mirror of
https://github.com/ruvnet/RuView
synced 2026-07-22 17:23:19 +00:00
1fb5397ddf
Add archive/v1/DEPRECATED.md tombstone and a loud deprecation notice atop archive/v1/README.md: DensePoseHead is architecture-only (random kaiming_normal_ init, zero committed checkpoints under archive/v1/), superseded by the v2/ workspace and the wifi-densepose 2.x / ruview pip wheel. Add a 'Model weights: what's real, what's not' three-tier table to README.md and docs/user-guide.md distinguishing real+validated (presence 82.3%, MM-Fi pose 82.69% torso-PCK@20, count_v1), real-but-weak (committed pose_v1 at PCK@20=3.0%, runtime confidence=0 stub, below ADR-079 target), and architecture-only (archive/v1). Caveat the live single-ESP32 17-keypoint cog advertisement and answer #509 SISO / #1125. Refs #509, #1125
2.6 KiB
2.6 KiB
⚠️ DEPRECATED — unmaintained and superseded
This tree is the original pure-Python implementation and is kept only as a research archive. It receives no fixes, reviews, or support. Read
DEPRECATED.mdbefore using anything below.
- Its
DensePoseHeadis architecture-only with random-initialized weights and ships no trained checkpoint — running it produces random output, not real pose accuracy.- The maintained path is the
v2/Rust workspace and thewifi-densepose 2.x/ruviewpip wheel (ADR-117). Thewifi-densepose1.x line is tombstoned on PyPI (1.99.0 raisesImportError).- Real trained weights live elsewhere:
ruvnet/wifi-densepose-pretrained(presence, 82.3%) andruvnet/wifi-densepose-mmfi-pose(17-keypoint pose, 82.69% torso-PCK@20).- The only still-live artifact here is the deterministic proof
data/proof/verify.py(ADR-028), which stays. See ADR-187.
WiFi-DensePose v1 (Python Implementation)
This directory contains the original Python implementation of WiFi-DensePose.
Structure
v1/
├── src/ # Python source code
│ ├── api/ # REST API endpoints
│ ├── config/ # Configuration management
│ ├── core/ # Core processing logic
│ ├── database/ # Database models and migrations
│ ├── hardware/ # Hardware interfaces
│ ├── middleware/ # API middleware
│ ├── models/ # Neural network models
│ ├── services/ # Business logic services
│ └── tasks/ # Background tasks
├── tests/ # Test suite
├── docs/ # Documentation
├── scripts/ # Utility scripts
├── data/ # Data files
├── setup.py # Package setup
├── test_application.py # Application tests
└── test_auth_rate_limit.py # Auth/rate limit tests
Requirements
- Python 3.10+
- PyTorch 2.0+
- FastAPI
- PostgreSQL/SQLite
Installation
cd v1
pip install -e .
Usage
# Start API server
python -m src.main
# Run tests
pytest tests/
Note
This is the legacy Python implementation. For the new Rust implementation with improved performance, see /v2/.