Chicago - USA area


#1

If anyone is in the Chicago area I’d be up for a live study group type of thing, for sure.


(Naresh) #2

Hi Larcat,
I am not exactly in Chicago, But I am in Bentonville, Arkansas and we share the same timezone. Would like to join the study group.


(Daniel Armstrong ) #3

Hi @larcat and @nareshr8,
I live in the chicagoland area. I would be interested in joining a study group, but that being said, I am an early bird, I wake up around 4am to study before work, so maybe I need to join an asia group :wink:


#4

I’m envious! I have spurts of early-bird for work, etc, but can never seem to cement it in – natural night owl :wink:


(Sasha) #5

Down for weekend study groups.


(Daniel Armstrong ) #6

I love it, I am so much more productive. There is almost no distractions, everyone is sleeping.


#7

After the admins aren’t busy teaching, I’ll ask that this thread be merged into the UTC-6 group.

What part of the city are people in?

Near south here (Pilsen)


(Daniel Armstrong ) #8

I can’t do every weekend. I have two small children. I think it would fun to meet local fast.ai students. I have done all three classes, but I don’t have many people to talk about it.


(Daniel Armstrong ) #9

I am in the western suburbs, wheaton/naperville area.


(Sasha) #10

I’m northwest in Norwood Park however I’m in SF for the class weekly, which is why I suggest external study groups in case people wanna get together and go over questions & stuff.


#11

That’s alot of flying! Jealous that you’re doing it in person though, that’s awesome!

I’ll poke around abit and try and find a decent centralish location for weekend studying.

Saturdays or Sundays better for folks?


(Sasha) #12

Sundays.

I had the miles and it seemed like a good idea at the time. And I want the certificate!


(Daniel Armstrong ) #13

Sundays for me as well.


#14

Great – Sundays are generally better for me as well.


(Eugene Krayni) #15

I’m also in the chicagoland area and would be up for joining a meetup.


(Sasha) #16

What do we say we do Sundays around lunchtime - something between 10 and 2. Something at the crossroads of some trains since it seems we have people from all neighborhoods. Deep learning lunch and learn!


#17

Hi. I am from St. Louis MO and would like to join this study group if possible. Saturdays or Sundays work for me. Thanks.


(Sasha) #18

Since we’re all over, we should choose a convenient time to discuss where we are at and what we’re doing. I say we block off 3-4 hours on Sundays that we tune in weekly here, otherwise just post questions when you have them? Thoughts?

1-4pm Sunday?


(Sasha) #19

Here is a current summary of what I’ve been doing and issues I’ve run into:

I’m using Paperspace to work on the class. I originally set up my computer using old instructions (because I did it a week before class). I originally chose the fastai set up paperspace machine. I pulled in course-v3 from github and have gone through the code for lesson one and am working on training my own code.

Some issues I’ve run into - wrong version of PyTorch on my machine - found information to update on official PyTorch website.

I added
import torch

GPU issues -
Running torch.cuda.is_available() produced FALSE.
After troubleshooting I restarted my instance. That worked.

Issues with normalize:
ValueError: padding_mode needs to be 'zeros' or 'border', but got reflection
Added padding_mode='zeros' to ImageDataBunch.

I’m ready to start playing with my own dataset. I’ve found one I like on kaggle that I want to try out first. Has anyone worked with adding labels from a csv to categorize images? Any help would be much appreciated.

UPDATE:

I was successful in using lavels from csv using the following code:
from pathlib import Path
import pandas as pd

path = Path("/home/paperspace/data/DecorPatterns/images/")
df = pd.read_csv("/home/paperspace/data/DecorPatterns/decor.csv")
#df.head()

df1 = df[['file', 'decor']]

df1.columns = ['name', 'label']
df1.head()

data = ImageDataBunch.from_df(path, df1, size=224)

[solved] Local Linux setup: ValueError: padding_mode needs to be 'zeros' or 'border', but got reflection
(Emilian Bold) #20

I’m also getting this but I wonder if it’s not some other error about the versions installed? We should not be patching fastai directly…