readme.md

Violence GRU Model

Model Architecture

• Type: CNN-GRU Hybrid
• Components:
  • CNN Backbone: 4-Layer 2D CNN to extract spatial features from each frame.
  • Recurrent Unit: 2-Layer GRU (Gated Recurrent Unit) to model temporal dependencies.
  • Classifier: Fully Connected Layer.
• Input: Video sequence of 16 frames, resized to 112x112.
• Output: Binary Classification (Violence vs No-Violence).

Dataset Structure

The code expects a Dataset folder in the parent directory.

Dataset/
├── violence/
└── no-violence/

How to Run

1. Install dependencies: torch, opencv-python, scikit-learn, numpy.
2. Run python train.py.