analogdevicesinc/ai8x-synthesis
Quantization and Synthesis (Device Specific Code Generation) for ADI's MAX78000 and MAX78002 Edge AI Devices
11 Releases
Latest: 1y ago
Final PyTorch 1.8 Release20240705Latest
rotx-eva·1y ago·July 5, 2024📋 What's Changed
- Updated FaceID by @oguzhanbsolak in https://github.com/analogdevicesinc/ai8x-synthesis/pull/322
- Add NAS KWS model (trained using dynamic augmentation) by @alicangok in https://github.com/analogdevicesinc/ai8x-synthesis/pull/324
- Add Autoencoder Model by @asyatrhl in https://github.com/analogdevicesinc/ai8x-synthesis/pull/329
- Fix pooling when the operator is None and the input is 1d by @ermanok in https://github.com/analogdevicesinc/ai8x-synthesis/pull/343
- Scripts, Logs & Trained Model Files for MSnoise Mixed Trained NAS & v3 models by @EyubogluMerve in https://github.com/analogdevicesinc/ai8x-synthesis/pull/332
- Final PyTorch 1.8 release - freeze requirements by @rotx-maxim in https://github.com/analogdevicesinc/ai8x-synthesis/pull/349
- Documentation updates
- Bug fixes
- + 1 more
Updated and new pre--trained weights; bug fixes and documentation updates20231219
rotx-eva·2y ago·December 19, 2023📋 What's Changed
- Bug fixes and documentation updates
- New and updated pre-trained weights for Face detection, Feature Pyramid Detector - PASCAL VOC, Action Recognition model, Bayer2RGB model, Cats&Dogs model, KWSv3
- Add support for cropping (in_crop)
- Ubuntu 22.04 support
Bug fixes, documentation updates, weight deduplication, latency estimates20221220
rotx-eva·3y ago·December 20, 2022📋 What's Changed
- Bug fixes
- Documentation updates
- Link to latest SDK
- Allow multiple output layers to have mixed output widths
- Add latency estimates for MAX78000
- Add weight deduplication for MAX78000 and MAX78002
- Update VSCode & Makefile project generators
- Full Changelog: https://github.com/MaximIntegratedAI/ai8x-synthesis/compare/20220711...20221220
Object detection model; various improvements20220711
rotx-eva·3y ago·July 12, 2022📋 Changes
- Object detection model and example
- Bug fixes
- Improved default settings
- Improved documentation
- Updated examples
- Updated submodules
Updates to SDK, MAX78002, Documentation20220420
rotx-eva·4y ago·April 20, 2022📋 Changes
- SDK updates
- MAX78002 support / bug fixes
- Improved documentation
Improved documentation and Windows support, bug fixes20211217
rotx-eva·4y ago·December 20, 2021📋 Changes
- Documentation improvements
- Bug fixes
- Windows support (WSL2 and native)
- Dilated Conv1d
- Additional models and datasets
- Updated SDK
Improved documentation, bug fixes20210813
rotx-eva·4y ago·August 19, 2021📋 Changes
- Documentation improvements
- Bug fixes
- Built-in update checker
Updated SDK and Documentation, Bugfixes20210624
rotx-eva·5y ago·June 24, 2021• Update documentation • Update SDK • Update models • Improve kernel memory allocation • Bug fixes Please follow the instructions in README.md to upgrade (ignore the zip files in the Release).
PyTorch 1.8.1, updated SDK and Documentation, Bugfixes20210422Pre-release
rotx-eva·5y ago·April 22, 2021📋 Changes
- Update documentation
- Update SDK
- Upgrade to PyTorch 1.8.1
- ConvTranspose2d support
- Update models
- Improve bias memory allocation
- Bug fixes
QAT, updated SDK, Bugfixes20210126Pre-release
rotx-eva·5y ago·January 26, 2021📋 Changes
- PyTorch 1.71, Python 3.8.6, CUDA 11
Feather Support20201106Pre-release
rotx-eva·5y ago·November 9, 2020This release adds support for the Feather evaluation board, plus a number of smaller improvements. To upgrade, please follow the instructions in the README.md file (instead of downloading the archive).