Command line

All commands: imgad <command> -h shows every option.

imgad list
imgad fit --model openai/clip-vit-base-patch16 --detector knn -p k=1 --prep l2 \
          --train data/bottle/train/good --out bottle.joblib

# inference: images and/or folders; output to stdout, .csv or .json
imgad predict --model bottle.joblib new.png data/bottle/test --out preds.csv
imgad predict --model bottle.joblib folder/ --only-anomalies --threshold 0.02 --device cpu

# re-tune the threshold on labelled validation data (f1 | youden | fpr | tpr)
imgad calibrate --model bottle.joblib --normal val/good --anomalous val/defects --method f1 --out bottle_cal.joblib
imgad info --model bottle_cal.joblib         # configuration, threshold and metadata

imgad benchmark --config configs/mvtec_benchmark.yaml --out results.csv --report report/ --log-file run.log
imgad benchmark --config configs/mvtec_benchmark.yaml -j 8 --devices auto   # parallel, several models per GPU
imgad devices                                # GPUs, free memory and parallel plan

# gated Hugging Face models (see [Gated Hugging Face models](gated-models.md))
imgad hf-login
imgad hf-check facebook/dinov3-vitb16-pretrain-lvd1689m

# Anomalib models: -p sets the model kwargs; predict saves heatmaps and masks
imgad fit --anomalib patchcore -p backbone=wide_resnet50_2 "layers=[layer2,layer3]" \
          --image-size 256 --train data/bottle/train/good --out bottle_pc.joblib
imgad predict --model bottle_pc.joblib data/bottle/test --maps-dir maps/ --out preds.csv

Commands

Command	What it does
imgad list	available extractors, detectors, preprocessing steps and Anomalib models
imgad fit	train a feature pipeline (--model) or an Anomalib model (--anomalib) on normal images
imgad predict	score images/folders; --maps-dir saves heatmaps and masks (Anomalib)
imgad calibrate	re-tune the threshold on labelled validation images
imgad info	configuration, threshold and metadata of a saved model
imgad benchmark	run a YAML grid; --report, --stats, -j/--devices (parallel), --intensity, --k-shots (few-shot protocol), --stop-on-error
imgad report	rebuild a report from benchmark --scores-out
imgad stats	statistical comparison of saved results
imgad devices	GPUs, free memory and memory estimate per model
imgad models	recommended medical feature extractors per modality (-m), --check, --yaml, --zero-shot (vision–language models) (Medical imaging)
imgad hf-login / hf-logout / hf-check	tokens and access to gated Hugging Face models