I have the following custom layer. struct Activation{F} f::F Activation(f::Function) = new{typeof(f)}(f) end (m::Activation)(x::AbstractArray) = m.f.(x) I test whether it allows a model to be trained using the following code using Flux function test_training(model,x,y) opt = Descent(…

My mistake, I thought the @info logging was unconditional for some reason. In that case, my working theory would be that all the updates from the previous calls to test_training leave the weights of test_layer on some kind of local minima or saddle point by the time it reaches the activation test. T…

Parameters not updating in Flux

Specific Domains Machine Learning

ToucheSir July 7, 2021, 4:40pm 5

What exactly is the failure you’re running into here? Is it an error? If so, can you post a full stacktrace + MWE with @functor? If not, can you explain in detail what the failure mode on GH actions looks like?

Topic		Replies	Views
Params not getting updated during training New to Julia flux	25	1789	October 11, 2020
How to use Flux.train! to train custom layer? Machine Learning question	2	1836	September 2, 2019
Custom layer with new parameters in Flux.jl Machine Learning flux	3	1563	December 11, 2019
Stacking layers example Flux - Flux.params empty New to Julia question	2	846	December 12, 2019
Question about writting custom training function using Flux.jl Machine Learning question	2	839	July 28, 2020

Parameters not updating in Flux

Related topics