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

Practical Deep Learning for Coders 2018

fast.ai

Post reply on HN
Print view View original

21–30 of 64 posts

Re: Practical Deep Learning for Coders 2018

#21

Post by jph00 »

testdeep wrote: post #19
jph00 wrote: post #3

Jeremy from fast.ai here. Happy to answer any questions about the course, fastai, or anything else relevant! BTW the 2018 version of the course is being discussed in this forum, for those interested: http://forums.fast.ai/c/part1-v2

Hi jeremy, I am a web dev, JS being my first lang of choice :-), and i have been trying to get into machine learning/deep learning/AI, but I am having a information overload. I have 0 knowledge about this field, so my question is should i just start with machine learning, instead of jumping right into deep learning ? Or is it ok to jump right into deep learning and is it possible to do all the stuff done with machine…

Just jump in with this course. Your background in web dev will be really helpful, but there will be plenty of new concepts to learn - don't try to understand everything perfectly the first time through, but just try to complete each week's assignments as best as you can. You'll need to learn python and numpy along the way, but there's plenty of free online resources you can refer to when you see something you don't understand. And use http://forums.fast.ai of course.

You can then go back through them a 2nd time and do a deeper dive. By that time, our Intro to Machine Learning course will be out too :)

Re: Practical Deep Learning for Coders 2018

#22

Post by briandw »

jph00 wrote: post #3

Jeremy from fast.ai here. Happy to answer any questions about the course, fastai, or anything else relevant! BTW the 2018 version of the course is being discussed in this forum, for those interested: http://forums.fast.ai/c/part1-v2

Jeremy,

Just wanted to say thanks for all your work. I'm taking some time off from my regular job as an iOS developer to pursue an ML project of mine. I wouldn't have had the confidence to do that with out your online course. I wrote up a project I did after last years class on Medium, also because of your guidance.

https://towardsdatascience.com/25-lights-part-ii-e021b66e449...

Re: Practical Deep Learning for Coders 2018

#23

Post by jph00 »

argc_argv wrote: post #18

Time to shill my little tool to help with rewatching lecture videos. Search the caption by keyword and jump to that timestamp of the video. https://github.com/mingrui/youtube_caption_search

Thank you for creating that! :)

BTW I just had a thought. What if instead of a txt file like you have:

    hi everybody welcome to practical deep
    00:00:00.000
    https://www.youtube.com/watch?v=IPBSB1HLNLo#t=00h00m00s
...you instead created a markdown file that had:

    [hi everybody welcome to practical deep]
    (https://www.youtube.com/watch?v=IPBSB1HLNLo#t=00h00m00s)
...then you'd have a readable transcript, where every phrase is hyperlinked! For bonus points, run it through the bidir RNN punctuator to add punctuation: https://github.com/ottokart/punctuator2 . (I plan to do this for the transcripts in the future BTW).

Re: Practical Deep Learning for Coders 2018

#24

Post by neves »

jph00 wrote: post #3

Jeremy from fast.ai here. Happy to answer any questions about the course, fastai, or anything else relevant! BTW the 2018 version of the course is being discussed in this forum, for those interested: http://forums.fast.ai/c/part1-v2

Do you have good references about how to setup the environment with a Nvidia GPU in a Windows machine?

Re: Practical Deep Learning for Coders 2018

#25

Post by jph00 »

briandw wrote: post #22
jph00 wrote: post #3

Jeremy from fast.ai here. Happy to answer any questions about the course, fastai, or anything else relevant! BTW the 2018 version of the course is being discussed in this forum, for those interested: http://forums.fast.ai/c/part1-v2

Jeremy, Just wanted to say thanks for all your work. I'm taking some time off from my regular job as an iOS developer to pursue an ML project of mine. I wouldn't have had the confidence to do that with out your online course. I wrote up a project I did after last years class on Medium, also because of your guidance. https://towardsdatascience.com/25-lights-part-ii-e021b66e449...

Thanks for sharing! FYI you may find resnet18 or (better still) densenet a good option for that dataset - you shouldn't need so many training images then.

Re: Practical Deep Learning for Coders 2018

#26

Post by jph00 »

neves wrote: post #24
jph00 wrote: post #3

Jeremy from fast.ai here. Happy to answer any questions about the course, fastai, or anything else relevant! BTW the 2018 version of the course is being discussed in this forum, for those interested: http://forums.fast.ai/c/part1-v2

Do you have good references about how to setup the environment with a Nvidia GPU in a Windows machine?

Yes, I've provided a step by step walk-through here: http://forums.fast.ai/t/howto-installation-on-windows/10439

This includes setup of fastai, pytorch, cuda90, cudnn, opencv, bcolz, and much more!

Re: Practical Deep Learning for Coders 2018

#27

Post by wodenokoto »

jph00 wrote: post #6
mcintyre1994 wrote: post #5

Earlier quoted context omitted.

What's the recommended cloud runtime for v2? Is it still AWS, or is it Crestle or similar?

We suggest Paperspace now. Lesson 1 walks you through getting set up. It's very easy - there's a fast.ai template there ready to go. They have the best price/performance ratio of anyone at the moment for GPUs.

How much should I budget for paperspace for completing the course?

Re: Practical Deep Learning for Coders 2018

#29

Post by rishaanpatel »

jph00 wrote: post #12
mcintyre1994 wrote: post #11

Earlier quoted context omitted.

Is the 'fastai' library on Pytorch something you'd recommend only for beginning/learning/this course, or is it intended to be used in production beyond the course? Is it being positioned more as a learning aid or as an open source library with a life beyond this course? Also, any chance of https on the forum?

Definitely well beyond the course. It's designed to be the easiest way to create world-class models. I'll be providing a lot more information on how we're doing this in the next week or two. PS: The focus of fastai is training, not production. The models you end up with are largely standard pytorch models, so standard pytorch approaches to production work fine. For most people, a simple flask endpoint with CPU infere…

Do you envision people using the fast.ai library without ever taking the course?

Re: Practical Deep Learning for Coders 2018

#30

Post by jph00 »

wodenokoto wrote: post #27
jph00 wrote: post #6

Earlier quoted context omitted.

We suggest Paperspace now. Lesson 1 walks you through getting set up. It's very easy - there's a fast.ai template there ready to go. They have the best price/performance ratio of anyone at the moment for GPUs.

How much should I budget for paperspace for completing the course?

If you remember to shut down your machine when you're done, and you do the suggested 10 hours per week, plus maybe an extra 5 hours of model training per week, at $0.45/hour for Paperspace's cheapest machine (still works great though): $47.25
Post reply on HN