Code of kaggle semantic segmentation competition: Steel Defect Detection.
-
Updated
Mar 7, 2022 - Python
Code of kaggle semantic segmentation competition: Steel Defect Detection.
This repo contains implementation of deep learning-based steel surface defect segmentation models. Extensive experiments on several deep learning frameworks have been presented with various performance analysis and comparison.
This repo contains implementation of semi-supervised defect segmentation based on pairwise similarity map consistency and ensemble-based cross pseudo labels
Open-source YOLOv8 steel surface defect detection project with training, inference, GUI, and Apple Silicon support.
Steel defect detection using 2 type of steel databased (NEU and Severstal)
CNN-based steel surface defect detection using NEU dataset, OpenCV preprocessing, and labeled output visualizations. Achieves ~96% accuracy.
Computer vision notebooks for Severstal steel defect detection and segmentation experiments.
SA-MoE-DefectDet: steel surface defect detection with morphology-aware sparse expert fusion on NEU-DET.
Steel surface defect detection using YOLOv8m on the Severstal dataset. Full pipeline: RLE-to-bbox conversion, image tiling, stratified splitting, custom balanced sampling, and Gradio deployment on HuggingFace Spaces.
End-to-end deep learning application for steel surface defect detection using TensorFlow, FastAPI, Streamlit, and Docker.
Code of Steel Defect Detection semantic segmentation.
🔍Explore steel plate defect prediction with EDA, modelling, and multi-class classification 🛠
AI-powered steel surface inspection system featuring defect diagnosis, GradCAM explainability, severity assessment, root cause analysis, and industrial risk evaluation.
A machine learning classification project aimed to predict faults on industrial steel plates.
Add a description, image, and links to the steel-defect-detection topic page so that developers can more easily learn about it.
To associate your repository with the steel-defect-detection topic, visit your repo's landing page and select "manage topics."