DeepSentry Book, Installation

Installation

This chapter covers all the ways to install and run DeepSentry. Choose the method that works best for your environment.

Prerequisites

Before starting, make sure you have:

Python 3.6+: The codebase uses Python 3.6 or newer. Check your version with python --version
Git: To clone the repository. Check with git --version
Bash or Zsh: For running shell scripts
~500 MB of disk space: For Python packages and sample models

Depending on your installation method, you may also need:

Docker (for Docker setup): Version 20.10+ recommended
CUDA/GPU support (optional): For training on GPUs, requires CUDA 11.0+ and NVIDIA GPU
Virtual environment (for local setup): Python venv or virtualenv

Method 1: Docker (Recommended for First-Time Users)

Docker is the easiest way to get started. It provides a complete, self-contained environment with all dependencies.

Step 1: Clone the Repository

git clone https://github.com/yourorg/deepsentry.git
cd deepsentry

Step 2: Build the Docker Image

bash docker_image_build.sh

This builds a Docker image with Python 3.8, TensorFlow, Keras, and all required dependencies.

Step 3: Verify the Installation

docker run -it deepsentry:latest python --version

Running Commands in Docker

Use the provided scripts in dockerrun/ to run training and evaluation.

Method 2: Local Installation with Virtual Environment

For development or local execution:

Step 1: Clone and Create Virtual Environment

git clone https://github.com/yourorg/deepsentry.git
cd deepsentry
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

Step 2: Install Dependencies

pip install --upgrade pip
pip install -r requirements.txt

Step 3: Verify Installation

python -c "import tensorflow; print(tensorflow.__version__)"
pytest t/ -v

Method 3: GPU Support

For NVIDIA GPU acceleration, install GPU-specific dependencies after Method 2:

pip install --upgrade tensorflow[and-cuda]
python -c "import tensorflow as tf; print(tf.config.list_physical_devices('GPU'))"

Project Structure

After installation:

deepsentry/
├── src/
│   ├── tx/               # Text encoding
│   ├── an/               # Anomaly detection
│   ├── live/             # Live monitoring
│   └── ...
├── ta/                   # Text autoencoder
├── kad/                  # Keras anomaly detector
├── dockerconfig/         # Config files
├── dockerrun/            # Run scripts
└── docs/                 # Documentation