MLX for Apple Silicon - Creative AI with Nono · Live 109

Подписаться 3,5 тыс.

Просмотров 3,2 тыс.

50% 1

Live streams on creative coding and machine intelligence with Nono Martínez Alonso.
Nono uses Apple's MLX for the first time-an array framework for Apple Silicon.
★ M3 Max 14-inch MacBook Pro → geni.us/m3-max
Watch to learn how to create a Python environment for MLX, run MLX code in Python, the role of unified memory in MLX, and generate images with Stable Diffusion on Apple silicon.
==================
LINKS
==================
- MLX repository github.com/ml-explore/mlx
- MLX examples repository github.com/ml-explore/mlx-exa...
==================
🎥 VIDEO CHAPTERS
==================
00:00 Start
00:15 Introduction
02:09 Today
03:55 Topics
07:18 Farrago
08:16 File Organization
10:09 Descript AI
19:33 Intro to MLX
22:03 Installation
23:57 Python Environment
36:59 Troubleshooting
45:35 Break
48:57 The Issue
50:29 Python Environment
52:53 Quick Start
57:39 Unified Memory
01:11:49 MLX Samples
01:14:33 Stable Diffusion with MLX
01:28:16 Outro
==================
Please support this channel by checking out our sponsors/affiliate links:
🎁 Sign up to DigitalOcean & get $200 of credit for 60 days → nono.ma/do
📕 Hands-On Machine Learning Book www.amazon.com/dp/1492032646/...
This channel is supported by its audience and may earn commission as an Amazon Associate and affiliate partner (or from referral links) on qualifying purchases.
🔴 Live Playlist: • 🧠 Live Streams
🧠 Machine Learning Series: • 🧠 Machine Intelligence
🕸 Web Development Playlist: • 🚀 Web
🍃 Getting Simple: gettingsimple.com
🎙 Podcast: gettingsimple.com/podcast
🗣 Ask Questions: gettingsimple.com/ask
💬 Discord: / discord
👨🏻‍🎨 Sketches: sketch.nono.ma
✍🏻 Blog: nono.ma
🐦 Twitter: / nonoesp
📸 Instagram: / nonoesp
#CreativeAI #CreativeCoding #MachineLearning

Наука

Опубликовано:

31 июл 2024

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 6

@crs117 6 месяцев назад

I enjoyed this video and will look at others you have created previously. I am still learning ML and trying to best utilize the Apple Silicon hardware. This is one of the first in depth videos I found regarding MLX and was thinking it may currently be hopeless. I totally empathize with you regarding importing mlx in python when you have a python file named mlx in the same folder. I will say getting tensorflow with GPU working on M1 Macs has wasted a large amount of time and internet sleuthing. Good job on the video, and it is good to know that we all fall into time traps when learning something new (not to mention while on a live stream). =)

6 месяцев назад

Hey! I'm glad you enjoyed this video. I often have to troubleshoot things live, but that's the joy of streaming-others can see the struggles, not just the "working summary." =) I'll cover more of MLX with Apple Silicon Macs in depth in the channel. We've previously recorded videos with TensorFlow and PyTorch examples. (Great guitar and singing videos on your channel, by the way!) Thanks for your message! Nono

@enzocaputodevos 6 месяцев назад

bonjour, je suis ravi d'avoir trouvé ce channel et sa communauté car il vraiment rare de trouver des ressources de qualité quand il s'agit de la compatibilité avec notre écosystème. Je te remercie pour le travail que tu accompli et surtout que tu partages tes résultats

6 месяцев назад

Merci beaucoup pour vos paroles ! Je suis heureux de l'entendre. Nono

@SDGwynn 5 месяцев назад

Had this happen in conda yesterday. Python vs python3. Think it might be a breaking change in conda?

5 месяцев назад

Hey! This heavily depends on your development environment setup. The python binary available in the command-line interface depends on what path or paths are exported. So when you type python or python3 the program could be loaded from different locations, like macOS default python install or Anaconda's or Homebrew's. The best thing is to first figure this out by running "which python" and "which python3". You can then decide whether those are the ones that you want to be running or you want to change. It's also important to note that when you "conda active your_env_name" running "which python" should return the python binary from that conda environment. I hope this helps! It can be extremely confusing. =)