We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
if you want to save and load models that contain this layers you shoud add get_config and from_config methods to custom layers like this
def get_config(self): config = super(DenseKAN, self).get_config() config.update({'units':self.units , 'grid_size':self.grid_size, 'spline_order':self.spline_order, 'grid_range':self.grid_range, 'basis_activation':self.basis_activation, 'use_bias':self.use_bias, 'spline_initialize_stddev':self.spline_initialize_stddev}) return config @classmethod def from_config(cls, config): return cls(**config)
and register them by "tf.keras.utils.get_custom_objects()['DenseKAN'] = DenseKAN"
The text was updated successfully, but these errors were encountered:
thasks for feedback, I will add these two methods into each KAN layer.🫡
KAN
Sorry, something went wrong.
No branches or pull requests
if you want to save and load models that contain this layers you shoud add get_config and from_config methods to custom layers like this
and register them by "tf.keras.utils.get_custom_objects()['DenseKAN'] = DenseKAN"
The text was updated successfully, but these errors were encountered: