@jeremy are we to apply the skills, that we learn on a weekly basis in the fast.ai course, to the projects that we applied with and deliver a completed project by the end of the course?
Ideally, that would be an excellent goal! In practice, many people will find that they’ll have plenty more to do once the course if finished - and the forum will keep running so that people can help each other on these projects.
4 Likes
thanks 
I completed this course and I enjoyed it. The content is very structural and started from basic concept.
Hi. What’s the link for the first class?
Note that the live stream link and all other resources for lesson 1 will be here: Lesson 1 In-Class Discussion
1 Like
You’ll also see that I’ve allocated you all to teams, based on time zones. At least one person tells me that he’s no longer in the spreadsheet - so it’s possible that someone has accidentally overwritten or removed some names. If you’re not in the spreadsheet, please just select a team that’s in your time-zone, and message your team-mates during class to let them know.
2 Likes
It might be better to group people based on state+country, instead of time zone. In this spreadsheet, even people in same cities reported with different time zones.
Perhaps, but I’m not going to change it now
1 Like
I’m one of those! The full-time job takes most of the day so I will need to work late hours. I wanted to make sure the other people in group are active around the time I do
Hi Jeremy! Regarding the 2nd Class scheduled for 6th Nov, is daylight saving time (which has started) taken into account and time remains as 6:30pm or are there any changes?
It’s 6.30p pacific time (which is no longer daylight savings, as of yesterday). https://www.google.com/search?q=6.30pm+pacific&ie=utf-8&oe=utf-8
The live stream will be at https://www.youtube.com/watch?v=4mwdySNmtYs . Will be running 10-15 mins before class.
If any international fellow doesn’t have a group (i.e. you didn’t update this spreadsheet, please use this thread to say so, so that other fellows without a group can team up with you. Currently group 163 has only 3 people, so you could join that group.
I could join them and strengthen the groups numbers if its alright my current group has 6 members
Now streaming. Let me know if any issues. You can see your class mates
1 Like
No issues here
Working here
This piece of code stop working after the git pull
arch=resnet34
data = ImageClassifierData.from_paths(PATH, tfms=tfms_from_model(arch, sz))
learn = ConvLearner.pretrained(arch, data, precompute=True)
learn.fit(0.01, 3)
try to clear tmp directory