6ed69a3d48
Major changes: - Organized Python v1 implementation into v1/ subdirectory - Created Rust workspace with 9 modular crates: - wifi-densepose-core: Core types, traits, errors - wifi-densepose-signal: CSI processing, phase sanitization, FFT - wifi-densepose-nn: Neural network inference (ONNX/Candle/tch) - wifi-densepose-api: Axum-based REST/WebSocket API - wifi-densepose-db: SQLx database layer - wifi-densepose-config: Configuration management - wifi-densepose-hardware: Hardware abstraction - wifi-densepose-wasm: WebAssembly bindings - wifi-densepose-cli: Command-line interface Documentation: - ADR-001: Workspace structure - ADR-002: Signal processing library selection - ADR-003: Neural network inference strategy - DDD domain model with bounded contexts Testing: - 69 tests passing across all crates - Signal processing: 45 tests - Neural networks: 21 tests - Core: 3 doc tests Performance targets: - 10x faster CSI processing (~0.5ms vs ~5ms) - 5x lower memory usage (~100MB vs ~500MB) - WASM support for browser deployment
1.5 KiB
1.5 KiB
ADR-003: Neural Network Inference Strategy
Status
Accepted
Context
The WiFi-DensePose system requires neural network inference for:
- Modality translation (CSI → visual features)
- DensePose estimation (body part segmentation + UV mapping)
We need to select an inference strategy that supports pre-trained models and multiple backends.
Decision
We will implement a multi-backend inference engine:
Primary Backend: ONNX Runtime (ort crate)
- Load pre-trained PyTorch models exported to ONNX
- GPU acceleration via CUDA/TensorRT
- Cross-platform support
Alternative Backends (Feature-gated)
tch-rs: PyTorch C++ bindingscandle: Pure Rust ML framework
Architecture
pub trait Backend: Send + Sync {
fn load_model(&mut self, path: &Path) -> NnResult<()>;
fn run(&self, inputs: HashMap<String, Tensor>) -> NnResult<HashMap<String, Tensor>>;
fn input_specs(&self) -> Vec<TensorSpec>;
fn output_specs(&self) -> Vec<TensorSpec>;
}
Feature Flags
[features]
default = ["onnx"]
onnx = ["ort"]
tch-backend = ["tch"]
candle-backend = ["candle-core", "candle-nn"]
cuda = ["ort/cuda"]
tensorrt = ["ort/tensorrt"]
Consequences
Positive
- Use existing trained models (no retraining)
- Multiple backend options for different deployments
- GPU acceleration when available
- Feature flags minimize binary size
Negative
- ONNX model conversion required
- ort crate pulls in C++ dependencies
- tch requires libtorch installation