Counting Playing cards The usage of Device Finding out and Python – RAIN MAN 2.0, Blackjack AI – Section 1



RAIN MAN 2.Zero is a card counting AI that is destined to be without equal blackjack participant! Created the usage of gadget studying and Python, RAIN MAN 2.Zero can simply rely his approach via a deck of taking part in playing cards. To spot playing cards, he makes use of a YOLO v3 detection style educated on 50,000 synthetically generated photographs.

This video explains how he works and what I plan to do with him. It is the first video in a sequence of movies that I will be able to be posting as I construct out his capability.

— Associate Hyperlinks —
If you have not noticed the film Rain Guy, you wish to have to observe it!!
Logitech C920 1080p webcam utilized by RAIN MAN 2.0:

Twitter:
RAIN MAN 2.Zero mission web page on Hackaday:

— Hyperlinks discussed in video —
geaxgx1’s taking part in card detection video:

Wizard of Odds web page, nice supply of blackjack data and technique:

— Track —
Summer time Espresso by way of Barradeen:

Hidden digital camera blackjack photos taken from Blackjack Military YouTube channel:

49 Replies to “Counting Playing cards The usage of Device Finding out and Python – RAIN MAN 2.0, Blackjack AI – Section 1”

  1. no offense but counting a single deck game is not hard at all. heck counting a double deck game is easy as pie. you dont need rain man to help you count a single deck game. but it's a cool toy nonetheless. the hardest part about counting a six deck shoe is deck estimation and I would suggest avoiding eight deck games unless you have a large bankroll and the casino offers good penetration

  2. Hidden secret computers have a series of tells where it looks like someone is counting cards based on their bets, but they way they play their hands are insane but successful. There are literally cases where a good card counting computer would tell you to do insane plays like split 5's that no human card counter could ever justify mathematically.

  3. Great project! Are you running inference on the GPUs in your gaming PC, or the CPU? If you're getting that performance on a GPU, do you think the RPi will be able to keep up with frame rates?

  4. hi, when can i buy a the more compact model using raspberry , do you have 2 decks onboard yet? also, easy to find true count by dividing by remanings decks, cool u rock

  5. Seems like the best market would be create a trainer for new card counters (have it give you a mild shock when you make a mistake, LOL). Playing at a real table with real cards would better simulate real world conditions. Could also verify basic strategy and deviations (I've done some Python code for that, driven by different XML files according to which exact strategy to follow, based on the type of game).

  6. Hi, Is it possible to share the dataset or the weights you train? I have 2 days left for my term paper. That's why I want it.

  7. use hidden camera glasses that takes photos everyonce in a while and sends the photos to a remote server to process and send the results back to you and read it out into your wireless headphone or show on apple watch or something

  8. I don't play blackjack but I've been facinated about card counting. Your video is excellent as you answer all of the questions that came to my mind. I hope that you make a fortune–if not in a casino–by some killer apps other card games or for people with impaired vision. Let me know if you need investors!

  9. Sir, I have successfully taken images of all 52 cards.
    100 images/card and now I have already labeled 5200 images manually by hand using LabelImg software.
    I am going to run the training using SSD Mobile net and I have a plan to convert it into TF-lite on Pi.
    Sir please guide me that I am choosing the right path for this or not ?

  10. I followed your program to train cards on windows 10. Followed each steps, I labelled 5 thousand cards but instead of labeling the whole card, I only label top right and bottom side manually. But after that it will not be able to detect anything.

  11. Good video.
    I have watched this video very carefully. Before I have tested this method(card recognition with yolo).
    When the distance between the camera and the card is short than 0.5m, it works well.
    But if distance increases, it doesn't detect card anymore(even if 1m).
    How can solve this problem?
    Can u kindly answer my question?
    My mail address is [email protected]163.com.
    I am looking forward to your reply.

  12. I just watched a movie called Inside the Edge about a card counter (with other techniques that could be programmed). It got me curious about AI & what is / will be possible with technology. That's why I ended up here.
    Port it to Raspberry, get decent resolution on a pinhole tie or glasses cam (if that is an issue) and program the heck out of it.
    I know technologically cheating is illegal in NV, not so sure about statutes the other states? It would be a fun experiment to fleece casinos if legal elsewhere. (similar to MIT back in the day)
    Good luck with your project. It's a disruptive idea that's fun to think about!

  13. isn't there a better way to count cards/maximize odds? i mean this formula(0, +1, -1) is easier for humans, but with a computer you could count more accurate, considering every different value/card in the deck.

  14. Any tips on how I would do a text based version of this? I want to start off with that before I work on my own counter using a camera or creating an oop simulator

  15. Question: What are you using to live stream the video from OpenCV?
    Are you just outputting the video result into a html page or something? Or perhaps streaming it somewhere?
    Im asking because im now getting started with Node.js and OpenCV4Nodejs using the Raspberry pi zero (With the same webcam lol). Right now im just taking an image every 200 mili-seconds and sending it to a node server to be viewed remotely.
    Theres a 2 second lag/delay.
    Thanks in advanced.

  16. It seems like eventually this will also be able to deviate from basic strategy and even the card counting published deviations because the data will be more granular than simple high lo count. Very cool video.

  17. Ah ah I was wondering why I had a sudden spike in the count of my subscribers :-)) Thanks for the big shout out, bro ! Your project is really great, I am already impatient to watch the following parts and curious about the port on the raspberry ! Your video editing is excellent and you seem to have fun doing it (I know how time consuming this task is 😉

    FYI, since the post of my video one year ago, I had the opportunity to test the following: take only one good picture of each card (instead of a video under varying lighting conditions) and rely on the image augmentation library to simulate the lighting. That works as well as previously, but is much less cumbersome.

    And good guess, you pronounce my id correctly !

Leave a Reply

Your email address will not be published. Required fields are marked *