What would be the cause of these errors using the ImageRestyle[] function when trying to use GPU for calculation? Both MXNet Neural Networks and raw CUDA functions and compiles are working pretty well with the configuration below. Why would this experimental function be failing?

ImageRestyle[headshot, modernart, PerformanceGoal -> "Speed", TargetDevice -> "GPU"] & /@ modernart

Message occurred during file:

/Users/dproffer/Library/Mathematica/Paclets/Repository/NeuralNetworks-11.2.127/Containers/NetChain.m

(above repeats several times)

ImageRestyle::badtrgdev: TargetDevice -> GPU could not be used, please ensure that you have a compatible NVIDIA graphics card and have installed the latest operating system drivers.

Configuration information:

MacOS High Sierra 10.13.2 (17C89)
NVIDIA Web Driver: 378.10.10.10.25.103 (Up to date)
CUDA Driver Version: 387.128

  Chipset Model:    NVIDIA GeForce GTX 1070
  Type: GPU
  Bus:  PCIe
  PCIe Lane Width:  x4
  VRAM (Total): 8 GB
  Vendor:   NVIDIA (0x10de)
  Device ID:    0x1b81
  Revision ID:  0x00a1
  ROM Revision: VBIOS 86.04.26.00.01
  Metal:    Supported, feature set macOS GPUFamily1 v3

  Chipset Model:    NVIDIA GeForce GTX 960
  Type: GPU
  Bus:  PCIe
  PCIe Lane Width:  x4
  VRAM (Total): 4 GB
  Vendor:   NVIDIA (0x10de)
  Device ID:    0x1401
  Revision ID:  0x00a1
  ROM Revision: VBIOS 84.06.26.00.12
  Metal:    Supported, feature set macOS GPUFamily1 v3

$Version
11.2.0 for Mac OS X x86 (64-bit) (September 11, 2017)

Text[CUDAInformation[]]

{1 -> {"Name" -> "GeForce GTX 1070", "Clock Rate" -> 1683000, 
    "Compute Capabilities" -> 6.1`, "GPU Overlap" -> 1, 
    "Maximum Block Dimensions" -> {1024, 1024, 64}, 
    "Maximum Grid Dimensions" -> {2147483647, 65535, 65535}, 
    "Maximum Threads Per Block" -> 1024, 
    "Maximum Shared Memory Per Block" -> 49152, 
    "Total Constant Memory" -> 65536, "Warp Size" -> 32, 
    "Maximum Pitch" -> 2147483647, 
    "Maximum Registers Per Block" -> 65536, 
    "Texture Alignment" -> 512, "Multiprocessor Count" -> 15, 
    "Core Count" -> 480, "Execution Timeout" -> 1, 
    "Integrated" -> False, "Can Map Host Memory" -> True, 
    "Compute Mode" -> "Default", "Texture1D Width" -> 131072, 
    "Texture2D Width" -> 131072, "Texture2D Height" -> 65536, 
    "Texture3D Width" -> 16384, "Texture3D Height" -> 16384, 
    "Texture3D Depth" -> 16384, "Texture2D Array Width" -> 32768, 
    "Texture2D Array Height" -> 32768, 
    "Texture2D Array Slices" -> 2048, "Surface Alignment" -> 512, 
    "Concurrent Kernels" -> True, "ECC Enabled" -> False, 
    "TCC Enabled" -> False, "Total Memory" -> 8589737984}, 
  2 -> {"Name" -> "GeForce GTX 960", "Clock Rate" -> 1278500, 
    "Compute Capabilities" -> 5.2`, "GPU Overlap" -> 1, 
    "Maximum Block Dimensions" -> {1024, 1024, 64}, 
    "Maximum Grid Dimensions" -> {2147483647, 65535, 65535}, 
    "Maximum Threads Per Block" -> 1024, 
    "Maximum Shared Memory Per Block" -> 49152, 
    "Total Constant Memory" -> 65536, "Warp Size" -> 32, 
    "Maximum Pitch" -> 2147483647, 
    "Maximum Registers Per Block" -> 65536, 
    "Texture Alignment" -> 512, "Multiprocessor Count" -> 8, 
    "Core Count" -> 256, "Execution Timeout" -> 1, 
    "Integrated" -> False, "Can Map Host Memory" -> True, 
    "Compute Mode" -> "Default", "Texture1D Width" -> 65536, 
    "Texture2D Width" -> 65536, "Texture2D Height" -> 65536, 
    "Texture3D Width" -> 4096, "Texture3D Height" -> 4096, 
    "Texture3D Depth" -> 4096, "Texture2D Array Width" -> 16384, 
    "Texture2D Array Height" -> 16384, 
    "Texture2D Array Slices" -> 2048, "Surface Alignment" -> 512, 
    "Concurrent Kernels" -> True, "ECC Enabled" -> False, 
    "TCC Enabled" -> False, "Total Memory" -> 4294770688}}

CUDAResourcesInformation[]

{{"Name" -> "CUDAResources", "Version" -> "11.2.53", 
  "BuildNumber" -> "", "Qualifier" -> "OSX", 
  "WolframVersion" -> "11.2", "SystemID" -> {"MacOSX-x86-64"}, 
  "Description" -> "{ToolkitVersion -> v8.0, MinimumDriver -> 290}", 
  "Category" -> "", "Creator" -> "", "Publisher" -> "", 
  "Support" -> "", "Internal" -> False, 
  "Location" -> 
   "/Users/dproffer/Library/Mathematica/Paclets/Repository/\
CUDAResources-OSX-11.2.53", "Context" -> {}, "Enabled" -> True, 
  "Loading" -> Manual, "Hash" -> "f436299397b86597718dcccb14b51105"}}