Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Deep Learning Foundations to Stable Diffusion

course.fast.ai

Post reply on HN
Print view View original

31–40 of 121 posts

Re: Deep Learning Foundations to Stable Diffusion

#31

Post by matsemann »

I just used fastai last week for an experiment at work. I have no to little DS experience, but quickly skimmed through part1.

Quite easily I managed to use a pretrained resnet to do some quite astonishing things on completely unrelated pictures we have. And it only took like 10 epochs at ~4 seconds each, so less than a minute of training and it was already quite good.

What I did was that we have taken pictures of things during a process. At that point, I know what the volume should be. So used ~thousand of those images to train a regression model to estimate volume of the thing in the image.

Then I run the model on other images and compare what the model thinks is the volume compared to what it should be. When it's off, the algorithm is mostly correct and we have an error on our side.

Quite astonished about how quick and easy this was to do with the high level api of fastai. Took me 2-3 days.

Re: Deep Learning Foundations to Stable Diffusion

#32

Post by jstx1 »

psychoslave wrote: post #28
jstx1 wrote: post #13

Earlier quoted context omitted.

This question isn't specific to machine learning - if you've given up already, don't bother learning anything and see how it goes.

I guess that the fear, be it well founded or delusional, is fueled by the idea that a hammer for example have a lesser potential to inadvertently beat humans at civilizational level.

I'm not questioning the fear at all. My point is that you should do the best you can with what you're given, and lifting up your arms and saying that you aren't going to learn anymore isn't doing the best you can.

Re: Deep Learning Foundations to Stable Diffusion

#33

Post by crakenzak »

jph00 wrote: post #26
novideolike123 wrote: post #24

Would it be possible to have a transcription of the videos? I have never been able to follow a video for learning, for me the video format if like someone else controlling the way I learn.I much prefer to be able to design my own schedule in text. By using text I am able to skim quickly and select only those parts I consider important. Maybe other people are able to do that with video but I am not in that group.

Yes every lesson has a complete transcript written by our wonderful community members. You can access through the usual YouTube interface.

Is there any chance that the transcripts can be published on the website? I'd love to be able to search through them. love the course btw!

Re: Deep Learning Foundations to Stable Diffusion

#34

Post by jph00 »

crakenzak wrote: post #33
jph00 wrote: post #26

Earlier quoted context omitted.

Yes every lesson has a complete transcript written by our wonderful community members. You can access through the usual YouTube interface.

Is there any chance that the transcripts can be published on the website? I'd love to be able to search through them. love the course btw!

In youtube click "show transcript". It's searchable. Click in it to jump to that part of the video.

Re: Deep Learning Foundations to Stable Diffusion

#35

Post by stevesimmons »

crakenzak wrote: post #33
jph00 wrote: post #26

Earlier quoted context omitted.

Yes every lesson has a complete transcript written by our wonderful community members. You can access through the usual YouTube interface.

Is there any chance that the transcripts can be published on the website? I'd love to be able to search through them. love the course btw!

This would be ideal. I much prefer seeing everything in text form, in the same place, without having to jump out to YouTube.

I can read many times faster than listen, and more easily skim back if I realise I don't understand something.

Re: Deep Learning Foundations to Stable Diffusion

#36

Post by whatyesaid »

nbzso wrote: post #10

This is cool, but I have a fundamental question. Why learn machine learning when all the machines will learn how to create and control themselves and powerful elites will offload the burden of governments to control us? Or we race ourselves to fulfill the last jobs on earth? Is this progress for humanity or enslavement and the end of our species? I am serious. This question is honest. Maybe my IQ is too low to unders…

If you don't need to learn anything and can fulfil and sustain yourself then I wouldn't. The reality is that's not the case for most people. You also don't need to learn things with the expectation of a job.

Re: Deep Learning Foundations to Stable Diffusion

#37

Post by startup_99 »

jph00 wrote: post #4

Hi folks. Nice to see our new free (and ad-free) course here on HN! This course is for folks that are already comfortable training neural nets and understand the basic ideas of SGD, cross-entropy, embeddings, etc. It will help you both understand these foundations more deeply, since you'll be creating everything from scratch (i.e. from only Python and its standard library), and to understand modern generative modelin…

not to derail the conversation...

I came across your APL study session videos while exploring the other material. I used APL professionally for about a decade back in the early 80's. I am always pleasantly surprised when I see interesting work being done in APL. Interestingly enough I always thought APL would eventually evolve into a central language for AI. There were attempts at designing hardware-based APL machines way back when. Of course, much as the language, they were ahead of the technology of the times.

I don't do much with APL these days. I do keep it around for quick calculations and exploration, far more so than doing any projects. In many ways, a thinking tool of sorts.

Re: Deep Learning Foundations to Stable Diffusion

#38

Post by wodenokoto »

jph00 wrote: post #4

Hi folks. Nice to see our new free (and ad-free) course here on HN! This course is for folks that are already comfortable training neural nets and understand the basic ideas of SGD, cross-entropy, embeddings, etc. It will help you both understand these foundations more deeply, since you'll be creating everything from scratch (i.e. from only Python and its standard library), and to understand modern generative modelin…

How long does it take to go through the course? I know the on-demand are self paced, but are we talking “expect 1 lecture a week full time”?

Re: Deep Learning Foundations to Stable Diffusion

#39

Post by noob_eng »

jph00 wrote: post #14
detrites wrote: post #12

Earlier quoted context omitted.

> since you'll be creating everything from scratch (i.e. from only Python and its standard library) Is this correct? I skimmed the notes for both parts 1 & 2 and they stated requiring PyTorch?

Yes, after we create something from scratch, we then see how to use implementations from libraries such as PyTorch. For basic operations like convolution, whilst we do create a GPU-accelerated version, it's not as fast as PyTorch/cudnn's highly-optimised version, so we use the PyTorch implementation for the rest of the course, rather than our handmade version. So that means that nothing is mysterious, since we know h…

Something of this sort is also done by Andrej Karpathy in his Zero to Hero Series:https://karpathy.ai/zero-to-hero.html

Re: Deep Learning Foundations to Stable Diffusion

#40

Post by narag »

maelito wrote: post #30
nbzso wrote: post #10

This is cool, but I have a fundamental question. Why learn machine learning when all the machines will learn how to create and control themselves and powerful elites will offload the burden of governments to control us? Or we race ourselves to fulfill the last jobs on earth? Is this progress for humanity or enslavement and the end of our species? I am serious. This question is honest. Maybe my IQ is too low to unders…

I don't get why your question is getting unvoted. This is a serious question. For engineers and "normal people" as well : why bother learning ?

That's not a serious question, it's the very definition of trolling. You can replace Stable Diffusion with any other subject to learn, and that particular doom scenario with a similar one or, if you don't feel very inclined to ellucubrate, just say the good old "why learn anything when we all are eventually going to die and be forgotten".

Not cool.

Post reply on HN