New models and datasets, bug fixes, documentation updates

What's Changed

• Bug fixes and documentation updates
• Add depthwise convolution support to Conv1d, and depthwise ConvTranspose2d to MAX78002
• Updated face detection, KWS and cats & dogs models
• New action recognition model and Kinetics400 dataset
• New object detection model: Feature Pyramid Detector (FPN) - PascalVOC
• New Bayer2RGB network for debayerization

Bug fixes, documentation updates, model improvements

What's Changed

• Bug fixes
• Documentation updates
• Add support for pool dilation on MAX78002
• Add notebook to evaluate a trained KWS model with audio files

Full Changelog: 2022071...2022122

Object detection model; various improvements

• Object detection model and example
• Bug fixes
• Improved documentation
• Updated examples
• Updated submodules

Documentation updates and bug fixes

• Bug fixes
• Improved documentation

Please follow the instructions in README.md to upgrade (ignore the zip files under “Assets”).

Improved documentation and Windows support, bug fixes

Note: “develop” is now the default branch. The virtual environment is now in the “venv” folder.

• Documentation improvements
• Bug fixes
• Windows support (WSL2 and native)
• Dilated Conv1d
• Additional models and datasets
• Updated SDK

Please follow the instructions in README.md to upgrade (ignore the zip files under “Assets”).

Bug fixes, documentation improvements

• Minor bug fixes to training script
• Documentation improvements

Please follow the instructions in README.md to upgrade (ignore the zip files in the Release).

Network Architecture Search (NAS), updated Documentation, Bugfixes

•	Network Architecture Search (NAS)
•	Update documentation
•	Update models and data loaders
•	Bug fixes

Please follow the instructions in README.md to upgrade (ignore the zip files in the Release).

PyTorch 1.8.1, updated Documentation, Bugfixes

• Update documentation
• Upgrade to PyTorch 1.8.1
• ConvTranspose2d support
• Update models and data loaders
• Bug fixes

Please follow the instructions in README.md to upgrade (ignore the zip files in the Release).

Quantization-Aware Training, Python 3.8.6, Bugfixes

The main improvement in this release is enabling Quantization-Aware Training (QAT) by default.
Additionally, it upgrades to:

• PyTorch 1.71, Python 3.8.6, CUDA 11
  There is also a number of bug fixes and documentation improvements.

Please follow the instructions in README.md to upgrade (ignore the zip files in the Release).

Feather support

This 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).