Back to directory

ADI MAX78000/MAX78002 Model Training and Synthesis

A model-training and code-synthesis toolchain for Analog Devices' MAX78000 and MAX78002 ultra-low-power machine-learning accelerator chips, converting a trained PyTorch model into C code for the device.

ADI MAX78000/MAX78002 Model Training and Synthesis

This repository is the synthesis half of a five-repository project for Analog Devices' MAX78000 and MAX78002 edge AI chips: a companion training repository handles model development and training in PyTorch, while this repository's "izer" tool converts a trained model into C code that runs on the device. A software development kit repository supplies drivers and example programs for the evaluation kits, and a reference-design repository provides host and sample applications such as a camera reference design.

The project documents installation requirements, including a specific PyTorch version, and file-system layout expectations for combining the training and synthesis repositories with the software development kit. Support for TensorFlow and Keras is deprecated in favor of PyTorch.

It is written in Python and released under the Apache-2.0 license.

More in Models

See all 405
  • mini-AGI

    github.com

    A continual learning language model that trains from scratch on a single 8 GB VRAM GPU, assembling its own architecture and adapting its size to the hardware and data available rather than shipping as a fixed pretrained model.

  • An open-source contrastive-embedding pipeline that maps technical CVE vulnerability descriptions to formal cybersecurity compliance controls in NIST SP 800-53 and CMMC, published with its model generation, fine-tuning and evaluation code.

  • peekaboolean

    github.com

    A small vision-language model, fine-tuned with LoRA on a 500-million-parameter backbone, that answers typed multiple-choice, ordinal-score and yes/no questions about an image with calibrated probabilities, in about 400 milliseconds on a laptop.