Runs in your browser · nothing uploaded

Spot a road accident
in 30 milliseconds

Rakshak is an open-source computer-vision model that tells an accident scene apart from ordinary traffic. Train it on your own footage in minutes on a laptop CPU, then ship it to Python, the edge, or straight into a web page.

—Test accuracy
—Accident recall
~6 MBONNX model
0Images uploaded
Live demo

Try it on a real photo

The model is downloaded once and runs inside this tab with onnxruntime-web. Your image is never sent anywhere.

Selected road scene
Drop a road photo here or click to browse · JPG, PNG, WebP

Or try a sample

?
Waiting for an image Pick a photo to see the prediction
Loading…
Research preview. Rakshak is trained on a few hundred public web images. It is a solid demonstration of the pipeline, not a safety-certified system — do not use it as the only trigger for emergency response.
Why it exists

Small, honest, and actually runnable

Most accident-detection repos are a notebook that no longer runs. This one is a package, a test suite, and a model you can execute right now.

⚡

Trains in minutes on CPU

Two-phase transfer learning on a frozen ImageNet backbone. No GPU required, and the whole run finishes while you make coffee.

📦

One command each way

rakshak train, evaluate, predict and export. Or import AccidentDetector and call .predict().

🌐

Runs anywhere ONNX runs

Export folds normalisation and softmax into the graph, so browsers, mobile and edge runtimes all get identical numbers to Python.

🔍

Metrics that matter

Precision, recall, F1 and ROC-AUC on the accident class — not just accuracy, which hides exactly the errors you care about.

🧪

Tested, not hoped

66 tests cover the data split, the freezing logic, checkpoint round-trips, ONNX export and the CLI. CI runs them on every push.

🗂️

Bring your own data

Point it at any two-folder dataset. Folder names are matched loosely, and class weights adjust automatically if your split is skewed.

Pipeline

How it works

Five steps from a folder of photos to a model running in a web page.

Collect

rakshak scrape pulls openly licensed images and records the licence for each one.

Split

Validation is carved out of Train with a fixed seed, so Test stays genuinely held out.

Train head

The backbone is frozen and only the classifier learns — the key trick for a few-hundred-image dataset.

Fine-tune

Everything unfreezes at a 10× lower learning rate to adapt the features without destroying them.

Export

The best checkpoint becomes ONNX, verified against PyTorch to 1e-4 before it ships.

Benchmarks

Results on the held-out test set

Measured on 100 images the model never saw during training or validation. Reproduce with rakshak evaluate --split Test.

Metric Score What it means
Accuracy — Share of all test images classified correctly
Recall (accident) — Share of real accidents the model catches
Precision (accident) — Share of accident alerts that are correct
F1 (accident) — Balance of precision and recall
ROC AUC — Ranking quality across every threshold
Quickstart

Running in under a minute

terminal
# Install
git clone https://github.com/4ryanwalia/Rakshak---Car.git
cd Rakshak---Car
pip install -e ".[onnx]"

# Train on the bundled dataset (CPU is fine)
rakshak train --epochs 12 --finetune-epochs 8

# Score it on the held-out test set
rakshak evaluate --split Test

# Classify anything
rakshak predict my_dashcam_frame.jpg
python
from rakshak import AccidentDetector

detector = AccidentDetector.from_checkpoint("models/rakshak.pt")
result = detector.predict("scene.jpg")

print(result.label)                 # 'accident'
print(result.accident_probability)  # 0.94

# Whole folder in batches
for r in detector.predict_dir("frames/"):
    if r.is_accident:
        alert(r.path, r.confidence)

Help Rakshak grow up

The roadmap is video and dashcam streams, severity grading, and a dataset with properly licensed images at scale. Stars help people find it; sponsorship pays for the compute and the data work.