Hi Everyone,
Our wonderful SOURCE CODE: Mid-Level API Study group has decided to spend some time on going through the fastbook and then go back to the API Code.
We’ve voted to meet on Saturdays & Sundays at 7:30 AM IST.
**Next Call: TBD
Agenda: Chapters 1-8 have been discussed so far. We’re going at a 4 chapters/week discussion. Although don’t hesitate to discuss those if you join, all questions and discussions are welcomed.
Who can Join?
This is an uncool group! Please feel free to join, anyone and everyone is welcome. Any/all questions will be welcome! Although please note that the discussions might be fairly fast and advanced as most of the people in this group have been doing FastAI for quite a while.
For any questions with zoom URL, please check this top wiki or ping @init_27
I’ve setup a zoom call to join the SG but I’ve decided not to set it to record by default.
We’re discussing the materials for the book and this falls under a gray area of re-distributing if we record the sessions, which is a violation of the license for the materials.
I suggest discussing it actively and then posting the summaries or imp discussion takeaways here and then the few of us who’ve read the chapters can then help others if they have any questions. Although IMO the book has very clear concepts and explanations. Q&A would be around building on top of the concepts.
Hi Everyone, just wanted to mention that I’m also starting a beginner friendly discussion with the MLT Community, this is for the folks that aren’t part of the Course-v4 and will be slightly slower paced than our current one.
Hey guys! I am also going through the book and trying to get a hang of the sheer amount of amazing techniques implemented by fastai and was looking at other ways to implement these approaches taught.
I was wondering if anyone would be interested in a collaboration to reimplement the various applications and techniques taught in the book on other datasets. Maybe some of the Kaggle competitions that have recently completed? So we can see where a fastai approach would lead us to on the public leaderboard and then maybe re-implement the winners solutions(if available) by modifying the fastai2 functions in the process?
This may be self-motivated cause the sheer amount of knowledge in the book has put my brain into overdrive and I’m trying to work on many things at once. Maybe a collaboration would help hone in the focus and work on something concrete!
Any suggestions on how to go about this or giving any insights on the datasets you guys have worked on previously where these techniques can be applied to would be really helpful!