RecoilNet

RecoilNet is a wrapper for Meta's Mask R-CNN designed for efficient track detection on CR39 scans.
It provides a streamlined interface for detecting tracks on CR39 detectros scans with high accuracy and speed.

---

• 🧩 Supports HPC workflows with easyHPC.

---

Remember to download the pre-trained model
and place it inside the models/ directory:

📥 Installation

1. Clone the repository (with submodules):

   git clone --recurse-submodules https://github.com/yourusername/RecoilNet.git
   cd RecoilNet

If you already cloned without submodules, run:

  git submodule update --init --recursive  

2. Install the packages:

  pip install -r requirements.txt

3. Install Detectron2:

  python -m pip install --no-build-isolation 'git+https://github.com/facebookresearch/detectron2.git'

4 Run the application:

  python main.py