Kunpeng
25fa0c5825
Backend:
- Persist alert events and robot delivery counters in SQLite (data/app.db,
YOLO_DB_PATH override); EventStore keeps its interface, DeliveryStatsStore
uses read/write-through UPSERT; in-memory fallback remains for standalone
AlertManager use
- Serve /api/detect from a sync endpoint and serialize YOLO inference with a
lock, so concurrent requests no longer block the event loop
- Unify single-image and session detection: requests without session_id
share the fixed single-image session and run full frame confirmation
- Store UTC Z-suffixed timestamps for sortable string comparison; close
executor and database on shutdown via FastAPI lifespan
Frontend:
- Split app.js into ES modules (main.js + modules/{dom,api,ui,charts,store}
+ views/{dashboard,inspection,events,robots,robotCards}), no build step
- Escape all server data interpolated into innerHTML; guard missing
event.classes; replace lazy element ID list with memoized qs()
- Remove hardcoded fake stats (trend badge, device donut segment)
Docs:
- Rewrite README: accurate weight policy (only trained best.pt committed,
no Git LFS), SQLite persistence, single-worker note, data asset inventory
- Align models/pretrained/README.md with actual files; add YOLO_DB_PATH to
.env.example; add persistence unit tests; ruff clean
103 lines
4.8 KiB
Markdown
103 lines
4.8 KiB
Markdown
# Smoke and Fire YOLO
|
|
|
|
Ultralytics YOLO training, validation, prediction, and export pipeline for the Smoke-Fire-Detection-YOLO dataset, plus an integrated fire prevention management platform (FastAPI + browser frontend).
|
|
|
|
## Project layout
|
|
|
|
```text
|
|
configs/datasets/smoke_fire.yaml Dataset configuration
|
|
models/pretrained/ Locally cached base weights (not committed)
|
|
src/yolo/cli.py Command-line entry point
|
|
src/yolo/config.py Training configuration
|
|
src/yolo/defaults.py Project defaults
|
|
src/yolo/engine.py Train, validate, predict, and export
|
|
src/yolo/checkpoints.py Checkpoint discovery and resume support
|
|
src/yolo/reporting.py Training result reporting
|
|
backend/ FastAPI inference API and alerting
|
|
frontend/ Browser management platform (no build step)
|
|
```
|
|
|
|
## Setup
|
|
|
|
```bash
|
|
uv sync
|
|
```
|
|
|
|
Trained deployment weights are committed as regular files under `runs/detect/*/weights/best.pt`, so the API works right after cloning. Checkpoint files (`epoch*.pt`, `last.pt`) and re-downloadable base weights are excluded by `.gitignore`.
|
|
|
|
## Commands
|
|
|
|
Fine-tune from the current best YOLO11s checkpoint:
|
|
|
|
```bash
|
|
uv run fire-yolo train
|
|
```
|
|
|
|
Resume from the newest checkpoint:
|
|
|
|
```bash
|
|
uv run fire-yolo train --resume
|
|
```
|
|
|
|
Validate a trained model:
|
|
|
|
```bash
|
|
uv run fire-yolo val --weights runs/detect/<run-name>/weights/best.pt
|
|
```
|
|
|
|
Run inference:
|
|
|
|
```bash
|
|
uv run fire-yolo predict --weights runs/detect/<run-name>/weights/best.pt --source path/to/image-or-video
|
|
```
|
|
|
|
Export a model:
|
|
|
|
```bash
|
|
uv run fire-yolo export --weights runs/detect/<run-name>/weights/best.pt --format onnx
|
|
```
|
|
|
|
## Default training settings
|
|
|
|
- Model: `runs/detect/smoke_fire_yolo11s_v1-4/weights/best.pt`
|
|
- Dataset: `configs/datasets/smoke_fire.yaml`
|
|
- Epochs: 80
|
|
- Image size: 768
|
|
- Batch: 24
|
|
- Workers: 0
|
|
- Optimizer: AdamW
|
|
- Initial learning rate: 0.0002
|
|
- Mosaic/MixUp: disabled
|
|
- Prediction confidence: 0.40
|
|
- Checkpoint interval: every 5 epochs
|
|
- Output: `runs/detect`
|
|
|
|
Training writes `last.pt`, `best.pt`, periodic checkpoints, and `best_point.json` to the run directory.
|
|
|
|
The committed best weights and evaluation evidence are summarized in [`docs/model_comparison.md`](docs/model_comparison.md). Only trained `best.pt` files are committed; to make a newly trained model available for deployment, commit its `weights/best.pt` after the run finishes.
|
|
|
|
## Web Detection Service
|
|
|
|
After training finishes, install the web dependencies and run the integrated frontend and inference API:
|
|
|
|
```bash
|
|
uv sync
|
|
uv run uvicorn backend.main:app --host 127.0.0.1 --port 8000
|
|
```
|
|
|
|
Open `http://127.0.0.1:8000` to use the fire prevention management platform. It provides a system overview, local-video inspection, alert event handling, a risk register, robot channel status, and effective model settings. The browser plays selected videos locally and sends sequential JPEG frames to `POST /api/detect`; requests do not overlap.
|
|
|
|
Management endpoints include `GET /api/dashboard`, `GET /api/events`, `PATCH /api/events/{event_id}`, and `GET /api/robots`. Alert events can be marked as pending, acknowledged, or resolved. The robot endpoint reports Enterprise WeChat and Feishu configuration and delivery statistics without exposing webhook credentials. Use `POST /api/robots/{channel}/test` to send a connection test to a configured group robot.
|
|
|
|
Events and robot delivery counters are persisted in SQLite (`data/app.db` by default, override with `YOLO_DB_PATH`), so they survive service restarts. The event store keeps the most recent 500 events. Run the API with a single uvicorn worker: per-session consecutive-frame state lives in the process.
|
|
|
|
The local `.env` file contains optional robot settings. Set `WECHAT_WEBHOOK_URL` for an Enterprise WeChat group robot, `FEISHU_WEBHOOK_URL` for a Feishu custom group robot, or both. If Feishu signature verification is enabled, also set `FEISHU_SECRET`. Alerts require three consecutive positive frames by default and use separate 60-second cooldowns for fire and smoke. `ALERT_CONFIRM_FRAMES` and `ALERT_COOLDOWN_SECONDS` override these settings. Without a webhook, video detection still works and the UI reports that notifications are disabled.
|
|
|
|
Detection requests without a `session_id` share the fixed `single-image` session, so the consecutive-frame confirmation also applies to them; reset it with `DELETE /api/sessions/single-image`.
|
|
|
|
## Data assets
|
|
|
|
- `data/Smoke-Fire-Detection-YOLO/` — main smoke/fire dataset (train/val/test).
|
|
- `data/fire-dataset/` — incremental hard-negative collection (395 train / 87 val images, Pascal VOC XML plus YOLO labels); not yet wired to a training config.
|
|
- `runs/audit/` — label audit tooling: `scan_missing_labels.py` finds unlabeled images that the current model detects, `render_missing_label_candidates.py` renders them for review.
|