Where communities thrive


  • Join over 1.5M+ people
  • Join over 100K+ communities
  • Free without limits
  • Create your own community
People
Activity
  • Nov 28 2021 14:16
    oprypin closed #12
  • Nov 28 2021 14:16
    oprypin commented #12
  • Nov 28 2021 14:13
    bararchy closed #10
  • Nov 28 2021 14:13
    bararchy commented #12
  • Nov 28 2021 14:12

    bararchy on v1.2.0

    (compare)

  • Nov 28 2021 14:11

    bararchy on master

    sync version (compare)

  • Nov 28 2021 14:10

    bararchy on master

    Fix for Crystal 1.2.2 fix format (compare)

  • Nov 27 2021 12:04
    oprypin commented #12
  • Jan 26 2021 19:49
    oprypin opened #12
  • Oct 24 2019 09:26
    fab1an2 commented #11
  • Oct 23 2019 10:25
    bararchy closed #11
  • Oct 23 2019 09:27
    bararchy commented #11
  • Oct 23 2019 09:23
    bararchy commented #11
  • Oct 23 2019 09:19
    fab1an2 opened #11
  • Sep 21 2019 10:36
    bararchy commented #10
  • Sep 21 2019 10:35
    bararchy commented #10
  • Sep 21 2019 10:34
    bararchy commented #10
  • Sep 21 2019 10:13
    xor256 edited #10
  • Sep 21 2019 10:12
    xor256 opened #10
  • Dec 17 2017 11:41

    bararchy on v1.1.1

    (compare)

Bar Hofesh
@bararchy
@hugoabonizio great work on the load\save feature, when it get merged, I want to make a new release, as we solved the damn MSE bug + added great features
Hugo Abonizio
@hugoabonizio
thank you @bararchy!
I'm glad to help :smile:
Bar Hofesh
@bararchy
Serdar Dogruyol - Sedo セド
@sdogruyol
@bararchy :tada:
Bar Hofesh
@bararchy
@Qwerp-Derp Thanks for the PR, would you mind adding the last part and I'll merge ?
Hanyuan Li
@hanyuone
Ah yes, forgot about it :P will do
Bar Hofesh
@bararchy
:+1: :)
Bar Hofesh
@bararchy
@Qwerp-Derp so , do you want me to maybe merge and fix if you don't have time to add it ?
Hugo Abonizio
@hugoabonizio
hi @bararchy!

I'm having an issue with crystal-fann, can you help me with that?
I'm trying to train a Network::Standard on iris dataset, but my model always evaluate to the same class, it's not learning the patterns
am I doing something wrong?

https://gist.github.com/anonymous/6acbb9787167f72fb2ea2b5ff17a30a9

running it on neural_net.cr sample gives 96% accuracy
but with crystal-fann it's about 33% (always the same class)
Bar Hofesh
@bararchy
Hi @hugoabonizio I would strongly suggest not using single iiteration learning method, and instead use batch with the Data structure example , I would also suggest playing around with different activation functions , FANNs default to liner , which is in 90% of the cases not what you want ;)
Also, if you prefer the lib to do most things for you automatically, try the Cascade network, for me on different data sets it gave best results (keep in mind the net will build its own hidden network, so only input and output are relevant.)
Please update me on how it go, I'll also try your example
Hugo Abonizio
@hugoabonizio
@bararchy thanks for answering!
I was using batch training, like that:
ann.train_batch(data, {:max_runs => 500000, :desired_mse => 0.01_f64, :log_each => 1000})
but changed to single iteration to make it more similar to the neural_net sample I was testing
I think the default activation function is sigmoid (http://leenissen.dk/fann/html/files2/advancedusage-txt.html), but I'm testing others anyway
Bar Hofesh
@bararchy
@hugoabonizio Does using Cascade and batch gives you a better result ?
Hugo Abonizio
@hugoabonizio
I'll try Cascade later and let you know the results!
Bar Hofesh
@bararchy
:thumbsup: thanks
Oh, one more thing, which source did you use to get the FANN lib from ?
Hugo Abonizio
@hugoabonizio
hi @bararchy
I followed this installation http://leenissen.dk/fann/wp/help/installing-fann/ and cloned from github repo
on lib_fann.cr file I was replacing @[Link("doublefann")] with @[Link("fann")] to experiment
with doublefann it's giving 96% accuracy now!
(but sometimes it's 30%, I think that's a problem with the random weights initialization)
I think it's fine now, thanks!
Bar Hofesh
@bararchy
Oh I see XD
well, as we binded against douablefann we changed Float64\Float32 ratio to acompany this :) so using the non double version indeed introduces issues
thanks for the update :) @hugoabonizio
Hugo Abonizio
@hugoabonizio
I didn't thought about that :laughing:
thanks for your help!
Martyn Jago
@mjago
Hi @bararchy The example on github readme seems to fail for me as in I get a result > 0.1 ~ any ideas?
Max epochs     8000. Desired error: 0.0010000000.
Epochs            1. Current error: 0.5189931989. Bit fail 2.
Epochs         1000. Current error: 0.2500000000. Bit fail 4.
Epochs         2000. Current error: 0.2500000000. Bit fail 4.
Epochs         3000. Current error: 0.2500000596. Bit fail 4.
Epochs         4000. Current error: 0.2500000000. Bit fail 4.
Epochs         5000. Current error: 0.2500000000. Bit fail 4.
Epochs         6000. Current error: 0.2500000596. Bit fail 4.
Epochs         7000. Current error: 0.2500000000. Bit fail 4.
Epochs         8000. Current error: 0.2500000596. Bit fail 4.
[0.5000107397550064]
false
Bar Hofesh
@bararchy

@mjago hmmm it seems you get "stuck" at an error rate and not getting out of it.

This could be because of few issues, Have you compiled and used doublefann? did you used the latest version of crystal-fann ?

specs are passing for me on HEAD
does running crystal spec works for you?
Bar Hofesh
@bararchy
Also, a quick question, which of the examples didn't work?
Martyn Jago
@mjago
Specs work
Finished in 71.3 milliseconds
14 examples, 0 failures, 0 errors, 0 pending
I compiled github/libfann head