Error 2 Example 2

ERROR: LoadError: TaskFailedException
Stacktrace:
 [1] wait
   @ ./task.jl:334 [inlined]
 [2] fetch(t::Task)
   @ Base ./task.jl:349
 [3] top-level scope
   @ ~/knightvision/piece_recognition/KnightVisionServer/test/test_cuda.jl:39

    nested task error: CUDNNError: CUDNN_STATUS_INTERNAL_ERROR (code 4)
    Stacktrace:
      [1] throw_api_error(res::CUDA.CUDNN.cudnnStatus_t)
        @ CUDA.CUDNN ~/.julia/packages/CUDA/0IDh2/lib/cudnn/error.jl:22
      [2] macro expansion
        @ ~/.julia/packages/CUDA/0IDh2/lib/cudnn/error.jl:35 [inlined]
      [3] cudnnCreate()
        @ CUDA.CUDNN ~/.julia/packages/CUDA/0IDh2/lib/cudnn/base.jl:3
      [4] #1218
        @ ~/.julia/packages/CUDA/0IDh2/lib/cudnn/CUDNN.jl:72 [inlined]
      [5] (::CUDA.APIUtils.var"#8#11"{CUDA.CUDNN.var"#1218#1224", CUDA.APIUtils.HandleCache{CUDA.CuContext, Ptr{Nothing}}, CUDA.CuContext})()
        @ CUDA.APIUtils ~/.julia/packages/CUDA/0IDh2/lib/utils/cache.jl:24
      [6] lock(f::CUDA.APIUtils.var"#8#11"{CUDA.CUDNN.var"#1218#1224", CUDA.APIUtils.HandleCache{CUDA.CuContext, Ptr{Nothing}}, CUDA.CuContext}, l::ReentrantLock)
        @ Base ./lock.jl:190
      [7] (::CUDA.APIUtils.var"#check_cache#9"{CUDA.APIUtils.HandleCache{CUDA.CuContext, Ptr{Nothing}}, CUDA.CuContext})(f::CUDA.CUDNN.var"#1218#1224")
        @ CUDA.APIUtils ~/.julia/packages/CUDA/0IDh2/lib/utils/cache.jl:22
      [8] pop!
        @ ~/.julia/packages/CUDA/0IDh2/lib/utils/cache.jl:46 [inlined]
      [9] (::CUDA.CUDNN.var"#new_state#1223")(cuda::NamedTuple{(:device, :context, :stream, :math_mode, :math_precision), Tuple{CUDA.CuDevice, CUDA.CuContext, CUDA.CuStream, CUDA.MathMode, Symbol}})
        @ CUDA.CUDNN ~/.julia/packages/CUDA/0IDh2/lib/cudnn/CUDNN.jl:71
     [10] #1221
        @ ~/.julia/packages/CUDA/0IDh2/lib/cudnn/CUDNN.jl:86 [inlined]
     [11] get!(default::CUDA.CUDNN.var"#1221#1227"{CUDA.CUDNN.var"#new_state#1223", NamedTuple{(:device, :context, :stream, :math_mode, :math_precision), Tuple{CUDA.CuDevice, CUDA.CuContext, CUDA.CuStream, CUDA.MathMode, Symbol}}}, h::Dict{CUDA.CuContext, NamedTuple{(:handle, :stream), Tuple{Ptr{Nothing}, CUDA.CuStream}}}, key::CUDA.CuContext)
        @ Base ./dict.jl:464
     [12] handle()
        @ CUDA.CUDNN ~/.julia/packages/CUDA/0IDh2/lib/cudnn/CUDNN.jl:85
     [13] (::CUDA.CUDNN.var"#1145#1147"{CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, CUDA.CUDNN.cudnnActivationMode_t, CUDA.CUDNN.cudnnConvolutionDescriptor, CUDA.CUDNN.cudnnFilterDescriptor, CUDA.CUDNN.cudnnTensorDescriptor, CUDA.CUDNN.cudnnTensorDescriptor, Base.RefValue{Float32}, Base.RefValue{Float32}, CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, CUDA.CUDNN.cudnnConvolutionFwdAlgoPerfStruct})(workspace::CUDA.CuArray{UInt8, 1, CUDA.Mem.DeviceBuffer})
        @ CUDA.CUDNN ~/.julia/packages/CUDA/0IDh2/lib/cudnn/convolution.jl:105
     [14] with_workspace(f::CUDA.CUDNN.var"#1145#1147"{CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, CUDA.CUDNN.cudnnActivationMode_t, CUDA.CUDNN.cudnnConvolutionDescriptor, CUDA.CUDNN.cudnnFilterDescriptor, CUDA.CUDNN.cudnnTensorDescriptor, CUDA.CUDNN.cudnnTensorDescriptor, Base.RefValue{Float32}, Base.RefValue{Float32}, CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer}, CUDA.CUDNN.cudnnConvolutionFwdAlgoPerfStruct}, eltyp::Type{UInt8}, size::CUDA.APIUtils.var"#2#3"{UInt64}, fallback::Nothing; keep::Bool)
        @ CUDA.APIUtils ~/.julia/packages/CUDA/0IDh2/lib/utils/call.jl:77
     [15] with_workspace
        @ ~/.julia/packages/CUDA/0IDh2/lib/utils/call.jl:58 [inlined]
     [16] #with_workspace#1
        @ ~/.julia/packages/CUDA/0IDh2/lib/utils/call.jl:53 [inlined]
     [17] with_workspace (repeats 2 times)
        @ ~/.julia/packages/CUDA/0IDh2/lib/utils/call.jl:53 [inlined]
     [18] 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:103
     [19] #cudnnConvolutionForwardWithDefaults#1143
        @ ~/.julia/packages/CUDA/0IDh2/lib/cudnn/convolution.jl:96 [inlined]
     [20] #cudnnConvolutionForward!#1142
        @ ~/.julia/packages/CUDA/0IDh2/lib/cudnn/convolution.jl:53 [inlined]
     [21] 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
     [22] conv!
        @ ~/.julia/packages/NNlibCUDA/IeeBk/src/cudnn/conv.jl:27 [inlined]
     [23] 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
     [24] 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
     [25] (::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
     [26] 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
     [27] Chain
        @ ~/.julia/packages/Flux/BPPNj/src/layers/basic.jl:49 [inlined]
     [28] inference(imgs::CUDA.CuArray{Float32, 4, CUDA.Mem.DeviceBuffer})
        @ Main ~/knightvision/piece_recognition/KnightVisionServer/test/test_cuda.jl:15
     [29] (::var"#15#16")()
        @ Main ./threadingconstructs.jl:178
in expression starting at /home/mattias/knightvision/piece_recognition/KnightVisionServer/test/test_cuda.jl:36