owl icon indicating copy to clipboard operation
owl copied to clipboard
verified publisher icon owlbarn

Freeze neuron's weight in training

Open jzstark opened this issue 7 years ago • 2 comments

In constructing a neural network in Tensorflow, user can choose to initialise the weight value as a tf.varialble or tf.const. The latter means that the weight will not be updated during training. I find this property useful in some use cases, such as neural style transfer. I think it would be great to have such "freeze" mechanism in Owl's NN module.

jzstark avatar May 04 '18 10:05 jzstark

@jzstark is this still relevant? or implemented already?

ryanrhymes avatar Nov 21 '19 23:11 ryanrhymes

Sorry my bad, this function is still not implemented yet.

jzstark avatar Nov 21 '19 23:11 jzstark