Week 15 Discussion Thread

Community Events Fastbook Reading Group
1
1 Like
2

Resources:

Blog posts from 2 weeks ago

1 Like
3

The group is ending? :scream: :scream: :cry:

4

This is the blog post on Optimizers - “Adam” and friends | Committed towards better future

3 Likes
5

Edit: Aman mentioned it too. I spoke too soon :slight_smile:

We also have a PyTorch study group too where the PyTorch topics will be covered soon for anyone interested :tea:

3 Likes
6

Hopefully others will have a better idea, but my “big project” from that break between fastai versions, which took over my life was Chai Time Data Science :smiley:

1 Like
7

Thanks Aman for doing these sessions. You have given us enough momentum to continue the learnings. Looking forward to stay connected in the Paper Reading Group.

4 Likes
8

How to get source code in vscode?

1 Like
9

I have a question on Head. For Classification, we could use certain architectures (VGG, ResNet etc). But for Segmentation or Object Detection, we usually hv different base architectures like UNet / RetinaNet etc.

Most of the work is really in the Data Prep. Can you speak a bit about Data Prep step in Object Detection. In it, we have location of objects, but the architecture might use Anchors or other techniques. So we no longer have the 1:1 we used to have in Classification or even Segmentation. How do you go about building Dataset for Object Detection tasks where each architecture might have different losses / outputs (unlike Classification or Segmentation tasks).

10

One neat trick you can try-> Head over to fastai repo on GH. And press dot on your keyboard :slight_smile:

(It launches a VSCode instance, not powerful enough for DL but p great for reading source code)

3 Likes
11

If that doesn’t work change github to github1s

4 Likes
12

We ran a hugging face study group too :tea:

Link: W&B Study Group: fastai x Hugging Face - YouTube

1 Like
13

NLP course by Rachel - new fast.ai course: A Code-First Introduction to Natural Language Processing · fast.ai

1 Like
14

Maybe I could start a fastai (NLP) study group next :thinking:

4 Likes
15

Once you get to transformers - here is another resource to help with your journeys! The Annotated GPT-2 | Committed towards better future

16

Professor Zach had created one

17

For tabular - Using AutoEncoders with Tabular Data (Intermediate) | walkwithfastai

18

Two more resources on CV:

19

Segmentation models pytorch is another great repository - GitHub - qubvel/segmentation_models.pytorch: Segmentation models with pretrained backbones. PyTorch.

20

This will always be remembered as our favourite (unofficial) fastai 2021 course. Thank you for hosting it! :tea:

5 Likes