Where communities thrive

  • Join over 1.5M+ people
  • Join over 100K+ communities
  • Free without limits
  • Create your own community
    Hi, is it anyone here?
    Nils Schaetti
    Hi :)
    Sir, I observed that you did not answer my Q posted on your github and I still could not solve the problem. Could you give me a hand?
    Manish Goyal
    Manish Goyal
    I recently install EchoTorch and tried running the NilsNet_example. But the error I am getting is "ModuleNotFoundError: No module named 'datasets'".

    Hi guys,
    I am working on this nice package (and thank you Nils for making this available) I want to add one FC layer to the network. however, when data is fed to the network, the output does not have the gradient attached to it and hence, it looses information that is needed for back propagation.
    i am able to incorporate ESNCell.py into my network and run backprop in it. however, if I use the ridge regression cell (RRCell.py) it generates an output that does not have the gradient and therefore no backprop on its output.
    I used both ESN.py , LiESN.py, and after calling the finalize method, and then testing the network, the output does not have the gradient.
    for example:

    esn= esn = etnn.LiESN(input_dim=input_dim, hidden_dim=n_hidden, output_dim=1, spectral_radius=spectral_radius, learning_algo='inv', leaky_rate=leaky_rate)
    and then y_predicted is just a tenson without any gradient attached to it

    any suggestions? @nschaetti

    Taehwan Kim
    @mag16154 I had the same error. you have to download the git files from https://github.com/nschaetti/EchoTorch and run setup.py file to download the necessary librarys/files
    Hi to everybody. I'm new to reservoir application and I'm a physics, but we're to start a project involving this paradigm and I'm interested in using Schaett's tool.
    I've been suffering a problem with feeding the network.
    I made several tris, with normal label and hot_encoded version either. Than I modify the dimension of the target into (output,batch_size) and I always cross this error: Dimension out of range (expected to be in range of [-1, 0], but got 1)
    with a simple tensor of dimension 1, this error occur: too many indices for tensor of dimension 1
    Guess I'm missing something, or I'm not proficient enough with pytorch. Does anybody could help me?
    many thank :)
    @Abolfazl-Alipour you succeded in using it
    What am I doing wrong?
    Hey everyone! I'm not sure if anyone is reading this but I also just started working with EchoTorch and I'm struggling a bit with choosing parameters for my model. I'm using v0.2.1. I looked at the examples provided by Nils on Github but they work with older versions... in particular I was wondering what a good practice is for setting "w_generator", "win_generator" and "wbias_generator". Do you have any recommendations or example code? Many thanks :)
    Thabang Lebese
    Hi, everyone.