# Reusing exact same layer and parameters

**URL:** https://discourse.julialang.org/t/reusing-exact-same-layer-and-parameters/61618
**Category:** Machine Learning
**Tags:** question, flux
**Created:** [May 22, 2021, 2:17am UTC](https://discourse.julialang.org/t/reusing-exact-same-layer-and-parameters/61618 "2021-05-22T02:17:53Z")
**Posts on this page:** 4
**Page:** 1

<div class="post-metadata">

### Author: ![crinders](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/crinders/32/8434_2.png) [@crinders](https://discourse.julialang.org/u/crinders)
#### Post date: [May 22, 2021, 2:17am UTC](https://discourse.julialang.org/t/reusing-exact-same-layer-and-parameters/61618/1 "2021-05-22T02:17:53Z")

</div>

I want to reuse the exact same layer in a network. But I can’t figure out whether my naive approach will do that. My toy architecture is

```julia
using Flux
D1 = Dense(2,2)
D2 = Dense(2,2)
NaiveReuse = Chain(D1, Parallel(vcat,Chain(D2,Parallel(vcat, D1, identity)), identity))

```

The output of `params(NaiveReuse)` is

```julia
Params([Float32[-1.1226765 0.9502689; 0.6875402 0.4517343], Float32[0.0, 0.0], Float32[-0.18272986 -0.16167739; 0.46781456 1.2025808], Float32[0.0, 0.0]])

```

but I’m having trouble interpreting that. It looks like only two matrices are being stored. Am I correct to assume that the parameters for D1 will be reused and properly updated by Zygote during training? If not, how would I go about that?

---

<div class="post-metadata">

### Author: ![ablaom](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/ablaom/32/4889_2.png) [@ablaom](https://discourse.julialang.org/u/ablaom)
#### Post date: [May 22, 2021, 3:56am UTC](https://discourse.julialang.org/t/reusing-exact-same-layer-and-parameters/61618/2 "2021-05-22T03:56:53Z")

</div>

The `Dense` and other layer constructors use `Random.GLOBAL_RNG` in initialisation by default. So your naive approach won’t work. There is a user interface point for specifying the RNG. This may be in the docs somewhere, but see [https://github.com/FluxML/Flux.jl/pull/1292](https://github.com/FluxML/Flux.jl/pull/1292) .

Or, you can just do `D2 = deepcopy(D1)`, unless you want to avoid deep copies for some memory/performance reason.

---

<div class="post-metadata">

### Author: ![ablaom](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/ablaom/32/4889_2.png) [@ablaom](https://discourse.julialang.org/u/ablaom)
#### Post date: [May 22, 2021, 8:11am UTC](https://discourse.julialang.org/t/reusing-exact-same-layer-and-parameters/61618/3 "2021-05-22T08:11:22Z")

</div>

Or perhaps I misunderstood. Do you want the the weights to be coupled?

---

<div class="post-metadata">

### Author: ![crinders](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/crinders/32/8434_2.png) [@crinders](https://discourse.julialang.org/u/crinders)
#### Post date: [May 22, 2021, 2:27pm UTC](https://discourse.julialang.org/t/reusing-exact-same-layer-and-parameters/61618/4 "2021-05-22T14:27:46Z")

</div>

Anthony,

Yes, I want the weights to be coupled.  
As in  
`\sigma(D1+\sigma(D1+D2))` instead of `\sigma(D1+\sigma(D1^\prime+D2))` if `D1` and `D2` were variables,i.e., I wouldn’t want the former to be implicitly changed to the latter.