Add PyTorch/ONNX prediction models with physics fallback

Browse Source

- Train 3 MLP networks (acid speed 14→1, tension 4→10, quality 6→2)
  on 12,000 synthetic samples generated from physics models + noise
- Export pre-trained ONNX models to pt_models/ directory
- Rewrite prediction.py: ONNX inference first, physics fallback if unavailable
- Add onnxruntime + numpy to requirements.txt (Aliyun mirror for Docker)
- Use Tsinghua mirror in Dockerfile for pip installs

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

...

This commit is contained in:

wangyu

2026-05-27 17:31:25 +08:00

parent 62599b9c40

commit 6ae24cb14d

8 changed files with 642 additions and 320 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

BIN

backend/app/services/pt_models/quality.onnx Normal file

Binary file not shown.