Hey Veeky Forums...

Hey Veeky Forums, I'm creating a machine learning model to classify pictures and predict the market based on the ratio of bog/pepe/wojak/other posts.

Send me a picture to test it on. It's still a work in progress. If the pic you send is one of the above it'll get added to my training data.

Pic related, percent chance the model thinks it's in a category.

Attached: Output_screenshot_18.03.2018.png (800x754, 72K)

Other urls found in this thread:

twitter.com/cryptoballoffcl

Attached: jo.jpg (3200x1680, 578K)

The bog/normal data definitely needs the most work.

Attached: john_oliver_judged.png (800x420, 451K)

Attached: 1520795442578.png (670x700, 295K)

Attached: guesswho.jpg (259x194, 15K)

Gonna add this to both the pepe and wojak datasets.

Deformed wojaks like that are harder I guess.

Attached: together.png (800x835, 381K)

The outline of the merchant looks a lot like Pepe, actually.

Attached: merchant.png (800x599, 282K)

Bump, give me more data fuckers.

>market sentiment analysis for images
>no sminem section

don't waste your time breh

Give me some smimen and i'll add him in.

congrats im gonna make a program that randomly post pink wojaks when the price is going up and green nujaks when the price is going down
hahaha faggot

Please do. I can grab the signal out of that.

Attached: 1514925556528-biz.jpg (500x750, 64K)

sure you can kiddo
ill murky your signal more than you could ever imagine
i graduating top of my class of software engineering btw

Attached: got_it.png (800x1200, 943K)

Got any good jobs lined up?
>Implying GPA matters.

Attached: berry-valentine.jpg (282x299, 22K)

Attached: 1521388623223.jpg (1080x1349, 85K)

>i graduating
sounds like its from a top university, user

Attached: fuck.png (800x848, 270K)

Attached: 57B7B013-6B49-4CEA-A2FF-208089AA2C31.jpg (396x382, 48K)

Attached: it_can_tell.png (800x999, 600K)

Attached: thinks_its_a_wojak.png (800x771, 352K)

you need special brrrrrrrrrrrrrrrrrrrrrap and trap categories for Veeky Forums

Attached: carlos.jpg (1280x720, 73K)

Attached: nothing.png (800x450, 332K)

Attached: usdt.png (200x200, 15K)

Attached: tether_confirmed_pepe.png (800x800, 28K)

Now the real question since 50% of shitposts on Veeky Forums are about it.

Attached: linky.jpg (694x800, 71K)

also i'm quite certain this wojak will be pepe

Attached: 1521103501572.png (646x700, 166K)

Attached: Fibwojack.jpg (1217x1685, 1.12M)

Big if true

Attached: BD6023C4-A822-4157-95CC-C65D2C8F629E.jpg (250x250, 16K)

>Nothing

Attached: stiny_linky.png (800x922, 384K)

Attached: 1474924931266.jpg (761x915, 107K)

Attached: oold5ygcwlcy.jpg (540x378, 34K)

>bog 0%
never ever above $1 confirmed

Attached: 1520578596610.jpg (472x472, 27K)

Attached: 1417862633609.png (1000x1000, 51K)

can you make a program that counts how many times a coin is mentioned to see which coins are being talked about most and least on Veeky Forums?

Already exists
twitter.com/cryptoballoffcl

Can you make a trading bot that takes the latest 100 images on Veeky Forums and decides whether to buy or sell depending on the Pepe/Wojak ratio.

Attached: pard.png (241x241, 60K)

You're right, but I was close.

Attached: greenie.png (800x866, 217K)

Attached: def_confirmed.png (800x560, 563K)

would it be better for the machine to concentrate on the top 100 used images of pepe and wojak? Pareto principle.

That's the idea.

Attached: baby_pepe_wojak.png (800x800, 205K)

Oops didn’t see other reply.

The images often get edited slightly, but I may weigh those images more based on how often they appear. I need a lot more training data.

See if it recognizes this.

Attached: 1519487972459.jpg (904x583, 325K)

Here's an easier one.

Attached: 1517849062966.jpg (225x224, 9K)

Attached: kamikaze_pepe_judged.png (800x515, 462K)

Here's a bit harder.

Attached: 1521069357156.jpg (960x720, 501K)

After I threw it in azure's computer vision API

{ "tags": [ "plane", "airplane", "flying", "skiing", "air", "small", "smoke", "red", "jet", "blue", "snow", "white", "man", "riding" ], "captions": [ { "text": "a plane flying in the air", "confidence": 0.5739788 } ] }

Attached: 1521351708059.jpg (485x443, 40K)

Impressive.

Attached: 1514739638927.jpg (900x900, 77K)

Attached: wrong8.png (800x796, 194K)

Seems like the change in outline throws it off.

Attached: furry_wojak_judged.png (800x600, 629K)

Attached: judged_grug.png (800x730, 295K)

Strange that it recognized the plane one so accurately.

Maybe it was the coloring.

Attached: 1518919577788.jpg (466x615, 65K)

Attached: 56F89342-D533-4E63-BD0D-C22BF0C81EA2.png (600x600, 345K)

Attached: 100_percent_pepe.png (800x800, 479K)

Does it false-positive smug anime faces as wojaks?

Attached: C9ZlmpwWsAEP7ff.jpg (478x380, 27K)

The pictures are a response to the market movements, so unless you implicitly conjecture that Veeky Forums and the markets are an effective feedback loop, you're basing predictions off of reactions to past events which makes no sense.

Very nice.

Attached: smug_face_anime_girl_steam_avatars.jpg (184x184, 7K)

Try this.

Attached: 1498261440064.png (280x291, 88K)

Yeah, guessing color. Not a hint of green there.

Post more bogs fuckers.

Attached: tritium.png (800x1055, 922K)

Almost.

Attached: almost_wojak.png (800x635, 399K)

Definetly a wojak

Attached: FOR_SURE.png (800x831, 245K)

This, the pictures usually imply some sort of emotion behind it.

I.e. there's a difference between a suicidal pink wojack and a green wojack with arrows flying behind him

Yeah. I'm probably gonna add more subcategories.

desu my plan is less to trade with it and more to see if the ratios actually correlate with market movements over time, just as a side project.

I see

Try this on for size

Attached: incoming-call-verizon-wireless-bogdanoff-reject-call-with-message-14385930.png (500x555, 52K)

Does he false-positive as a bog?

Attached: benedict-cumberbatch.jpg (2034x2940, 1.01M)

Green must have thrown it off.

Alright, give me a minute. Going to re-train it.

Shit, forgot image.I'll do it next.

Attached: strang.png (800x888, 235K)

Confirmed descended from ancient bloodlines

Attached: confirmed_cumber.png (800x1156, 1005K)

Attached: 1515263652097.jpg (400x400, 27K)

Attached: h6nqzAAq_400x400.jpg (400x400, 19K)

I think that's it for tonight, thanks for the data!

May return later this week with more refined models.

Well, it's pink.

How does your algorithm work, OP? Do you detect the most common color in the picture? Or maybe feed the bot some hashes of common images (which I would find very troublesome)?

Attached: wojak_wilde.png (500x480, 119K)

add mutts to algo

Attached: 20f947c0a41e6ed495867441e9d2c16c.jpg (600x600, 38K)

Neural network.

Just multiple layers.

The whole point is I don't know how it works. I just feed it the training data.

how about dis?

Attached: nolonger.jpg (800x600, 138K)

Attached: index.png (229x220, 8K)

Attached: 1519275219019.jpg (512x512, 59K)

Attached: 1521185698382.jpg (409x395, 56K)

Attached: 312fj.png (441x429, 278K)

Attached: IMG_6662.png (960x1280, 1.26M)

I already did this, it basically parses OP images in the catalog and returns a coefficient which evaluates overall market feeling

As a friendly pointer, bog posts provide no meaningful insight or data

You are what Clif High aspires to be.

Attached: 1521273698344.jpg (893x1024, 130K)

Attached: 1519535910600.jpg (720x720, 47K)

Nice; what features/images did you end up parsing out as important?

If you want to share, ofc.

Rolling

Attached: 5B420467-0E22-4105-AF38-FCB26E0AFDDD.jpg (905x905, 209K)

How large is your current data set and how long did you spend preparing it?

make the bot run every 30 minutes or so and have it post the results to a private telegram channel that us Veeky Forumslets can see. this is an interesting project desu

Attached: IMG_2141.jpg (3200x3200, 888K)

~100 images each. I need more. Not very long.

Share the link of the GitHub repository OP. Once you are done

Try this

Attached: 37d.png (1037x1037, 1.09M)