Pipeline training and inference Anomalib models UI in Anomaly Detection

Optimized PaDim based on Anodet

Repo public pour le challenge IA de Valeo. Ne contient pas les données disponibles sur le site du challenge : https://challengedata.ens.fr/challenges/157 . Pour les fichiers contenants les paramètres des modèles, contacter tristanscuillereng@gmail.com

Anomaly detection pipeline for industrial surface inspection using the MVTec AD dataset. Includes classical computer vision baselines, autoencoder models, and PaDiM-based feature embeddings for detecting subtle manufacturing defects.

detect and segment anomalies on wood surfaces using unsupervised deep learning models

PaDiM-inspired anomaly detection for AWS infrastructure metrics (CloudWatch + Cost Explorer)

Anomaly Detection with Localization developed for the Machine Learning for Vision and Multimedia course @polito. Tech stack: PyTorch, Python.

A PyTorch-based framework for unsupervised anomaly detection on the MVTec AD dataset. Implements PaDiM, PatchCore, FastFlow, and AutoEncoder models with utilities for dataset preparation, training, evaluation, and reporting.