[Unofficial, Virtual] SF/Bay Area Study Group

Part 1 (2020) Study Groups
65

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
67

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
68

Hey @butchland , Could you share the repo for the datablock practice notebooks?

69

Hi,
if you mean my notebooks on exploring kaggle for fingers datasets
they’re here

70

I am referring to this. Could you share the repo? @butchland

71

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!

72

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

73

@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
74

David and others – Just added everyone that was in my direct message inbox. Sorry for delay – was a little busy with work last week :slight_smile:

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
75

Hi all,
For my presentation in our study group meeting this Monday, April 27, I wrote up a long rambling :smiley: 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

76

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).

77

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
78

Thank you so much @gansme for organizing this. looking forward to meeting you guys again @steef @marii

2 Likes
79

I’ve updated the top post with these details, thank you for hosting this :tea:

1 Like
80

Is there a link for the Biweekly Thursday meetings that start today?

81

@steef Is the correct person to message for Thursday meetings, as we are not organizing those. I am currently attempting to contact him as well.

2 Likes
82

Yes, here is the Thurs meet link.

2 Likes
83

Thanks for sharing the link Megan!

I’ve just added a few more people to the calendar invite and the meeting notes. If more folks want the invite please DM me your email address.

1 Like
84

Hi all, reminder that fastai2 study group kicks off tonight at 6pm PST at this URL: meet.google.com/bhx-jwph-bnx . See you there!

P.S. I’ve updated the wiki post on this thread with the link. If you’d like to be added to the calendar invites message me your email.

85

Possible Ch2 related topics we could cover:

  1. What kind of tabular data is deep learning NOT particularly good at?
  2. How might an e-commerce company like Amazon tackle the downsides of deep learning based recommendation systems such as: recommending books by the same author, or items someone has already purchased?
  3. Map the steps of the Drivetrain approach to a Kaggle contest (for ex: Titanic, Amazon Rainforests, or your choice)
  4. Take a past work (or side) project you’ve done that had a data component and imagine a deep learning model was applied. What would be an example of “domain shift” for that project?
  5. For a project you’re interested in applying deep learning to, a) Describe how the 3 stages of deployment processes (manual process, limited scope, gradual expansion) would work. b) Pretend you’ve completed that future project already, and it went really, really well? Describe what’s happened as a result.
  6. Share the link to an image recognition model you created using data you curated that is deployed on the web.
  7. Share the link to a deep learning blog post you wrote.
1 Like