Skip to content

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Repository files navigation

Factory Defect Detection

Unsupervised anomaly detection for factory parts, built around the MVTec AD dataset you already have downloaded. The idea: train a model only on images of good parts, then use it to flag anything that looks different at test time.

The first baseline implemented is a compact PatchCore-style model:

  1. A pretrained CNN (ResNet-18 by default) embeds every image into patch-level features.
  2. Training stores all patch features from the good images in a memory bank (optionally subsampled to a smaller "coreset").
  3. At inference, every test patch is scored by its k-nearest-neighbour distance to the memory bank. Far-from-normal patches are anomalous.
  4. Patch scores are upsampled to full image resolution and written as TIFF anomaly maps, ready for the official MVTec evaluation scripts.

Setup

python3 -m venv .venv
.venv/bin/pip install -r requirements.txt
.venv/bin/pip install -e . --no-deps

The pretrained backbone weights are downloaded automatically on first use. Everything runs on CPU out of the box; pass --device cuda when a GPU is available.

Quick start

Train, predict, and evaluate a single category end to end:

.venv/bin/factory-defect run --category metal_nut

Or run the steps separately:

# 1. Build the memory bank from good training images
.venv/bin/factory-defect train --category metal_nut

# 2. Score every test image and write anomaly maps
.venv/bin/factory-defect predict --category metal_nut

# 3. Compute official metrics (image AUROC + pixel-level AU-PRO)
.venv/bin/factory-defect evaluate --category metal_nut

Use --category all to process all 15 categories. Useful options:

  • --backbone wide_resnet50_2 — stronger (and slower) feature extractor
  • --coreset-ratio 0.1 — memory-bank size (default 10%)
  • --k-neighbors 9 — k for the kNN patch scoring
  • --max-train-images 50 — limit training images for quick experiments

Inspect the results visually:

.venv/bin/python scripts/visualize.py --category metal_nut

This writes side-by-side panels (input / ground truth / anomaly overlay) to outputs/visualizations/.

Charts and figures

Generate the full presentation figure set from the evaluation results:

.venv/bin/python scripts/plot_results.py

Figures are written to outputs/figures/:

File Shows
01_metrics_bar.png Grouped AUROC / AU-PRO bars per category
02_auroc_vs_aupro.png Detection vs. localization scatter
03_roc_curves.png All image-level ROC curves + mean
04_pro_curves.png All pixel-level PRO curves + mean
05_metrics_heatmap.png Annotated results matrix
06_examples_grid.png Input / ground truth / prediction panels
07_hardest_defects.png 15 hardest defect types by AUROC
08_model_comparison.png ResNet-18 → WRN-50-2 (random → greedy coreset)

Pixel-level curves are computed once with the official algorithm and cached compactly under outputs/metrics/<category>/curves.npz, so re-running the script is fast.

Jupyter notebook

A complete walkthrough of the project is in Factory_Defect_Detection.ipynb: environment and GPU check, dataset overview with example images, the PatchCore method, model inspection, reproduction commands, the full results table, every figure, model progression, per-defect-type analysis, and next steps.

Launch it from the project root:

.venv/bin/jupyter notebook Factory_Defect_Detection.ipynb

Most cells read the artifacts already in outputs/, so they run quickly. The only slow cell is the optional full-benchmark reproduction, which is guarded by RUN_FULL_BENCHMARK = False.

Outputs

Everything is written under outputs/:

Path Contents
outputs/checkpoints/<category>.pt Memory bank + model config
outputs/anomaly_maps/<category>/test/<defect>/<id>.tiff Full-resolution anomaly maps
outputs/predictions/<category>_scores.csv Per-image scores and labels
outputs/metrics/<category>/metrics.json Official evaluation results
outputs/metrics/summary.json Aggregated table across categories

Results

Best configuration so far: Wide-ResNet-50-2, 10% greedy coreset, k = 9, RTX 5070 Ti. Reproduce with:

.venv/bin/factory-defect run --category all --device cuda \
  --backbone wide_resnet50_2 --coreset-method greedy
category image AUROC AU-PRO
bottle 0.998 0.911
cable 0.928 0.875
capsule 0.924 0.929
carpet 0.991 0.940
grid 0.843 0.806
hazelnut 0.992 0.952
leather 0.998 0.968
metal_nut 0.971 0.822
pill 0.823 0.914
screw 0.849 0.924
tile 0.917 0.800
toothbrush 0.983 0.878
transistor 0.880 0.849
wood 0.985 0.838
zipper 0.920 0.905
mean 0.933 0.887

Progression across configurations:

configuration mean AUROC mean AU-PRO
ResNet-18, random coreset 0.835 0.801
WRN-50-2, random coreset 0.905 0.863
WRN-50-2, greedy coreset 0.933 0.887

The greedy coreset run is slow to train (roughly 15–20 minutes on GPU) because the farthest-point selection is sequential; the remaining categories can still be improved with a larger coreset ratio or higher-resolution input.

Note: a full run writes about 5 GB of anomaly maps plus checkpoints under outputs/ — that directory is git-ignored.

Project layout

src/factory_defect/
  cli.py       # train / predict / evaluate / run commands
  data.py      # MVTec dataset loaders and test metadata
  patchcore.py # feature extraction, memory bank, kNN scoring
  coreset.py   # random and farthest-point coreset selection
  constants.py # categories and backbone defaults
scripts/visualize.py  # anomaly-map visualization helper
mvtec_ad_evaluation/  # official MVTec evaluation scripts
mvtec_anomaly_detection/  # dataset

Roadmap / ideas

  • Swap in wide_resnet50_2 and compare metrics across all categories.
  • Add PaDiM or FastFlow-style baselines behind the same CLI.
  • Use the greedy coreset when you have a GPU (it is more faithful to PatchCore but slow on CPU).
  • Add image-level threshold selection on a validation split for deployment.
  • Note: MVTec AD is licensed for non-commercial research; check the license in mvtec_anomaly_detection/<category>/license.txt before any production use.

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages