# Flux: GPU not working as expected

**URL:** <https://discourse.julialang.org/t/flux-gpu-not-working-as-expected/43759>\
**Category:** Machine Learning\
**Tags:** flux\
**Created:** [July 27, 2020, 1:10pm UTC](https://discourse.julialang.org/t/flux-gpu-not-working-as-expected/43759 "2020-07-27T13:10:11Z")\
**Posts on this page:** 1\
**Showing post:** 3

<div class="post-metadata">

**Author:** ![Ruan\_Stander](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/ruan_stander/32/11304_2.png) [@Ruan\_Stander](https://discourse.julialang.org/u/Ruan_Stander)\
**Post date:** [July 27, 2020, 6:50pm UTC](https://discourse.julialang.org/t/flux-gpu-not-working-as-expected/43759/3 "2020-07-27T18:50:33Z")

</div>

> [@ToucheSir](#):
>
> ata setup and training code? The snippet above doesn’t run actually run the model on any data, so it’s impossible to tell what the performance bottleneck is.

Sure, essentially the same as the Model Zoo example (swapped 28,28,N input pictures with 5,10,N also Float32)  
Only utilising 7% of GPU [Nvidia 1060] when I increase N above a small number (i.e. CPU is faster

```julia
if has_cuda() # Check if CUDA is available
    @info "CUDA is on"
    import CuArrays # If CUDA is available, import CuArrays
    CuArrays.allowscalar(false)
end

@with_kw mutable struct Args
    η::Float64 = 3e-4 # learning rate
    batchsize::Int = 32 # batch size
    epochs::Int = 10 # number of epochs
    device::Function = cpu # set as gpu, if gpu available
end
function getdata(args)
    # Loading Dataset
    endOfTrain=Int64(trunc(length(Output)*0.7))
    xtrain=Imatrix[:,:,1:endOfTrain]
    xtest=Imatrix[:,:,endOfTrain+1:length(Output)]

    ytrain=Output[1:endOfTrain]
    ytest=Output[endOfTrain+1:length(Output)]
    # Reshape Data for flatten the each image into linear array
    xtrain = Flux.flatten(xtrain)
    xtest = Flux.flatten(xtest)

    # One-hot-encode the labels
    ytrain, ytest = onehotbatch(ytrain, 0:1), onehotbatch(ytest, 0:1)

    # Batching
    train_data = DataLoader(xtrain, ytrain, batchsize=args.batchsize, shuffle=true)
    test_data = DataLoader(xtest, ytest, batchsize=args.batchsize)

    return train_data, test_data
end

function build_model(; imgsize=(5,10,1), nclasses=2)
    return Chain(
 	    Dense(prod(imgsize), 32, relu),Dense(32,32,relu),
            Dense(32, nclasses))
end

function loss_all(dataloader, model)
    l = 0f0
    for (x,y) in dataloader
        l += logitcrossentropy(model(x), y)
    end
    l/length(dataloader)
end

function train(; kws...)
    # Initializing Model parameters
    args = Args(; kws...)

    # Load Data
    train_data,test_data = getdata(args)

    # Construct model
    m = build_model()
    train_data = args.device.(train_data)
    test_data = args.device.(test_data)
    #m = args.device(m)
    m = args.device(m)
    loss(x,y) = logitcrossentropy(m(x), y)

    ## Training
    evalcb = Flux.throttle( () -> @show(loss_all(train_data, m),accuracy(test_data, m)),5)
    
    opt = ADAM(args.η)

    @epochs args.epochs Flux.train!(loss, Flux.params(m), train_data, opt)

    @show accuracy(train_data, m)

    @show accuracy(test_data, m)
    return m
end
```

---

_[View the full topic](https://discourse.julialang.org/t/flux-gpu-not-working-as-expected/43759)._