Commit Graph

5 Commits

Author SHA1 Message Date
6e88d2392f feat: add dynamic config reload, unique device identity (UUID), and MQTT support
- New StreamManager for dynamic RTSP/FLV stream lifecycle
- Dynamic worker scaling for inference
- Device UUID generation and persistence
- Telegraf config and NPU monitoring scripts
- .gitignore for build artifacts
2026-05-08 16:26:10 +08:00
2e7245d62e feat: 边缘侧服务代码初始化与配置同步准备 2026-05-08 11:33:43 +08:00
ee9be85292 fix: ACL bytes_to_ptr GC bug + 添加 NPU 模型转换指南
python/infer_server.py:
- 修复 acl.util.bytes_to_ptr() 后 bytes 被 GC 回收导致全零输出的 bug
- 保持 bytes 引用直到 memcpy 完成
- 正确解析 FP16 模型输出 (half precision -> float32)

docs/CONVERSION_GUIDE.md:
- 完整的 YOLOv8 ONNX->OM 转换流程文档
- ATC 转换参数详解及低内存设备配置
- 已知问题排查表 (OOM/全零输出/算子不支持)
- 其他 YOLOv8 尺寸模型参考

start.sh: 一键启动脚本
2026-05-06 23:30:49 +08:00
c69d9b1457 feat: add YOLOv8n ONNX model and ATC conversion script
- yolov8n.onnx (13MB) exported from ultralytics YOLOv8n
- scripts/atc_convert.sh for ONNX->OM conversion on Ascend 310B4
- Use FP16 precision for faster inference on edge device
2026-05-06 22:49:13 +08:00
f6a85d7dfc init: tianyan-edge edge agent with Ascend NPU inference backend
- Go main process: stream ingestor, infer client, event uploader,
  heartbeat, config agent, OTA agent
- Python inference server rewritten to use CANN ACL (acl module)
  replacing ultralytics/PyTorch; supports YOLOv8 raw and YOLOv10
  NMS-free output formats via OUTPUT_FORMAT env var
- systemd services for edge-agent and edge-infer
- build/install/package scripts targeting arm64

Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-05-06 21:49:04 +08:00