Lesson 1 official topic

Part 1 2022
62

FastAI does not have a labelling tool, there a bunch of opensource ones available.

1 Like
63

It’s a Jupyter extension, @ilovescience found it: Lesson 1 official topic ✅ - #21

3 Likes
67

Why is a DataBlock called a DataBlock? I guess it’s a pretty hard thing to name, but I feel like a DataPreparation would be a more intuitive name.

4 Likes
70

Can we get access to Jeremy’s slides before the course video is released? Or is the same content covered in the lesson videos/book/etc?

72

Notebooks are great:

Book written with notebooks - GitHub - fastai/fastbook: The fastai book, published as Jupyter Notebooks
Library written with notebooks - fastai/nbs at master · fastai/fastai · GitHub (using nbdev)
Blogs written with notebooks - https://fastpages.fast.ai
Presentations in notebooks- RISE — RISE 5.7.1

18 Likes
73

There are some variations in this iteration of the course versus the previous version. But the core concepts are the same.

I will ask Jeremy to post if he feels appropriate.

1 Like
74

Feels like Google/Deep Mind tries to rethink their ML stack and use JAX for some recent publications, like Gopher?

75

You could use prodigy to help you with that. I hope that helps. @falmerbid

6 Likes
76

Datablock name? IIRC fastai called it a Databunch before settling on Datablock. Pytorch natively has a “Dataset” to feed dataloaders. A datablock is essentially a Dataset with a bunch of helpers.

EDIT: Jeremy corrects me, "DataBunch was renamed to DataLoaders. DataBlock isn’t much related to a Dataset. It’s a builder for DataLoaders."

I have misremembered from 2yr ago. Good thing I am doing the course :slight_smile:

4 Likes
77

I used LabelBox for my medical research. It offers free access for small private dataset and education sector. It is great for multi-users in different locations.

For single user, there are multiple open sources, such as Label Studio. It is very easy to customize for your needs.

14 Likes
78

Thanks for an amazing lecture 1. It’s always so great to be back in the fastai classroom :pray: :smiley:

10 Likes
79

Great lecture thanks! See you in the share your work thread :slight_smile:

1 Like
80

Thanks for the great lecture :slight_smile: . First time hearing that familiar voice and wrapping up style in live

2 Likes
82

Great lecture thanks @jeremy! Does anyone know if there is a significant difference between the book via fastbook notebooks and the ebook version? I do like to read in bed with my kindle, so just wondering if I should preference the new notebooks over the 2020 book for any reason?

83

2 posts were merged into an existing topic: Help: Using Colab or Kaggle :white_check_mark:

84

They’re identical content - the book just has some nicer formatting.

1 Like
85

The slides are in the Kaggle notebooks linked in the top post of this thread.

3 Likes
86

You’ve misremembered a bit there! DataBunch was renamed to DataLoaders. DataBlock isn’t much related to a Dataset. It’s a builder for DataLoaders.

7 Likes
87

Is it a bird? Is is a plane? IT’S SUPERMAN!!!

Taking a cue from Jeremy’s notebook shown in today’s lecture, I tweaked it a bit to classify images into three types.

Over the week, I am planning to annotate it with my thoughts and explanations. Posting this here to keep myself accountable! The notebook is just barebones atm.
It was fun to do this so a big thank you to Jeremy and the fast.ai team!!

Also, we dont have a share-your-work topic for this iteration of the course. Maybe that can be created and posts such as these could go there?

15 Likes
88

Just wanting to confirm… at fast.ai Live - Lesson 1 - YouTube
when Jeremy says “If you are watching this video right now on youtube, I strongly head over to course.fast.ai and watch it there instead”, is that an example of what was mentioned earlier as being related to after public release? I presume this content is not yet there.

1 Like