Lesson 11 official topic

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

<<< Lesson 10Lesson 12 >>>

Lesson resources

Links from the lesson


If we are talking about DiffEdit in this lesson, I’m reaaaally looking forward to it! Hoping to learn some new stuff which will help with the work I’ve been doing on prompt editing :slightly_smiling_face:


Sometimes a paper has an associated explanation video posted to YouTube (especially if the paper is from a major research lab) and so it’s worth searching the paper title there or on Google video search to check if such a video exists.


To find the LaTeX symbols via drawing them in lieu of describing them in Google, I recommend Detexify: Detexify LaTeX handwritten symbol recognition


I haven’t tried it yet. LaTeX-to-Python
I expect some better converters exist?

1 Like

Anki Study Deck. Greek Letter for Deep Learning (fastai)


I see it will work on the foreground objects, Can DiffEdit be used for changing the background of the Images?

If you use negative queries that invert the mask maybe?

Theoretically, you should be able to mask the foreground object that you want to retain and then reverse the mask to mask only the object and let everything else be modified. That should allow you to modify the background …

1 Like

Background can have many attributes - Its will be difficult to engineer a prompt for that. But, I will look on it what can be done.

What is the approach of the course teachers to scan literature and pick up papers of interest this fast? Alert filters?

1 Like

Yes, It will work when there is a single object in foreground, But it is difficult when there are multiple objects in foreground.

You could define your foreground object and then expand the query engine so that you can use a symbol like ^ to select everything but that foreground object. So say if you want to change the background of the horse image, you could use “^horse on seaside” as a query.

1 Like

https://twitter.com/_akhaliq ← must follow!

Also if I find a paper I really like I will check the authors and if they consistently do good work I often will follow them on Twitter. Sometimes they will post their own tweets or even threads about their paper.


This thread could also be useful as well ML news - real-world examples - #2 by bencoman


These sites are also quite good to find trending papers:
https://mlfeed.tech/ and https://papers.labml.ai/papers/weekly


This site shows a aggregated list of new developments in AI. Kind of useful if you don’t want to go all over the place to find all the new papers :slightly_smiling_face:


A pure python implementation of broadcasting broadcasting.py · GitHub

def broadcast(a, b, op):

    if isinstance(a, Number) and isinstance(b, Number):
        return op(a, b)

    result = []
    if a.ndim == b.ndim:
        if a.shape[0] != b.shape[0]:
            if a.shape[0] == 1:
                a = cycle(a)
            elif b.shape[0] == 1:
                b = cycle(b)
                raise ValueError(
                    f"Could not broadcast together with shapes {a.shape} {b.shape}")
    elif a.ndim < b.ndim:
        a = cycle([a])
        b = cycle([b])

    for a_in, b_in in zip(a, b):
        result.append(broadcast(a_in, b_in, op))

    return np.array(result)```

Be friends with @johnowhitaker . Who in turn stalks https://twitter.com/_akhaliq on twitter. Noone knows how _akhaliq does what he does. Magic I think.