search

nschaetti / EchoTorch

A Python toolkit for Reservoir Computing and Echo State Network experimentation based on pyTorch. EchoTorch is the only Python module available to easily create Deep Reservoir Computing models.
https://nschaetti.github.io/echotorch.github.io/
GNU General Public License v3.0
441 stars 117 forks source link

optimizer got an empty parameter list #6

Open flaviadcasag opened 5 years ago

flaviadcasag commented 5 years ago

Hi, I am trying to run the code time series prediction sgd but I got an error "optimizer got an empty parameter list". I googled and found we need to register some parameters. Do you have an updated code for LiESN with the parameters list fixed?

Thank you!

Fuxino commented 5 years ago

Same problem. I tried using the ESN module for my project but it's giving me this error: ValueError: optimizer got an empty parameter list

Also trying to run the time series prediction example code gives the same error.

AlexanderRadovic commented 5 years ago

I also have the exact same problem trying to run the time series prediction example code.

Aak6ash commented 5 years ago

It is also giving the same error in my code when using ESN with SGD.

JordanMajd commented 3 years ago

Same error, relevant code snippets:

esn = etnn.ESN(
    input_dim=input_dim,
    hidden_dim=n_hidden,
    output_dim=output_dim,
    learning_algo='grad',
    w_generator=w_generator,
    win_generator=win_generator,
    wbias_generator=wbias_generator,
)
optimizer = optim.SGD(esn.parameters(), lr=learning_rate, momentum=momentum, weight_decay=weight_decay)