Lesson 1 official topic

Thanks for sharing

1 Like

Hi @jkorte,
I’d say probably the easiest way to understand how this works is to take a look at this notebook which demonstrates how this technique can be used.

12 Likes

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

The timm package is truly great and also quite often updated with new architectures or adjustments to the existing ones.

7 Likes

make sure to install from master to make use of the cutting-edge SOTA models as soon as it’s added:

pip install git+https://github.com/rwightman/pytorch-image-models.git

12 Likes

6 posts were merged into an existing topic: Help: Basics of fastai, PyTorch, numpy, etc

for image segmentation, dose fastai library have a labeling tool for it?

1 Like

How do I get the same presentation setup Jeremy is using in jupyter? I have not seen that functionality to switch between powerpoint and code

4 Likes

I had the same question, it’s pretty neat :slight_smile:

1 Like

No I haven’t seen a labeling tool for this. There are setups for image classification however

@nchukaobah As this is a popular question, I will ensure he addresses it.

1 Like

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

1 Like

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

3 Likes

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

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?

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

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

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

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

6 Likes

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