Lesson 4 In-Class Discussion ✅

Part 1 (2019)
440

Experienced folks: How to set up Vim environment like Jeremy?

16 Likes
441

The smoothness of the curve

442

@Rachel 6+. People wanna be cool Deep Learning practitioners like Jeremy.

1 Like
443

copy his .vimrc file?

4 Likes
444

Rather ask for his .vimrc file to share on forums.

1 Like
445

I will ask Jeremy when he finishes this thought, but here you can find a link to his .vimrc

9 Likes
446

Just like how in CNN each subsequent layer combines features (learnt) from previous layers (curves, lines, etc.) to deduce more useful info, in this what is the intuition (what is learnt) at each subsequent layer of the network? Is there any good analogy?

3 Likes
447
448

https://www.youtube.com/watch?v=F90C0A6UmVI

https://www.youtube.com/watch?v=GK1XhPM3K0g

Use the 2nd one

449

What is squeeze?
res = dot.sum(1) + self.u_bias(users).squeeze() + self.i_bias(items).squeeze()

3 Likes
450

Using a sigmoid seems reasonable, but doesn’t that build in a bias, or somehow skew the results sort of like if you remove all the UNKs from the NLP case?

451

Can we use VS Code on a remote machines?

452

If any of you have a good guide to use the features Jeremy just alluded to in vs code that’d be great !

453

Does anybody from fastai team use a visual debugger or IDE? It seems like you’re all perfectly fine with Vim and Jupyter =) Do you prefer set_trace (or breakpoint) calls instead of using UI tools?

4 Likes
454

squeeze is a PyTorch method to remove a dimension.

4 Likes
455

Any intuition about what this neural network learns in each intermediate layer (like the visualization he showed for CNN)? - that would help us understand what representation the network is building/improving…

3 Likes
456

same question for NLP?

457

@rachel I hope didn’t forget this one! :slight_smile:

1 Like
458

Not unless you’re Remote-Desktop-ing into it where you can see the graphical user interface. VSCode is a windowed, GUI app; not a terminal app.

459

Would X11 help?