A Detection Toolbox for Tensorflow2
-
Updated
Apr 27, 2023 - Python
A Detection Toolbox for Tensorflow2
Unsupervised anomaly detection system using PatchCore and ResNet-50 on the MVTec AD dataset. Achieves 96–100% accuracy with image- and pixel-level localization. Includes heatmap visualizations, segmentation maps, and GPU-accelerated inference.
Add a description, image, and links to the patch-core topic page so that developers can more easily learn about it.
To associate your repository with the patch-core topic, visit your repo's landing page and select "manage topics."