v0.5.23

Lux v0.5.23

Diff since v0.5.22

Merged pull requests:

• CompatHelper: add new compat entry for MLUtils at version 0.4 for package SimpleChains, (keep existing compat) (#530) (@github-actions[bot])
• Move replicate to LuxCore (#532) (@MartinuzziFrancesco)
• Fix #534 (#535) (@avik-pal)

Closed issues:

• Should replicate be part of LuxCore? (#531)
• pad=SamePad() does not work as intended in ConvTranspose. (#534)

v0.5.22

Lux v0.5.22

Diff since v0.5.21

Merged pull requests:

• New Interface to switch between frameworks (#529) (@avik-pal)

v0.5.21

Lux v0.5.21

Diff since v0.5.20

Merged pull requests:

• General Quality of Life Enhancements (#521) (@avik-pal)
• CompatHelper: add new compat entry for Literate at version 2 for package Basics, (keep existing compat) (#522) (@github-actions[bot])
• CompatHelper: add new compat entry for Literate at version 2 for package BayesianNN, (keep existing compat) (#523) (@github-actions[bot])
• CompatHelper: add new compat entry for Literate at version 2 for package GravitationalWaveForm, (keep existing compat) (#524) (@github-actions[bot])
• CompatHelper: add new compat entry for Literate at version 2 for package HyperNet, (keep existing compat) (#525) (@github-actions[bot])
• CompatHelper: add new compat entry for Literate at version 2 for package NeuralODE, (keep existing compat) (#526) (@github-actions[bot])
• CompatHelper: add new compat entry for Literate at version 2 for package PolynomialFitting, (keep existing compat) (#527) (@github-actions[bot])
• CompatHelper: add new compat entry for Literate at version 2 for package SimpleRNN, (keep existing compat) (#528) (@github-actions[bot])

Closed issues:

• Bug in ConvTranspose? (#455)
• Support for MultiRNNCell (#472)
• Recurrent Layers don't take Vectors as Input (#478)

v0.5.20

Lux v0.5.20

Diff since v0.5.19

Merged pull requests:

• fixes ImageNet, SimpleRNN examples (#504) (@avik-pal)
• Documentation Fixes (#505) (@avik-pal)
• Fix tutorial numbering (#509) (@avik-pal)
• CompatHelper: add new compat entry for LuxAMDGPU at version 0.2 for package Basics, (keep existing compat) (#510) (@github-actions[bot])
• CompatHelper: add new compat entry for Metalhead at version 0.9 for package ImageNet, (keep existing compat) (#511) (@github-actions[bot])
• CompatHelper: add new compat entry for Flux at version 0.14 for package ImageNet, (keep existing compat) (#512) (@github-actions[bot])
• Patches (#519) (@avik-pal)
• Docs Again (#520) (@avik-pal)

Closed issues:

• Documentation Enhancement Suggestions (#387)
• How to choose a specific GPU device (#480)
• AMDGPU CI takes a lot of time (#495)
• SimpleRNN example is broken on AMDGPU (#498)
• Bayesian NN example throws Pkg Extension load errors (#507)
• 404 many Tutorial links are invalid (#508)
• uninitiated tutorial replicate part shows different numbers but should show the same (#513)
• uninitiated tutorial - Code Font confusing for pipe |> (#514)
• Documentation Request: Also list GeometricML.jl and SciML.ai under Ecosystem (#518)

v0.5.19

Lux v0.5.19

Diff since v0.5.18

Merged pull requests:

• Add outputsize for Chain (#503) (@SebastianM-C)

Closed issues:

• Gradients of shared parameters do not behave as expected (#420)
• Support for multi-core CPUs? (#502)

v0.5.18

Lux v0.5.18

Diff since v0.5.17

Merged pull requests:

• Add output lengths for layers (#491) (@SebastianM-C)
• Format code (#493) (@avik-pal)
• Move Stateful lux layer out of experimental (#497) (@avik-pal)

v0.5.17

Lux v0.5.17

Diff since v0.5.16

Merged pull requests:

• Parallel Testing + Distributed Docs build (#490) (@avik-pal)

v0.5.16

Lux v0.5.16

Diff since v0.5.15

Merged pull requests:

• Remove extensions in favor of GPUArraysCore (#488) (@avik-pal)

v0.5.15

Lux v0.5.15

Diff since v0.5.14

Merged pull requests:

• Bump actions/cache from 3 to 4 (#479) (@dependabot[bot])
• Bump codecov/codecov-action from 3 to 4 (#484) (@dependabot[bot])
• Bump peter-evans/create-pull-request from 5 to 6 (#485) (@dependabot[bot])
• Drop 1.6 support + Patches to Fix Tests (#487) (@avik-pal)

Closed issues:

• Training in batches and building gradient as mean of individual gradients (#481)
• No Gradients with respect to parameters using Custom Layers (#483)
• Where is the API doc for activatations (#486)

v0.5.14

Lux v0.5.14

Diff since v0.5.13

Merged pull requests:

• CompatHelper: bump compat for Adapt to 4, (keep existing compat) (#470) (@github-actions[bot])
• Patch Metal Recurrent Neural Networks (#474) (@avik-pal)

Closed issues:

• GPU evaluation of Recurrence() broken on Metal (#473)