Local CV pipeline dashboard

Inspect every stage of your run with Reticus

Dataset, training, results, inference — for image classification and object detection, on one machine. No account, no cloud; your data never leaves the box.

pip install "reticus[all]"
100% local Zero network calls Python 3.8+ MIT licensed

How it works

One dashboard, every stage of the pipeline

Add a handful of calls to your existing training script. Reticus sits beside your loop, reads values you already compute, and opens a live dashboard at 127.0.0.1:8765. Each stage below is a page you can open.

Get started

Running in five minutes

1

Install

Core is tiny (numpy + Pillow). Add [all] for the dashboard and Grad-CAM.

2

Add a few calls to your training script

Construct once, start_run, log each epoch, then end_run.

3

Watch it live

The dashboard opens automatically in your browser. Re-open later with reticus <project>.

InstallAddsUse when
reticusnumpy, PillowHeadless logging, no UI
reticus[dashboard]fastapi, uvicornThe local web dashboard
reticus[torch]torch, grad-camGrad-CAM heatmaps
reticus[all]everythingOne-shot full install
# train.py
from reticus import Reticus

r = Reticus("my_project")  # opens the dashboard
r.start_run(config={
    "task": "classification",
    "class_names": ["cat", "dog", "bird"],
})

for epoch in range(1, 11):
    r.log({
        "epoch": epoch,
        "train_loss": train_loss,
        "val_loss": val_loss,
        "val_acc": val_acc,
    }, total_epochs=10)

# after eval: per-class metrics, confusion matrix, ...
r.log_predictions(
    images=val_images, class_names=CLASSES,
    task="classification", preds=preds, targets=targets,
)
r.end_run()

Object detection works the same way — pass task="od" with boxes in YOLO, COCO, VOC, or xyxy format.

Why local

Your training data never leaves the machine

No cloud, no account

The server binds to 127.0.0.1 only. No login, no telemetry, no external services.

Zero network calls

Charts, fonts, and reports are all bundled. Works fully offline, air-gapped if you need.

CV-specific out of the box

Box overlays, Grad-CAM, dataset health checks, and quality flags — not a generic logger.