Jeremy gave us a hint on the discord a few days ago in regards to this. Likely it will be redoing Part 1, with more content included in it. (No ETA)
My concern is the very low activity since basically Sylvain left and Jeremy moved back to Australia. The book released last year is great and I thought that was the sign of a new impetus for the framework, but then things became very quiet. The only new content I see on the blog is about covid and ethics.
Not complaining because, of course, fastai and the courses are all free, but this field moves quickly and there are now a lot of companion libraries and tools for Pytorch that make regular developersā lives easier so I feel fastai has a bit lost its advantage and appeal as a framework accessible to the masses.
To be honest, Iām a bit worried about the future of fastai and that itās stuck in 2019. Iād very much like to see the ball rolling again, with coverage of the hot new stuff of the past 2 years. So hopefully weāll see some good news in the next days/weeks.
Where do you get an equivalent content using TF2.0?
I have yet to find such a comprehensive course using TF2.0.
Hi
May I recommend Deep Learning with Tensorflow 2 and Keras by Guilli,Kapoor,Pal but you need to understand fastai first as it not quite a total beginners book.
Obviously it is worth doing all the old fastai courses especially the NLP and Computation Linear Algebra.
Regards Conwyn
thanks, will take a look at this then after I finish fastai.
I did this course
Itās from zero to mastery, and then did their more advanced course. Itās not perfect and it costs money. But if you did the fast.ai courses and have a good understanding, you will probably breeze through a lot of the material. Again itās not perfect, but Itāll get you far enough that you can play around TF.
Edit: I just saw that they have the first 14 hours available on YT, so I guess check that out, see if you like their teaching style.
Oh, hey cheers for that⦠Iāll have a look
awesome thanks, Iāll finish fast.ai before, this looks good to get a hand on TF after having done fast.ai.
Is the Discord a better place than the forums, for staying up to date?
I am waiting for the next video.
ā¦seems like the moocs are rather dead? Is there any big development planned for the fastai framework? I really liked the idea of fastai but now it seems not suitable for productive use?!
Yeah, looks like itās flatlining unfortunately. Hopefully Jeremy and Rachel will get settled down in Australia and reboot the moocs cycle!
Fast.ai part 1⦠but with some new elements in it.
Iām definitely interested in learning about transformers!
You may want to check out the d2l.ai book and associated courses; STAT 157 at Berkeley or the CS239p at Stanford.
https://c.d2l.ai/stanford-cs329p/
The book is at https://d2l.ai/ and it has code in mx.net, pytorch and TF2 (the d2l library abstracts over the frameworks I think)
I havenāt tried it, so YMMV.
Cheers,
Mike
Awesome news!
You can register your interest for the course and get the latest info about it by submitting this form: Expression of Interest - Practical Deep Learning for Coders
This is exciting! Thank you for sharing
Looking forward to this!
It seems to me the form is for those attending the course in person.
If you want to be invited to attend the live course remotely. Be active in the forum now and contribute. It is OK to answer simple questions to build up your confidential.
Check out the reason behind by scrolling my previous post before and after.
I hope to see you all in virtual classroom in few weeksā time.
Really? Thatās not clear from the text in the form. It mentions that āthe course will be offered onsite at the UQ St Lucia campus and streaming onlineā and It doesnāt say anywhere that only people who would like to attend in person should submit the form. It says "Sign up here to keep in the loop! " so I interpreted that as āweāll send you regular info about the courseā. The health message below also specifies āKey health messages (for those intending on attending in-person)ā so it does seem like people who want to attend online are included.