# \#deep-learning

**URL:** https://discourse.julialang.org/tag/deep-learning/1606.md

[Latest](https://discourse.julialang.org/latest.md) · [Categories](https://discourse.julialang.org/categories.md) · [Tags](https://discourse.julialang.org/tags.md)

---

## [Human pose estimation?](https://discourse.julialang.org/t/human-pose-estimation/136513)

<div class="topic-metadata">

**Author:** [@mahmah](https://discourse.julialang.org/u/mahmah)\
**Replies:** 2\
**Last updated:** [April 2, 2026, 9:15pm UTC](https://discourse.julialang.org/t/human-pose-estimation/136513 "2026-04-02T21:15:04Z")

</div>

Is there any package for human pose estimation written in Julia?

---

## [Reactant.jl + Enzyme: ~10 min compilation overhead triggered by hidden-to-hidden Dense layers](https://discourse.julialang.org/t/reactant-jl-enzyme-10-min-compilation-overhead-triggered-by-hidden-to-hidden-dense-layers/136374)

<div class="topic-metadata">

**Author:** [@Yuan-Ru-Lin](https://discourse.julialang.org/u/Yuan-Ru-Lin)\
**Replies:** 1\
**Last updated:** [March 27, 2026, 11:22am UTC](https://discourse.julialang.org/t/reactant-jl-enzyme-10-min-compilation-overhead-triggered-by-hidden-to-hidden-dense-layers/136374 "2026-03-27T11:22:11Z")

</div>

I’ve been investigating compilation times with Reactant.jl + Lux + AutoEnzyme() on an NVIDIA GPU and found a reproducible jump in TTFT (Time-To-First-Training) when a model includes hidden-to-hidden Dense layers. Minima…

---

## [Reinforcement learning packages for CartPole example with Julia v1.11 or v1.10?](https://discourse.julialang.org/t/reinforcement-learning-packages-for-cartpole-example-with-julia-v1-11-or-v1-10/125261)

<div class="topic-metadata">

**Author:** [@greatpet](https://discourse.julialang.org/u/greatpet)\
**Replies:** 2\
**Last updated:** [January 28, 2025, 11:10am UTC](https://discourse.julialang.org/t/reinforcement-learning-packages-for-cartpole-example-with-julia-v1-11-or-v1-10/125261 "2025-01-28T11:10:16Z")

</div>

I’ve been looking at reinforcement learning packages in Julia. Some of them are unfortunately slightly out of maintenance and have broken dependencies. Does anyone have a fully working CartPole training example (a well k…

---

## [Options for simple board game GUI](https://discourse.julialang.org/t/options-for-simple-board-game-gui/119851)

<div class="topic-metadata">

**Author:** [@greatpet](https://discourse.julialang.org/u/greatpet)\
**Replies:** 2\
**Last updated:** [September 26, 2024, 7:04am UTC](https://discourse.julialang.org/t/options-for-simple-board-game-gui/119851 "2024-09-26T07:04:50Z")

</div>

I’d like to explore ReinforcementLearning.jl and AlphaZero.jl for playing board games with AI, and I’d like to visualize the games and allow a human player to place pieces on the board. Therefore, I’d like to make an ext…

---

## [AutoEncoderToolkit.jl - A package for training (Variational) Autoencoders](https://discourse.julialang.org/t/autoencodertoolkit-jl-a-package-for-training-variational-autoencoders/115985)

<div class="topic-metadata">

**Author:** [@mrazomej](https://discourse.julialang.org/u/mrazomej)\
**Replies:** 0\
**Last updated:** [June 21, 2024, 4:30pm UTC](https://discourse.julialang.org/t/autoencodertoolkit-jl-a-package-for-training-variational-autoencoders/115985 "2024-06-21T16:30:45Z")

</div>

Announcing AutoEncoderToolkit.jl: A New Package for Training Autoencoders We are excited to introduce AutoEncoderToolkit.jl, a new package designed to simplify the training and usage of Flux.jl-based autoencoders and va…

---

## [\[ANN\] MLJFlux.jl 0.5](https://discourse.julialang.org/t/ann-mljflux-jl-0-5/115675)

<div class="topic-metadata">

**Author:** [@ablaom](https://discourse.julialang.org/u/ablaom)\
**Replies:** 0\
**Last updated:** [June 14, 2024, 10:30pm UTC](https://discourse.julialang.org/t/ann-mljflux-jl-0-5/115675 "2024-06-14T22:30:02Z")

</div>

MLJFlux.jl allows users to quickly build, train and optimise Flux.jl neural network models using the high-level, general purpose machine learning framework MLJ.jl. The new 0.5 release assimilates a number of substantial…