Error Example 1

ERROR: LoadError: TaskFailedException

    nested task error: Out of GPU memory trying to allocate 897.217 MiB
    Effective GPU memory usage: 52.47% (5.726 GiB/10.913 GiB)
    Memory pool usage: 3.117 GiB (3.656 GiB reserved)
    Stacktrace:
      [1] macro expansion
        @ ~/.julia/packages/CUDA/0IDh2/src/pool.jl:219 [inlined]
      [2] macro expansion
        @ ./timing.jl:299 [inlined]
      [3] #_alloc#180
        @ ~/.julia/packages/CUDA/0IDh2/src/pool.jl:187 [inlined]
      [4] #alloc#179
        @ ~/.julia/packages/CUDA/0IDh2/src/pool.jl:173 [inlined]
      [5] alloc
        @ ~/.julia/packages/CUDA/0IDh2/src/pool.jl:169 [inlined]
      [6] CuArray
        @ ~/.julia/packages/CUDA/0IDh2/src/array.jl:44 [inlined]
      [7] CuArray
        @ ~/.julia/packages/CUDA/0IDh2/src/array.jl:125 [inlined]
      [8] CuArray
        @ ~/.julia/packages/CUDA/0IDh2/src/array.jl:132 [inlined]
      [9] with_workspace(f::CUDA.CUDNN.var"#1150#1153"{Vector{CUDA.CUDNN.cudnnConvolutionFwdAlgoPerfStruct}, Vector{Int32}, Int64, CUDA.CUDNN.cudnnTensorDescriptor, CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, CUDA.CUDNN.cudnnFilterDescriptor, CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, CUDA.CUDNN.cudnnConvolutionDescriptor, CUDA.CUDNN.cudnnTensorDescriptor, CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}}, eltyp::Type{UInt8}, size::CUDA.CUDNN.var"#workspaceSize#1152"{CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}}, fallback::Nothing; keep::Bool)
        @ CUDA.APIUtils ~/.julia/packages/CUDA/0IDh2/lib/utils/call.jl:65
     [10] with_workspace
        @ ~/.julia/packages/CUDA/0IDh2/lib/utils/call.jl:58 [inlined]
     [11] #with_workspace#1
        @ ~/.julia/packages/CUDA/0IDh2/lib/utils/call.jl:53 [inlined]
     [12] with_workspace (repeats 2 times)
        @ ~/.julia/packages/CUDA/0IDh2/lib/utils/call.jl:53 [inlined]
     [13] #1149
        @ ~/.julia/packages/CUDA/0IDh2/lib/cudnn/convolution.jl:179 [inlined]
     [14] get!(default::CUDA.CUDNN.var"#1149#1151"{CUDA.CUDNN.cudnnTensorDescriptor, CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, CUDA.CUDNN.cudnnFilterDescriptor, CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, CUDA.CUDNN.cudnnConvolutionDescriptor, CUDA.CUDNN.cudnnTensorDescriptor, CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}}, h::Dict{Tuple, CUDA.CUDNN.cudnnConvolutionFwdAlgoPerfStruct}, key::Tuple{CUDA.CUDNN.cudnnTensorDescriptor, CUDA.CUDNN.cudnnFilterDescriptor, CUDA.CUDNN.cudnnConvolutionDescriptor, Nothing, CUDA.CUDNN.cudnnActivationMode_t})
        @ Base ./dict.jl:464
     [15] cudnnConvolutionFwdAlgoPerf(xDesc::CUDA.CUDNN.cudnnTensorDescriptor, x::CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, wDesc::CUDA.CUDNN.cudnnFilterDescriptor, w::CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, convDesc::CUDA.CUDNN.cudnnConvolutionDescriptor, yDesc::CUDA.CUDNN.cudnnTensorDescriptor, y::CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, biasDesc::Nothing, activation::CUDA.CUDNN.cudnnActivationMode_t)
        @ CUDA.CUDNN ~/.julia/packages/CUDA/0IDh2/lib/cudnn/convolution.jl:174
     [16] cudnnConvolutionForwardAD(w::CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, x::CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, bias::Nothing, z::CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}; y::CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, activation::CUDA.CUDNN.cudnnActivationMode_t, convDesc::CUDA.CUDNN.cudnnConvolutionDescriptor, wDesc::CUDA.CUDNN.cudnnFilterDescriptor, xDesc::CUDA.CUDNN.cudnnTensorDescriptor, yDesc::CUDA.CUDNN.cudnnTensorDescriptor, zDesc::CUDA.CUDNN.cudnnTensorDescriptor, biasDesc::Nothing, alpha::Base.RefValue{Float32}, beta::Base.RefValue{Float32}, dw::Base.RefValue{Any}, dx::Base.RefValue{Any}, dz::Base.RefValue{Any}, dbias::Base.RefValue{Any}, dready::Base.RefValue{Bool})
        @ CUDA.CUDNN ~/.julia/packages/CUDA/0IDh2/lib/cudnn/convolution.jl:102
     [17] #cudnnConvolutionForwardWithDefaults#1143
        @ ~/.julia/packages/CUDA/0IDh2/lib/cudnn/convolution.jl:96 [inlined]
     [18] #cudnnConvolutionForward!#1142
        @ ~/.julia/packages/CUDA/0IDh2/lib/cudnn/convolution.jl:53 [inlined]
     [19] conv!(y::CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, x::CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, w::CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, cdims::DenseConvDims{2, (5, 5), 3, 6, 1, (1, 1), (0, 0, 0, 0), (1, 1), false}; alpha::Int64, beta::Int64, algo::Int64)
        @ NNlibCUDA ~/.julia/packages/NNlibCUDA/IeeBk/src/cudnn/conv.jl:34
     [20] conv!
        @ ~/.julia/packages/NNlibCUDA/IeeBk/src/cudnn/conv.jl:27 [inlined]
     [21] conv(x::CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, w::CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, cdims::DenseConvDims{2, (5, 5), 3, 6, 1, (1, 1), (0, 0, 0, 0), (1, 1), false}; kwargs::Base.Pairs{Symbol, Union{}, Tuple{}, NamedTuple{(), Tuple{}}})
        @ NNlib ~/.julia/packages/NNlib/tvMmZ/src/conv.jl:91
     [22] conv(x::CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, w::CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, cdims::DenseConvDims{2, (5, 5), 3, 6, 1, (1, 1), (0, 0, 0, 0), (1, 1), false})
        @ NNlib ~/.julia/packages/NNlib/tvMmZ/src/conv.jl:89
     [23] (::Conv{2, 4, typeof(relu), CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, CUDA.CuArray{Float32, 1, CUDA.Mem.DeviceBuffer}})(x::CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer})
        @ Flux ~/.julia/packages/Flux/BPPNj/src/layers/conv.jl:166
     [24] applychain(fs::Tuple{Conv{2, 4, typeof(relu), CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, CUDA.CuArray{Float32, 1, CUDA.Mem.DeviceBuffer}}, MaxPool{2, 4}, Conv{2, 4, typeof(relu), CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, CUDA.CuArray{Float32, 1, CUDA.Mem.DeviceBuffer}}, MaxPool{2, 4}, typeof(flatten), Dense{typeof(relu), CUDA.CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, CUDA.CuArray{Float32, 1, CUDA.Mem.DeviceBuffer}}, Dense{typeof(relu), CUDA.CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, CUDA.CuArray{Float32, 1, CUDA.Mem.DeviceBuffer}}, Dense{typeof(identity), CUDA.CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, CUDA.CuArray{Float32, 1, CUDA.Mem.DeviceBuffer}}}, x::CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer})
        @ Flux ~/.julia/packages/Flux/BPPNj/src/layers/basic.jl:47
     [25] Chain
        @ ~/.julia/packages/Flux/BPPNj/src/layers/basic.jl:49 [inlined]
     [26] inference(imgs::CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer})
        @ Main ~/knightvision/piece_recognition/KnightVisionServer/test/test_cuda.jl:15
     [27] (::var"#5#6")()
        @ Main ./threadingconstructs.jl:178

...and 11 more exceptions.

Stacktrace:
 [1] sync_end(c::Channel{Any})
   @ Base ./task.jl:381
 [2] top-level scope
   @ task.jl:400
in expression starting at /home/mattias/knightvision/piece_recognition/KnightVisionServer/test/test_cuda.jl:25