Stuck on an issue?

Lightrun Answers was designed to reduce the constant googling that comes with debugging 3rd party libraries. It collects links to all the places you might be looking at while hunting down a tough bug.

And, if you’re still stuck at the end, we’re happy to hop on a call to see how we can help out.

'Layer' object has no attribute 'activation_function'

See original GitHub issue

Hi,

Here is my setup:

from neupy import algorithms, layers, environment

environment.reproducible()

cgnet = algorithms.ConjugateGradient(
    connection=[
        layers.Layer(5),
        layers.Sigmoid(100),
        layers.Output(1),
    ],
    shuffle_data = False,
    show_epoch=300,
    verbose=True,
    search_method='golden',
    update_function='fletcher_reeves',
    addons=[algorithms.LinearSearch],
)

Do you know why I have following error:

[THEANO] Initializing Theano variables and functions. AttributeError: ‘Layer’ object has no attribute ‘activation_function’

Thanks.

Issue Analytics

State:
Created 7 years ago
Comments:10 (5 by maintainers)

Top GitHub Comments

2reactions

itdxercommented, Apr 13, 2016

I’ve added an update and pushed it in the issue_79_termios_error_25 branch. Could you please check whether it works for you?

0reactions

denisvolokhcommented, Apr 14, 2016

Yes, it works.

Thank you.

Kind regards, Denis Volokh

On Thu, Apr 14, 2016 at 1:03 AM, Yurii Shevchuk notifications@github.com wrote:

I’ve added an update and pushed it in the issue_79_termios_error_25 branch. Could you please check whether it works for you?

— You are receiving this because you authored the thread. Reply to this email directly or view it on GitHub https://github.com/itdxer/neupy/issues/79#issuecomment-209547005