anomaly-detection

Computer-vision anomaly detection for industrial manufacturing defect inspection.
Anomaly detection app: input image, heatmap, mask and segmentation of a defective hazelnut
/ Overview
N. 01
A web pipeline for training and inference on Anomalib models, with a UI for MVTec-style datasets and per-image predictions.
Role
Author
Year
2022
Stack
Python, PyTorch, Flask
Final Result
N. 02
Source on GitHub; details in the Anomalib discussion forum.
/ Details
N. 03

This project showcases an end-to-end training and inference pipeline build on top of Anomalib. It provides a web-based UI for uploading MVTec style datasets and training them on the available Anomalib models. It also has sections for calling inference on individual images as well as listing all the images with their predictions in the database.

You can view the project on Github For more details see the Discussion forum

Technology used

image

App Flask

python app.py

Open local URL: http://127.0.0.1:5000

Default account login:

  • Username: anomalib
  • Password: anomalib

Models supported: image

Login: image

Signup: image

Homepage: image

Train: image

Inference: image

Database: image

/ More Projects
N. 04
Kilomet homepage: a trail runner on a green mountain slope with the headline "Đồng hành cùng runner trên hành trình chạy bộ"
kilomet.com.vn
/2026
Terminal output of the website-kit new-poc.sh script listing nine modules and creating a repo from github-pages/astro
website-kit
/2026
Close-up of textured black sand with subtle wave-like patterns and small sparkling grains.
Have a project in mind?
Let’s Talk
Email me