# Flux con! warning

**URL:** <https://discourse.julialang.org/t/flux-con-warning/49456>\
**Category:** Machine Learning\
**Created:** [November 2, 2020, 12:04pm UTC](https://discourse.julialang.org/t/flux-con-warning/49456 "2020-11-02T12:04:18Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![Krzysztof\_Langner](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/krzysztof_langner/32/19126_2.png) [@Krzysztof\_Langner](https://discourse.julialang.org/u/Krzysztof_Langner)\
**Post date:** [November 2, 2020, 12:04pm UTC](https://discourse.julialang.org/t/flux-con-warning/49456/1 "2020-11-02T12:04:18Z")

</div>

Hi,

I’m trying to build simple model which works with MNIST dataset. It works fine, but I get some warning and was wandering if this is something which I can improve  
Here is the model:

```julia
Chain(
        Conv((5, 5), 1=>8, pad=2, stride=2, relu),
        Conv((3, 3), 8=>16, pad=1, stride=2, relu),
        Conv((3, 3), 16=>32, pad=1, stride=2, relu),
        Conv((3, 3), 32=>32, pad=1, stride=2, relu),
        GlobalMeanPool(),
        flatten,
        Dense(32, 10),
        softmax
    )

```

And here is the warning:

```julia
Warning: Slow fallback implementation invoked for conv! You probably don't want this; check your datatypes.
│ yT = Float32
│ T1 = FixedPointNumbers.Normed{UInt8,8}
│ T2 = Float32
└ @ NNlib ~/.julia/packages/NNlib/haems/src/conv.jl:206

```

As I said the model works ok even with this warning, but I’m curious what have I done wrong here.

Thanks in advance for any tips.

---

<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 2, 2020, 2:04pm UTC](https://discourse.julialang.org/t/flux-con-warning/49456/2 "2020-11-02T14:04:12Z")

</div>

Not tested but I suspect you want to convert your input intho `Float32` before you start.  
Since looks like hte MNIST data is stored as a `FixedPointNumbers.Normed{UInt8,8}`  
You could do that when you loaded it as a preprocessing step.

---

<div class="post-metadata">

**Author:** ![Krzysztof\_Langner](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/krzysztof_langner/32/19126_2.png) [@Krzysztof\_Langner](https://discourse.julialang.org/u/Krzysztof_Langner)\
**Post date:** [November 2, 2020, 4:09pm UTC](https://discourse.julialang.org/t/flux-con-warning/49456/3 "2020-11-02T16:09:05Z")

</div>

I see. Makes sense.  
But when I try to convert the train data to float with the command

```julia
x_test = float(x_test) ./ 256

```

I get an error:

```julia
 MethodError: no method matching ∇meanpool(::Array{Float64,4}, ::Array{Float32,4}, ::Array{Float32,4}, ::PoolDims{2,(2, 2),(2, 2),(0, 0, 0, 0),(1, 1)})

```

Sorry if this is something naive, but I’m quite new to Julia.

---

<div class="post-metadata">

**Author:** ![mcabbott](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/mcabbott/32/6603_2.png) [@mcabbott](https://discourse.julialang.org/u/mcabbott)\
**Post date:** [November 2, 2020, 4:35pm UTC](https://discourse.julialang.org/t/flux-con-warning/49456/4 "2020-11-02T16:35:39Z")

</div>

This is a bit of a sharp corner. The initial complaint was about mixing Float32 and `Normed{UInt8,8}`, which meant you got a slow fallback version of `conv`. The new complaint is about mixing Float64 and Float32, for which it seems nobody wrote such a fallback version of `∇meanpool` at all.

The solution is probably to convert more explicitly:

```julia
julia> Float32.(rand(UInt8, 2,2,1,1)) ./ 256 
2×2×1×1 Array{Float32,4}:
...

julia> float(rand(UInt8, 2,2,1,1)) # turns out to give Float64
2×2×1×1 Array{Float64,4}:

```

---

<div class="post-metadata">

**Author:** ![Krzysztof\_Langner](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/krzysztof_langner/32/19126_2.png) [@Krzysztof\_Langner](https://discourse.julialang.org/u/Krzysztof_Langner)\
**Post date:** [November 2, 2020, 9:41pm UTC](https://discourse.julialang.org/t/flux-con-warning/49456/5 "2020-11-02T21:41:59Z")

</div>

It worked, Thank you!  
BTW it looks that the MNIST dataset has values in range 0-1 even if it is not float.  
So just converting to float is enough. Interesting type (FixedPointNumbers.Normed) 🙂

And it is also faster this way (what was expected)