Lesson 8 (2019) discussion & wiki

Part 2 (2019)
2
3

I think its lesson 1 instead of Lesson 8.

1 Like
4

I believe the lesson orders are all connected. Part 1 had the first seven lessons. Part 2 will have the next set of lessons starting at #8.

8 Likes
10

It is lesson 8 mod 7: )

10 Likes
21

https://www.crestle.com/dashboard

I don’t see the course ml2 link, will it be open soon?

1 Like
38

Small question before the beginning of the lesson : how redundant is part 2 v3 with part 2 v2 ? Is it worth it to go through part 2 v2 after finishing part 2 v3 ?

40

I got them from github: https://github.com/fastai/fastai_docs/tree/master/dev_course/dl2
which the forum tells me @jeremy also posted here recently.

41

The notebooks for today’s class look great!

2 Likes
43

Gentle reminder to avoid @ mentioning unless necessary.

9 Likes
46

Noob tip:
I keep 2 setups:

  • Bleeding edge (pip installed)
  • Conda installed setup (For no bleeding)
13 Likes
47

What will the “suggested homework” look like for that new format of fastai part 2 ? In part 1 it was using what we saw in kaggle competitions for example, how to do that with the lessons focused on building fastai from foundations ?

1 Like
49

#off topic
Finally Jeremy is kinda teaching Python As well indirectly!
Thanks :slight_smile:

6 Likes
50

I’m so glad you asked the question! Homework is writing docs and new tests :slight_smile:
You will know how the library works, so you’ll have all the tools to do that!

29 Likes
52

what is the best way to study this part 2?

(for part 1 we learnt the best way is to watch videos 3 times, write blogposts and try blah). Is the approach for part 2 the same?

3 Likes
54

That’s another way to get lots of contributors to the fastai librairy haha :wink:

9 Likes
56

For the distributed training, will we examine multi-node single/multi-GPU in addition to single-node mult-GPU?

57

Not sure. It will probably will be single-node only.

58

I love the new direction of part2 of the course! Getting into the fundamentals can eliminate those last little bits of hesitation and delay when dealing with modifying and customizing state-of-the-art training algorithms. Also I’m very excited about the direction of performance optimization, distributed training, and the emphasis on engineering. I have already convinced our engineers to get into pytorch, and I will have a year or two before I can get them to get into Swift.

21 Likes
59

I heard Julia language is built for numerical computation, why not Julia instead?

5 Likes
60

Jeremy is answering it :wink:

2 Likes