Creating An AI To DESTROY Fruit Ninja

  Рет қаралды 870,593

Tyler Mommsen

Tyler Mommsen

Күн бұрын

Пікірлер: 444
@TylerMommsen
@TylerMommsen 2 ай бұрын
Sorry it's late guys, but here is the code if you're interested github.com/TylerMommsen/fruit-ninja-bot
@justjuniorjaw
@justjuniorjaw 2 ай бұрын
Image Recognition? Dog. Pig. Dog. Pig. Dog. Pig. Loaf of Bread. SYSTEM ERROR!
@goat_yllw
@goat_yllw Ай бұрын
@@justjuniorjaww mitchels vs the machines reference
@rainbowman4723
@rainbowman4723 Ай бұрын
do you think it would be possible to make this for mobile?
@CustomGameing
@CustomGameing Ай бұрын
​@@rainbowman4723nha i thik mobile software need different codes(I think)
@AceOrS
@AceOrS Ай бұрын
​@@rainbowman4723yes
@CuriosityIgnited
@CuriosityIgnited 2 ай бұрын
Just spent 10 minutes convincing myself that watching an AI play Fruit Ninja is the productive break I needed. Can confirm: still procrastinating.
@hamzamotara4304
@hamzamotara4304 2 ай бұрын
Psst. Stop procrastinating. Go do it.
@miguelcardoso5084
@miguelcardoso5084 2 ай бұрын
Not procrastinating, just doing side-quests
@Vo_tex
@Vo_tex 2 ай бұрын
i am doing the same thing
@whifle1445
@whifle1445 Ай бұрын
Doing the same
@wesleyneff5510
@wesleyneff5510 Ай бұрын
Same
@DavidKassa
@DavidKassa 2 ай бұрын
I’m kinda disappointed that the AI didn’t absolutely obliterate the pomegranates
@fizzlanderr
@fizzlanderr 2 ай бұрын
yeah seeing it get like 100+ slices would have been cooler
@Mikustan39
@Mikustan39 Ай бұрын
Same here. Might just not be good enough unfortunately.
@zincalloycopper2
@zincalloycopper2 Ай бұрын
Sword draw, first form: death by a thousand cuts
@KJ.420
@KJ.420 Ай бұрын
It would've been even cooler if it also went for combos as well, but it's just an algorithm that looks for given images and doesn't really know the game strategies, so maybe I'm expecting too much from it.
@dadoul9905
@dadoul9905 Ай бұрын
get a better cpu and you'll get better pomegranates
@mingamerking
@mingamerking 2 ай бұрын
I think allowing it to recognize how to combo fruits would make this even better, Ike have it wait before slicing and if multiple fruits are on the screen it does one big slice
@gameplaysuffering1620
@gameplaysuffering1620 2 ай бұрын
yeah but that would add like 2 to 5 years to dev time
@justascreamingcat2964
@justascreamingcat2964 2 ай бұрын
​@@gameplaysuffering162099% of that time being procrastination
@justenoughrandomness8989
@justenoughrandomness8989 2 ай бұрын
yeah
@dillzilla4454
@dillzilla4454 Ай бұрын
i got one even better, make a simple bot slice where there is motion with the bombs being a no-go zone determined by image recognition. this means it is only looking for one item, allowing it to be quick and confident in its determination, allows it to pretty easily do combos, and makes it much more responsive when slicing the fruits
@ryforg
@ryforg Ай бұрын
1:43 that’s why captchas have you identify common things found on streets. You are training their self driving car ai.
@anonym5160
@anonym5160 2 ай бұрын
No fruits are being harmed in the making of this video.
@ika32
@ika32 2 ай бұрын
more like no bombs
@Mrshaep
@Mrshaep 2 ай бұрын
he probably ate one during it
@hamzamotara4304
@hamzamotara4304 2 ай бұрын
No, fruits were harmed in the making of this video.
@mr_pigman1013
@mr_pigman1013 2 ай бұрын
Liar liar pants on fire
@Randomname-yb7hs
@Randomname-yb7hs 2 ай бұрын
Except for the ones that were
@theradomguy5581
@theradomguy5581 2 ай бұрын
Big props for making an Ai on the orginal game! Happy to see that rather then a recreation of it
@elliott6158
@elliott6158 2 ай бұрын
I feel like the recreation is just as cool
@elliott6158
@elliott6158 2 ай бұрын
it shows off more fundamental ML concepts rather than "I imported an image recognition library :B"
@slouch186
@slouch186 2 ай бұрын
​@@elliott6158agreed. i much prefer ML stuff when the AI has access to the data behind the game rather than just recognizing screenshots
@GwnTim1
@GwnTim1 2 ай бұрын
I love how the AI was 95% certain that the bomb was a bomb, and as soon as it hit the bomb it plummited to 80% like the AI said "nuh-uh, that wasn't a bomb THAT WAS NOT A BOMB!"
@morphe904
@morphe904 Ай бұрын
I‘m guessing that the bomb as it was exploding, was looking less and less like the bombs the AI was trained to recognize
@HitSpaceGD
@HitSpaceGD 2 ай бұрын
If the AI sliced the menu fruit (🍉 = play again), it could keep training for hours.
@jmvr
@jmvr 2 ай бұрын
Well, it's not training when it's running, so all you're doing is making it play forever, without it being trained on anything. Maybe a modification to it to make the current AI model train a new one while it plays would be cool, but wouldn't be necessary, because this isn't meant to be a perfect AI
@gaymerjerry
@gaymerjerry 2 ай бұрын
this ai is just the photo recognition if you want it to learn to play the game better youd need a neural network thats fed the image recognition ai data as an input
@modzyy
@modzyy Ай бұрын
​@@jmvrit takes more pictures while its running which can be used for training later on, this is common sense.
@jmvr
@jmvr Ай бұрын
@@modzyy key word: _can_ be. It's not currently made to train a new AI. All it does is take a screenshot, analyze it, and do some input. Then the screenshot may as well be discarded, because it does not use the image further. As well, AIs are trained at a specific point in the process, but aren't trained further. For example, ChatGPT will not get better when people use it, and neither will most AI models. Typically when an AI trains itself, it gets worse. By definition, the day it doesn't is the day of the AI singularity, where it can improve itself into infinity
@modzyy
@modzyy Ай бұрын
@@jmvr yap yap yap
@weetikveelpik-wq5bx
@weetikveelpik-wq5bx 2 ай бұрын
0:39 amazing, well said
@tuloxe
@tuloxe 2 ай бұрын
totaly on your side 😂
@evereq8970
@evereq8970 2 ай бұрын
Language..
@evereq8970
@evereq8970 2 ай бұрын
​@@tuloxelanguage..
@Sensei-Ollie
@Sensei-Ollie 2 ай бұрын
@@evereq8970what?
@weetikveelpik-wq5bx
@weetikveelpik-wq5bx Ай бұрын
Fym language?​@@evereq8970
@GemedetAdept
@GemedetAdept 2 ай бұрын
If you think about it, YOLO (c. end of the world, 2012) and YOLO (object recognition) are really the same thing: You'll find out *very* quickly that You Only Live Once if You Only Look Once while crossing the road!
@DanielLCarrier
@DanielLCarrier 2 ай бұрын
Unless anime was right and you find out that you live at least twice.
@windy5405
@windy5405 2 ай бұрын
@@DanielLCarrieronly work if it’s a truck with its headlight open
@locrianphantom3547
@locrianphantom3547 2 ай бұрын
@@windy5405Or a tractor going 2 mph.
@lunademorgan
@lunademorgan 2 ай бұрын
​@locrianphantom3547 no not Kazuma.
@iresineherb7
@iresineherb7 Ай бұрын
Man that 2012 was awkward
@gregoryk4365
@gregoryk4365 2 ай бұрын
So painful seeing him do all this when he could've just had something search the specific pixel color of the fruit/bombs to slice them instead of training a whole ai to recognize fruit
@blizyon30fps86
@blizyon30fps86 Ай бұрын
Exactly
@sakshambaranwal132
@sakshambaranwal132 Ай бұрын
I am guessing that if he did that then the ai would proceed to again cut the fruits which have already been sliced
@Mostsanewriomain
@Mostsanewriomain Ай бұрын
@@sakshambaranwal132I can totally imagine the AI doing that
@kabii
@kabii 2 ай бұрын
i would love to see an updated version of the ai, doing fruit combos because atm it slices each fruit individually it would be so satisfying if it would do the best slicing combos possible
@Solrex_the_Sun_King
@Solrex_the_Sun_King 2 ай бұрын
Now teach an AI to play feed the deep.
@samstromberg5593
@samstromberg5593 2 ай бұрын
This channel is the most perfect example I have ever encountered of a Blue Ocean Besides maybe the Wright Brothers
@arthurkaramazov8932
@arthurkaramazov8932 2 ай бұрын
Amazing video, thanks! Can't believe you have only ~7k subscribers. 🔥
@Jallahruud
@Jallahruud 2 ай бұрын
Your channel is gonna blow up dude this is really high quality and entertaining content. Keep it up!
@server642
@server642 Ай бұрын
Trajectory prediction would be wicked to see! Especially in the case of avoiding a slice if a bomb will intercept. And couple that with what I’ve seen others say: getting combos by slicing multiple fruit in one motion. If it can predict the best time to get combos based on the trajectories, I’d love to see how high a score it can really get 😈
@clivah1499
@clivah1499 2 ай бұрын
some time ago, they needed pigeons to do this.
@HitSpaceGD
@HitSpaceGD 2 ай бұрын
I think England still does
@ThisIsAHandle-xz5yo
@ThisIsAHandle-xz5yo 2 ай бұрын
They needed pigeons to play fruit ninja for them?
@HitSpaceGD
@HitSpaceGD 2 ай бұрын
@@ThisIsAHandle-xz5yo I guess
@lukasschriefer799
@lukasschriefer799 2 ай бұрын
Bro, I agree
@musictomyshears
@musictomyshears Ай бұрын
It would be interesting to try a roguelike - pixel dungeon/shattered pixel dungeon is FOSS, and I haven't seen anyone do anything like it. You'd have a variety of skills the AI would have to learn: fight mechanics, resource management, item mechanics and selection, synergies etc. You'd probably choose just one class, and since it's FOSS, if it's too complex you could easily tone it down by reducing items, making it set seed, making item generation deterministic, just doing one floor etc (but it'd be a hell of a video to do the whole game haha but maybe there's a reason no one's done it before).
@number1-willstetsonsimp
@number1-willstetsonsimp Ай бұрын
that sounds actually sick
@solodemon8465
@solodemon8465 Ай бұрын
8:00 Mangoes have as much vitamin C as oranges
@Label_sabke_niklenge
@Label_sabke_niklenge 24 күн бұрын
Loved your hardwork ❤❤😂
@kogames3191
@kogames3191 2 ай бұрын
absolutley amazing video and also very educational, nice man
@GameJam230
@GameJam230 2 ай бұрын
I’m not sure how feasible it would have been to decompile the game and get the models for the fruit and bombs, but if those are obtainable then would it not have been easier to train the AI using screenshots of those models rotated programmatically? Then, instead of searching the entire screen space for fruit, you only need to look in areas with a significant amount of pixels changed between consecutive frames, as these locations have either a fruit or bomb in them. However, if it’s a fruit, then you don’t actually care WHICH fruit it is, you cut it regardless. You ONLY need to care about whether or not it’s a bomb, and so when screen pixels change in an area, check the surrounding region for a bomb. If a bomb is not found, cut, otherwise avoid. It should be noted too that this approach would likely have issues with areas where bombs and fruit overlap, but that can be dealt with. This approach could ALSO be done without the decompiled models at all, instead only providing the model with gameplay screenshots of bombs and fruit overlapping bombs. By providing the AI with these images, it alerts it NOT to cut them, but if it DOESN’T see matches for that data, it DOES cut whenever it sees changed pixels. The main efficiency of this comes from not needing to run image recognition for each individual fruit, and also not running image recognition checks over the whole screen constantly, but instead only in surrounding regions where changed pixels are when those changes occur.
@mayzar8646
@mayzar8646 6 күн бұрын
Cool it’s another KZbinr that is underrated and has good content (:
@XX-ot4pb
@XX-ot4pb 5 күн бұрын
Hi, I love your channel! I would say it is the best channel for game AIs, I love your videos. I am wondering what tool you use to train the YOLOS; thanks!
@martinkoblitz1285
@martinkoblitz1285 Ай бұрын
it would have been so much cooler if the ai would have learned to slice more then 1 fruit at a time but still a really cool vid man keep up the good work! : )
@jamieehoover3132
@jamieehoover3132 Ай бұрын
omgg you’re only 9k subs ?! you deserve way more
@sunofabeach9424
@sunofabeach9424 Ай бұрын
python is simple to created an image recognition AI with, but it is so slow that by the time it has finished processing the image the results are already outdated. this pretty much sums up this whole situation where the most performance dependent tasks are solved with one of the slowest languages out there
@ahdog8
@ahdog8 Ай бұрын
Generally, doing image recognition in Python involves making calls to some library that is actually written in C (or a similar, actually fast language). As a result, relatively little time is spent in Python-land which mitigates the slowness of the language. I don't know what the code used in the video looks like. There could be a bunch of complicated Python code that slows it down. Or maybe it's not Python's fault at all.
@sunofabeach9424
@sunofabeach9424 Ай бұрын
@@ahdog8 I know that Python libraries utilize C, however, the overhead that Python introduces is still too much even for complied C code
@DANIDANI310
@DANIDANI310 27 күн бұрын
In the same way you can teach AI to recognize an enemy soldier and an ally and make it shoot in less than a second. AI is becoming scary .
@blubaylon
@blubaylon 4 күн бұрын
Well yeah, that's how classification algorithms work lol
@Me-0063
@Me-0063 2 ай бұрын
Great video! I would suggest adding combos
@HùngNguyễn-z8z7v
@HùngNguyễn-z8z7v 28 күн бұрын
May be another way of approaching this problem is using the AI to detech the colors instead of the fruit themselves? Because the background color is distinctive.
@HSonyoutube
@HSonyoutube Ай бұрын
Here's another challenge for you. Try hitting combos. Basically you've got to track the motion of all fruits by taking continuous screenshots. By that you can make predictions on when a bunch on fruits might be closest to one another. And make a hit. And hit individual fruits only when those are at the end of downward motion
@nostew1604
@nostew1604 21 күн бұрын
throw the gameplay into after effect -> use motion tracking -> render sequence of image -> label into seperate folder and auto rename much more easy way to do the labeling task
@pawansapkota3970
@pawansapkota3970 Ай бұрын
Yes using the predicitons from the previous models and reannotating is the best option for the faster finetunning of the model.
@Johnny31323
@Johnny31323 2 ай бұрын
A pixel search algorithm would've been faster, via color indexing. All fruits have one solid color, so having a simple hex variation of lets say (green) for an apple 🍏 would be way faster and probably even better to find all the fruits. Same goes for the bomb since it is a solid black color, so the AI never would try to attack it within a solid square hit box on screen.
@HappyMajor
@HappyMajor 2 ай бұрын
that wouldnt work with bombs you need to use the red outline for them to get their actual hitbox the rest is fine as is tho if u wanna go fancy u can go with outline detection or just as u said a simple HSV range for each fruit #edit another problem would be the already sliced fruits since they have the same color
@lekkobot
@lekkobot 2 ай бұрын
I feel like that might cause issues with the ai going after splatter.
@HitSpaceGD
@HitSpaceGD 2 ай бұрын
​@@lekkobotWhen the reply has more likes than the original comment:
@-CENSORED0-
@-CENSORED0- 2 ай бұрын
@@HitSpaceGDthat’s called a ratio young one
@HitSpaceGD
@HitSpaceGD 2 ай бұрын
@@-CENSORED0- thanks for enlightening me 👍
@aleksanderwalenciej
@aleksanderwalenciej Ай бұрын
You could’ve tried first idea of image recognition but with checking only for range of colors. And the fruits would have a specific range of it. When you would make it small for each fruit it could’ve worked
@Krissoh
@Krissoh 2 ай бұрын
You could make a system of hierarchies, where the AI ​​cuts the least important fruits first and then the most important ones, this way you could avoid cases where it cuts the pomegranate fruit, losing the other fruits.
@shaynegoldstein1329
@shaynegoldstein1329 Ай бұрын
i think just using color to find everything that isnt a bomb would be faster. the red and black on the bomb look unique.
@call_me_ondreo
@call_me_ondreo Ай бұрын
You can easily increase your model speed if you use lower screenshot resolution (not a game resolution), then turn image black and white, then use color contrast to make objects looks clear. And also, check to click on fruit little bit away from bomb.
@T110-E5
@T110-E5 Ай бұрын
Way too underrated channel ❤
@joselopes9061
@joselopes9061 2 ай бұрын
Idk if it is only me, but here: 5:40 you could have put only the AI Vision or 20 seconds one 20 seconds another. The both at the same time are weird.
@SasamuelTheCool
@SasamuelTheCool 2 ай бұрын
Vision issue
@Not_A_Lazy_Dev
@Not_A_Lazy_Dev 2 ай бұрын
@@SasamuelTheCool maybe brainrot isn't that bad, maybe the attention span of a goldfish isnt that bad ... MAYBE FAMILY GUY, SUBWAY SURFERS, MINECRAFT PARKOUR AND ROCKET LEAGUE CLIPS ALONG WITH THE ACTUAL VID AT THE SAME TIME ISN'T THAT BA-
@BlankyB4
@BlankyB4 20 күн бұрын
Who gonna tell bro 😭🙏
@KoonKlausGamer
@KoonKlausGamer 28 күн бұрын
2:15 respect this job
@castleofwonders1
@castleofwonders1 2 ай бұрын
You're doing a great job in content creation.... 🎉
@Pavlov-shack
@Pavlov-shack 16 күн бұрын
It was pitch black in my room watching this a inch away from my face it felt like a real flash bang
@Punch_Card
@Punch_Card 2 ай бұрын
wake up babe Tyler just uploaded a new video
@Poonda-ju8xe
@Poonda-ju8xe Ай бұрын
I love Yolo Ai. Amazing for digital surveillance and AI cheating in games like Counter Strike. What an amazingly versatile piece of software.
@josephholman2401
@josephholman2401 Ай бұрын
If you wanted to improve the ai, you only need 3 frames and some calculus to predict the exact trajectory of the fruit meaning you'd be able to slice every fruit on the 4th frame that it's on screen
@mathew6041
@mathew6041 2 ай бұрын
1:58 lies, i have done this, but did absolutely nothing with it :)
@En3vity0
@En3vity0 Ай бұрын
3:24 the voices- they won’t stop…
@Nightly_MiniMilitia
@Nightly_MiniMilitia Ай бұрын
FISH
@mohammedalhammadi3547
@mohammedalhammadi3547 13 күн бұрын
3:18 You know bro's been taken by the Terminator when he called the AI "His"
@iPxter
@iPxter 2 ай бұрын
What program did you use for the labelling of the objects at 2:16?
@TylerMommsen
@TylerMommsen 2 ай бұрын
Roboflow
@gg-gn3re
@gg-gn3re 2 ай бұрын
0:55 you use spiral detection from center and dynamic bitmap or just color tolerances. It'd take several thousand times less processing power and work about the same. Things like simba have made this very easy for decades
@peterchristensen8843
@peterchristensen8843 Ай бұрын
Color ID won't work well since the fruits splatter after being sliced, meaning your AI would continue slicing fruit juices long after the fruits were sliced.
@gg-gn3re
@gg-gn3re Ай бұрын
@@peterchristensen8843 that isn't ai
@Guns4Peace
@Guns4Peace Ай бұрын
Bro you chose the most complex way, all what it needed was an image recognition only for the bomb and for other moving objects And an if statement If object != bomb Slice
@blubaylon
@blubaylon 4 күн бұрын
How would the AI be able to tell that fruits are on the screen?
@arkilagr5510
@arkilagr5510 Ай бұрын
Quick question, how did you get both visions side by side? I just wanna know for future use
@Usual_turtle
@Usual_turtle Ай бұрын
4:38 This is not a 77.78% difference. A 77.78% difference would be about 819118 pixels, not 2073600 pixels. It's actually closer to 43.75% difference.
@cyn7261
@cyn7261 Ай бұрын
it's a 77.78% difference from 1080p to 1440p and 43.75% vice versa but he should've said there's about a 1.6 million pixel difference between them
@MusicLabMadScientist
@MusicLabMadScientist 2 ай бұрын
Here before this channel BLOWS UP!
@mr.czesky
@mr.czesky 2 ай бұрын
TOP content bro
@DoobLand
@DoobLand 2 ай бұрын
should’ve made it insane at the part where it combos
@DEVY69420
@DEVY69420 Ай бұрын
now i want you to make an ai that can solve captcha
@IsaacLmao111
@IsaacLmao111 2 ай бұрын
This guy is godly
@achilles7498
@achilles7498 Ай бұрын
Ai's worst enemy, pomegranates.
@DinosaurusTerbaik
@DinosaurusTerbaik 2 ай бұрын
This guy worth more subscribers guys.
@Mazeop69
@Mazeop69 Ай бұрын
0:39 That was a little to personal 💀
@dillzilla4454
@dillzilla4454 Ай бұрын
there is a significantly faster way of doing this which is looking for clusters of pixels that have changed and only using the AI to detect the bombs to make sure those are in blocked off zones for the motion detection
@blubaylon
@blubaylon 4 күн бұрын
But then what would stop the AI from continuing to try to slice the fruits even after they've already been sliced
@whatevenisazero
@whatevenisazero Ай бұрын
We got fruit ninja aim bot before GTA VI
@tonic-music
@tonic-music Ай бұрын
Now you need a genetic algorithm model
@unclesamsonite-y3k
@unclesamsonite-y3k Ай бұрын
bros ai: if its green or blue or yellow then its a fruit but if its BLACK THEN ITS A BOMB
@akio.69
@akio.69 Ай бұрын
Me with yellow and green bomb.😈
@thunderd7904
@thunderd7904 Ай бұрын
The fruits and bombs are seemingly predetermined and the same every time, so could you just use reinforcement learning until your AI could get to a score of like 100,000? Also could scanning the screen for non black or non brown pixels work?
@GonFrecsses-kl8bx
@GonFrecsses-kl8bx 2 ай бұрын
I like that he dosent respect the viewers when they say any bad comments and he doesn't ignore them
@noah2718
@noah2718 Ай бұрын
This video is the exact amount of time it takes me to eat a Totino's pepperoni party pizza.
@ninjaride1312
@ninjaride1312 Ай бұрын
Making it not hit the bomb should had been easy enough
@whatsaname2usern
@whatsaname2usern Ай бұрын
grandma's gonna be happy with this one
@nathanjohnson2066
@nathanjohnson2066 5 күн бұрын
Now feed the recognized images (x,y,w,h,type,confidence) to a neural network and see how well it can learn to play. Maybe it would even learn combos!
@poohritkun5068
@poohritkun5068 Ай бұрын
Now this is a real AI. Finally!!
@jbsthegamer
@jbsthegamer 2 ай бұрын
my personal best in that mode is closely around 800 is what happens when you have over 2 years of fruit ninja gameplay
@darkrathwheito9818
@darkrathwheito9818 Ай бұрын
My all time best was 11932 with the best ammount of pomegranate hits being 89, seeing an AI getting 600 with not perfect "technique" makes me cry imagining that in 1 year of development it could become so good that reaching 6 digits would be easy T_T
@fridolineckerd6135
@fridolineckerd6135 2 ай бұрын
Can you show what kind of ai you used?
@Xander4096
@Xander4096 2 ай бұрын
I did this a while back but simpler, just looking for specific ranges of colors per pixel cause the lighting is pretty static, then made a modified TSP algo to be able to chain slice.
@R2Bl3nd
@R2Bl3nd Ай бұрын
You could've scaled down the screenshots to a much smaller size before feeding that to the AI.
@dudical111
@dudical111 2 ай бұрын
I would love to see what happens when you train the ai on as low a resolution as you can go on the golden fruit level. I wanna see it obliterate them, dude.
@redhood-n2v
@redhood-n2v Ай бұрын
Man I am so dumb I thought the normal version was the run where he reached 488
@hank4134
@hank4134 2 ай бұрын
I mean the vid is fine but without any bad/dumb/dark jokes of CodeBullet it just won't cut it
@GemsZone
@GemsZone 2 ай бұрын
Great job, but watching the game play there was a lack of combos, if you ever want to revisit fruit ninja that's a thing you could look at.
@DaviMineBoy-7862
@DaviMineBoy-7862 8 күн бұрын
3:24, FISH🐟
@steff3135
@steff3135 Ай бұрын
What about Teachable Machine? because u could learn it with the 3d model right?
@CheezeWreak
@CheezeWreak 2 күн бұрын
You could of also made it so if the bomb is overlapping wait for it to un overlap
@JulianGaming007
@JulianGaming007 2 ай бұрын
Awesome video
@joshuachan6317
@joshuachan6317 2 ай бұрын
What is the software that is used for labeling?
@Chezmanrealwow
@Chezmanrealwow Ай бұрын
Could you have used pyautoguis image recognition? Because of the confidence parameter I feel like you would have only had to take 15 different images of the fruit
@henriks5008
@henriks5008 2 ай бұрын
You should program an AI to label the fruits and bombs ;)
@GD_Abomination
@GD_Abomination 2 ай бұрын
You could have used a second screenshot to predict the movement of the fruits allowing for a single slice per fruit rather than spamming for each one.
@Yesbutnoimnot
@Yesbutnoimnot 2 ай бұрын
Overall that would make the ai slower because it has to take 1 SS, process it, take a second, process it and then calculate the exact velocity of the fruit then compare how the "gravity" affects the loss of momentum.
@CoolDude-mq8dh
@CoolDude-mq8dh 2 ай бұрын
@@Yesbutnoimnotso many idiots in the newest replies lol you are right
@Yesbutnoimnot
@Yesbutnoimnot 2 ай бұрын
@@CoolDude-mq8dh lol the only reason I bothered replying to them was because I code and it's painful watching things like this
@Andhira.Faldhi
@Andhira.Faldhi 7 күн бұрын
I think it's gonna sick if you train the ai to play FNAF, what it can be if you put the AI on custom night on 20/20 😂
@psychtank8681
@psychtank8681 Ай бұрын
What if you make it wait to slice perfect combo and account for bonus points by perfect rounded hundred score or triple number score? Like make it learn to leave some fruits at the end to gain bonus points from 700 or 777 score.
@thegamerkitten2190
@thegamerkitten2190 Ай бұрын
is this guy just code bullet but not swearing
@christophermoore6110
@christophermoore6110 2 ай бұрын
The dev of fruit ninja made a new game called feed the deep, I suggest watching Aliensrock play it
@BabySisZ_VR
@BabySisZ_VR 2 ай бұрын
you can just hit any moving object that isn't a bomb, I think that'd be easier. but I don't know what you'd do for objects that need multiple slices
@mirzu42
@mirzu42 5 күн бұрын
You could have just found a hex color that only exists in the fruits (not the splashes behind) and looked for that color to slice.
@blubaylon
@blubaylon 4 күн бұрын
The AI would just keep trying to slice the fruit even after it's sliced
@mirzu42
@mirzu42 4 күн бұрын
@@blubaylon it wouldnt really be an issue though? Sure it would overkill the fruits but it would also make less mistakes because it computes faster.
@xx__miqu__xx3812
@xx__miqu__xx3812 Ай бұрын
its happening, rise of the machines and fall of the humankind. skynet starts here
@blubaylon
@blubaylon 4 күн бұрын
These image recognition models have been around for a while lol
@Moroha-m
@Moroha-m Ай бұрын
Wouldn't labeling the colour also work? Like make the ai slash the fruit colours and avoid the black or red colour found on the bomb Idk much about programming so idk if this would work
@boxcar36
@boxcar36 Ай бұрын
coconut is too similar to the background so would be able to identify it as well
I made so much money it COMPLETELY BROKE REALITY!
26:48
Real Civil Engineer
Рет қаралды 228 М.
AI Learns to Play SUIKA GAME
13:46
Code Bullet
Рет қаралды 3,8 МЛН
Fake watermelon by Secret Vlog
00:16
Secret Vlog
Рет қаралды 33 МЛН
AI Learns How To Play The Worlds Hardest Game
8:21
Tyler Mommsen
Рет қаралды 219 М.
Testing illegal Minecart rail techniques
11:25
Element X
Рет қаралды 356 М.
Modded Bopl Battle but Abilities Are 100X STRONGER
8:23
Glitchee
Рет қаралды 9 М.
I Built the World's Comfiest Mouse (ft. Bambu Lab A1)
6:22
Play Conveyor
Рет қаралды 4,2 МЛН
This Weight Weighs 997,813,452 Tons
12:19
PeoplePolter
Рет қаралды 422 М.
100 DEVS Make a GAME without COMMUNICATING! (1-25)
17:14
Blackthornprod
Рет қаралды 2 МЛН
AI Learns to Play Tag (and breaks the game)
10:29
AI Warehouse
Рет қаралды 4 МЛН
The Escapists Speedruns are INCREDIBLY HARD
33:34
Crog
Рет қаралды 216 М.
My game is 262,000 times faster than Minecraft. I'll show you how.
12:20
IGoByLotsOfNames
Рет қаралды 1,1 МЛН
AI Learns to play JUMP KING
27:12
Code Bullet
Рет қаралды 8 МЛН