# Flux differentiation error

**URL:** https://discourse.julialang.org/t/flux-differentiation-error/49811
**Category:** Machine Learning
**Tags:** zygote
**Created:** [November 8, 2020, 11:52pm UTC](https://discourse.julialang.org/t/flux-differentiation-error/49811 "2020-11-08T23:52:03Z")
**Posts on this page:** 20
**Page:** 1

<div class="post-metadata">

### Author: ![Honza9723](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/honza9723/32/7807_2.png) [@Honza9723](https://discourse.julialang.org/u/Honza9723)
#### Post date: [November 8, 2020, 11:52pm UTC](https://discourse.julialang.org/t/flux-differentiation-error/49811/1 "2020-11-08T23:52:03Z")

</div>

Dear All,

I am working on a solution of simple differential equation y(x) - y’(x) = 0 using neural network. I am using a two-layer softplus network for parameterization of y(x). To get y’(x), I am using simple Flux.gradient. Gradient itself works well (d𝛰.(xGrid) generate derivative at all grid points for example), however, when I put it into the loss function and run Flux.train! loop, I get following error

" Can’t differentiate foreigncall expression"

Could somebody please give me some guidance how to fix this problem?

Best,  
Honza

```julia
#(B) Solve simple differential equation
#(1) Generate grid
xGrid = sort(rand(Uniform(-1,1),1,ϰ),dims=1)

#(2) Build neural network and its derivative
Ο = Flux.Chain(Dense(1,16,softplus),Dense(16,1,softplus))
𝛰(x) = Ο([x])[1]
d𝛰(x) = Flux.gradient(𝛰,x)[1]

#(3) Build loss function
function 𝕰(x)
    𝕰 = sum((𝛰.(x) .- d𝛰.(x)).^2)
    𝕭 = (𝛰(1)-1).^2
    𝕷 = 𝕰+𝕭
    return 𝕷
end

𝜣 = Flux.params(Ο)
Data = [xGrid]
opt = ADAM(0.13)

cb = () -> println(𝕰(xGrid))
@time Flux.@epochs 5000 Flux.train!(𝕰,𝜣,Data,opt,cb=cb)

```

---

<div class="post-metadata">

### Author: ![Honza9723](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/honza9723/32/7807_2.png) [@Honza9723](https://discourse.julialang.org/u/Honza9723)
#### Post date: [November 9, 2020, 12:54am UTC](https://discourse.julialang.org/t/flux-differentiation-error/49811/2 "2020-11-09T00:54:35Z")

</div>

To be more specific, I would like to ask, how to take a derivative of a neural network, such that Flux is able to differentiate it again.

Edit: I tried to get around this problem by computing the derivative using ForwardDiff. I computed the first derivative of neural network using ForwardDiff, and then computed second derivative using Flux.gradient on the ForwardDiff derivative as a trial. It worked without any problems. However, when I plugged the ForwardDiff derivative into the loss function (loss function itself works) and tried to optimize it using Flux.train! loop, I get following error:

```julia
TypeError: in typeassert, expected Float32, got ForwardDiff.Dual{Nothing,Float32,1}
in top-level scope at base\util.jl:175
in macro expansion at Juno\n6wyj\src\progress.jl:119
in macro expansion at Flux\Fj3bt\src\optimise\train.jl:122
in at Flux\Fj3bt\src\optimise\train.jl:79
in #train!#12 at Flux\Fj3bt\src\optimise\train.jl:81
in macro expansion at Juno\n6wyj\src\progress.jl:119 
in macro expansion at Flux\Fj3bt\src\optimise\train.jl:92 
in update! at Flux\Fj3bt\src\optimise\train.jl:31
in update! at Flux\Fj3bt\src\optimise\train.jl:25
in apply! at Flux\Fj3bt\src\optimise\optimisers.jl:175
in materialize! at base\broadcast.jl:823
in copyto! at base\broadcast.jl:864 
in copyto! at base\broadcast.jl:909 
in macro expansion at base\simdloop.jl:77 
in macro expansion at base\broadcast.jl:910 
in setindex! at base\multidimensional.jl:545 
in setindex! at base\array.jl:828 

```

Code

```julia
#(B) Solve simple differential equation
#(1) Generate grid
xGrid = sort(rand(Uniform(-1,1),1,ϰ),dims=1)

#(2) Build neural network and its derivative
Ο = Flux.Chain(Dense(1,16,softplus),Dense(16,1,softplus))
ο(t) = Ο([t])[1]
dο(t) = ForwardDiff.derivative(ο,t)[1]
ddο(t) = Flux.gradient(dο,t)[1]

#(3) Build loss function
function 𝕰(x)
    𝕰 = sum((ο.(x) .- dο.(x)).^2)
    𝕭 = (ο(1)-1).^2
    𝕷 = 𝕰+𝕭
    return 𝕷
end

𝕰(xGrid)

𝜣 = Flux.params(Ο)
Data = [xGrid]
opt = ADAM(0.13)

cb = () -> println(𝕰(xGrid))
@time Flux.@epochs 5000 Flux.train!(𝕰,𝜣,Data,opt,cb=cb)

```

Edit 2: I made ddο(t) work using fix suggested by @ChrisRackauckas  
[https://github.com/SciML/DiffEqFlux.jl/blob/v1.7.0/src/DiffEqFlux.jl#L53-L64](https://github.com/SciML/DiffEqFlux.jl/blob/v1.7.0/src/DiffEqFlux.jl#L53-L64)

```julia
# ForwardDiff integration

ZygoteRules.@adjoint function ForwardDiff.Dual{T}(x, ẋ::Tuple) where T
  @assert length(ẋ) == 1
  ForwardDiff.Dual{T}(x, ẋ), ḋ -> (ḋ.partials[1], (ḋ.value,))
end

ZygoteRules.@adjoint ZygoteRules.literal_getproperty(d::ForwardDiff.Dual{T}, ::Val{:partials}) where T =
  d.partials, ṗ -> (ForwardDiff.Dual{T}(ṗ[1], 0),)

ZygoteRules.@adjoint ZygoteRules.literal_getproperty(d::ForwardDiff.Dual{T}, ::Val{:value}) where T =
  d.value, ẋ -> (ForwardDiff.Dual{T}(0, ẋ),)

```

However, I can’t still get gradient of LossFunction, I am getting following error:  
**MethodError: no method matching Float32(::ForwardDiff.Dual{ForwardDiff.Tag{typeof(ο),Float64},Float64,1})**

Does somebody have an idea, how to fix it (use ForwardDiff/other autodiff in loss function, and still be able to train it in Flux)?

---

<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: [November 9, 2020, 2:07pm UTC](https://discourse.julialang.org/t/flux-differentiation-error/49811/3 "2020-11-09T14:07:45Z")

</div>

> [@Honza9723](#):
>
> Float32(::ForwardDiff.Dual{ForwardDiff.Tag{typeof(ο),Float64},Float64,1})

You’re mixing Float64 and Float32: you might want to make everything Float32.

---

<div class="post-metadata">

### Author: ![Honza9723](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/honza9723/32/7807_2.png) [@Honza9723](https://discourse.julialang.org/u/Honza9723)
#### Post date: [November 9, 2020, 2:10pm UTC](https://discourse.julialang.org/t/flux-differentiation-error/49811/4 "2020-11-09T14:10:40Z")

</div>

Dear Chris, thank you. So, I should convert xGrid to Float32? Is it a problem of input (xGrid), or do I need to fix something inside loss function?

---

<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: [November 9, 2020, 2:12pm UTC](https://discourse.julialang.org/t/flux-differentiation-error/49811/5 "2020-11-09T14:12:50Z")

</div>

Yes, you probably want to convert what comes out of `rand` to a Float32 (or make it directly sample Float32s).

---

<div class="post-metadata">

### Author: ![Honza9723](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/honza9723/32/7807_2.png) [@Honza9723](https://discourse.julialang.org/u/Honza9723)
#### Post date: [November 9, 2020, 2:14pm UTC](https://discourse.julialang.org/t/flux-differentiation-error/49811/6 "2020-11-09T14:14:31Z")

</div>

I tried that, and I still get this error

```julia
MethodError: no method matching Float32(::ForwardDiff.Dual{ForwardDiff.Tag{typeof(ο),Float32},Float64,1})

```

Code

```julia
#(B) Solve simple differential equation
#(1) Generate grid
xGrid = sort(rand(Uniform(-1,1),1,ϰ),dims=1)

xGrid = convert(Array{Float32},xGrid)

#(2) Build neural network and its derivative
Ο = Flux.Chain(Dense(1,16,softplus),Dense(16,1,softplus))
ο(t) = Ο([t])[1]
dο(t) = ForwardDiff.derivative(ο,t)
ddο(t) = Flux.gradient(dο,t)[1]

dο(5)

ddο(5)

ddο.(xGrid)

#(3) Build loss function
function 𝕰(x)
    𝕰 = sum((ο.(x) .- dο.(x)).^2)
    𝕭 = (ο(1)-1).^2
    𝕷 = 𝕰+𝕭
    return 𝕷
end

𝕰(xGrid)

𝜣 = Flux.params(Ο)
Data = [xGrid]
opt = ADAM(0.13)

cb = () -> println(𝕰(xGrid))
@time Flux.@epochs 5000 Flux.train!(𝕰,𝜣,Data,opt,cb=cb)

```

---

<div class="post-metadata">

### Author: ![Honza9723](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/honza9723/32/7807_2.png) [@Honza9723](https://discourse.julialang.org/u/Honza9723)
#### Post date: [November 9, 2020, 5:19pm UTC](https://discourse.julialang.org/t/flux-differentiation-error/49811/7 "2020-11-09T17:19:09Z")

</div>

Hi, sorry for spamming with this problem. I differentiated my loss function with respect to parameters of the neural network and get the following gradient. So, Zygote was able to differentiate ForwardDiff stuff.

```julia
∇𝕰 = Flux.gradient(()->𝕰(xGrid),𝜣)
∇𝕰.grads

```

However, the gradient had the following structure (include dual numbers, hence update of parameters fails in Flux.train! loop). It looks like the fix suggested by @ChrisRackauckas doesn’t work. Any idea, how to fix this?

```julia
IdDict{Any, Any} with 5 entries
16×1 Array{Float32,2}:
 => 16×1 Array{ForwardDiff.Dual{ForwardDiff.Tag{typeof(ο),Float32},Float32,1},2}:
 Dual{ForwardDiff.Tag{typeof(ο),Float32}}(-0.2634682,1271.0961)
 Dual{ForwardDiff.Tag{typeof(ο),Float32}}(0.036139756,-196.31708)
 Dual{ForwardDiff.Tag{typeof(ο),Float32}}(0.2237638,-1756.2749)
 Dual{ForwardDiff.Tag{typeof(ο),Float32}}(0.14364085,-776.0406)
 Dual{ForwardDiff.Tag{typeof(ο),Float32}}(0.0034865336,-18.079405)
 Dual{ForwardDiff.Tag{typeof(ο),Float32}}(0.27216268,-1725.1829)
 Dual{ForwardDiff.Tag{typeof(ο),Float32}}(-0.07260824,479.56946)
 Dual{ForwardDiff.Tag{typeof(ο),Float32}}(0.020844292,-140.64598)
 Dual{ForwardDiff.Tag{typeof(ο),Float32}}(-0.23060206,1787.3832)
 Dual{ForwardDiff.Tag{typeof(ο),Float32}}(0.17264761,-1272.322)
 Dual{ForwardDiff.Tag{typeof(ο),Float32}}(0.33930257,-1820.1713)
 Dual{ForwardDiff.Tag{typeof(ο),Float32}}(-0.056477264,478.3624)
 Dual{ForwardDiff.Tag{typeof(ο),Float32}}(0.3520169,-1696.228)
 Dual{ForwardDiff.Tag{typeof(ο),Float32}}(-0.039859835,272.59702)
 Dual{ForwardDiff.Tag{typeof(ο),Float32}}(0.19189215,-1461.739)
 Dual{ForwardDiff.Tag{typeof(ο),Float32}}(-0.08595074,513.59863)
Vector{Float32} with 16 elements
0.00
0.00
0.00
0.00
0.00
0.00
0.00
0.00
0.00
0.00
0.00
0.00
0.00
0.00
0.00
0.00
 => 
Vector{ForwardDiff.Dual{ForwardDiff.Tag{typeof(ο),Float32},Float32,1}} with 16 elements
Dual{ForwardDiff.Tag{typeof(ο),Float32}}(-0.26234788,357.27512)
Dual{ForwardDiff.Tag{typeof(ο),Float32}}(0.03616306,-26.888998)
Dual{ForwardDiff.Tag{typeof(ο),Float32}}(0.22294879,373.919)
Dual{ForwardDiff.Tag{typeof(ο),Float32}}(0.14253888,-111.39714)
Dual{ForwardDiff.Tag{typeof(ο),Float32}}(0.0034794048,-3.4679422)
Dual{ForwardDiff.Tag{typeof(ο),Float32}}(0.27468497,44.10873)
Dual{ForwardDiff.Tag{typeof(ο),Float32}}(-0.07365812,-31.0434)
Dual{ForwardDiff.Tag{typeof(ο),Float32}}(0.020888403,11.870704)
Dual{ForwardDiff.Tag{typeof(ο),Float32}}(-0.23005879,-363.95084)
Dual{ForwardDiff.Tag{typeof(ο),Float32}}(0.17167568,205.64714)
Dual{ForwardDiff.Tag{typeof(ο),Float32}}(0.33812273,-275.50446)
Dual{ForwardDiff.Tag{typeof(ο),Float32}}(-0.05754064,-129.68915)
Dual{ForwardDiff.Tag{typeof(ο),Float32}}(0.35195476,-477.36105)
Dual{ForwardDiff.Tag{typeof(ο),Float32}}(-0.04028002,-26.315512)
Dual{ForwardDiff.Tag{typeof(ο),Float32}}(0.19163737,276.66525)
Dual{ForwardDiff.Tag{typeof(ο),Float32}}(-0.08639604,17.339998)
1×16 Array{Float32,2}:
 -0.407974 0.0630915 0.566018 0.249386 … -0.0877669 0.470995 -0.165193
 => 1×16 Array{ForwardDiff.Dual{ForwardDiff.Tag{typeof(ο),Float32},Float32,1},2}:
Vector{Float32} with 1 element
0.00
 => 
Vector{ForwardDiff.Dual{ForwardDiff.Tag{typeof(ο),Float32},Float32,1}} with 1 element
Dual{ForwardDiff.Tag{typeof(ο),Float32}}(1.009891,-46.851746)
:(Main.xGrid) => 1×2500 Array{Float32,2}:

```

Do I understand it correctly, that it computed gradient correctly, and I need just to “de-dualize” it? Is there some easy way, how to do it, ideally such that Flux.train! loop would work?

---

<div class="post-metadata">

### Author: ![Honza9723](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/honza9723/32/7807_2.png) [@Honza9723](https://discourse.julialang.org/u/Honza9723)
#### Post date: [November 10, 2020, 4:41pm UTC](https://discourse.julialang.org/t/flux-differentiation-error/49811/8 "2020-11-10T16:41:53Z")

</div>

Hi, any guidance on what to do with this problem? Sorry for spamming with this, but I desperately need advice. 😃 I think it should be something simple, but I can’t find the solution. @ChrisRackauckas @MikeInnes

---

<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: [November 12, 2020, 1:50pm UTC](https://discourse.julialang.org/t/flux-differentiation-error/49811/9 "2020-11-12T13:50:53Z")

</div>

> [@Honza9723](#):
>
> Do I understand it correctly, that it computed gradient correctly, and I need just to “de-dualize” it? Is there some easy way, how to do it, ideally such that Flux.train! loop would work?

Yes, GalacticOptim.jl actually hard codes the workaround:

> <https://github.com/SciML/Optimization.jl/blob/master/src/function.jl#L174>

---

<div class="post-metadata">

### Author: ![Honza9723](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/honza9723/32/7807_2.png) [@Honza9723](https://discourse.julialang.org/u/Honza9723)
#### Post date: [November 12, 2020, 2:07pm UTC](https://discourse.julialang.org/t/flux-differentiation-error/49811/10 "2020-11-12T14:07:42Z")

</div>

@ChrisRackauckas Thank you very much! I did something like that on my own, just very inefficient. 😃 So, I just need to plug my loss function into GalacticOptim?

---

<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: [November 13, 2020, 2:29pm UTC](https://discourse.julialang.org/t/flux-differentiation-error/49811/11 "2020-11-13T14:29:29Z")

</div>

I think so. 🤞. If it doesn’t, let me know.

---

<div class="post-metadata">

### Author: ![Honza9723](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/honza9723/32/7807_2.png) [@Honza9723](https://discourse.julialang.org/u/Honza9723)
#### Post date: [November 13, 2020, 3:19pm UTC](https://discourse.julialang.org/t/flux-differentiation-error/49811/12 "2020-11-13T15:19:44Z")

</div>

@ChrisRackauckas Thank you very much! I will try it! Is there some example, how to put user-defined loss function with Flux neural networks inside to GalacticOptim.jl?

PS: I make it work using my implementation of ADAM that manually de-dualize gradient. Thank you for your guidance!

 ![Differential](https://global.discourse-cdn.com/julialang/original/3X/7/b/7b215d06580a36d2425f68e6fee35eb46061f6e9.png)

---

<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: [November 14, 2020, 1:00am UTC](https://discourse.julialang.org/t/flux-differentiation-error/49811/13 "2020-11-14T01:00:35Z")

</div>

No problem!

---

<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: [November 14, 2020, 6:41pm UTC](https://discourse.julialang.org/t/flux-differentiation-error/49811/14 "2020-11-14T18:41:37Z")

</div>

And for the future, see this update on where our AD tools are going: [DifferentialEquations - Derivatives in ODE function/ nesting AD - #2 by ChrisRackauckas](https://discourse.julialang.org/t/differentialequations-derivatives-in-ode-function-nesting-ad/50100/2)

---

<div class="post-metadata">

### Author: ![Honza9723](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/honza9723/32/7807_2.png) [@Honza9723](https://discourse.julialang.org/u/Honza9723)
#### Post date: [November 18, 2020, 4:48pm UTC](https://discourse.julialang.org/t/flux-differentiation-error/49811/15 "2020-11-18T16:48:34Z")

</div>

Hi Chris, I tried to install GalacticOptim.jl, and I get the following error. Is there some tutorial on how to solve this?

Also, I would like to ask, how to optimize loss function which contains Flux neural network with those implicit parameters. Simply collect them using Flux.params?

```julia
ERROR: Unsatisfiable requirements detected for package Compat [34da2185]:
 Compat [34da2185] log:
 ├─possible versions are: [1.0.0-1.0.1, 1.1.0, 1.2.0, 1.3.0, 1.4.0, 1.5.0-1.5.1, 2.0.0, 2.1.0, 2.2.0-2.2.1, 3.0.0, 3.1.0, 3.2.0, 3.3.0-3.3.1, 3.4.0, 3.5.0, 3.6.0, 3.7.0, 3.8.0, 3.9.0-3.9.1, 3.10.0, 3.11.0, 3.12.0, 3.13.0, 3.14.0, 3.15.0, 3.16.0, 3.17.0, 3.18.0, 3.19.0, 3.20.0, 3.21.0, 3.22.0, 3.23.0] or uninstalled
 ├─restricted by compatibility requirements with BlackBoxOptim [a134a8b2] to versions: [1.0.0-1.0.1, 1.1.0, 1.2.0, 1.3.0, 1.4.0, 1.5.0-1.5.1, 2.0.0, 2.1.0, 2.2.0-2.2.1, 3.0.0, 3.1.0, 3.2.0, 3.3.0-3.3.1, 3.4.0, 3.5.0, 3.6.0, 3.7.0, 3.8.0, 3.9.0-3.9.1, 3.10.0, 3.11.0, 3.12.0, 3.13.0, 3.14.0, 3.15.0, 3.16.0, 3.17.0, 3.18.0, 3.19.0, 3.20.0, 3.21.0, 3.22.0, 3.23.0]
 │ └─BlackBoxOptim [a134a8b2] log:
 │ ├─possible versions are: [0.4.0, 0.5.0] or uninstalled
 │ └─restricted to versions * by an explicit requirement, leaving only versions [0.4.0, 0.5.0]
 ├─restricted by compatibility requirements with TensorFlow [1d978283] to versions: [1.0.0-1.0.1, 1.1.0, 1.2.0, 1.3.0, 1.4.0, 1.5.0-1.5.1, 2.0.0, 2.1.0, 2.2.0-2.2.1]
 │ └─TensorFlow [1d978283] log:
 │ ├─possible versions are: [0.10.2, 0.10.4, 0.11.0] or uninstalled
 │ └─restricted to versions * by an explicit requirement, leaving only versions [0.10.2, 0.10.4, 0.11.0]   
 └─restricted by compatibility requirements with Optim [429524aa] to versions: [3.2.0, 3.3.0-3.3.1, 3.4.0, 3.5.0, 3.6.0, 3.7.0, 3.8.0, 3.9.0-3.9.1, 3.10.0, 3.11.0, 3.12.0, 3.13.0, 3.14.0, 3.15.0, 3.16.0, 3.17.0, 3.18.0, 3.19.0, 3.20.0, 3.21.0, 3.22.0, 3.23.0] — no versions left
   └─Optim [429524aa] log:
     ├─possible versions are: [0.15.3, 0.16.0, 0.17.0-0.17.2, 0.18.0-0.18.1, 0.19.0-0.19.7, 0.20.0-0.20.6, 0.21.0, 0.22.0, 1.0.0, 1.1.0, 1.2.0] or uninstalled
     ├─restricted to versions * by an explicit requirement, leaving only versions [0.15.3, 0.16.0, 0.17.0-0.17.2, 0.18.0-0.18.1, 0.19.0-0.19.7, 0.20.0-0.20.6, 0.21.0, 0.22.0, 1.0.0, 1.1.0, 1.2.0]
     └─restricted by compatibility requirements with GalacticOptim [a75be94c] to versions: [0.22.0, 1.0.0, 1.1.0, 1.2.0]
       └─GalacticOptim [a75be94c] log:
         ├─possible versions are: [0.1.0-0.1.3, 0.2.0-0.2.2, 0.3.0-0.3.1, 0.4.0-0.4.1] or uninstalled        
         └─restricted to versions * by an explicit requirement, leaving only versions [0.1.0-0.1.3, 0.2.0-0.2.2, 0.3.0-0.3.1, 0.4.0-0.4.1]

```

---

<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: [November 18, 2020, 5:33pm UTC](https://discourse.julialang.org/t/flux-differentiation-error/49811/16 "2020-11-18T17:33:22Z")

</div>

I think TensorFlow.jl might be implicitly upper bounding compat.jl? @oxinabox

Though this is an entirely diferent topic so it shouldn’t be in the same thread.

---

<div class="post-metadata">

### Author: ![oxinabox](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/oxinabox/32/206603_2.png) [@oxinabox](https://discourse.julialang.org/u/oxinabox)
#### Post date: [November 18, 2020, 8:19pm UTC](https://discourse.julialang.org/t/flux-differentiation-error/49811/17 "2020-11-18T20:19:50Z")

</div>

Having TensorFlow.jl in your dependency tree seems like a mistake.  
Its pretty stale these days. Like it works, but it is bound to an old version of LibTensorFlow, and its just less fun to use than Flux etc.

---

<div class="post-metadata">

### Author: ![Honza9723](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/honza9723/32/7807_2.png) [@Honza9723](https://discourse.julialang.org/u/Honza9723)
#### Post date: [November 18, 2020, 8:45pm UTC](https://discourse.julialang.org/t/flux-differentiation-error/49811/18 "2020-11-18T20:45:14Z")

</div>

How should I kill it?

---

<div class="post-metadata">

### Author: ![oxinabox](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/oxinabox/32/206603_2.png) [@oxinabox](https://discourse.julialang.org/u/oxinabox)
#### Post date: [November 19, 2020, 12:58pm UTC](https://discourse.julialang.org/t/flux-differentiation-error/49811/19 "2020-11-19T12:58:47Z")

</div>

`] rm TensorFlow` i guess.  
I recommend reading the package managers docs.  
[https://julialang.github.io/Pkg.jl/v1/](https://julialang.github.io/Pkg.jl/v1/)

---

<div class="post-metadata">

### Author: ![Honza9723](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/honza9723/32/7807_2.png) [@Honza9723](https://discourse.julialang.org/u/Honza9723)
#### Post date: [November 19, 2020, 1:20pm UTC](https://discourse.julialang.org/t/flux-differentiation-error/49811/20 "2020-11-19T13:20:51Z")

</div>

Thank you, it works!