part UV coordinate regression.
Modality Translator -- Translates CSI feature embeddings into visual feature space, bridging the domain gap between WiFi signals and image-based pose estimation.

Features

ONNX Runtime backend (default) -- Load and run .onnx models with CPU or GPU execution providers.
PyTorch backend (tch-backend) -- Native PyTorch inference via libtorch FFI.
Candle backend (candle-backend) -- Pure-Rust inference with candle-core and candle-nn.
CUDA acceleration (cuda) -- GPU execution for supported backends.
TensorRT optimization (tensorrt) -- INT8/FP16 optimized inference via ONNX Runtime.
Batched inference -- Process multiple CSI frames in a single forward pass.
Model caching -- Memory-mapped model weights via memmap2.

Feature flags

Flag	Default	Description
`onnx`	yes	ONNX Runtime backend
`tch-backend`	no	PyTorch (tch-rs) backend
`candle-backend`	no	Candle pure-Rust backend
`cuda`	no	CUDA GPU acceleration
`tensorrt`	no	TensorRT via ONNX Runtime
`all-backends`	no	Enable onnx + tch + candle together

Quick Start

use wifi_densepose_nn::{InferenceEngine, DensePoseConfig, OnnxBackend};

// Create inference engine with ONNX backend
let config = DensePoseConfig::default();
let backend = OnnxBackend::from_file("model.onnx")?;
let engine = InferenceEngine::new(backend, config)?;

// Run inference on a CSI feature tensor
let input = ndarray::Array4::zeros((1, 256, 64, 64));
let output = engine.infer(&input)?;

println!("Body parts: {}", output.body_parts.shape()[1]); // 24

Architecture

wifi-densepose-nn/src/
  lib.rs          -- Re-exports, constants (NUM_BODY_PARTS=24), prelude
  densepose.rs    -- DensePoseHead, DensePoseConfig, DensePoseOutput
  inference.rs    -- Backend trait, InferenceEngine, InferenceOptions
  onnx.rs         -- OnnxBackend, OnnxSession (feature-gated)
  tensor.rs       -- Tensor, TensorShape utilities
  translator.rs   -- ModalityTranslator (CSI -> visual space)
  error.rs        -- NnError, NnResult

Crate	Role
`wifi-densepose-core`	Foundation types and `NeuralInference` trait
`wifi-densepose-signal`	Produces CSI features consumed by inference
`wifi-densepose-train`	Trains the models this crate loads
`ort`	ONNX Runtime Rust bindings
`tch`	PyTorch Rust bindings
`candle-core`	Hugging Face pure-Rust ML framework

License

MIT OR Apache-2.0

3.7 KiB Raw Blame History