How I Made The Best GeoGuessr AI In The World 

Would love to see a more detailed video on how you actually created it/how it works in the background

Damn really impressive THIS IS YOUR FIRST VIDEO?

Thanks GabrielGeoo for taking me here

When the square guesser gives weights on each square it believes it could be, instead of picking the center of the most probable on, what about picking the gravity center of the weights.. wonder if that would increase performance a little bit, especially when squares are clustered 🤔 Great video!

The thing with this AI is the fact that it doesn't look at a map. It looks at tiles. If somehow this AI could lock the region and then search for road layouts and types and even topographic information… The government might be at your door

I am not intrested in AI or Geoguessing but the video was great and I am suprised it hasn't millions of views.

This is a banger video and deserves more recognition

Hi ! Where did you get the training data ? Are the images used for the training the same frames as the ones that are used on the geogussr maps ?

uh yeah this isn't concerning in the slightest and definitely cant be used maliciously

Great video! Always excited about new AI content creators. Hoping to see some more exciting stuff soon :)

Now this is the content i want to watch, high quality and educational on how to solve a problem

this is amazing stuff man, great video!

Truly amazing content. Keep it up!

That's amazing work, keep up

Out of curiousity, did you try to train a regressor on the x/y coordinate instead of a classifier? I think that it could help the system, because I suppose that it currently can be as much penalized for guessing a neighbor region as for guessing smg very far currently. Using regression would enable you to define your loss in such a way that it will penalize big errors an therefor the model will focus on avoiding this. Btw if you have a public github with your code, I would be happy to try it and make a merge request for you if it works.

Impressive work, keep going!

Really good video man, keep it up 👍

Awesome vid bro 👊🏻

Great project! I wish so much that this project becomes popular and receives incentives for improved new versions, and maybe becomes accessible to the public to play, setup, and contribute.

I was quite literally going to look into doing this myself and you beat me to it. Props to you!

Nice vid! Looking forward to the content :3

Great video, can't believe it hasn't blown out yet

Yooo the video is sick. I don't know why you dont have millions of views already lol The only thing that in my mind would've improved the video is if you described the technical part in a bit more detailed way, like where you got the dataset, how did you train the AI, etc. But that's just my opinion. Anyway, you got a new subscriber ❤

This is super impressive! As someone with a programming and (some) AI background I’d be super interested to see what the process was of building the dataset, I’ve scraped small google maps/streetview datasets but it got.. pretty large, would love to hear more about your process of building it!

release it open source and spark a community I really wanna see how far this gonna go ♥

amazing video!

How is this your first video! The quality is outstanding!

Great stuff!

What dataset are you using? Did you use the maps API or is there one available? I would be very interested in the code and further details. Btw great video

It'd be great if you visualized the attention maps of your ViT network as well, I would show what the network actually looks at. I would expect it to recognize some small-scale patterns like types of plants, letters, skyline. Plus memorization of the specific camera features (like color balance, crispness etc.) used in the different parts of the world. And did you try to run it manually on the images outsize its training distribution (like for example Yandex street view panoramas or just random photos or panoramas from the internet) to check if those 96%/50% hold? That is, how much it memorized the non-generalizable features (like camera, actual season in GSV) vs the generalizable features.

This is really cool!

This is amazing content! How do you only have 50 subscribers??

that is amazing also how is this your first video while also being an amazing video

Awesome video! Do you have a computer science background? :)

Wow, this is really impressive! What language did you use to send the coordinates to Geoguessr automatically? It could be improved by moving into a different country when it selects a country without coverage or a road with coverage. However, if it's between 2 roads with coverage, I think it could just hedge. Knowing the road angle could also help, I think it wasn't scanned in the input. This is a really good AI, I don't think I can make something remotely impressive as this though, and this is your first video!

This is an amazing video. I don’t understand how you have so few views.

Honestly. Compared to the amazing video quality. I am surprised this has not gone viral. anyway. keep it up!

Love it !!

Wow great video and great project. I am just wondering how did you collect data for training model and how did it take so little time to train it. And do you have some tips for someone starting with ai?

I thought I was watching some big youtuber who has a name in this field, surprised to see you are not, and wish you all luck and success!

great content

Really neat to see the transformer pick up on geo-specific hierarchical features so well

Amazing video, would love to see a more technical video! Open source ???

What's more insane about this is that this AI can't even read and you spend like what, a few days training it? Just imagine a full-blown huge AI trained by like OpenAI or something across months of non-stop training. It would probably be able to get the exact coordinates within like a few meters.

What impressed me the most about this video was your ability to quickly recognize the Korean power pole at 5:42

I would be very intrested in a deep dive on how you built all the project 🎉

this is fr really good but whats better if you make it use Elevation maps so it can be even more accurate its like when it sees a hills it specify the search just on the hills from the map

I would love a way more in depth machine learning vid on this plz 🙏🙏

Imagine making this a tool for reverse searching. Users can upload a photo and know exactly where it was taken

I have a feeling the AI could become nearly perfect if it could also interact with the Map and this way get more context of the location it is guessing and thus perform better. It may take a lot longer to train and make predictions, but I think the boost in accuracy would be worth it.

so awesome!

It's insane!

Very impressive

Cool Video! Where did you get the data for you model?

how do you only have 700 followers ? Very cool video

its very imprrssive that something this simple can perform this good

I’d like to see some kind of graphic made from this AI that shows some kind of similarity between different blocks or countries. I wonder how much it picks up on camera quality.

This cool do you have a blog or a github related to this it would be interesting to check out.

Crazy

A bit disappointed about the title and what was actually in the video. "How I made the best Geoguesser AI in the world" -> "It's complicated, I just put 600 000 images to the model and trained it 18 hours." .. Yeah, ofc you put a shitload of images and their locations, but that's the part that is interesting, but 3/4 of the video was about playing against it. I really hope you're going to release a more detailed video. What hardware, libraries,, what was working during your test, what wasn't, data normalization, finetuning on geoguesser meta ( poles, roads, cars etc ), how you created the "region grid"All the interesting stuff is missing ! 😁

Super cool! Maybe you could give it the ability to move around?

i want to see rainbolt vs this ai now

We need an ai vs rain bolt

This is awesome. What dataset did you use? I can't find any with 600k samples online

Keep up the good work impressive af

Even if you don’t make a video on it, would really appreciate some sort of public source code on this. Myself and others have spent a lot of time on Geoguessr AI and this could be interesting to learn from.

I wonder if this can be used to develop new metas like how exactly did it region guess Peru what did it see that we might not have

Cold

I wish you'd explain the region guessing part a bit better, what is it looking for? how does it work? what specifically did you train it on?

Ur underrated

Marking down 185 subs for now- cuz I’m sure that will go up a lot

Only 45 subs??? First 50, remember me when you blow up!

This one is gonna be a viral

The Toxic Avenger soundtrack is a perfect fit for this video 🤩

If this thing could scan for road direction it could be reliably getting 5ks

Duude awsome

not bad!

Just save the photo and location every time it gets confused then train it a bit more on just those places once you got maybe 50 stored up.

Good luck with your youtube carrier, it's peak

get rainbolt on it boys

what about a more algorithmic predetermined approach for a bot to play it? like recognizing tree species or flowers and cutting the area down to a smaller radius?

You should release the model weights

crazy

Would really love to play with this. Can you make it open source?

Really small but really powerful. Sound familiar

Pretty sure a group of students from Stanford built a model for this that was extremely accurate.

Nice

Have thou thought of using the YFCC100 dataset in addition to google maps?

I didn't hear you say anything about separating you training and testing sets. Without doing that, the AI may just have "memorized" the images it was given during training, and it may not be able to generalize at all. I'd definitely want to hear more about the design of the AI.

nice would be to change a bit the AI brains to be able to get out useful insights in an automated way of what to look, and what characteristics the AI is using to guess the region. I bet there is dumb stuff that we overlooked that help to guess right. I would love to learn this stuff.

is the region guesser just a one-hot classification layer on top of the ViT?

Smart bro

Instead of using squares, could we use semantic geocell creation to leverage regional distinctions?

Can u make a tutorial on how to build this

Here before it went viral

But is it just overfitting on the training data or actually generalizing? How did you do your test/train/validation splits?

W video

Hi, this is my first year in university in A.I major, i was really interested on this project, is it possible to share the source for it and share some more details about the training process specially the square guessing model.

How is this your first video!?!?!?

Do you know to what extent minor image imperfections like humanly imperceptible smudges on the lens are used by the AI? Do you have a way of illustrating which part of a picture provide the most information?