# Why is there a "Warning: Slow Fallback implementation" and a DimensionMismatch error?

**URL:** <https://discourse.julialang.org/t/why-is-there-a-warning-slow-fallback-implementation-and-a-dimensionmismatch-error/55283>\
**Category:** General Usage\
**Tags:** images, flux, csv\
**Created:** [February 14, 2021, 11:59pm UTC](https://discourse.julialang.org/t/why-is-there-a-warning-slow-fallback-implementation-and-a-dimensionmismatch-error/55283 "2021-02-14T23:59:37Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![SatvikDuddukuru](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/satvikduddukuru/32/19509_2.png) [@SatvikDuddukuru](https://discourse.julialang.org/u/SatvikDuddukuru)\
**Post date:** [February 14, 2021, 11:59pm UTC](https://discourse.julialang.org/t/why-is-there-a-warning-slow-fallback-implementation-and-a-dimensionmismatch-error/55283/1 "2021-02-14T23:59:37Z")

</div>

I am trying to create a convolutional neural network to classify MNIST data with Flux in Julia. I downloaded the data as a csv from this link: [MNIST in CSV | Kaggle](https://www.kaggle.com/oddrationale/mnist-in-csv).  
My code is below:

```julia
using CSV
using DataFrames
using Images
using Base.Iterators: partition
using Flux

sqrt(x) = convert(Int64, floor(x^0.5))
matrixize(x) = cat([x[i:i+sqrt(length(x))-1] for i in 1:sqrt(length(x)):length(x)]..., dims=2)'
img(x) = Gray.(x)
process(row) = img(matrixize(row[2:length(row)])), convert(Int, 255*row[1]) |> gpu

train_data = DataFrame(CSV.File("MNIST_data/mnist_train.csv"))
train_X = []
train_y = Int64[]
for row in eachrow(train_data)
    row = convert(Array, row)
    row = [i/255 for i in row]
    X, y = process(row)
    push!(train_X, X)
    push!(train_y, y)
end
train_y = Flux.onehotbatch(train_y, 0:9)
train = [(cat(float.(train_X[i])..., dims=4), train_y[:, i]) for i in partition(1:size(train_data)[1], 1000)] |> gpu
test_data = DataFrame(CSV.File("MNIST_data/mnist_train.csv"))
test_X = []
test_y = Int64[]
for row in eachrow(test_data)
    row = convert(Array, row)
    row = [i/255 for i in row]
    X, y = process(row)
    push!(test_X, X)
    push!(test_y, y)
end
test_y = Flux.onehotbatch(test_y, 0:9)
println("Pre-processing Complete")

m = Chain(
    Conv((5, 5), 1=>16, relu),
    MaxPool((2, 2)),
    Conv((5, 5), 16=>8, relu),
    MaxPool((2, 2)),
    Flux.flatten,
    Dense(200, 100),
    Dense(100, 10),
    Flux.softmax
) |> gpu
loss(x, y) = Flux.Losses.crossentropy(m(x), y) |> gpu
opt = Momentum(0.01) |> gpu
println("Model Creation Complete")

println()
epochs = 10
for i in 1:epochs
    for j in train
        gs = gradient(params(m)) do
            l = loss(j...)
        end
        update!(opt, params(m), gs)
    end
    @show accuracy(test_X, test_y)
end

println()
@show accuracy(test_X, test_y)

```

When I check values of test\_X, test\_y, train\_X, and train\_y, they are all in the appropriate format, but I get this error when I try to run the code:

```julia
┌ Warning: Slow fallback implementation invoked for conv! You probably don't want this; check your datatypes.
│ yT = Float64
│ T1 = Gray{Float64}
│ T2 = Float32
└ @ NNlib /Users/satvikd/.julia/packages/NNlib/PI8Xh/src/conv.jl:206
┌ Warning: Slow fallback implementation invoked for conv! You probably don't want this; check your datatypes.
│ yT = Float64
│ T1 = Float64
│ T2 = Float32
└ @ NNlib /Users/satvikd/.julia/packages/NNlib/PI8Xh/src/conv.jl:206
DimensionMismatch("A has dimensions (100,200) but B has dimensions (128,1000)")

```

The stack trace refers to line 55, the one with the gradient.  
Any help would be appreciated.

---

<div class="post-metadata">

**Author:** ![Tamas\_Papp](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/tamas_papp/32/25949_2.png) [@Tamas\_Papp](https://discourse.julialang.org/u/Tamas_Papp)\
**Post date:** [February 16, 2021, 9:03am UTC](https://discourse.julialang.org/t/why-is-there-a-warning-slow-fallback-implementation-and-a-dimensionmismatch-error/55283/2 "2021-02-16T09:03:52Z")

</div>

Your `train_X` and `test_X` have element type `Any`. Choose something concrete.