Live data from Hacker News

Viewing profile — indy7500

indy7500

HN member
Joined
Thu, Feb 14, 2019, 3:59 PM UTC
HN karma
66
Public activity
34 items

About indy7500

No profile information was provided.

Recent public activity

  1. comment
    Comment #20140241

    264GB in client profile pictures perhaps, that would be a lot of people affected!

  2. comment
    Comment #20140214

    Human rights written by westerners.

  3. comment
    Comment #19501215

    Sounds unlikely lol but why would you want to? Definitely more expensive than missile

  4. comment
    Comment #19501176

    Only problem is I don't know how likely it would be that the writing is neatly separated by character for mnist to work, and handwriting recognition isn't accurate enough. Maybe so…

  5. story
  6. comment
    Comment #19201909

    Would you mind quickly explaining what you guys mean? Sorry, I'd love to improve it but I'm not sure I get it. If you had a bunch of bubbles for each square and piece etc. wouldn't…

  7. comment
    Comment #19186439

    No, not a clear reason other than wanted to get the product out earlier. We'll work on an opt-in, that does sound the best. Wouldn't other pieces affect this though? For example, w…

  8. comment
    Comment #19173945

    Yes that's all possible, just a lot more expensive.

  9. story
  10. comment
    Comment #19173767

    https://github.com/Messier-16/Reine

  11. comment
    Comment #19173762

    We did use that for the postprocessing actually, the part where moves are cross-checked for lower probability predictions.

  12. comment
    Comment #19173751

    https://github.com/Messier-16/Reine

  13. comment
    Comment #19169031

    Now open sourced. https://github.com/Messier-16/Reine/

  14. comment
    Comment #19169027

    Yes, that is the plan. That should heavily increase accuracy. Do you mean handwriting recognition as opposed to character recognition? It wasn't that we tried it and decided it wou…

  15. comment
    Comment #19168640

    We currently don't store scoresheets when uploaded to our website. Would you be able to send the pictures to us at info@reinechess.com? You could add comments about how it went (or…

  16. comment
    Comment #19168302

    We have decided to make it open source! Will publish in another article perhaps, when it has enough comments added in the next two days!

  17. comment
    Comment #19167489

    Wait, are you GM Parimarjan? If so, this is truly an honor.

  18. comment
    Comment #19167452

    I just posted this project on #share over on that Slack. Their #help channel helped me a ton (especially Jameson and hart!) Fully endorse this

  19. comment
    Comment #19167430

    Don't say that, you're definitely more experienced than me :) I'll try to clarify, but I could be wrong. This is from the chess.com article on it here: https://www.chess.com/blog/R…

  20. comment
    Comment #19167364

    I think you'll be pleasantly surprised, this is a thing!! I thought about making it but quickly decided computer vision wasn't up to the task yet. It seems I was horribly wrong: ht…

  21. comment
    Comment #19167056

    That would be an awful lot of bubbles per move, no?

  22. comment
    Comment #19167049

    Also, a slight problem with b) is that it must be in the context of the whole game, since incorrect moves may only arise later on. This makes it harder with characters too ofc

  23. comment
    Comment #19167044

    The way we check legality and adjust is with the character recognition. We use the second highest and third highest confidence characters. So, if you write a 5 and the model recogn…

  24. comment
    Comment #19167036

    Now that I think about it, you're right. I don't know what the accuracy would be like, but it's certainly possible and worth a try.

  25. comment
    Comment #19165672

    (I am OP) I thought about doing it that way but found that handwriting recognition was pretty weak as of now and wanted to try something solid. The reason is, usually, handwriting …