Where communities thrive


  • Join over 1.5M+ people
  • Join over 100K+ communities
  • Free without limits
  • Create your own community
People
Activity
  • Apr 09 12:50
    dave-aimusic closed #459
  • Apr 05 17:03
    dave-aimusic edited #459
  • Apr 05 15:58
    dave-aimusic edited #459
  • Apr 05 15:57
    dave-aimusic edited #459
  • Apr 05 15:48
    dave-aimusic opened #459
  • Apr 02 00:26

    ljvmiranda921 on add-firefly-cpp

    (compare)

  • Apr 02 00:26

    ljvmiranda921 on master

    Add firefly-cpp as a contributo… (compare)

  • Apr 02 00:26
    ljvmiranda921 closed #458
  • Apr 02 00:22
    allcontributors[bot] commented #456
  • Apr 02 00:22
    allcontributors[bot] opened #458
  • Apr 02 00:22

    allcontributors[bot] on add-firefly-cpp

    docs: update .all-contributorsr… (compare)

  • Apr 02 00:22

    allcontributors[bot] on add-firefly-cpp

    docs: update README.md [skip ci] (compare)

  • Apr 02 00:22

    allcontributors[bot] on add-firefly-cpp

    (compare)

  • Apr 02 00:22
    ljvmiranda921 commented #456
  • Apr 02 00:22

    ljvmiranda921 on master

    Installation instructions for F… (compare)

  • Apr 02 00:22
    ljvmiranda921 closed #456
  • Apr 02 00:22
    ljvmiranda921 commented #456
  • Apr 01 07:36
    songyuc opened #457
  • Mar 31 20:23
    firefly-cpp opened #456
  • Mar 30 21:49
    dvolgyes commented #455
Lj Miranda
@ljvmiranda921

The docs for our dev branch seems to be failing with respect to the last merge commit. The error says:

Problem parsing YAML configuration. Invalid "requirements_file": path ./requirements_dev.txt does not exist

Which is weird, because we definitely have a requirements_dev.txt file, and it was not changed during the latest commit. Anyway, I searched around and figured out that this could be related to a ReadTheDocs bug: rtfd/readthedocs.org#4378 (posted today, still no fix yet)

Lj Miranda
@ljvmiranda921
Idk why but merging whenever the master branch is different from the development branch has been very tricky with me lately... hah
*tricky for me
Siobhán K Cronin
@SioKCronin
Did this proposed solution provide any help? rtfd/readthedocs.org#4379
Lj Miranda
@ljvmiranda921
Hi @SioKCronin , it seems that it fixed itself on its own, so now our docs are working well :+1:
MinaTugraz
@MinaTugraz
Hi everyone, I want to use Pyswarm to optimize a parameter(which is not neither Weight nor Baise ) in ANN . and I use Keras to train my network. how can I pass loss function of Keras to optimizer.optimze in Pyswarm ?
Gabriel
@gmichelassi
Hi everyone, I want to use Pyswarm to optimize some parameters of my SKLearn Classifier (Random Forest)... I want to know if this is possible and what's the best way to do it, since I do not found any specification in the documentation
khaliltalib277
@khaliltalib277
I want to use Pyswarm to optimize some parameters of SVR (for regression problems)... I want to know if this is possible and what's the best way to do it?
Patrick Bezzina
@pbezz1
Any luck with using Pyswarms to optimize RF or SVR parameters please @gmichelassi / @khaliltalib277 ? Can you share your views ? I'd like to have some ideas please
AbbasThajeel
@AbbasThajeel
Hello, my friends, I want to code for Particle Swarm Optimization with
Dynamic and Static Topologies
pierremifasol
@pierremifasol

Hello,

I am interested in using PySwarm for 2D geometric optimisation. All my variable are and need to be integers thus I would like to use the discrete method. However it seems that it does not handle bounds neither constraints on the variables as the continuous method does. Is it something you plan to add ?

houhoubema
@houhoubema
hello, i want to add PSO as a new optimizer in optimizers.py (python file) please help
Ashish Upadhyay
@panditu2015
can someone point me towards some materials explaining the speed of running pso in pywarms. thnaks in advance
Aaron
@whzup
@MinaTugraz Examine the Keras function as to what its signature is and then create a custom function which fits the signature of the pyswarms optimize method in the Optimizer class
@gmichelassi I don't know anything about SKLearn but maybe the same method would work for you
@pierremifasol There is a base class for the discrete optimizer from which you can inherit. You can implement the functions as you wish. Maybe it's already enough to slightly adjust the optimize function in the binary optimizer.
Aaron
@whzup
@AbbasThajeel Do you want to contribute? If so there are some open issues on Github where you can let us know if you want to contribute anything :D If you don't find anything that suits you, you can also create a new feature request and we'll discuss how we can implement this together.
@houhoubema I'm afraid I do not really understand your question :/ Do you want to contribute or do you want to create your own optimizer? In the former case see the answer above and in the latter, there are base classes from which you can inherit to create your own optimizer.
@panditu2015 Unfortunately, this is still an open issue ljvmiranda921/pyswarms#206 :/
YI35
@YI35
How to set the optimal integer solution when solving the optimal solution, such as optimizing the number of neural network layers, it must be an integer to make sense
pznaseri
@pznaseri
Hi, I know pyswarms.single.global_best.GlobalBestPSO.optimize has an option for parallelization in the evaluation of the particles through the n_processes parameter. I have an expensive function where it simulates a structure and writes the response in a file and return a loss value. When I tried to increase n_processes to any value more than 1, it just didn't work. Can you please help me?
Aaron
@whzup
@YI35 Please see #400
@pznaseri there was a problem with that the MP pool wasn't closed at the end of the optimization, this has been fixed in the latest master branch, but is not yet released. See #394.
pznaseri
@pznaseri

@pznaseri there was a problem with that the MP pool wasn't closed at the end of the optimization, this has been fixed in the latest master branch, but is not yet released. See #394.

Thank you very much!

AbbasThajeel
@AbbasThajeel

Hello dear
Send me the entire problem and I will try to help you

Hi, I know pyswarms.single.global_best.GlobalBestPSO.optimize has an option for parallelization in the evaluation of the particles through the n_processes parameter. I have an expensive function where it simulates a structure and writes the response in a file and return a loss value. When I tried to increase n_processes to any value more than 1, it just didn't work. Can you please help me?

AbbasThajeel
@AbbasThajeel

@AbbasThajeel Do you want to contribute? If so there are some open issues on Github where you can let us know if you want to contribute anything :D If you don't find anything that suits you, you can also create a new feature request and we'll discuss how we can implement this together.

Hello dear
I thank you very much
Of course, there are many problems when solving some problems using PSO, but it is possible to solve these problems when we link the PSO with another tool.
I hope to be a group and develop solutions to these problems by preparing an expanded study on PSO problems and possible solutions to these problems using new tools.

Farhim Ferdous
@AluBhorta
Hey guys! Is there a straight-forward way of setting bounds to DiscreteSwarmOptimizer?
It's worth noting that my problem domain is of integers within a certain bound. Basically a scheduling problem.
wtransue
@wtransue
Hi all, is there a way to obtain a history of the cost of each particle at each step? Or can this functionality be added? The _populate_history function only seems to record the current best in self.cost_history rather than the history of each particle's cost. I've written a decorator to modify pyswarms.base.base_single.SwarmOptimizer._populate_history to try self.custom_cost_history.append(self.swarm.current_cost) but this is a hack-y way to tackle the issue that might break with future pyswarms versions.
darshan
@Darshanlvalecha_twitter
hello any one can helped in pyswarm in anaconda
NaderN
@NaderNazemi
Hi all
I would like to start learning Swarm Intelligence with Python from Basics 101
Are there Easy to Follow books with plenty of Examples or preferably Video Tutorials in Python
I would appreciate it.
Thank you
Aarati
@aarati2
Hi all
Can you please help me how to work on Recursive Feature Elimination (RFE) for feature selection on PSO-SVM algorithm ??
I would be so grateful for your help !
Maxime G
@joihn
I'm trying to optimize a NN with PSO.
Is interfacing pyswarm with pyTorch a good idea ? or with tensorFlow ?
Antonio Nappi
@Antonio-Nappi
Hi everybody, I'm new in pyswarm and I'm still studying its architecture but maybe you could help me to find the right answers. I would like to implement a PSO with TVAC (Time-Varying Acceleration Coefficients) and these coefficents depends on the current iteration and the max_iteration number. Looking in the file I've seen that the velocity and position update are made in operators script. So my question is: should I define a new method in that script (maybe a "me_velocity_update") with the right coefficients and then changing the behaviour of the topology classes in order to let them use my new method? In this way how could I pass the current iteration number? Or (maybe) there is a simpler way than this which I've not considered?
Lj Miranda
@ljvmiranda921
Hi @aarati2 what do you mean by RFE? What implementation do you have in mind?
Hi @joihn , to be honest there's no support for pytorch or tensorflow using pyswarms yet. It's a big feature that unfortunately, no one has the time to do. Any ideas to get started will be appreciated! I think the best approach here would be to create a Pytorch optimizer that wraps any pyswarms function that we have (rather than supporting it natively)
Hi @Antonio-Nappi I think we've already conversed in #427. Let me know if you still have more questions! :)
tridungduong16
@tridungduong16
Hi, I wonder if I can set the solution belong to a category space like [0,1,2,3]
Tartila Sahid
@dihasalitrat_twitter
Hi, everyone, i was wondering if i could use pyswarm to change a covariance matrix. i have two matrix of 5x5 and would ike to use PSO to find the optimum matrix for a function
EliasGhalib
@EliasGhalib
Hi, could someone please tell me why the "best cost" can not match the "best position"? For instance, if I use the sum function, the best position (4,1) should go along with the best cost 4+1 = 5 and not, as it does, with -12
Ali-Qais
@AliQais-1985
Hi , can I apply pyswarms algorithm to solve assignment problem ?
Antonio Nappi
@Antonio-Nappi
@EliasGhalib but the cost is about the objective function while the position is about the knowledge space
@AliQais-1985 what does you mean with assignment problem?
Kamran-Aslam
@Kamran-Aslam
Hi, i have just started using PSO, I want to optimize a function with multiple variables. Current examples are showing one variable only, could you please explain, how can we assign boundaries for multiple variables? Thanks.
Pranav Kumar
@pranavkr29
I second this question. Also, was there any advancement on providing GPU capabilities by using pytorch instead of numpy, as @ljvmiranda921 suggested in an issue long back?