Conversation

Replying to

2/ I am doing course.fast.ai again. I did part 1 in 2018 but binged the first 4 lessons fri-sun. Jeremy was kind enough to invite me to the 2022 version on going. Wait a few weeks before pursuing this which will show you new tools and a few new concepts.

course.fast.ai

Practical Deep Learning for Coders - Practical Deep Learning

A free course designed for people with some coding experience, who want to learn how to apply deep learning and machine learning to practical problems.

337

Suhail

@Suhail

Jun 27, 2022

3/ I made a custom Twitter list to follow certain AI people: twitter.com/i/lists/153949 Mostly to stay on top of the cutting edge and keep up to date.

208

4/ I’ve been messing around with prompts again in OpenAI playground with DALL-E and GPT-3 to experiment. Made some album art for a song I plan to release next month and prototyped a new feature for

@MightyApp

I hope we’ll ship later. Just keeping up the momentum/motivation.

104

Suhail

@Suhail

Jun 27, 2022

5/ Going to start writing real code and compete in a competition on Kaggle to apply my knowledge now before prototyping/building things for

@MightyApp

s/o jeremyphoward for the guidance Next step:

kaggle.com

First Steps: Road to the Top, Part 1

Explore and run machine learning code with Kaggle Notebooks | Using data from Paddy Doctor: Paddy Disease Classification

132

Suhail

@Suhail

Jun 28, 2022

6/ I was somewhat surprised how complicated getting a dev env was today. Lots of choices but it's all kind of expensive, running weird versions of pkgs, bespoke notebook UIs. I mostly just wanna use a local jupyter environment and connect to a GPU/macOS/not pay $1K/mo

111

Suhail

@Suhail

Jun 28, 2022

7/ Trying Paperspace but their remote kernel environment in VS Code doesn't work. Might give up and just use the funky jupyter lab thing and get to work.

Replying to

and

paperspace is the best provider i found (i was able to get vscode remote ssh plug-in working - their jupiter lab hack is jank though). i ended up just buying my own machine and setting up a local environment in the end since paperspace startup time was painful.

Replying to

and

Idk why but when I add the remote url, vs code doesn't do anything or show anything. It doesn't seem like it connects even though it shows a last connection date. It kills me a little to have the janky setup. I move so slowly.

Replying to

and

Bummer :/ might be a bug with the plugin If you're serious about investing the time in ML learning, you could probably justify just buying a gaming rig and installing linux - nothing beats to the simplicity of connecting to a local machine you can remote into from a laptop.