Bot releases are hidden (Show)

lava-dl - Lava Deep Learning 0.3.3

Published by mgkwill over 1 year ago

What's Changed

Changing dependency of lava-nc back to main for development by @PhilippPlank in https://github.com/lava-nc/lava-dl/pull/124
Link to SDN tutorial in Pilotnet training tutorial by @weidel-p in https://github.com/lava-nc/lava-dl/pull/126
Cancel old CI run if new one is queued by @PhilippPlank in https://github.com/lava-nc/lava-dl/pull/128
Add netx support for rf.Dense and rf_iz.Dense by @Michaeljurado42 in https://github.com/lava-nc/lava-dl/pull/110
Stats printout by @bamsumit in https://github.com/lava-nc/lava-dl/pull/131
Small fix to check for complex synapse in create_dense by @Michaeljurado42 in https://github.com/lava-nc/lava-dl/pull/130
Link lava-dl decolle in readme by @bamsumit in https://github.com/lava-nc/lava-dl/pull/133
Changed pre-/post hooks by @PhilippPlank in https://github.com/lava-nc/lava-dl/pull/138
version change due to lava release by @PhilippPlank in https://github.com/lava-nc/lava-dl/pull/139
Version change back to main branch after release by @PhilippPlank in https://github.com/lava-nc/lava-dl/pull/141
updating Bandit to resolve dependabot alert by @michaelbeale-IL in https://github.com/lava-nc/lava-dl/pull/145
Dependabot fixes by @michaelbeale-IL in https://github.com/lava-nc/lava-dl/pull/146
Dependabot fixes by @michaelbeale-IL in https://github.com/lava-nc/lava-dl/pull/147
Benchmark notebooks updated to new callback_fx api in Loihi2HwCfg by @bamsumit in https://github.com/lava-nc/lava-dl/pull/152
Fixed Spikemax for moving window case by @Michaeljurado42 in https://github.com/lava-nc/lava-dl/pull/144
Fix for netx mishandling scalar input dimension by @bamsumit in https://github.com/lava-nc/lava-dl/pull/156
Update templates by @PhilippPlank in https://github.com/lava-nc/lava-dl/pull/157
Bump cryptography from 39.0.0 to 39.0.1 by @dependabot in https://github.com/lava-nc/lava-dl/pull/161
Persistent delay buffer to correctly run slayer blocks one timestep at a time by @bamsumit in https://github.com/lava-nc/lava-dl/pull/169
truncate weight matrix if min/max out of bounds by @stevenabreu7 in https://github.com/lava-nc/lava-dl/pull/171
Axonal delay as synaptic delay in NetX by @bamsumit in https://github.com/lava-nc/lava-dl/pull/173
Release 0.3.3 by @mgkwill in https://github.com/lava-nc/lava-dl/pull/184

New Contributors

@PhilippPlank made their first contribution in https://github.com/lava-nc/lava-dl/pull/124
@weidel-p made their first contribution in https://github.com/lava-nc/lava-dl/pull/126
@Michaeljurado42 made their first contribution in https://github.com/lava-nc/lava-dl/pull/110
@michaelbeale-IL made their first contribution in https://github.com/lava-nc/lava-dl/pull/145
@stevenabreu7 made their first contribution in https://github.com/lava-nc/lava-dl/pull/171

Full Changelog: https://github.com/lava-nc/lava-dl/compare/v0.3.2...v0.3.3

lava-dl - Lava Deep Learning 0.3.2

Published by PhilippPlank almost 2 years ago

Lava Deep Learning v0.3.2 Release Notes

New Features and Improvements

No new features or improvements in this release.

Bug Fixes and Other Changes

Updated dependency on lava-nc from main to version 0.5.1.

Breaking Changes

No breaking changes in this release.

Known Issues

No known issues in this release.

Thanks to our Contributors

Intel Labs Lava Developers

Full Changelog: https://github.com/lava-nc/lava-dl/compare/v0.3.1...v0.3.2

lava-dl - Lava Deep Learning 0.3.1

Published by mathisrichter almost 2 years ago

Lava Deep Learning v0.3.1 Release Notes

October 31, 2022

The lava-dl library version 0.3.1 now includes additional deep SNN inference and benchmarking tutorials.

New Features and Improvements

Merged a PilotNet LIF inference tutorial (#119)
Merged benchmarking tutorials for PilotNet SDNN and PilotNet LIF (#119)[^1]

Bug Fixes and Other Changes

Fixed issue with imports for recurrent tests (#112)
Fixed a bug for improper device configuration for lava.lib.dl.slayer neuron normalization (#116)

Breaking Changes

No breaking changes in this release.

Known Issues

Issue training with GPU for lava-dl-slayer on Windows machine.

Thanks to our Contributors

Intel Labs Lava Developers
Tobias Fischer
fangwei123456

Full Changelog: https://github.com/lava-nc/lava-dl/compare/v0.3.0...v0.3.1

[^1]: Intel Core i5-5257U with 32GB RAM, running Ubuntu 20.04.2 LTS with lava v0.5.1. Performance results are based on testing as of November 2022 and may not reflect all publicly available security updates. Results may vary.

lava-dl - Lava Deep Learning 0.3.0

Published by mgkwill about 2 years ago

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

Improved lava-dl SLAYER codebase with bugfixes and additional documentation (PR #78, #105)

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 https://github.com/lava-nc/lava-dl/pull/56
Update mnist.py by @uslumt in https://github.com/lava-nc/lava-dl/pull/71
Updated notebooks with new hyperparameters and typo fixes by @bamsumit in https://github.com/lava-nc/lava-dl/pull/76
Add pilotnet integration tests by @mgkwill in https://github.com/lava-nc/lava-dl/pull/79
Slayer fixes by @bamsumit in https://github.com/lava-nc/lava-dl/pull/78
Changes to lava-dl to reflect api changes in lava 0.4.0 by @bamsumit in https://github.com/lava-nc/lava-dl/pull/88
Added ConvT and Unpool block for neurons by @alexggener in https://github.com/lava-nc/lava-dl/pull/80
Update ci-build.yml, Remove redundant poetry updates by @mgkwill in https://github.com/lava-nc/lava-dl/pull/89
Recurrent mechanic by @timcheck in https://github.com/lava-nc/lava-dl/pull/103
Bump nbconvert from 6.5.0 to 6.5.1 by @dependabot in https://github.com/lava-nc/lava-dl/pull/93
fix bug of block.AbstractInput by @fangwei123456 in https://github.com/lava-nc/lava-dl/pull/105
Loihi Tutorials by @bamsumit in https://github.com/lava-nc/lava-dl/pull/107
Add conda install instructions with intel-numpy by @mgkwill in https://github.com/lava-nc/lava-dl/pull/91
Version 0.3.0 by @mgkwill in https://github.com/lava-nc/lava-dl/pull/109

New Contributors

@Tobias-Fischer made their first contribution in https://github.com/lava-nc/lava-dl/pull/56
@uslumt made their first contribution in https://github.com/lava-nc/lava-dl/pull/71
@alexggener made their first contribution in https://github.com/lava-nc/lava-dl/pull/80
@timcheck made their first contribution in https://github.com/lava-nc/lava-dl/pull/103
@dependabot made their first contribution in https://github.com/lava-nc/lava-dl/pull/93
@fangwei123456 made their first contribution in https://github.com/lava-nc/lava-dl/pull/105

Full Changelog: https://github.com/lava-nc/lava-dl/compare/v0.2.0...v0.3.0

lava-dl - Lava Deep Learning 0.2.0

Published by mgkwill over 2 years ago

The lava-dl library version 0.2.0 now supports automated generation of Lava processes for a trained network described by hdf5 network configuration using our Network Exchange (NetX) library.

New Features and Improvements

Released Network Exchange (NetX) library to support automated creation of Lava process for a deep network. We support hdf5 network exchange format. Support for more formats will be introduced in future. (PR #30, Issue #29)

Bug Fixes and Other Changes

Fixed bug with pre-hook quantization function on conv blocks (PR#13)

Breaking Changes

No breaking changes in this release

Known Issues

Issue training with GPU for lava-dl-slayer on Windows machine.

What's Changed

Create PULL_REQUEST_TEMPLATE.md & ISSUE_TEMPLATE.md by @mgkwill in https://github.com/lava-nc/lava-dl/pull/27
Hardware neuron parameters exchange and fixed precision instruction precision compatibility by @bamsumit in https://github.com/lava-nc/lava-dl/pull/25
Pilotnet link fix by @bamsumit in https://github.com/lava-nc/lava-dl/pull/31
Bugfix: CUBA neuron normalization applied to current state by @bamsumit in https://github.com/lava-nc/lava-dl/pull/35
Netx by @bamsumit in https://github.com/lava-nc/lava-dl/pull/30
Streamline PilotNet SNN notebook with RefPorts by @bamsumit in https://github.com/lava-nc/lava-dl/pull/37
Fix for failing tests/lava/lib/dl/netx/test_hdf5.py by @bamsumit in https://github.com/lava-nc/lava-dl/pull/44
Update ci-build.yml by @mgkwill in https://github.com/lava-nc/lava-dl/pull/42
Install by @mgkwill in https://github.com/lava-nc/lava-dl/pull/45
Lava Deep Learning 0.2.0 by @mgkwill in https://github.com/lava-nc/lava-dl/pull/46
Lava Deep Learning 0.2.0 - update lock by @mgkwill in https://github.com/lava-nc/lava-dl/pull/47

Full Changelog: https://github.com/lava-nc/lava-dl/compare/v0.1.1...v0.2.0

lava-dl - Lava Deep Learning v0.1.1

Published by mgkwill almost 3 years ago

Lava Deep Learning 0.1.1 is a bugfix dot release.

Features and Improvements

Added more content to tutorial_01. Some tuning guidelines of learning rates α and β for the QP solver have been added

Bug Fixes and Other Changes

Fixed bug with pre-hook quantization function on conv blocks. (PR#13)

Known Issues

No known issues at this point

What's Changed

Adding init.py to lava-dl/lava by @awintel in https://github.com/lava-nc/lava-dl/pull/10
Clean up of explicit namespace declaration by @bamsumit in https://github.com/lava-nc/lava-dl/pull/11
Fix Pool layer when pre_hook function is not None by @valmat07 in https://github.com/lava-nc/lava-dl/pull/13

New Contributors

@awintel made their first contribution in https://github.com/lava-nc/lava-dl/pull/10
@valmat07 made their first contribution in https://github.com/lava-nc/lava-dl/pull/13

Full Changelog: https://github.com/lava-nc/lava-dl/compare/v0.1.0...v0.1.1

lava-dl - Lava Deep Learning 0.1.0

Published by mgkwill almost 3 years ago

Lava Deep Learning Library

This first release of lava-dl under BSD-3 license provides two new modes of training deep event-based neural networks, either directly with SLAYER 2.0 or through hybrid ANN/SNN training using the Bootstrap module.

SLAYER 2.0 (lava.lib.dl.slayer) provides direct training of heterogenous event-based computational blocks with support for a variety of learnable neuron models, complex synaptic computation, arbitrary recurrent connection, and many more new features. The API provides high level building blocks that are fully autograd enabled and training utilities that make getting started with training SNNs extremely simple.

Bootstrap (lava.lib.dl.bootstrap) is a new training method for rate-coded SNNs. In contrast to prior ANNto-SNN conversion schemes, it relies on an equivalent “shadow” ANN during training to maintain fast training speed but to also accelerate SNN inference post-training dramatically with only few spikes. Although Bootstrap is currently separate from SLAYER, its API mirrors the familiar SLAYER API, enabling fast hybrid ANN-SNN training for minimal performance loss in ANN to SNN conversion.

At this point in time, Lava processes cannot be trained directly with backpropagation. Therefore, we will soon release the Network Exchange (lava.lib.dl.netx) module for automatic generation of Lava processes from SLAYER or Bootstrap-trained networks. At that point, networks trained with SLAYER or Bootstrap can be executed in Lava.

Open-source contributions to these libraries are highly welcome. You are invited to extend the collection neuron models supported by both SLAYER and Bootstrap. Check out the Neurons and Dynamics tutorial to learn how to create custom neuron models from the fundamental linear dynamics’ API.

New Features and Improvements

lava.lib.dl.slayer is an extension of SLAYER for natively training a combination of different neuron models and architectures including arbitrary recurrent connections. The library is fully autograd compatible with custom CUDA acceleration when supported by the hardware.
lava.lib.dl.bootstrap is a new training method for accelerated training of rate based SNN using dynamically estimated ANN as well as hybrid training with fully spiking layers for low latency rate coded SNNs.