@go_go_gadget If I can do anything to help you get a project off the ground, feel free to reach out. My sister has kids at home and I know how challenging it is right now. We don’t have children yet, so we have lots of free time! Let me know if there’s anything I can do to help!
4 Likes
Thanks, I really appreciate it!
Hey Everyone,
During the study group tonight we were discussing the structure of Thursday’s 7:30-8:30 meeting; we decided to experiment with taking a poll to see how people would like to spend the time (you can pick more than 1 option when you vote).
I’m adding some suggestions below but please ping me if you’d like me to add your idea (I don’t think anyone can edit this but if you can then go for it). Also, please vote by Wednesday so we can do some organizing around what gets decided if it’s needed. And if we don’t get enough votes then I assume we can just chat about it on Thursday.
Thanks!
- Extended Q/A session: Questions can be added to a shared doc, people vote on which ones to discuss, we group think the answers (should ask questions specific to lecture material, notebooks, cloud stuff).
- Breakout into smaller groups and have a very niche Q/A session (vision, text, tabular, and research):
- Paired programming: chose an application type (vision, text, tabular) and recreate a notebook from scratch (may require some homework for people to pre-download a dataset and be ready to analyze)
- Breakout into groups to come up with mini projects
0 voters
2 Likes
Hi all,
Aside from the “major” long-term projects that we can signup for, maybe we can also propose or suggest some short-term mini-projects that we can do that are more or less in tune with whatever the official class lecture discussed for the week or previous week.
For example, I’m doing a mini-project (a small set of notebooks) that uses the DataBlock api to prepare all kinds of datasets for model training.
My goal is get familiar with the capabilities of the datablock api as well as get me into thinking about the different kinds of ML research areas I might want to focus on.
Another “mini-project” is getting familiar with today’s MNIST example to build a simple NN but instead use synthetic data (ie. I can create a small program to generate “1” and “0” as the images instead of using MNIST but with some randomization). The nice thing about using synthetic data is that I can control
the x,y inputs and observe how the weights (ie. w’s) evolve from random to a structure that can learn to distinguish between the two…
If you have ideas for “mini-projects”, please share them here – maybe we can do pair programming to work them out?
Best regards,
Butch
3 Likes
Hey @butchland I really like your idea about a mini project and wanted to do something very similar (the data block notebooks). It seems the poll is trending this way too so I can foresee us breaking out into small groups and doing mini projects. I’m going to add a section in meetings notes for mini-projects and I’ll add your ideas there to get it started (as well as sign up for one 
).
3 Likes
Came across this thread. I actually like those practice problems
https://forums.fast.ai/t/introducing-fastpractice-exercises-for-each-fastai-lesson/67569
5 Likes
I know someone was having issues with an error ralating to a label 1717(some number >1000).
When using ImageDataLoaders.from_df you should be able to pass in verbose=True. This may help making sure it is reading your dataset correctly, it should give you some logs to work with.
1 Like
Ah ok,
I still need to clean up my data block exercise notebooks but @Dina shared a post above about data block examples here
I also found another great resource in this megathread here
HTH!
Hey All! I’m in the East Bay and would like to join. Sent a note to @steef but haven’t seen an email. Do we still need an email to join?
Thanks,
David
@quantum,
Nope, just lookup the meeting notes here.
There’s a link to the zoom meeting id which happens every Monday 630PM and Thursdays 730PM (there’s a beginners QA zoom at 630PM which the members also attend which is why we start an hour later).
HTH!
1 Like
David and others – Just added everyone that was in my direct message inbox. Sorry for delay – was a little busy with work last week
For others wanting to be included, feel free to direct message me with your email and I can add you to calendar invites.
3 Likes
Hi all,
For my presentation in our study group meeting this Monday, April 27, I wrote up a long rambling 
blog post (about 30+ min reading time) about my understanding of machine learning so far.
I’d like to get feedback on it so I published it hopefully early enough for anyone who might care to read it.
Thanks in advance,
Butch
Hey guys, I was a maybe for this Thursday as I was going to try and build off of last weeks presentation but rather than make more technical progress I just turned my previous work into a blog. So here is my show and tell for Thursday (I won’t need any time to speak but feel free to read and comment).
Hi all,
We have 2 post-class SF/Bay Area study group meetups. Timing is optimized for after regular work hours in the Bay Area, folks from any time zone are welcome.
- Weekly on Tuesdays 6-9PM PST Silent notebook work & 30 mins discussion starting May 26th.
- Biweekly on Thursdays 7-8:30PM PST Demos of class related work starting May 21st.
You can find our meeting notes and topic schedule here. Prior to Tues discussion, post topics in this thread: Bay Area Study group thread.
For more info on the Tuesday group reach out to cohosts Molly Beavers (@marii) or Megan O’Rorke (@gansme). For info on the Thursday demos reach out to host Steef Van Winkel (@steef).
8 Likes
Thank you so much @gansme for organizing this. looking forward to meeting you guys again @steef @marii
2 Likes
I’ve updated the top post with these details, thank you for hosting this 
1 Like
Is there a link for the Biweekly Thursday meetings that start today?