# InfinitySearch Docker & Fashion-MNIST

Runs **InfinitySearch** (formerly QGNN) on 10 000 Fashion-MNIST images (80 % train / 20 % batch query), then prints queries/sec and mean Rank Order error.

---

## Prerequisites

- **Docker**  
  Install from https://docs.docker.com/get-docker/

---

## Files

- **`infinity_search.py`**  
  Full implementation (training, indexing, querying)  
- **`vp_tree_bind.cpp`** & **`vp_tree_q.hpp`**  
  VP-Tree C++/pybind11 extension sources  
- **`Dockerfile`**  
  Builds the image, installs dependencies, compiles the extension, and sets the entrypoint

---

## Build & Run

```bash
# 1. Build the Docker image
docker build -t infinitysearch:latest .

# 2. Run the container
docker run --rm infinitysearch:latest
