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.
Per Jeremyās posts
Thanks Moody, thatās very helpful.
Itās hard to follow fast.ai across all their communication channels!
Thank you so much for all the updates Moody!!
Truly appreciate it.
Looking forward to this course and the subsequent part 2.
I totally agree! Why arenāt anouncements made on the forum? I do not follow twitter. And there is the discord channel as well. I do not see any sense in using all those different mediasā¦
Save the time if you want to attend the course live.
Is there any information released yet for the remote version like in past years?
Donāt want to miss out on Jeremy explaining transformers.
Is there no free online offering this year?
I had signed up for the course news and it seems theyāre accepting applications (in-person AND remote). The fee is 575 AUD for standard learners and something called āconcessionā is 175 AUD ā¦ the course will be from 6:00pm to 8:00 pm Australian Eastern Time.
In his tweet Jeremy had mentioned that some info might be posted to the fast.ai forums but I have not seen anything āofficialā as of yet.
Since this course is being offered by a third party and not fast.ai per se, Iām not sure if the videos would (at all) be made public like they used to do for the previous years when it was delivered in San Francisco etc.
Jeremy has tweeted that the videos will be made public.
Why TF, you can look at icevision, its a modern CV library build on fastai. Unfortunately fastai lacks modern CV tools to tackle instance segmentation or use modern models.
Or you could learn Pytorch Lightning. Itās not like fastai is the only PyTorch library.
Are there videos available? On the website of the course, I can see only slides