Part 1, online study group

taposh · November 29, 2019, 10:48pm

I am interested as well.

Mobarmg · November 29, 2019, 11:22pm

Hi I would like to join this study group. If it’s possible.

joeljose · November 30, 2019, 6:42am

Hi, I would like to join the study group. Please add me in too.

madebymaze · November 30, 2019, 6:56am

I am interested.

amitkayal · November 30, 2019, 7:42am

I am also interested to join this study group

rsiri · November 30, 2019, 10:54am

Hello, I am interested too.

chinmaydas · November 30, 2019, 1:28pm

Hi everyone I am interested too

shahnoza · November 30, 2019, 2:04pm

Great @chinmaydas! We are having an online meetup in 1 hour Join Zoom at 3PM GMT https://zoom.us/j/564723458

shahnoza · November 30, 2019, 3:39pm

We used up free 40 min of Zoom, this is the new link for today https://zoom.us/j/641244020?pwd=T0V5c2VMS0lYOEpWVmFwY2ZwTU9UQT09

shahnoza · November 30, 2019, 4:19pm

New link: https://zoom.us/j/850858083?pwd=am1uRW9sbDZxZzREeXFlcXJnalhCUT09

lakshya_am · November 30, 2019, 5:39pm

Hi,

I feel like I am a little late for today’s meetup but I am very much interested in these meetups.

kshitijpatil09 · November 30, 2019, 6:04pm

Hello. I’m currently in the middle of exams but still would love to join the slack group and meetups. Please invite me!

Adeeb · November 30, 2019, 6:54pm

Hello everyone. I am a high school student from Waterloo and I am interested in being a part of the group. Unfortunately, I was unavailable for today’s meeting but I would love to join the slack and be a part of future discussions!

Thanks!

vaasanthk · November 30, 2019, 9:11pm

Hi, I’m interested too please send me the invite for upcoming events.

Miske · December 1, 2019, 3:27am

Hey guys i started the Deep learning course 3 days ago , so i am new in this and it’s not easy, how to set up the dataBunch for Flowers Dataset.

shahnoza · December 1, 2019, 4:27pm

Hi @Miske! One idea is to transform text files into a dataframe. The df should have 3 columns: name of image, label of an image, and whether it is from a validation set. E.g:

Then you can use ImageList.from_df(your_df, path).split_from_df(). You can read more in the docs.

Here is the sample code that worked for me:

from fastai.vision import *
path = untar_data('https://s3.amazonaws.com/fast-ai-imageclas/oxford-102-flowers'); path

#Take txt file and turn it to df, add new col
cols = ["name", "label"]
train = pd.read_csv(path/'train.txt', sep=" ", names= cols )
train ["is_valid"] = False

valid = pd.read_csv(path/'valid.txt', sep=" ", names= cols )
valid ["is_valid"] = True

#Join train and valid dataframes
train = train.append(valid)
train.sample(4)

tfms = get_transforms()
data = (ImageList.from_df(train, path)
                 .split_from_df()
                 .label_from_df()
                 .transform(tfms, size=64)
                 .databunch()
                 .normalize(imagenet_stats))
data

You will also need to create the second DataBunch for the test data.

P.S. I am also a beginner, so there might be a more elegant solution

dharanish · December 1, 2019, 5:04pm

Hi, I would like to join as well!

shahnoza · December 1, 2019, 6:32pm

#meetup_notes

We had our 4th meetup on 30th of November! More people joined thanks to @jeremy ’s tweet Thanks everyone for the meetup and there will be another one next Saturday at 3PM GMT

Project. We talked about our first Kaggle challenge: Kannada MNIST. Our biggest trouble was to configure proper DataBunch for training set. So we discussed how to turn tabular data into images and how to add pretrained models to the kernel. We are far from the top of the leaderboard, and therefore we will keep working on the challenge during the coming week.

Lessons. More beginners joined this time. So @rugan01 went through the notebook for Lesson 1, and we discussed the main learnings from it. We also talked about cloud platforms (GCP, AWS), experience with Google Colab, data augmentation and transfer learning.

Communication. We decided to post all questions related to fastai in the fastai forum and have this thread as the main communication channel. There is also an open slack channel for discussions regarding the projects and chit chats.

P.S. The meetup is informal and dedicated for sharing, learning, and keeping each other motivated. Feel free to join anytime, you will not be late, usually, people discuss/present/ask questions from the lesson they are in.

P.S.S. Currently we are using a free version of Zoom for meetups but it disconnects every 45 mins. What do you guys think, can we get unlimited calls in any other platform? Or crowdsource/rotate payment for zoom? The upgrade is 15$.

jeremy · December 2, 2019, 4:37am

Thanks for the update @shahnoza!

Miske · December 2, 2019, 12:36pm

Thanks @shahnoza it worked perfect . Thank you this solution is elegant and more than a nought for me . You own me one .