Skip to content

Roboflow AMD Training

Status: Active local experiment track
Last synthesized: April 2026
Purpose: Track the Roboflow-based drawing-training and AMD Windows runtime work that currently lives in the local DraftLint experiment repo.

Why This Subsection Exists

This subsection exists because the current drawing-analysis training work is not just about labeling classes. It also depends on the runtime and tooling path used to make detector experiments practical on local hardware.

The current tracked repo is:

D:\02_Code\41_Training_drawing_roboflow_windowscode

That repo combines several concerns in one place:

  • Roboflow-hosted layout detection experiments
  • OCR runtime and backend-selection work
  • YOLO-based symbol-detection experiments
  • Windows AMD DirectML inference enablement

So this subsection is the wiki home for that combined training/runtime story.

What Lives Here

Current Operational Truth

The DraftLint repo is useful, but it should currently be treated as a parts donor and experiment bed rather than a product-ready runtime. The strongest reusable work there is the OCR and inference runtime split, especially for Windows AMD local inference.

The weakest area is still layout detection, because it depends on a hosted Roboflow model and falls back to simple heuristics when that hosted path fails.

Sources

  • D:\02_Code\41_Training_drawing_roboflow_windowscode
  • C:\Users\adeel\OneDrive\100_Knowledge\203_TextCAD\01_Product_Project_Management\00_Project_Management_n_skills\01_tracks\cad-intelligence\handover\260411_draftlint-repo-assessment-and-doc-map.md