IIoT-LogicNets: LogicNets for IIoT Network Intrusion Detection

LogicNets is a methodology for designing, training and deploying sparse, quantized neural networks based on hardware building blocks. They are able to achieve extremely high throughput and low latency on Xilinx FPGAs.

Prerequisites

• Python>=3
• PyTorch
• Brevitas
• Verilator
• PyVerilator
• oh-my-xilinx
• Vivado Design Suite

Installation

Follow the steps below to install LogicNets within a docker container:

1. Install Vivado Design Suite
2. Install docker.
3. Clone the LogicNets repository using: git clone [email protected]:DarthHyperion/IIoT-LogicNets.git
4. Create an environment variable VIVADO_SETTINGS_FILE which points to the settings64.sh in your Vivado installation (e.g., export VIVADO_SETTINGS_FILE=/path/to/Vivado/settings64.sh)
5. (Optional): Set your XILINXD_LICENSE_FILE or LM_LICENSE_FILE variables to point to a specific license server
6. Run ./docker/run-docker.sh from the root directory of the repository
7. (Optional): Copy your Vivado license file over to the running docker container

You are now ready to run an example, browse to /workspace/logicnets/experiments/binary_classification/