# Saving an Echo State Network (ReservoirComputing.jl)

**URL:** <https://discourse.julialang.org/t/saving-an-echo-state-network-reservoircomputing-jl/95338>\
**Category:** Machine Learning\
**Created:** [February 28, 2023, 2:54pm UTC](https://discourse.julialang.org/t/saving-an-echo-state-network-reservoircomputing-jl/95338 "2023-02-28T14:54:29Z")\
**Posts on this page:** 7\
**Page:** 1

<div class="post-metadata">

**Author:** ![monstera](https://avatars.discourse-cdn.com/v4/letter/m/47e85d/32.png) [@monstera](https://discourse.julialang.org/u/monstera)\
**Post date:** [February 28, 2023, 2:54pm UTC](https://discourse.julialang.org/t/saving-an-echo-state-network-reservoircomputing-jl/95338/1 "2023-02-28T14:54:29Z")

</div>

Hi,

I am trying to save an Echo State Network (ESN) struct + output Matrix in Julia to load it again in another script to predict a time series. Out of several thousand ESNs, I am choosing the hundred best ones and try to save them. I tried it with JLD, however I cannot load them again. I guess because the struct does not purely consist of arrays. The error I get:

```julia
error parsing type string ReservoirComputing.ESN{Core.Int64,Core.Array{Core.Float64,2},ReservoirComputing.Default,ReservoirComputing.NLADefault,Core.Array{Core.Float64,2},ReservoirComputing.RNN{NNlib.#tanh_fast,Core.Float64},Core.Array{Core.Float64,2},Core.Array{Core.Float64,2},ReservoirComputing.StandardStates,Core.Int64,Core.Array{Core.Float64,2}}
Error encountered while load FileIO.File{FileIO.DataFormat{:JLD}, String}("esn_states/esn.jld").

Fatal error:
ERROR: LoadError: syntax: incomplete: premature end of input

```

How can I save the ESN (or the determining matrices) in the smartest way to be able to construct the ESN again?

---

<div class="post-metadata">

**Author:** ![ChrisRackauckas](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/chrisrackauckas/32/77_2.png) [@ChrisRackauckas](https://discourse.julialang.org/u/ChrisRackauckas)\
**Post date:** [March 1, 2023, 8:27am UTC](https://discourse.julialang.org/t/saving-an-echo-state-network-reservoircomputing-jl/95338/2 "2023-03-01T08:27:35Z")

</div>

> [@monstera](#):
>
> I tried it with JLD, however I cannot load them again. I guess because the struct does not purely consist of arrays. The error I get:

You have to load the packages before re-loading the model from JLD

---

<div class="post-metadata">

**Author:** ![monstera](https://avatars.discourse-cdn.com/v4/letter/m/47e85d/32.png) [@monstera](https://discourse.julialang.org/u/monstera)\
**Post date:** [March 1, 2023, 9:02am UTC](https://discourse.julialang.org/t/saving-an-echo-state-network-reservoircomputing-jl/95338/3 "2023-03-01T09:02:52Z")

</div>

Hi Chris,

I load the same packages that I used in the script to save before. I try it with JLD2 now, saving and loading seems to work:

```julia
using JLD2
jldsave("W_Matrix/W_1.jld2"; Wₒᵤₜ)
jldsave("esn_states/esn_1.jld2"; esn)
esn = jldopen("esn_states/esn_1.jld2")
Wₒᵤₜ =jldopen("W_Matrix/W_1.jld2")
prediction = esn(Predictive(val_x), Wₒᵤₜ)

```

however I get

```julia
ERROR: LoadError: MethodError: objects of type JLD2.JLDFile{JLD2.MmapIO} are not callable

```

when I try to predict with the loaded ESN.

---

<div class="post-metadata">

**Author:** ![ChrisRackauckas](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/chrisrackauckas/32/77_2.png) [@ChrisRackauckas](https://discourse.julialang.org/u/ChrisRackauckas)\
**Post date:** [March 1, 2023, 9:03am UTC](https://discourse.julialang.org/t/saving-an-echo-state-network-reservoircomputing-jl/95338/4 "2023-03-01T09:03:15Z")

</div>

Interesting. Open an issue.

---

<div class="post-metadata">

**Author:** ![monstera](https://avatars.discourse-cdn.com/v4/letter/m/47e85d/32.png) [@monstera](https://discourse.julialang.org/u/monstera)\
**Post date:** [March 1, 2023, 9:04am UTC](https://discourse.julialang.org/t/saving-an-echo-state-network-reservoircomputing-jl/95338/5 "2023-03-01T09:04:10Z")

</div>

In JLD2.jl or ReservoirComputing.jl?

---

<div class="post-metadata">

**Author:** ![ChrisRackauckas](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/chrisrackauckas/32/77_2.png) [@ChrisRackauckas](https://discourse.julialang.org/u/ChrisRackauckas)\
**Post date:** [March 1, 2023, 9:15am UTC](https://discourse.julialang.org/t/saving-an-echo-state-network-reservoircomputing-jl/95338/6 "2023-03-01T09:15:19Z")

</div>

ReservoirComputing.jl

---

<div class="post-metadata">

**Author:** ![MartinuzziFrancesco](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/martinuzzifrancesco/32/220474_2.png) [@MartinuzziFrancesco](https://discourse.julialang.org/u/MartinuzziFrancesco)\
**Post date:** [January 24, 2026, 6:22pm UTC](https://discourse.julialang.org/t/saving-an-echo-state-network-reservoircomputing-jl/95338/7 "2026-01-24T18:22:50Z")

</div>

Since v0.12 ReservoirComputing.jl builds on LuxCore.jl, so saving an ESN only requires saving the parameters `ps` and states `st`. [Here](https://docs.sciml.ai/ReservoirComputing/dev/tutorials/saveload/) is the documentation page with a quick example.

Assuming you have defined and trained an ESN, now you only need to specify the construction parameters

```julia
spec = (
  in_size = 3,
  res_size = 300,
  out_size = 3,
  radius = 1.2,
  sparsity = 6/300,
  state_modifiers = :NLAT2,
  # include any non-default knobs you used:
  # leak_coefficient = 1.0, input_scaling = 0.1, use_bias=false, etc.
)

```

and save them

```julia
using JLD2
@save "esn_trained.jld2" ps st spec

```

You can then load them in the same way, and rebuild the ESN:

```julia
@load "esn_trained.jld2" ps st spec

esn = ESN(spec.in_size, spec.res_size, spec.out_size;
          init_reservoir=rand_sparse(; radius=spec.radius, sparsity=spec.sparsity),
          state_modifiers = getfield(ReservoirComputing, spec.state_modifiers))

```

which is now fully defined by the `ps` and `st` you have loaded