Quickdraw with Google AI | Hacker News Reader

Quickdraw with Google AI

quickdraw.withgoogle.com

132 pointsaloknnikhil45 comments

Many people here have pointed out that the data is available -- https://github.com/googlecreativelab/quickdraw-dataset

I toyed with it some time ago and was impressed to see that -- in the raw data set -- each drawing is a time-series of strokes i.e. you get a person's drawing (of a penguin, the Mona Lisa, etc.) after 0.1 second of drawing, after 0.2 seconds, etc.

I made and (shameless plug!) sell giant algorithmically generated posters which illustrate and play with this idea: each group of 8 rows shows doodles after a decreasing number of seconds. It's fascinating to see how someone's drawing of a "koala" is pretty much set for "success" after a few strokes, while other drawings don't ever really improve with time... or how universal and "well-defined" are drawings of matchsticks, unlike those of kangaroos.

https://gumroad.com/l/quickdrawposter if anyone's ever so inclined!

Cheers

This is neat!

Love that!

I too was inspired to use this dataset in some way, and made this toy program where you point your camera at your face, and it renders your eyes and nose as doodles (and barfs out more if you open your mouth): https://github.com/goberoi/sketch_face

That's really great, congrats! I'm sure that a web/javascript version of that would be popular.

Let me know if you'd like to do a quick collaboration!

Thanks. Alas I don’t have bandwidth to take it on, but encourage you to do so wholeheartedly. Bonne chance!

Maybe needs a (2016) in the title.

Past discussion: https://news.ycombinator.com/item?id=12965311

What is amazing takes the fun away at the same time: The detection is way too fast/early. For example you are tasked to draw an octagon, the detection will already trigger once you drew three lines that are roughly aligned at 135° to each other. Draw an elephant? I can see there is something that remotely looks like a trunk and there is an attempt to draw an ear that's merely a stroke at this point. It's an elephant alright!

Things like that made me play the game in a different way: Draw it so the AI won't detect it but a human would most likely instantly recognize it. Example: Microphone. Just draw a microphone hanging from a two-segment microphone arm. Start with the arm and add the microphone last and draw a circle around it or point at it. Clearly someone would recognize this as a microphone, while the AI struggles and thinks it's something completely unrelated.

Check this repo out - didn't make it but I use it to teach my students about adversarial learning: https://github.com/jayelm/bad-flamingo

That's how I play this too! I've found it's very very bad at dealing with rotations. Carrot right side up? No problem, carrot at a 230° angle? It'll never figure it out.

"Draw Flip Flops in Under 20 Seconds".

And, of course, I wasted half of it trying to remember what a latch circuit looked like. Before remembering they probably meant beach shoes.

I read the title as if it was some kind of classic Macintosh API to Google’s “AI”.

The title needs rethinking.

When I read the headline, I thought it was QuickDraw, and it was going to be some kind of classic MacOS / Google mashup.

Same here. This is "Quick, Draw!".

The punctuation is important. Like "Works on Contingency No Money Down".

"Let's eat grandma"

As a few other other have pointed out, the data from this game is open-source and accessible in number of ways [1].

For an introductory exercise to deep learning for image classification, it's a great alternative (or follow-up) to the classic MNIST dataset [2], which serves as a common "Hello, world" for image-based ML.

We trained and deployed such a model for a demo of our mobile ML tool [3][4]. Feel free to ping me if you're interested, would love to chat.

[1] https://github.com/googlecreativelab/quickdraw-dataset#get-t...

[2] https://codelabs.developers.google.com/codelabs/cloud-tensor...

[3] https://imgur.com/UagduZX

[4] https://palletml.com

Is there any way to get to a “free-play” mode? I’d like to just try drawing stuff and see if the AI gets it.

Link to previous discussion on HN, 4 years ago! https://news.ycombinator.com/item?id=12965311

I assume this is picking from a predefined set of things? As in not all nouns, but a smaller list of possibilities. Otherwise it is pretty impressive that it went 6 for 6 with my terrible drawing abilities.

It has to be. I was prompted to draw "police car", and started about drawing a regular car with a siren on top. It guessed police car before I was even done drawing a generic car body - so I assume it wasn't trained on just a regular "car".

Edit: I was half wrong. It is selecting from a limited list, but both police car _and_ a regular car are actually in that list. https://quickdraw.withgoogle.com/data

I’m not sure I understand it. It prompts you to draw a certain thing, then it “guesses” what you drew, but of course it already knows because it just told you exactly what to draw. Maybe I’m missing something but the game makes no sense. If I told you what to draw then tried to tell you what you were drawing I’d get 100%.

It would be better if it just said “draw something.”

> of course it already knows because it just told you exactly what to draw

It's a computer. It doesn't know that unless it's explicitly told to remember it.

You can very easily test this by just drawing whatever you want as if it did say "draw something". It's very accurate at guessing any of the objects in the dataset, even if it's not the one you're meant to be drawing.

By telling you what to draw, Googles gets a training set of drawings and their (sanitized) descriptions.

It'd be cool if the learning set was built on humans coming up with challenges and then strangers drawing them, and then them being guess by a third person, and then validated by the challenger as true/false.

I drew a beautiful sea turtle; I was sure it was going to guess it! But no, it couldn't. Then I checked the training set, and it was full of tortoises...

I guess they should check their training set :P

Hrm, I'm not sure maybe it was a fluke, my drawing is terrible https://imgur.com/a/R8KE87K

don't be too hard on yourself, it wasn't able to recognize my badly drawn rake

I made a camera version of this a few years ago (https://www.youtube.com/watch?v=GEUrMbx_uac) using QuickDraw to train the model. I generated thousands of paper-like backgrounds (grayish noise) and pasted the raw drawings on top of it to generate JPEGs.

I love using this as an English Foreign Language teacher. I just wish I could choose a subset of the vocab because some of the words are a bit obscure like "megaphone"

"Draw the mona lisa in under 20 seconds"

Who do you think I am?

(2016)

https://news.ycombinator.com/item?id=12965311

Hmmm...

https://m.imgur.com/a/y73R5Ir

Here is mine : https://i.imgur.com/5Ul3x0e.png

https://i.imgur.com/wS4bMIi.png

I remember it worked better in 2016...

Well, I learned the I’m bad at drawing :(

It doesn't recognise dicks, even though I'm pretty sure it's, uhm, well trained for that.

Draw: Sock "I see socks" "sorry I couldn't guess it"