Lava Deep Learning 0.3.0
The lava-dl library version 0.3.0 now enables inference for trained spiking networks seamlessly on CPU or Loihi 2 backends and can leverage Loihi 2’s convolutional network compression and graded spike features for improved memory usage and performance.
New Features and Improvements
- Added Loihi 2 support in lava-dl NetX utilizing Loihi 2 convolution support and graded spikes (PR #88, #107).
- Added a tutorial demonstrating PilotNet application running on Intel Loihi 2 (PR #107).
- Added accelerated training of recurrent topologies in lava-dl SLAYER (PR #103)
- Added Transposed Convolution and Unpool support in lava-dl SLAYER (PR #80)
Bug Fixes and Other Changes
Breaking Changes
- No breaking changes in this release
Known Issues
- Issue training with GPU for lava-dl-slayer on Windows machine.
What's Changed
- Remove unnecessary imports by @Tobias-Fischer in #56
- Update mnist.py by @uslumt in #71
- Updated notebooks with new hyperparameters and typo fixes by @bamsumit in #76
- Add pilotnet integration tests by @mgkwill in #79
- Slayer fixes by @bamsumit in #78
- Changes to lava-dl to reflect api changes in lava 0.4.0 by @bamsumit in #88
- Added ConvT and Unpool block for neurons by @alexggener in #80
- Update ci-build.yml, Remove redundant poetry updates by @mgkwill in #89
- Recurrent mechanic by @timcheck in #103
- Bump nbconvert from 6.5.0 to 6.5.1 by @dependabot in #93
- fix bug of
block.AbstractInput
by @fangwei123456 in #105 - Loihi Tutorials by @bamsumit in #107
- Add conda install instructions with intel-numpy by @mgkwill in #91
- Version 0.3.0 by @mgkwill in #109
New Contributors
- @Tobias-Fischer made their first contribution in #56
- @uslumt made their first contribution in #71
- @alexggener made their first contribution in #80
- @timcheck made their first contribution in #103
- @dependabot made their first contribution in #93
- @fangwei123456 made their first contribution in #105
Full Changelog: v0.2.0...v0.3.0