huangyebiaoke/steel-pipe-weld-defect-detection
Deep Learning Based Steel Pipe Weld Defect Detection
Implements YOLOv5-based object detection to classify eight weld defect types (air holes, cracks, slag inclusions, etc.) with dual dataset formats (YOLO and PASCAL VOC 2007). Includes a curated benchmark dataset with 6,783 annotated steel pipe weld samples addressing severe class imbalance, enabling reproducible training and evaluation of defect detection models.
104 stars. No commits in the last 6 months.
Stars
104
Forks
25
Language
Jupyter Notebook
License
GPL-3.0
Category
Last pushed
Dec 06, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/huangyebiaoke/steel-pipe-weld-defect-detection"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
RajdeepBiswas/Manufacturing-Quality-Inspection
I have built the computer vision models in 3 different ways addressing different personas,...
LukeVassallo/RL_PCB
RL_PCB is a novel learning-based method for optimising the placement of circuit components on a...
utkarsh-ankit/Defect-Detection-of-PCB
A repository for creating a Deep Learning model for Defect Detection in PCBs and to design a Web...
khornlund/severstal-steel-defect-detection
Kaggle Segmentation Challenge
Elias-Arbash/PCBVision
A Multiscene RGB-Hyperspectral Benchmark Dataset of Printed Circuit Boards