I am following an example here . The neural network is defined as Chain(Dense(2,50,tanh),Dense(50,2)). The resulting “.minimizer” array of values has 252 entries. How are each of these entries mapped to the W1, b1, W2, b2 matrices? It looks to me like the first 100 values are the entries of the 5…

DiffEqFlux.sciml_train resulting parameters

ChrisRackauckas April 29, 2020, 4:25pm 4

p,re = Flux.destructure(dudt2) gives re as the restructure function re(p).

Topic		Replies	Views
Parameters in DiffEqFlux New to Julia flux	2	684	August 15, 2020
Flux/DiffEqFlux: error when a loss function does not use all the weights of the NN Machine Learning diffeq , flux	8	640	June 3, 2021
Optimizing parameters of ODE in DiffEqFlux: Not implemented: convert tracked Tracker.TrackedReal{Float64} to tracked Float64 Machine Learning diffeq , flux , optimization	4	1465	March 31, 2019
Stacking layers example Flux - Flux.params empty New to Julia question	2	847	December 12, 2019
Interpretation of the weights returned by Flux in model zoo example New to Julia flux	3	1149	September 21, 2018