Megan Moscony – Software Engineer

The Deepwave Digital team is happy to announce a new release of AirPack that adds deep learning source code using PyTorch. PyTorch is the fastest growing training framework in AI and deep neural networks (DNN). This new release provides source code and documentation to walk you through training, optimizing, and deploying a convolutional neural network (CNN) to detect and classify radio frequency signals using either PyTorch, TensorFlow2, or TensorFlow1.

AirPack is a comprehensive introductory solution for developers who are looking to integrate deep learning classifiers into software defined radio systems. This software package will provide you with all of the tools you need to build and deploy your first neural network on the AIR-T in less than an hour.

The AirPack package contains:

• Custom Docker file to easily build the training environment
• Labeled synthetic training data
• Python source code for a TensorFlow or PyTorch CNN model
• Data reader Python classes for TensorFlow and PyTorch
• Python script to train the model
• Python script to perform inference
• Toolkit to deploy the trained model on the AIR-T

Check out the documentation site to learn more, submit an inquiry to purchase, or download the new release from the developer portal if you are already an AirPack customer with active support and Maintenance.