| --- |
| license: apache-2.0 |
| tags: |
| - computer-vision |
| - circuit-recognition |
| - deep-learning |
| - object-detection |
| - pose-estimation |
| pipeline_tag: image-classification |
| --- |
| |
| # HCD Circuit Recognition Weights |
|
|
| This repository hosts the pretrained weights for the paper: |
|
|
| **Deep Learning-Based Recognition and Structural Parsing of Hand-Drawn Circuit Diagrams** |
|
|
| ## Components |
|
|
| The repository contains pretrained weights for the following models used in the pipeline: |
|
|
| - YOLOv10 component detector |
| - PARSeq text recognition model |
| - HAWP wire/junction detection model |
| - DINOv2 component subtype classification model |
| - ViTPose endpoint semantic inference model |
|
|
| ## Files |
|
|
| - `weights_yolo_parseq.zip` – YOLOv10 + PARSeq weights |
| - `weights_hawp.zip` – HAWP junction detection weights |
| - `weights_dinov2.zip` – DINOv2 component subtype classifier weights |
| - `weights_vitpose.zip` – ViTPose endpoint semantic inference weights |
|
|
| SHA256 checksums are provided in `SHA256SUMS.txt`. |
