Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Commit 113011e

Browse files
authored
fix: WebSocket race condition, data source indicators, auto-start pose detection (ruvnet#96)
* feat: RVF training pipeline & UI integration (ADR-036) Implement full model training, management, and inference pipeline: Backend (Rust): - recording.rs: CSI recording API (start/stop/list/download/delete) - model_manager.rs: RVF model loading, LoRA profile switching, model library - training_api.rs: Training API with WebSocket progress streaming, simulated training mode with realistic loss curves, auto-RVF export on completion - main.rs: Wire new modules, recording hooks in all CSI paths, data dirs UI (new components): - ModelPanel.js: Dark-mode model library with load/unload, LoRA dropdown - TrainingPanel.js: Recording controls, training config, live Canvas charts - model.service.js: Model REST API client with events - training.service.js: Training + recording API client with WebSocket progress UI (enhancements): - LiveDemoTab: Model selector, LoRA profile switcher, A/B split view toggle, training quick-panel with 60s recording shortcut - SettingsPanel: Full dark mode conversion (issue ruvnet#92), model configuration (device, threads, auto-load), training configuration (epochs, LR, patience) - PoseDetectionCanvas: 10-frame pose trail with ghost keypoints and motion trajectory lines, cyan trail toggle button - pose.service.js: Model-inference confidence thresholds UI (plumbing): - index.html: Training tab (8th tab) - app.js: Panel initialization and tab routing - style.css: ~250 lines of training/model panel dark-mode styles 191 Rust tests pass, 0 failures. Closes ruvnet#92. Refs: ADR-036, ruvnet#93 Co-Authored-By: claude-flow <[email protected]> * fix: real RuVector training pipeline + UI service fixes Training pipeline (training_api.rs): - Replace simulated training with real signal-based training loop - Load actual CSI data from .csi.jsonl recordings or live frame history - Extract 180 features per frame: subcarrier amplitudes, temporal variance, Goertzel frequency analysis (9 bands), motion gradients, global stats - Train calibrated linear CSI-to-pose mapping via mini-batch gradient descent with L2 regularization (ridge regression), Xavier init, cosine LR decay - Self-supervised: teacher targets from derive_pose_from_sensing() heuristics - Real validation metrics: MSE and [email protected] on 80/20 train/val split - Export trained .rvf with real weights, feature normalization stats, witness - Add infer_pose_from_model() for live inference from trained model - 16 new tests covering features, training, inference, serialization UI fixes: - Fix double-URL bug in model.service.js and training.service.js (buildApiUrl was called twice — once in service, once in apiService) - Fix route paths to match Rust backend (/api/v1/train/*, /api/v1/recording/*) - Fix request body formats (session_name, nested config object) - Fix top-level await in LiveDemoTab.js blocking module graph - Dynamic imports for ModelPanel/TrainingPanel in app.js - Center nav tabs with flex-wrap for 8-tab layout Co-Authored-By: claude-flow <[email protected]> * fix: WebSocket onOpen race condition, data source indicators, auto-start pose detection - Fix WebSocket onOpen race condition in websocket.service.js where setupEventHandlers replaced onopen after socket was already open, preventing pose service from receiving connection signal - Add 4-state data source indicator (LIVE/SIMULATED/RECONNECTING/OFFLINE) across Dashboard, Sensing, and Live Demo tabs via sensing.service.js - Add hot-plug ESP32 auto-detection in sensing server (auto mode runs both UDP listener and simulation, switches on ESP32_TIMEOUT) - Auto-start pose detection when backend is reachable - Hide duplicate PoseDetectionCanvas controls when enableControls=false - Add standalone Demo button in LiveDemoTab for offline animated demo - Add data source banner and status styling Co-Authored-By: claude-flow <[email protected]>
1 parent c193cd4 commit 113011e

20 files changed

Lines changed: 6124 additions & 83 deletions
Lines changed: 228 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,228 @@
1+
# ADR-036: RVF Model Training Pipeline & UI Integration
2+
3+
## Status
4+
Proposed
5+
6+
## Date
7+
2026-03-02
8+
9+
## Context
10+
11+
The wifi-densepose system currently operates in **signal-derived** mode — `derive_pose_from_sensing()` maps aggregate CSI features (motion power, breathing rate, variance) to keypoint positions using deterministic math. This gives whole-body presence and gross motion but cannot track individual limbs.
12+
13+
The infrastructure for **model inference** mode exists but is disconnected:
14+
15+
1. **RVF container format** (`rvf_container.rs`, 1,102 lines) — a 64-byte-aligned binary format supporting model weights (`SEG_VEC`), metadata (`SEG_MANIFEST`), quantization (`SEG_QUANT`), LoRA profiles (`SEG_LORA`), contrastive embeddings (`SEG_EMBED`), and witness audit trails (`SEG_WITNESS`). Builder and reader are fully implemented with CRC32 integrity checks.
16+
17+
2. **Training crate** (`wifi-densepose-train`) — AdamW optimizer, [email protected]/OKS metrics, LR scheduling with warmup, early stopping, CSV logging, and checkpoint export. Supports `CsiDataset` trait with planned MM-Fi (114→56 subcarrier interpolation) and Wi-Pose (30→56 zero-pad) loaders per ADR-015.
18+
19+
3. **NN inference crate** (`wifi-densepose-nn`) — ONNX Runtime backend with CPU/GPU support, dynamic tensor shapes, thread-safe `OnnxBackend` wrapper, model info inspection, and warmup.
20+
21+
4. **Sensing server CLI** (`--model <path>`, `--train`, `--pretrain`, `--embed`) — flags exist for model loading, training mode, and embedding extraction, but the end-to-end path from raw CSI → trained `.rvf` → live inference is not wired together.
22+
23+
5. **UI gaps** — No model management, training progress visualization, LoRA profile switching, or embedding inspection. The Settings panel lacks model configuration. The Live Demo has no way to load a trained model or compare signal-derived vs model-inference output side-by-side.
24+
25+
### What users need
26+
27+
- A way to **collect labeled CSI data** from their own environment (self-supervised or teacher-student from camera).
28+
- A way to **train an .rvf model** from collected data without leaving the UI.
29+
- A way to **load and switch models** in the live demo, seeing the quality improvement.
30+
- Visibility into **training progress** (loss curves, validation PCK, early stopping).
31+
- **Environment adaptation** via LoRA profiles (office → home → warehouse) without full retraining.
32+
33+
## Decision
34+
35+
### Phase 1: Data Collection & Self-Supervised Pretraining
36+
37+
#### 1.1 CSI Recording API
38+
Add REST endpoints to the sensing server:
39+
```
40+
POST /api/v1/recording/start { duration_secs, label?, session_name }
41+
POST /api/v1/recording/stop
42+
GET /api/v1/recording/list
43+
GET /api/v1/recording/download/:id
44+
DELETE /api/v1/recording/:id
45+
```
46+
- Records raw CSI frames + extracted features to `.csi.jsonl` files.
47+
- Optional camera-based label overlay via teacher model (Detectron2/MediaPipe on client).
48+
- Each recording session tagged with environment metadata (room dimensions, node positions, AP count).
49+
50+
#### 1.2 Contrastive Pretraining (ADR-024 Phase 1)
51+
- Self-supervised NT-Xent loss learns a 128-dim CSI embedding without pose labels.
52+
- Positive pairs: adjacent frames from same person; negatives: different sessions/rooms.
53+
- VICReg regularization prevents embedding collapse.
54+
- Output: `.rvf` container with `SEG_EMBED` + `SEG_VEC` segments.
55+
- Training triggered via `POST /api/v1/train/pretrain { dataset_ids[], epochs, lr }`.
56+
57+
### Phase 2: Supervised Training Pipeline
58+
59+
#### 2.1 Dataset Integration
60+
- **MM-Fi loader**: Parse HDF5 files, 114→56 subcarrier interpolation via `ruvector-solver` sparse least-squares.
61+
- **Wi-Pose loader**: Parse .mat files, 30→56 zero-padding with Hann window smoothing.
62+
- **Self-collected**: `.csi.jsonl` from Phase 1 recording + camera-generated labels.
63+
- All datasets implement `CsiDataset` trait and produce `(amplitude[B,T*links,56], phase[B,T*links,56], keypoints[B,17,2], visibility[B,17])`.
64+
65+
#### 2.2 Training API
66+
```
67+
POST /api/v1/train/start {
68+
dataset_ids: string[],
69+
config: {
70+
epochs: 100,
71+
batch_size: 32,
72+
learning_rate: 3e-4,
73+
weight_decay: 1e-4,
74+
early_stopping_patience: 15,
75+
warmup_epochs: 5,
76+
pretrained_rvf?: string, // Base model for fine-tuning
77+
lora_profile?: string, // Environment-specific LoRA
78+
}
79+
}
80+
POST /api/v1/train/stop
81+
GET /api/v1/train/status // { epoch, train_loss, val_pck, val_oks, lr, eta_secs }
82+
WS /ws/train/progress // Real-time streaming of training metrics
83+
```
84+
85+
#### 2.3 RVF Export
86+
On training completion:
87+
- Best checkpoint exported as `.rvf` with `SEG_VEC` (weights), `SEG_MANIFEST` (metadata), `SEG_WITNESS` (training hash + final metrics), and optional `SEG_QUANT` (INT8 quantization).
88+
- Stored in `data/models/` directory, indexed by model ID.
89+
- `GET /api/v1/models` lists available models; `POST /api/v1/models/load { model_id }` hot-loads into inference.
90+
91+
### Phase 3: LoRA Environment Adaptation
92+
93+
#### 3.1 LoRA Fine-Tuning
94+
- Given a base `.rvf` model, fine-tune only LoRA adapter weights (rank 4-16) on environment-specific recordings.
95+
- 5-10 minutes of labeled data from new environment suffices.
96+
- New LoRA profile appended to existing `.rvf` via `SEG_LORA` segment.
97+
- `POST /api/v1/train/lora { base_model_id, dataset_ids[], profile_name, rank: 8, epochs: 20 }`.
98+
99+
#### 3.2 Profile Switching
100+
- `POST /api/v1/models/lora/activate { model_id, profile_name }` — hot-swap LoRA weights without reloading base model.
101+
- UI dropdown lists available profiles per loaded model.
102+
103+
### Phase 4: UI Integration
104+
105+
#### 4.1 Model Management Panel (new: `ui/components/ModelPanel.js`)
106+
- **Model Library**: List loaded and available `.rvf` models with metadata (version, dataset, PCK score, size, created date).
107+
- **Model Inspector**: Show RVF segment breakdown — weight count, quantization type, LoRA profiles, embedding config, witness hash.
108+
- **Load/Unload**: One-click model loading with progress bar.
109+
- **Compare**: Side-by-side signal-derived vs model-inference toggle in Live Demo.
110+
111+
#### 4.2 Training Dashboard (new: `ui/components/TrainingPanel.js`)
112+
- **Recording Controls**: Start/stop CSI recording, session list with duration and frame counts.
113+
- **Training Progress**: Real-time loss curve (train loss, val loss) and metric charts ([email protected], OKS) via WebSocket streaming.
114+
- **Epoch Table**: Scrollable table of per-epoch metrics with best-epoch highlighting.
115+
- **Early Stopping Indicator**: Visual countdown of patience remaining.
116+
- **Export Button**: Download trained `.rvf` from browser.
117+
118+
#### 4.3 Live Demo Enhancements
119+
- **Model Selector**: Dropdown in toolbar to switch between signal-derived and loaded `.rvf` models.
120+
- **LoRA Profile Selector**: Sub-dropdown showing environment profiles for the active model.
121+
- **Confidence Heatmap Overlay**: Per-keypoint confidence visualization when model is loaded (toggle in render mode dropdown).
122+
- **Pose Trail**: Ghosted keypoint history showing last N frames of motion trajectory.
123+
- **A/B Split View**: Left half signal-derived, right half model-inference for quality comparison.
124+
125+
#### 4.4 Settings Panel Extensions
126+
- **Model section**: Default model path, auto-load on startup, GPU/CPU toggle, inference threads.
127+
- **Training section**: Default hyperparameters, checkpoint directory, auto-export on completion.
128+
- **Recording section**: Default recording directory, max duration, auto-label with camera.
129+
130+
#### 4.5 Dark Mode
131+
All new panels follow the dark mode established in ADR-035 (`#0d1117` backgrounds, `#e0e0e0` text, translucent dark panels with colored accents).
132+
133+
### Phase 5: Inference Pipeline Wiring
134+
135+
#### 5.1 Model-Inference Pose Path
136+
When a `.rvf` model is loaded:
137+
1. CSI frame arrives (UDP or simulated).
138+
2. Extract amplitude + phase tensors from subcarrier data.
139+
3. Feed through ONNX session: `input[1, T*links, 56]``output[1, 17, 4]` (x, y, z, conf).
140+
4. Apply Kalman smoothing from `pose_tracker.rs`.
141+
5. Broadcast via WebSocket with `pose_source: "model_inference"`.
142+
6. UI Estimation Mode badge switches from green "SIGNAL-DERIVED" to blue "MODEL INFERENCE".
143+
144+
#### 5.2 Progressive Loading (ADR-031 Layer A/B/C)
145+
- **Layer A** (instant): Signal-derived pose starts immediately.
146+
- **Layer B** (5-10s): Contrastive embeddings loaded, HNSW index warm.
147+
- **Layer C** (30-60s): Full pose model loaded, inference active.
148+
- Transitions seamlessly; UI badge updates automatically.
149+
150+
## Consequences
151+
152+
### Positive
153+
- Users can train a model on **their own environment** without external tools or Python dependencies.
154+
- LoRA profiles mean a single base model adapts to multiple rooms in minutes, not hours.
155+
- Training progress is visible in real-time — no black-box waiting.
156+
- A/B comparison lets users see the quality jump from signal-derived to model-inference.
157+
- RVF container bundles everything (weights, metadata, LoRA, witness) in one portable file.
158+
- Self-supervised pretraining requires no labels — just leave ESP32s running.
159+
- Progressive loading means the UI is never "loading..." — signal-derived kicks in immediately.
160+
161+
### Negative
162+
- Training requires significant compute: GPU recommended for supervised training (CPU possible but 10-50x slower).
163+
- MM-Fi and Wi-Pose datasets must be downloaded separately (10-50 GB each) — cannot be bundled.
164+
- LoRA rank must be tuned per environment; too low loses expressiveness, too high overfits.
165+
- ONNX Runtime adds ~50 MB to the binary size when GPU support is enabled.
166+
- Real-time inference at 10 FPS requires ~10ms per frame — tight budget on CPU.
167+
- Teacher-student labeling (camera → pose labels → CSI training) requires camera access, which may conflict with the privacy-first premise.
168+
169+
### Mitigations
170+
- Provide pre-trained base `.rvf` model downloadable from releases (trained on MM-Fi + Wi-Pose).
171+
- INT8 quantization (`SEG_QUANT`) reduces model size 4x and speeds inference ~2x on CPU.
172+
- Camera-based labeling is **optional** — self-supervised pretraining works without camera.
173+
- Training API validates VRAM availability before starting GPU training; falls back to CPU with warning.
174+
175+
## Implementation Order
176+
177+
| Phase | Effort | Dependencies | Priority |
178+
|-------|--------|-------------|----------|
179+
| 1.1 CSI Recording API | 2-3 days | sensing server | High |
180+
| 1.2 Contrastive Pretraining | 3-5 days | ADR-024, recording API | High |
181+
| 2.1 Dataset Integration | 3-5 days | ADR-015, CsiDataset trait | High |
182+
| 2.2 Training API | 2-3 days | training crate, dataset loaders | High |
183+
| 2.3 RVF Export | 1-2 days | RvfBuilder | Medium |
184+
| 3.1 LoRA Fine-Tuning | 3-5 days | base trained model | Medium |
185+
| 3.2 Profile Switching | 1 day | LoRA in RVF | Medium |
186+
| 4.1 Model Panel UI | 2-3 days | models API | High |
187+
| 4.2 Training Dashboard UI | 3-4 days | training API + WS | High |
188+
| 4.3 Live Demo Enhancements | 2-3 days | model loading | Medium |
189+
| 4.4 Settings Extensions | 1 day | model/training APIs | Low |
190+
| 4.5 Dark Mode | 0.5 days | new panels | Low |
191+
| 5.1 Inference Wiring | 3-5 days | ONNX backend, pose tracker | High |
192+
| 5.2 Progressive Loading | 2-3 days | ADR-031 | Medium |
193+
194+
**Total estimate: 4-6 weeks** (phases can overlap; 1+2 parallel with 4).
195+
196+
## Files to Create/Modify
197+
198+
### New Files
199+
- `ui/components/ModelPanel.js` — Model library, inspector, load/unload controls
200+
- `ui/components/TrainingPanel.js` — Recording controls, training progress, metric charts
201+
- `rust-port/.../sensing-server/src/recording.rs` — CSI recording API handlers
202+
- `rust-port/.../sensing-server/src/training_api.rs` — Training API handlers + WS progress stream
203+
- `rust-port/.../sensing-server/src/model_manager.rs` — Model loading, hot-swap, 32LoRA activation
204+
- `data/models/` — Default model storage directory
205+
206+
### Modified Files
207+
- `rust-port/.../sensing-server/src/main.rs` — Wire recording, training, and model APIs
208+
- `rust-port/.../train/src/trainer.rs` — Add WebSocket progress callback, LoRA training mode
209+
- `rust-port/.../train/src/dataset.rs` — MM-Fi and Wi-Pose dataset loaders
210+
- `rust-port/.../nn/src/onnx.rs` — LoRA weight injection, INT8 quantization support
211+
- `ui/components/LiveDemoTab.js` — Model selector, LoRA dropdown, A/B spsplit view
212+
- `ui/components/SettingsPanel.js` — Model and training configuration sections
213+
- `ui/components/PoseDetectionCanvas.js` — Pose trail rendering, confidence heatmap overlay
214+
- `ui/services/pose.service.js` — Model-inference keypoint processing
215+
- `ui/index.html` — Add Training tabhee
216+
- `ui/style.css` — Styles for new panels
217+
218+
## References
219+
- ADR-015: MM-Fi + Wi-Pose training datasets
220+
- ADR-016: RuVector training pipeline integration
221+
- ADR-024: Project AETHER — contrastive CSI embedding model
222+
- ADR-029: RuvSense multistatic sensing mode
223+
- ADR-031: RuView sensing-first RF mode (progressive loading)
224+
- ADR-035: Live sensing UI accuracy & data source transparency
225+
- Issue: https://github.com/ruvnet/wifi-densepose/issues/92
226+
- RVF format: `crates/wifi-densepose-sensing-server/src/rvf_container.rs`
227+
- Training crate: `crates/wifi-densepose-train/src/trainer.rs`
228+
- NN inference: `crates/wifi-densepose-nn/src/onnx.rs`

0 commit comments

Comments
 (0)