Lesson 1 official topic

[jeremy (Jeremy Howard)]

This post is for topics related to lesson 1 of the course.

This is a wiki post - feel free to edit to add links from the lesson or other useful info which is appropriate for beginners.

Lesson 2 >>>

Lesson resources

• Recording
• Notebooks for this lesson:
  • Is it a bird? Creating a model from your own data
  • Jupyter Notebook 101
• Setup help
• The fastai book:
  • Published version
  • Free notebook version
• fastai repo
• Solutions to chapter 1 questions from the book
• Anki flashcards
• The AI Dictionary

Links from the lesson

• How to learn - highly recommended books for fast.ai students
  • Meta Learning
  • A Mathematician’s Lament by Paul Lockhart
  • Making Learning Whole by David Perkins
• Homework
• Summaries + Things Jeremy Says to do + Qs
• Jupyter
  • Presentations: RISE
  • Blogging: fastpages
  • The fast.ai book, as notebooks
  • The notebooks used to create the fastai library
  • nbdev - the system we built to create Python libraries using Jupyter
• Fastai: A Layered API for Deep Learning paper: Information Journal or arxiv or fast.ai
• Dall-e 2 illustrations of Twitter bios
• timm: PyTorch Image Models
• fastcups - for getting quick student feedback
• PixSpy

Other useful links

• Providing a Good Education in Deep Learning: fast.ai teaching philosophy
• How not to do fastai”
• What you need to do deep learning: on what GPUs are and why you (probably) need a cloud service
• Jupyter NoteBook handy ShortCuts
• Jupyter Collapsible Headers and other cool nb-extensions

Discussion

Please use this topic to ask any question about the course (even if you think they are stupid, we really love stupid questions). Note that this is the beginners topic, so if you have already followed the course and your question/intervention is more advanced, please use the non-beginner discussion topic.

Questions with lots of likes will be asked live by John. If you see a question you’d really like to be answered, click on the heart under it to like it. Don’t post duplicate questions if possible. They will be removed by the moderators (don’t be mad if this happens to you, it’s nothing personal). If your question is not answered during the course, it will be answered on this topic after the lesson.

This topic will be very crowded, so please refrain from getting too much off track (create another topic for this) and please like the post of someone who replied to you instead of replying with thank you.

Notes

• Remember that the book has a chapter containing details on each lesson

[init_27 (Sanyam Bhutani)]

Hi Jeremy,

@jeremy

please use the non-beginner discussion topic.

I think the non-beginner topic wasn’t created so I made one and updated the wiki-I hope that’s okay

[Gabriel_Syme (Theodoros Galanos)]

A bit of OT question: is it okay if we snapshot an image of the class at some point for a social media post? Given that it’s not yet public yet, I wasn’t sure

[KevinB (Kevin Bird)]

What are the specs of your laptop that you can handle streaming, recording, and training a model

[arora_aman (Aman Arora)]

IIRC, Jeremy has Surface Book 3.

[VishnuSubramanian (Jarvislabs.ai)]

I guess he is using Windows Surface … some variant.

[ilovescience (Tanishq)]

I was mostly curious what is the setup Jeremy has to have Jupyter notebooks as slides. I think it is this:
https://rise.readthedocs.io/en/stable/

[kurianbenoy]

How to use vision_learner to use latest computer vision models?

[ilovescience (Tanishq)]

Pass a string of the name of the pretrained model from timm… See the example at the bottom of https://timm.fast.ai

[init_27 (Sanyam Bhutani)]

• Here is the cups link for quick reference
• Radek’s Tweet, please join us in congratulating him there
• Link to Radek’s book

[n-e-w (Nick)]

I’m one of the live TA’s. If you have any issues or would like any help…please “@” me and I’ll do my best to help!

[imrandude (Imran)]

Could be mercury → Interactive Presentation - a Hugging Face Space by pplonski

[checkmate404]

Jeremy says you learn best when you read the questionnaire first. Is this the questionnaire for lesson 1?

[Podcast + Writeup] Summaries + Things Jeremy Says to do + Qs

Hi Everyone! About & Motivation behind starting this The motivation behind this (wiki) thread is to provide a very quick summary of the lectures + “Things Jeremy says to do”-which has been a way by which we could access Jeremy’s wisdom and suggestions from the lectures. Note, since the lectures are not public and my hosting platform doesn’t give a method of keeping audio links unlisted, I’m not sure of the best method to share audio, so I’ll share the YouTube links and then release audio once …

[init_27 (Sanyam Bhutani)]

To anyone that might feel a bit uncomfortable with the top down learning methods:

I had written extensively about my struggles in “How not to do fastai”, I cover my pains of someone who studied in university-of how difficulty it was to learn something in top down fashion

We had also shared this in a “reverse” interview where Jeremy kindly interviewed me. I hope this helps

[ilovescience (Tanishq)]

The questionnaire is in the book. Check the fastbook repo notebooks for the Jupyter notebook versions of the book.

Here is the chapter for lesson 1:

fastai/fastbook/blob/master/01_intro.ipynb

[jkorte (Jessica Korte)]

Yes, Jeremy said the forum was overloaded at the start of the lecture.

[jwuq (John Williams)]

@n-e-w is it possible to sort this page by # likes? To select questions for pushing into the lecture?

[MaheshKhatri]

Thanks for your introduction. I saw both ‘bird.png’ and ‘bird.jpg’ in the presentation earlier. Just wanted to point it out.

[jkorte (Jessica Korte)]

Is there somewhere I can get more info on the project which used recurrence plots as input to DL? (mentioned by Jeremy in the lecture just now; I missed if there was a reference)