Skip to content

Getting Started

Anubha Parashar edited this page Aug 10, 2026 · 1 revision

Getting Started

Before running the project

The public repository contains the core Python package, adapters, configs, scripts, tests, Docker assets and technical notes. Raw datasets, large model checkpoints and generated experiment outputs are intentionally excluded.

Expected top-level components include:

adapters/
app/
configs/
docs/
incidentgraph/
scripts/
tests/
requirements.txt
requirements-deep.txt
pyproject.toml
Dockerfile
docker-compose.yml

Windows setup

git clone https://github.com/dranubhaparashar/IncidentGraph.git
cd IncidentGraph

python -m venv .venv
Set-ExecutionPolicy -Scope Process -ExecutionPolicy RemoteSigned
.\.venv\Scripts\Activate.ps1
python -m pip install --upgrade pip
pip install -r requirements.txt

For deep-learning dependencies:

pip install -r requirements-deep.txt

The repository also includes scripts/install_deep_windows.ps1; review it before execution when adapting the environment.

Verify the software layer

python -m pytest -q

Discover the available CLIs

python .\scripts\benchmark.py --help
python .\scripts\train_meva_activity.py --help
python .\scripts\train_meva_activity_resumable.py --help
python .\scripts\evaluate_meva_activity.py --help

Real-MEVA workflow

The codebase contains dedicated scripts for:

  1. downloading official annotations;
  2. downloading/preparing an annotated subset;
  3. inventorying annotations;
  4. building the activity manifest;
  5. rebalancing the split at video level when required;
  6. training and resumable training;
  7. evaluation and extended evaluation.

Read docs/REAL_MEVA_AND_DEEP_TRAINING.md before a long run.

Controlled diagnostic workflow

The synthetic/system path uses configs/synthetic.yaml, scripts/generate_synthetic.py, scripts/benchmark.py, and the matching incidentgraph modules.

Warning

The controlled benchmark is a software/evaluation diagnostic, not a substitute for independent real multi-camera validation.

Data hygiene

Keep raw video, private evidence, model checkpoints and generated outputs outside normal Git tracking. The repository .gitignore is intended to exclude these classes of files.

Clone this wiki locally